IJACSA Volume 13 Issue 2 - thesai.org

IJACSA Volume 13 Issue 2

Copyright Statement: This is an open access publication licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.

View Full Issue

Paper 1: Random-Valued Impulse Noise Detection and Removal based on Local Statistics of Images

Abstract: Random-valued impulse noise removal from images is a challenging task in the field of image processing and computer vision. In this paper, an effective three-step noise removal method was proposed using local statistics of grayscale images. Unlike most existing denoising algorithms that assume the noise density is known, our method estimated the noise density in the first step. Based on the estimated noise density, a noise detector was implemented to detect corrupted pixels in the second step. Finally, a modified weighted mean filter was utilized to restore the detected noisy pixels while leaving the noise-free pixels unchanged. The noise removal performance of our method was compared with 10 well-known denoising algorithms. Experimental results demonstrated that our proposed method outperformed other denoising algorithms in terms of noise detection and image restoration in the vast majority of the cases.

Author 1: Mickael Aghajarian

Author 2: John E. McInroy

Keywords: Random-valued impulse noise; noise detection; image restoration; modified weighted mean filter

Paper 2: Robotic Ad-hoc Networks Connectivity Maintenance based on RF Signal Strength Mapping

Abstract: Network connectivity preservation is one of the substantial factors in achieving efficient mobile robot teams' maneuverability. We present a connectivity maintenance method for a robot team's communication. The proposed approach augments the Radio Frequency Mapping Recognition (RFMR) method and the signal strength gradient decent approach for an overall goal to create a Proactive Motion Control Algorithm (PMCA). The PMCA algorithm controls and helps strengthen mobile communicating robots' connectivity in the existent Radio Frequency (RF) obstacles. The RFMR method takes advantage of Hidden Markov Models (HMMs) results, which assist in learning electromagnetic environments depending on measurements of RF signal strength. The classification results of HMM lead the robots to resolve whether to continue the current trajectory for avoiding the obstacle shadow or move back to desirable robust Signal Strength (SS) positions. In both cases, the robot will run the gradient approach to determine the signal change trend and drive the robot toward the strong SS direction for maintaining link connectivity. The PMCA, depending on the results of RFMR and gradient approaches, promises to preserve robots' motion control and link connectivity maintenance.

Author 1: Mustafa Ayad

Author 2: Richard Voyles

Author 3: Mohamed Ayad

Keywords: RF mapping recognition; link connectivity; gradient algorithm

Paper 3: A Review of Mobility Supporting Tunneling Protocols in Wireless Cellular Networks

Abstract: With recent technology advancements mobility support is one of the major needed parameters by any wireless or mobile networks. Continuous mobile movement from one cell to another or from one network to another requires continuous mobility support. Previously, tunneling protocols employment was the technique to support UE’s inter or intra network mobility. More specifically, GRE, GTP, MIPv6 or PMIPv6 were employed for mobility support. In tunneling encapsulation of one protocol over another protocol is performed to deliver IP packet during inter network or intra network handover. In terms of usage scenario of each tunneling protocol, tunnel establishment, data transfer and tunnel release, an overview and comparison of tunneling protocols is presented in this paper. 3GPP and WLAN interworking, and GAN based usage scenarios and supported tunneling mechanisms has been discussed. Some insights regarding security, multiplexing, multiprotocol and packet sequencing support are also provided for each tunneling protocol.

Author 1: Zeeshan Abbas

Author 2: Wonyong Yoon

Keywords: Tunneling; mobility; 3GPP; WLAN; interworking

Paper 4: Extended Kalman Filter Sensor Fusion in Practice for Mobile Robot Localization

Abstract: Self-driving vehicles and autonomously guided robots could be very beneficial to today's civilization. However, the mobile robot's position must be accurately known, which referred as the localization with the task of tracking the dynamic position, in order for the robot to be active and useful. This paper presents a robot localization method with a known starting location by a real-time reconstructed environment model that represented as an occupancy grid map. The extended Kalman filter (EKF) is formulated as a nonlinear model-based estimator for fuse Odometry and a LIDAR range finder sensor. Because the occupancy grid map for the area is provided, just the inaccuracies of the LIDAR range finder will be considered. The experimental results on the “turtlebot” robot using robot operating system (ROS) show a significant improvement in the pose of the robot using the Kalman filter compared with sample Odometry. This paper also establishes the framework for using a Kalman filter for state estimation, providing all relevant mathematical equations for differential drive robot, this technique can be used to a variety of mobile robots.

Author 1: Alaa Aldeen Housein

Author 2: Gao Xingyu

Author 3: Weiming Li

Author 4: Yang Huang

Keywords: Autonomous navigation; Kalman filter; self-driving vehicle; simultaneous localization and mapping; occupancy grid map; ROS

Paper 5: The Adoption of Digital Games Among Older Adults

Abstract: The revolution of technology brings many benefits towards diverse population. Digital game is one of the digital technologies that has potential to facilitate older adults’ daily routine. However, some of them faces challenges to adopt the usage of digital games in their daily lives, one of which is that most commercial games are not suitable for older people. This paper discusses the investigation into the challenges associated with the older adults’ adoption of digital games, their interaction, and experiences with digital games and specifically explores the andragogical perspectives, and game design attributes. A set of questionnaires consisted of open-ended and close-ended questions were distributed, targeting the older adults across Malaysia, using online and non-probability sampling technique. 81 respondents were recruited, and 56 respondents (n=56) were eligible in this study. Four participants were recruited for informal interview session. The analysis of the results indicates that the older adults’ perception of digital games and game design aspects are the major factors influencing their digital game adoption. Game designs are important to attract many older adults to experience and interact with digital games.

Author 1: Nurul Farinah Mohsin

Author 2: Suriati Khartini Jali

Author 3: Sylvester Arnab

Author 4: Mohamad Imran Bandan

Author 5: Minhua Ma

Keywords: Digital games; Malaysia; older adults; technology

Paper 6: Evaluation of Consumer Network Structure for Cosmetic Brands on Twitter

Abstract: Since the early 2000s, the Internet has become increasingly popular for the development of information dissemination technology and as a platform for interaction. Therefore, the penetration rate of Social Networking Services (SNSs) is also increasing. Using the accounts created on SNSs, companies can disseminate information and communicate with users on SNSs for marketing purposes. Moreover, there are several influencer marketing activities that use influencers who are highly influential in their surroundings as marketing using SNSs. In this study, we aim to identify influencers on Twitter and consumer network structures for six cosmetic brands. Specifically, create a consumer network for each of the six cosmetic brands using follower data obtained from Twitter is created to identify the network structure. Furthermore, brand influencers were also identified. The consumer network of all six cosmetic brands was created to identify the influencers in the cosmetics industry. We compared the influencers of the brands with the influencers of the entire industry to examine any differences.

Author 1: Yuzuki Kitajima

Author 2: Kohei Otake

Author 3: Takashi Namatame

Keywords: Social networking services; community structure; network analysis; consumer network; influencer marketing

Paper 7: Combining Multiple Seismic Attributes using Convolutional Neural Networks

Abstract: Seismic exploration involves estimating the properties of the Earth's subsurface from reflected seismic waves then visualizing the resulting seismic data and its attributes. These data and derived seismic attributes provide complementary information and reduce the amount of time and effort for the geoscientist. Multiple conventional methods to combine various seismic attributes exist, but the number of attributes is always limited, and the quality of the resulting image varies. This paper proposes a method that can be used to overcome these limitations. In this paper, we propose using Deep Learning-based image fusion models to combine seismic attributes. By using convolutional neural network (CNN) capabilities in feature extraction, the resulting image quality is better than that obtained with conventional methods. This work implemented two models and conducted a number of experiments using them. Several techniques have been used to evaluate the results, such as visual inspection, and using image fusion metrics. The experiments show that the Image-fusion Framework, using the Image Fusion Framework Based on CNN (IFCNN) approach, outperformed all other models in both quantitative and visual analysis. Its QAB/F and MS-SSIM scores are 50% and 10%, respectively, higher than all other models. Also, IFCNN was evaluated against the current state-of-the-art solution, Octree, in a comparative study. IFCNN overcomes the limitation of the Octree method and succeeds in combining nine seismic attributes with a better-combining quality, with QAB/F and NAB/F scores being 40% higher.

Author 1: Abrar Alotaibi

Author 2: Mai Fadel

Author 3: Amani Jamal

Author 4: Ghadah Aldabbagh

Keywords: CNNs; neural networks; seismic attributes; seismic images; image fusion

Paper 8: Computational Intelligence Algorithm Implemented in Indoor Environments based on Machine Learning for Lighting Control System

Abstract: Retracted: After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IJACSA`s Publication Principles. We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

Author 1: Mohammad Ehsanul Alim

Author 2: Md. Nazmus Sakib Bin Alam

Author 3: Ihab Hassoun

Keywords: Machine learning algorithms; indoor lighting control system; internet of things (IoT); ultra-wide band sensors; lux sensors; remote access facility

Paper 9: Comparison of Latent Semantic Analysis and Vector Space Model for Automatic Identification of Competent Reviewers to Evaluate Papers

Abstract: The assignment of reviewers to papers is one of the most important and challenging tasks in organizing scientific events. A major part of it is the correct identification of proper reviewers. This article presents a series of experiments aiming to test whether the latent semantic analysis (LSA) could be reliably used to identify competent reviewers to evaluate submitted papers. It also compares the performance of the LSA, the vector space model (VSM) and the method of explicit document description by a taxonomy of keywords, in computing accurate similarity factors between papers and reviewers. All the three methods share the same input datasets, taken from real-life conferences and the produced paper-reviewer similarities are evaluated with the same evaluation methods, allowing a fair and objective comparison between them. Experimental results show that in most cases LSA outperforms VSM and could even slightly outperform the explicit document description by a taxonomy of keywords, if the term-document matrix is composed of TF-IDF values, rather than the raw number of term occurrences.

Author 1: Yordan Kalmukov

Keywords: Latent semantic analysis; vector space model; automatic assignment of reviewers to papers

Paper 10: Evaluation of Applicability of 1D-CNN and LSTM to Predict Horizontal Displacement of Retaining Wall According to Excavation Work

Abstract: During excavation works in downtown, stability and safety considerations of such excavations and constructions are crucial for which continuous wall structures with varying structural components are commonly used. Most of the current models used for this purpose are often complex, where the accepted parameters do not have a clear physical meaning. Moreover, accurate ground movement forecasts are challenging due to nonlinear and inelastic soil behavior. Therefore, this study proposes a method to predict the lateral displacement of the braced wall at each stage of excavation by using all the basic information necessary for braced wall design, including ground information of the excavation site, support methods such as the type of brace, location and stiffness, information about the neighboring buildings, and the results of numerical analysis. One-dimensional convolutional neural network and long short-term memory network are used for estimation and prediction to develop an optimal prediction model based on well-refined but limited data. The applicability of the braced wall was confirmed for safety management by predicting the horizontal displacement of the braced wall for each stage of excavation. The proposed model can be used to predict the stability of the horizontal wall for each excavation step and reduce accident risks, such as collapse of the retaining wall, which may occur during construction.

Author 1: Seunghwan Seo

Author 2: Moonkyung Chung

Keywords: Excavation; wall displacement; neural network; prediction wall deflection; CNN-LSTM

Paper 11: A Review on Classification Methods for Plants Leaves Recognition

Abstract: Plants leaves recognition is an important scientific field that is concerned of recognizing leaves using image processing techniques. Several methods are presented using different algorithms to achieve the highest possible accuracy. This paper provides an analytical survey of various methods used in image processing for the recognition of plants through their leaves. These methods help in extracting useful information for botanists to utilize the medicinal properties of these leaves, or for any other agricultural and environmental purposes. We also provide insights and a complete review of different techniques used by researchers that consider different features and classifiers. These features and classifiers are studied in term of their capabilities in enhancing the accuracy ratios of the classification methods. Our analysis shows that both of the Support Victor Machines (SVM) and the Convolutional Neural Network (CNN) are positively dominant among other methods in term of accuracy.

Author 1: Khaled Suwais

Author 2: Khattab Alheeti

Author 3: Duaa Al_Dosary

Keywords: Leaf recognition; feature extraction; leaf features; classifiers; image processing

Paper 12: Tracking Axonal Transports in Time-Lapse Images Obtained from a Microfluidic Culture Platform

Abstract: In this paper, a procedure is described for tracking moving object trajectories from image sequences acquired from a microfluidic culture platform. Since particles move along the axons, curve structures need to be detected first from the input image sequence. A kymograph analysis technique is applied to detect axon structures from the consolidated image of the input sequence. Horizontally and vertically oriented axons are then detected by applying the process twice to the original and the 90-degree rotated image. Multiple kymographs are generated along the detected axons by projecting image intensity variation through the time-axis. The trajectory detection process is then applied to each kymograph image. To obtain the particle motion information from the entire image sequence, an integration process is applied to each horizontal and vertical kymograph data set. The proposed technique has been applied to image sequences in the present application area. It is demonstrated that practical results can be obtained using time-lapse image sequence data.

Author 1: Nak Hyun Kim

Keywords: Axonal transports; kymograph; trajectory detection; image sequence analysis; motion parameter extraction

Paper 13: LPRNet: A Novel Approach for Novelty Detection in Networking Packets

Abstract: Novelty Detection is a task of recognition of abnormal data points within a given system. Recently, this task has been performed using Deep Learning Autoencoders, but they face several drawbacks which include the problem of identity mapping, adversarial perturbations and optimization algorithms. In this paper, we have proposed a novel approach LPRNet, a Denoising Autoencoder which uses algorithms such as Least Trimmed Square, Projected Gradient Descent and Robust Principal Component Analysis, to solve the above-mentioned problems. LRPNet is then trained and tested on NSL-KDD dataset, and experiments have been performed using Accuracy as performance metric for comparing the existing models with the proposed model. The results show that LRPNet has the maximum accuracy of 95.9% and performed better than all the previous state-of-the-art algorithms.

Author 1: Anshumaan Chauhan

Author 2: Ayushi Agarwal

Author 3: Angel Arul Jothi

Author 4: Sangili Vadivel

Keywords: Novelty detection; deep learning; autoencoders; unsupervised learning

Paper 14: A Proposed Model for Improving the Performance of Knowledge Bases in Real-World Applications by Extracting Semantic Information

Abstract: Knowledge Bases are information resources that convert factual knowledge to machine-readable formats to allow users to extract their desired data from multiple sources. The objective of knowledge base population frameworks is to extend KBs with semantic information to solve fundamental artificial intelligence problems such as understanding human knowledge. Information extraction entails the discovery of critical knowledge facts from unstructured text, which is important in the population of knowledge bases. The objective of this paper is to explore the concept of information extraction as a technique for accelerating the performance of knowledge bases with minimal annotation efforts for real-world applications such as content recommendation during a web search. This entails performing slot filling operations for data collection from large KBs and applying probabilistic estimations to determine the accuracy of the new information. The results are then used to explore the feasibility of applying knowledge bases to real-world tasks such as user-centric information access by encoding entities with deep semantic knowledge.

Author 1: Abdelrahman Elsharif Karrar

Keywords: Semantic information extraction; knowledge base; slot filling; content recommendation

Paper 15: Melody Difficulty Classification using Frequent Pattern and Inter-Notes Distance Analysis

Abstract: This research proposes a novel method for melody difficulty classification performed using frequent pattern and inter-notes distance analysis. The Apriori algorithm was used to measure the frequency of the notes in the note sequence, in which the melody length is also included in the calculation. In addition, the inter-notes distance analysis was also used to measure the difficulty level of composition based on the distance between successive notes. The classification was performed for traditional Javanese compositions known as Gamelan music. Symbolic representation, in which the Gamelan compositions music sheets were collected as the dataset, was chosen by asking experts to divide the compositions based on their difficulty level into basic, intermediate and advanced classes. Then, the proposed method was implemented to measure the difficulty value of each composition. The difference in the interpretation of the difficulty level between the experts and the difficulty value of the composition is solved by calculating the mean value to obtain the range of difficulty values in each class. Evaluation was performed using confusion matrix to measure the accuracy, precision and recall value, and the results reaching 82%, 82.1% and 82%, respectively.

Author 1: Pulung Nurtantio Andono

Author 2: Edi Noersasongko

Author 3: Guruh Fajar Shidik

Author 4: Khafiizh Hastuti

Author 5: Sudaryanto Sudaryanto

Author 6: Arry Maulana Syarif

Keywords: Multi-class classification; frequent analysis; Apriori; Symbolic music; Gamelan

Paper 16: Machine Learning: Assisted Cardiovascular Diseases Diagnosis

Abstract: Detecting cardiovascular problems during their early stages is one of the great difficulties facing physicians. Cardiovascular diseases contribute to the deaths of around 18 million patients every year worldwide. That's why heart disease is a critical worry that must be addressed. However, it can be difficult to detect heart disease because of the multiple factors that affect health, such as high blood pressure, increased cholesterol, abnormal pulse rate, and many other factors. Therefore, the field of artificial intelligence can be instrumental in detecting diseases early on and finding an appropriate solution. This paper proposes a model for diagnosing the probability of an individual having cardiovascular illness by employing Machine Learning (ML) models. The experiments were executed using seven algorithms, and a public dataset of cardiovascular disease was used to train the models. A Chi-square test was used to identify the most important features to predict cardiovascular disease. The experiment results showed that Multi-Layer Perceptron gives the highest accuracy of disease prediction at 87.23%.

Author 1: Aseel Alfaidi

Author 2: Reem Aljuhani

Author 3: Bushra Alshehri

Author 4: Hajer Alwadei

Author 5: Sahar Sabbeh

Keywords: Cardiovascular diseases; artificial intelligence; prediction; multi-layer perceptron

Paper 17: A Solution for Automatic Counting and Differentiate Motorcycles and Modified Motorcycles in Remote Area

Abstract: Motorcycles are the most significant contributor to the vehicle numbers in Indonesia, about 81% of all vehicles in the country. In addition, the growth of modified motorcycles has also increased in several areas, particularly remote places. Many studies have been conducted for detecting vehicles. However, most vehicle detection studies were conducted to detect cars or four-wheeled vehicles, and only a few studies were done to detect motorcycles. Further problems increase if the system is implemented in remote areas with limited electricity power resources that need low-cost budget specification computation. This study detects and calculates the number of motor vehicles and modified motorcycles passed on a highway from video data. It proposed Machine Learning instead of Deep Learning to suit the low computational video in remote areas. Computer vision-based methods used in the prediction are optical flow and Histogram Oriented Gradient (HOG) + Support Vector Machine (SVM). Five videos were used in the system testing, taken from the roadsides using a static camera with a resolution of 160x112 pixels at ±135º angle. This research showed that the accuracy of motorcycles and modified motorcycles detection and calculation systems using the HOG + SVM method is higher than the optical flow method. The average accuracy of HOG + SVM for motorcycles and modified motorcycles is 89.70% and 95.16%, respectively.

Author 1: Indrabayu

Author 2: Intan Sari Areni

Author 3: Anugrayani Bustamin

Author 4: Elly Warni

Author 5: Sofyan Tandungan

Author 6: Rizka Irianty

Author 7: Najiah Nurul Afifah

Keywords: Histogram of oriented gradient; optical flow; vehicles counting; support vector machine

Paper 18: PAD: A Pancreatic Cancer Detection based on Extracted Medical Data through Ensemble Methods in Machine Learning

Abstract: The considerable research into medical health systems is allowing computing systems to develop with the most cutting-edge innovations. These developments are paving the way for more efficient medical system implementations, including automatic identification of health-related disorders. The most important health research is being done to predict cancer, which can take several forms and affect many parts of the body. One of the most prevalent tumors that is expected to be incurable is pancreatic cancer. Pancreatic cancer is one of the most common cancers that is projected to be incurable. Previous research has found that a panel of three protein biomarkers (LYVE1, REG1A, and TFF1) found in urine can help detect respectable PDAC. To improve this panel in this study by replacing REG1A with REG1B from extracted data sets into CSV format. Finally, will analyze four significant biomarkers that are found in urine, creatinine, LYVE1, REG1B, and TFF1. Creatinine is a protein that is commonly utilized as a kidney function indicator. Lymphatic vessel endothelial hyaluronan receptor 1 (YVLE1) is a protein that may help tumors spread. REG1B is a protein that has been linked to pancreatic regeneration, while TFF1 is trefoil factor 1, which has been linked to urinary tract regeneration and repair It’s impossible to treat it properly once it's been diagnosed. Machine learning and neural networks are now showing promise for accurate pancreatic picture segmentation in real time for early diagnosis. This research looks at how to analyze pancreatic tumors using ensemble approaches in machine learning. According to preliminary data, the proposed technique looks to improve the classifier's performance for early diagnosis of pancreatic cancer.

Author 1: Santosh Reddy P

Author 2: Chandrasekar M

Keywords: Pancreatic; PDAC; LYVE1; REG1A; TFF1; CA19_9

Paper 19: Developing and Validating Instrument for Data Integration Governance Framework

Abstract: Data integration is one of the important subfields in data management. It allows users to access the same data from multiple sources without redundancy and preserving its integrity. Data Integration Governance Framework (DIGF) is being developed to guide the implementation of data integration. It functions as a reference and guideline for working level in data integration implementation. Hence the instrument used to validate the DIGF needs to be developed and validated for its accuracy, applicability, and suitability of use. The instrument comprises items structured as a questionnaire. This study proposes Lawshe’s technique to construe the content validity of the instrument. This technique involved the arithmetic of the Content Validity Ratio (CVR) to validate items in the questionnaire, which developed based on the factors identified for Data Integration Governance Framework. Each item in the questionnaire that validated based on the minimum CVR value of 0.75 endorsed as the final instrument of Data Integration Governance Framework to be used in Delphi Technique Evaluation.

Author 1: Noor Hasliza Mohd Hassan

Author 2: Kamsuriah Ahmad

Author 3: Hasimi Salehuddin

Keywords: Content validity; instrument development; data integration governance; Lawshe’s technique

Paper 20: The Method of Braille Embossed Dots Segmentation for Braille Document Images Produced on Reusable Paper

Abstract: Braille is the language of communication for blind and visually impaired people. Braille characters are embossed at points to convey the meaning. Typically, Braille documents can be produced on plain paper. Braille documents can be created on reusable paper, also known as a third-page paper; this reduces the paper cost, allowing more available documents to stimulate learning for blind or visually impaired persons. This research presents a method of Braille embossed dots segmentation for Braille document images produced on reusable paper to support the availability of cheaper learning material. Initially, Braille documents were imported with a calibrated scanner, Braille document image layer separation was then performed. Followed by edge removal, Braille embossed dot recovery, noise removal, and specify the embossed Braille point. This research was conducted by using four scanners, which scanned Braille documents images under four different lighting conditions. For each lighting condition, the Braille document image area was cropped to the desired size, considering the possible event conditions. They were used to create over 200,000 Braille cells, with over 12 billion patterns. When calculating the average performance under all lighting conditions, the values were Precision 1.0000, Recall 0.7817, Accuracy 0.8545, and F-Measure 0.8756. By effectively using Braille embossed dots segmentation, the process of Braille document recognition will also be efficient.

Author 1: Sasin Tiendee

Author 2: Charay Lerdsudwichai

Author 3: Somying Thainimit

Author 4: Chanjira Sinthanayothin

Keywords: Braille; embossed dots; document images; reusable paper; segmentation; recognition; blind; visually impaired

Paper 21: Implementation of Password Hashing on Embedded Systems with Cryptographic Acceleration Unit

Abstract: In this modern world where the proliferation of electronic devices associated with the Internet of Things (IoT) grows day by day, security is an imperative issue. The criticality of the information linked to the various electronic devices connected to the Internet forces developers to establish protection mechanisms against possible cyber-attacks. When using computer equipment or servers, security mechanisms can be applied without having problems with the number of resources associated with this activity; the opposite is the case when implementing such mechanisms on embedded systems. The objective of this document is to implement password hashing on a FRDM-K82F development board with ARM® Cortex™-M4 processor. It describes the basic criteria necessary to aim at moderate levels of security in specific purpose applications; that can be developed taking advantage of the hardware cryptographic acceleration units that these embedded systems have. Performance analysis of the implemented hash function is also presented, considering the variation in the number of iterations performed by the development board. The validation of the correct functioning of the hashing scheme using the SHA-256 algorithm is carried out by comparing the results obtained in real-time versus an application developed in Python software using the PyCryptodome library.

Author 1: Holman Montiel A

Author 2: Fredy Martínez S

Author 3: Edwar Jacinto G

Keywords: Cryptography; password hashing; embedded systems; cryptographic acceleration hardware; SHA-256

Paper 22: Prediction of Metastatic Relapse in Breast Cancer using Machine Learning Classifiers

Abstract: The volume and amount of data in cancerology is continuously increasing, yet the vast majority of this data is not being used to uncover useful and hidden insights. As a result, one of the key goals of physicians for therapeutic decision-making during multidisciplinary consultation meetings is to combine prediction tools based on data and best practices (MCM). The current study looked into using CRISP-DM machine learning algorithms to predict metastatic recurrence in patients with early-stage (non-metastatic) breast cancer so that treatment-appropriate medicine may be given to lower the likelihood of metastatic relapse. From 2014 to 2021, data from patients with localized breast cancer were collected at the Regional Oncology Center in Meknes, Morocco. There were 449 records in the dataset, 13 predictor variables and one outcome variable. To create predictive models, we used machine learning techniques such as Support Vector Machine (SVM), Nave Bayes (NB), K-Nearest Neighbors (KNN) and Logistic Regression (LR). The main objective of this article is to compare the performance of these four algorithms on our data in terms of sensitivity, specificity and precision. According to our results, the accuracies of SVM, kNN, LR and NB are 0.906, 0.861, 0.806 and 0.517 respectively. With the fewest errors and maximum accuracy, the SVM classification model predicts metastatic breast cancer relapse. The unbiased prediction accuracy of each model is assessed using a 10-fold cross-validation method.

Author 1: Ertel Merouane

Author 2: Amali Said

Author 3: El Faddouli Nour-eddine

Keywords: Machine learning; classification; personalized medicine; CRISP-DM; metastasis; breast cancer

Paper 23: Effective ANN Model based on Neuro-Evolution Mechanism for Realistic Software Estimates in the Early Phase of Software Development

Abstract: There is no doubt that the software industry is one of the fastest-growing sectors on the planet today. As the cost of the entire development process continues to rise, an effective mechanism is needed to estimate the required development cost to control better the cost overrun problem and make the final software product more competitive. However, in the early stages of planning, the project managers have difficulty estimating the realistic value of the effort and cost required to execute development activities. Software evaluation prior to development can minimize risk and upsurge project success rates. Many techniques have been suggested and employed for cost estimation. However, computations based on several of these techniques show that the estimation of development effort and cost vary, which may cause problems for software industries in allocating overall resources costs. The proposed research study proposes the artificial neural network (ANN) based Neural-Evolution technique to provide more realistic software estimates in the early stages of development. The proposed model uses the advantages of the topology augmentation using an evolutionary algorithm to automate and achieve optimality in ANN construction and training. Based on the results and performance analysis, it is observed that software effort prediction using the proposed approach is more accurate and better than other existing approaches.

Author 1: Ravi Kumar B N

Author 2: Yeresime Suresh

Keywords: Software cost estimation; COCOMO-II; neuro-evolution; artificial neural network; genetic algorithm

Paper 24: Incorporation of Computational Thinking Practices to Enhance Learning in a Programming Course

Abstract: The development of computational thinking skills is essential for information management, problem-solving, and understanding human behavior. Thus, the aim of the experience described here was to incorporate computational thinking practices to improve learning in a first Python programming course using programming tools such as PSeInt, CodingBat, and the turtle graphic library. A quasi-experimental methodological design was used in which the experimental and control groups are in different academic semesters. Exploratory mixed research was carried out. The control and experimental group consisted of 41 and 36 students, respectively. The results show that with the use of support programming tools, such as PSeInt, CodingBat, Python turtle graphic library, and the incorporation of computational thinking practices, the experimental group students obtained better learning results. It is concluded that student performance and motivation in university programming courses can be improved by using proper tools that help the understanding of programming concepts and the skills development related to computational thinking, such as abstraction and algorithmic thinking.

Author 1: Leticia Laura-Ochoa

Author 2: Norka Bedregal-Alpaca

Keywords: Programming tools; computational thinking; algorithmic thinking; motivation; abstraction

Paper 25: Detecting and Fact-checking Misinformation using “Veracity Scanning Model”

Abstract: The expeditious flow of information over the web and its ease of convenience has increased the fear of the rampant spread of misinformation. This poses a health threat and an unprecedented issue to the world impacting people’s life. To cater to this problem, there is a need to detect misinformation. Recent techniques in this area focus on static models based on feature extraction and classification. However, data may change at different time intervals and the veracity of data needs to be checked as it gets updated. There is a lack of models in the literature that can handle incremental data, check the veracity of data and detect misinformation. To fill this gap, authors have proposed a novel Veracity Scanning Model (VSM) to detect misinformation in the healthcare domain by iteratively fact-checking the contents evolving over the period of time. In this approach, the healthcare web URLs are classified as legitimate or non-legitimate using sentiment analysis as a feature, document similarity measures to perform fact-checking of URLs, and incremental learning to handle the arrival of incremental data. The experimental results show that the Jaccard Distance measure has outperformed other techniques with an accuracy of 79.2% with Random Forest classifier while the Cosine similarity measure showed less accuracy of 60.4% with the Support Vector Machine classifier. Also, when implemented as an algorithm Euclidean distance showed an accuracy of 97.14% and 98.33% respectively for train and test data.

Author 1: Yashoda Barve

Author 2: Jatinderkumar R. Saini

Author 3: Ketan Kotecha

Author 4: Hema Gaikwad

Keywords: Document similarity; fact-checking; healthcare; incremental learning; misinformation; sentiment analysis

Paper 26: Enhancing EFL Students’ COCA-Induced Collocational Usage of Coronavirus: A Corpus-Driven Approach

Abstract: The present study seeks to propose a novel pedagogical strategy for enhancing EFL students’ collocational usage of the node ‘coronavirus’ as currently used in the Corpus of Contemporary American English (COCA) across its five genre-based sections, viz. TV/Movies, Blog, Web-General, Spoken, Fiction, Magazine, Newspaper, and Academic. Drawing on a corpus-driven approach, we conducted a pedagogical descriptive analysis of the ‘coronavirus’ top collocates generated by the COCA. The target collocates have been calculated by the Mutual Information (MI) of 3 or above and specified in terms of the four main lexical parts of speech of nouns, verbs, adjectives, and adverbs. The study has reached three main results. First, employing the COCA as a pedagogical corpus tool can enhance the collocational competence of EFL students should a corpus-driven approach be used descriptively in the classroom. Second, the two methodological stages of demonstration and praxis could facilitate the process of topical priority as a significant index of collocational usage and its thematic relevance. Third, more empirically, the naturally occurring collocates of the node ‘coronavirus’ have proven significant to the pedagogical situation of teaching the node’s collocational meanings encoded in the syntactic categories of nouns, verbs, adjectives, and adverbs, e.g. infection, cause, novel, and closely, respectively.

Author 1: Amir H. Y. Salama

Author 2: Waheed M. A. Altohami

Keywords: COCA; collocations; coronavirus; corpus-driven approach; EFL learners; extended lexical units

Paper 27: A Computational Approach to Decode the Pragma-Stylistic Meanings in Narrative Discourse

Abstract: This paper presents a computer-based frequency distribution analysis to decode the pragma-stylistic meanings in one of the narrative discourse represented by Orwell’s dystopian novel Animal Farm. The main objective of the paper is to explore the extent to which computer software contribute to the linguistic analysis of texts. The paper uses the variable of frequency distribution analysis (FDA) generated by concordance software to decode the pragmatic and stylistic significance beyond the mere linguistic expressions employed by the writer in the selected data. Some words were selected to undergo a frequency distribution analysis so as to highlight their pragmatic and linguistic weight which, in turn, helps arrive at a comprehensive understanding of the thematic message intended by the writer. The paper is grounded on one analytical strand: Frequency distribution analysis conducted by concordance. Results reveal that applying a frequency distribution analysis to the linguistic analysis of large data fictional texts serves to (i) identify the various types of discourse in these texts; (ii) create a thematic categorization that is based on the frequency distribution analysis of specific words in texts; and (iii) indicate that not only high frequency words are indicative in the production of particular pragmatic and stylistic meanings in discourse, but also low frequency words are highly indicative in this regard. These results accentuate a further general finding that computer software contribute significantly to the linguistic analysis of texts, particularly those pertaining to literature. The paper recommends further and intensive incorporation of computer and CALL (computer-assisted language learning) software in teaching and learning literary texts in EFL (English as a foreign language) settings.

Author 1: Ayman Farid Khafaga

Author 2: Iman El-Nabawi Abdel Wahed Shaalan

Keywords: Frequency distribution analysis; narrative discourse; pragma-stylistic meanings; thematic categorization

Paper 28: An Evaluation of the Automatic Detection of Hate Speech in Social Media Networks

Abstract: Numerous approaches have been developed over recent years to detect hate speech on social media networks. Nevertheless, a great deal of what is generally recognized as hate speech cannot yet be detected. There remain many challenges to assuring the effectiveness and reliability of automatic detection systems in different languages, including Arabic. Social media platforms and networks such as Facebook continue to encounter difficulties regarding the automatic detection of hate speech in Arabic content. Given the importance of developing reliable artificial intelligence and automatic detection systems that can reduce the problems and crimes associated with the spread of hate speech on social media platforms, this study is concerned with evaluating the performance of the automatic detection and tracking of hate speech in Arabic content on Facebook. As an example, the study evaluates the period in October 2020 that came to be known as France’s cartoon controversy. Two different corpora were designed. The first corpus comprised 347 posts deleted by Facebook, now known as Meta. The second corpus was composed of 1,856 posts that were randomly selected using the hashtag إلا رسول الله (except the Prophet of Allah). The results indicate that there is a considerable amount of hate speech taken from or influenced by the Islamic religious discourse, but that automatic detection systems are unable to address the peculiar linguistic features of Arabic. There is also a lack of clarity in defining what constitutes “hate speech”. The study suggests that social media networks, including Facebook, need to adopt more reliable automatic detection systems that consider the linguistic properties of Arabic. Political thinkers and religious scholars should be involved in defining what constitutes hate speech in Arabic.

Author 1: Abdulfattah Omar

Author 2: Mohamed Elarabawy Hashem

Keywords: Artificial intelligence; automatic detection; Facebook; hate speech; Islamic discourse; social media networks

Paper 29: A Region-based Compression Technique for Medical Image Compression using Principal Component Analysis (PCA)

Abstract: Region-based compression technique is particularly useful for radiological archiving system as it allows diagnostically important regions to be compressed with near lossless quality while the non-diagnostically important regions (NROI) to be compressed at lossy quality. In this paper, we present a region-based compression technique tailored for MRI brain scans. In the proposed technique termed as automated arbitrary PCA (AAPCA), an automatic segmentation based on brain symmetrical property is used to separate the ROI from the background. The arbitrary-shape ROI is then compressed by block-to-row PCA algorithm (BTRPCA) based on a factorization approach. The ROI is optimally compressed with lower compression rate while the NROI is compressed with higher compression rate. The proposed technique achieves satisfactory segmentation performance. The subjective and objective evaluation performed confirmed that the proposed technique achieves better performance metrics (PSNR and CoC) and higher overall compression rate. The experimental results also demonstrated that the proposed technique is more superior to various state-of-the-art compression methods.

Author 1: Sin Ting Lim

Author 2: Nurulfajar Bin Abd Manap

Keywords: Principal component analysis; region-of-interest (ROI); automated segmentation; MRI brain scans; region-based compression

Paper 30: Identify Discriminatory Factors of Traffic Accidental Fatal Subtypes using Machine Learning Techniques

Abstract: In today's world, traffic accidents are one of the main reasons of mortality and long-term injury. Bangladesh is no exception in this case. Several vehicle accidents each year have become an everyday occurrence in Bangladesh. Bangladesh's largest highway, the Dhaka-Banglabandha National Highway, has a significant number of accidents each year. In this work, we gathered accident data from the Dhaka-Banglabandha highway over an eight-year period and attempted to determine the subtypes present in this dataset. Then we tested with various classification algorithms to see which ones performed the best at classifying accident subtypes. To describe the discriminatory factors among the subtypes, we also used an interpretable model. This experiment gives essential information on traffic accidents and so helps in the development of policies to reduce road traffic collisions on Bangladesh's Dhaka-Banglabandha National Highway.

Author 1: W. Z. Loskor

Author 2: Sharif Ahamed

Keywords: Traffic accident; clustering analysis; machine learning; feature selection; classification; discriminatory factors

Paper 31: A Review on Software Bug Localization Techniques using a Motivational Example

Abstract: Software bug localization is an essential step within the software maintenance activity, consuming about 70% of the time and cost of the software development life cycle. Therefore, the need to enhance the automation process of software bug localization is important. This paper surveys various software bug localization techniques. Furthermore, a running motivational example is utilized throughout the paper. Such motivational example illustrates the surveyed bug localization techniques, while highlighting their pros and cons. The motivational example utilizes different software artifacts that get created throughout the software development lifecycle, and sheds light on those software artifacts that remain poorly utilized within existing bug localization techniques, regardless of the rich wealth of knowledge embedded within them. This research thus presents guidance on what artifacts should future bug localization techniques focus, to enhance the accuracy of bug localization, and speedup the software maintenance process.

Author 1: Amr Mansour Mohsen

Author 2: Hesham Hassan

Author 3: Ramadan Moawad

Author 4: Soha Makady

Keywords: Bug localization; bug localization artifacts; information retrieval; program spectrum

Paper 32: Failure Region Estimation of Linear Voltage Regulator using Model-based Virtual Sensing and Non-invasive Stability Measurement

Abstract: Voltage regulator (VR) stability plays an essential role in ensuring maximum power delivery and long-lasting electronic lifespan. Capacitor with a specific equivalent series resistance (ESR) range is typically connected at the VR output terminal to compensate for instability of the VR due to sudden changes in load current. The stability of VR can be measured by analyzing output voltage during load transient tests. However, the optimum ESR range obtained from the ESR tunnel graph in its datasheet can only be characterized by testing a set of data points consisting of ESR and load currents. Characterization process is performed manually by changing the value of ESR and load current for each operating point. However, the inefficient process of estimating the critical value of ESR must be improved given that it requires a large amount of time and expertise. Furthermore, the stability analysis is currently conducted on the basis of the number of oscillation counts of VR output voltage signal. Therefore, a model-based virtual sensing approach that mainly focuses on black-box modeling through system identification method and training neural network on the basis of estimated transfer function coefficients is introduced in this study. The proposed approach is used to estimate the internal model of the VR and reduce the number of data points that need to be acquired. In addition, the VR stability is analyzed using noninvasive stability measurement method, which can measure phase margin from the frequency response of the VR circuit in closed-loop conditions. Results showed that the proposed method reduces the time it takes to produce an ESR tunnel graph by 84% with reasonable accuracy (MSE of 5×10−6, RMSE of 2.24×10−3, MAE of 1×10−3, and R2 of 0.99). Therefore, efficiency and effectiveness of ESR characterization and stability analysis of the VR circuit is improved.

Author 1: Syukri Zamri

Author 2: Mohd Hairi Mohd Zaman

Author 3: Muhammad Fauzi Mohd Raihan

Author 4: Asraf Mohamed Moubark

Author 5: M Marzuki Mustafa

Keywords: Voltage regulator; output capacitor; equivalent series resistance; failure region; system identification; neural network; noninvasive stability measurement

Paper 33: Mobile Mathematics Learning Application Selection using Fuzzy TOPSIS

Abstract: Impressive evolution of technology increased the usage frequency of smart mobile phones, and hence abundance in the quantity of available mobile applications has emerged as the vital problem of inventing practical and efficient ways for selecting suitable mobile applications for the desired use. Today, there are almost three million apps only at the Google Play store. Therefore, the need for an automated, effective, and less time-consuming approach towards suitable mobile application selection to choose the best alternative has gained more significance than ever. Despite the sudden growth in mobile learning applications, there exists a dearth of research in the effective way of selecting a suitable mobile application in that respect particularly in relation to mobile apps for Mathematics. Moreover, using multi-criteria decision-making methods (MCDM) is only recently applied in rare studies for that purpose. This paper focused on ISO/IEC 25010 software quality standards in selecting mobile Mathematics learning applications. Six highly rated applications were evaluated by two experts. This paper aims to apply the fuzzy Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to retrieve the best alternative among present applications. The results showed an objective and flexible assessment for ranking to eliminate ambiguity in decision-making. Results also identified significant features thus rendering a useful and valuable tool for decision-makers. The study assists users, teachers/instructors, students in their decision-making processes regarding finding the most suitable application for Mathematics.

Author 1: Seren Basaran

Author 2: Firass El Homsi

Keywords: Fuzzy TOPSIS; ISO/IEC 25010 standards; mathematics; mobile applications; multi-criteria decision making

Paper 34: An Optimal Execution of Composite Service in Decentralized Environment

Abstract: It is important for service-oriented architectures to consider about how the composition of web services affects business processes. For instance, a single web service may not have been adequate for most complex business operations, needing the use of multiple web services. This paper proposed a novel technique for optimal partitioning and execution of the services using a decentralized environment. The proposed technique is designed and developed using a genetic algorithm with multiple high task allocations on a single server. We compared three existing techniques, including meta-heuristic genetic algorithm, heuristics like Pooling-and-Greedy-Merge (PGM) technique, and Merge-by-Define-Use (MDU) technique, to a simulation of Business Process Execution Language (BPEL) partition using genetic algorithm through multiple high tasks allocation to single server node. The proposed technique is practical and advantageous. In terms of execution time, number of server requests, and throughput, the proposed technique outperformed the existing GA, PGM, and MDU techniques.

Author 1: Yashwant Dongre

Author 2: Rajesh Ingle

Keywords: Genetic algorithm; service composition; decentralized execution; composite service

Paper 35: Design Processes for User Engagement with Mobile Health: A Systematic Review

Abstract: Despite the importance of user engagement in mHealth system efficacy, many such interventions fail to engage their users effectively. This paper provides a systematic review of 10 years of research (32 articles) on mHealth design interventions conducted between 2011 and 2020. The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) model was used for this review with the IEEE, Medline EBSCO Host, ACM, and Springer databases searched for English language papers with the published range. The goal of this review was to find out which design process improves user engagement with mHealth in order to guide the development of future mHealth interventions. We discovered that the following six analytical themes influence user engagement: design goal, design target population, design method, design approach, socio-technical aspects, and design evaluation. These six analytical themes, as well as 16 other specific implementations derived from the reviewed articles, were included in a checklist designed to make designing, developing, and implementing mHealth systems easier. This study closes a gap in the literature by identifying a lack of consideration of socio-cultural contexts in the design of mHealth interventions and recommends that such socio-cultural contexts be considered and addressed in a systematic manner by identifying a design process for engaging users in mHealth interventions. Based on this, our systematic literature review recommends that a framework that captures the socio-cultural context of any mHealth implementation be refined or developed to support user engagement for mHealth.

Author 1: Tochukwu Ikwunne

Author 2: Lucy Hederman

Author 3: P. J. Wall

Keywords: Design process; mobile health; socio-cultural; user-centered design; user engagement

Paper 36: An Intelligent Metaheuristic Optimization with Deep Convolutional Recurrent Neural Network Enabled Sarcasm Detection and Classification Model

Abstract: Sarcasm is a state of speech in which the speaker says something that is externally unfriendly with a purpose of abusing/deriding the listener and/or a third person. Since sarcasm detection is mainly based on the context of utterances or sentences, it is hard to design a model to proficiently detect sarcasm in the domain of natural language processing (NLP). Despite the fact that various methods for detecting sarcasm have been created utilizing statistical machine learning and rule-based approaches, they are unable of discerning figurative meanings of words. The models developed using deep learning approaches have shown superior performance for sarcasm detection over traditional approaches. With this motivation, this paper develops novel deep learning (DL) enabled sarcasm detection and classification (DLE-SDC) model. The DLE-SDC technique primarily involves pre-processing stage which encompasses single character removal, multispaces removal, URL removal, stop word removal, and tokenization. Next to data preprocessing, the preprocessed data is converted into the feature vector by Glove Embeddings technique. Followed by, convolutional neural network with recurrent neural network (CNN-RNN) technique is utilized to detect and classify sarcasm. In order to boost the detection outcomes of the CNN+RNN technique, a hyper parameter tuning process utilizing teaching and learning based optimization (TLBO) algorithm is employed in such a way that the classification performance gets increased. The DLE-SDC model is validated using the benchmark dataset and the performance is examined interms of precision, recall, accuracy, and F1-score.

Author 1: K. Kavitha

Author 2: Suneetha Chittineni

Keywords: Sarcasm detection; data classification; deep learning; feature extraction; TLBO algorithm; parameter optimization

Paper 37: DBTechVoc: A POS-tagged Vocabulary of Tokens and Lemmata of the Database Technical Domain

Abstract: Vocabulary of a language has a great role to play in the Natural Language Processing (NLP) applications. Such applications make use of lists like stop-word list, general service list, academic word list and technical domain word list. The technical domain word list differs with each domain and though it is available for fields like medicine, biology, computer science, physics and law, the domain of databases in specific has still not been explored. For the first time, we propose technical vocabulary comprising of POS-tagged unigram tokens and POS-tagged unigram lemmata for the technical domain of databases. This vocabulary has been called DBTechVoc with a coined term. Notably, the multi-word phrases have also been considered, without their further tokenization, to maintain their semantics. The empirical results, with more than 1000 high quality research papers collected over a period of 45 years from 1976 to 2021, prove that the technical general word list of the domain of computer science is different from the technical and specific word list of the domain of databases. The overlap was found to be less than 2%. The research titles use 6% Rainbow stop words while 13% of the words used for the research paper titles are inflectional forms of lemmata.

Author 1: Jatinder kumar R. Saini

Author 2: Ketan Kotecha

Author 3: Hema Gaikwad

Keywords: Database; lemma; part-of-speech (POS); technical word list; token; unigram; vocabulary

Paper 38: Smart Monitoring System for Chronic Kidney Disease Patients based on Fuzzy Logic and IoT

Abstract: A Chronic Kidney Disease (CKD) monitoring system was proposed for early detection of cardiovascular disease (CVD) and anemia using Fuzzy Logic. To determine the heart rate and blood oxygen saturation, the proposed model was simulated using MATLAB and Simulink to handle ECG and PPG inputs. The Pan-Tompkins method was used to determine the heart rate, while the Takuo Aoyagi algorithm was used to assess blood oxygen saturation levels. The findings show that the ECG recorded using the CKD model has all of the characteristics of a typical ECG wave cycle, but with reduced signal degradation in the 0.8–1.3mV region. The heart rate signal processing yielded findings between 78 and 83 beats per minute is within the range of the supplied heart rate. Takuo Aoyagi's pulse oximeter simulation generated the same findings. For real-time verification, the proposed model was implemented in hardware using ESP8266 32-bit microcontroller with IoT integration via Wireless Fidelity for data storage and monitoring. In comparison with the Fuzzy Logic simulation done on MATLAB and Simulink, the CKD monitoring device has 100% accuracy in patient status detection. The CKD monitoring system has an overall accuracy of 99% in comparison with a commercial fingertip pulse oximeter.

Author 1: Govind Maniam

Author 2: Jahariah Sampe

Author 3: Rosmina Jaafar

Author 4: Mohd Faisal Ibrahim

Keywords: Anemia; cardiovascular disease (CVD); fuzzy logic; healthcare; internet of things

Paper 39: Trust Management in Industrial Internet of Things using a Trusted E-Lithe Protocol

Abstract: The IoT has gained significant recognition from research and industrial communities over the last decade. The concept of Industrial IoT (IIoT) has emerged to improve industrial processes and reduce downtime or breach in secure communication. If automated, industrial applications can make the implementation process more convenient, it also helps increase productivity, but an external attacker may cause distortion to the process, which could cause much damage. Thus, a trust management technique is proposed for securing IIoT. The transition of the Internet to IoT and for industrial applications to IIoT leads to numerous changes in the communication processes. This transition was initiated by wireless sensor networks that have unattended wireless topologies and were comprised due to the nature of their resource-constrained nodes. In order to protect the sensitivity of transmitted information, the security protocol uses the Datagram Transport Layer Security (DTLS) mandated by Secure Constrained Application Protocol (CoAP). However, DTLS was designed for powerful devices and needed strong support for industrial applications connected through high-bandwidth links. In the proposed trust management system, machine learning algorithms are used with an elastic slide window to handle bigger data and reduce the strain of massive communication. The proposed method detected on and off attacks on nodes, malicious nodes, healthy nodes, and broken nodes. This identification is necessary to check if a particular node could be trusted or not. The proposed technique successfully predicted 97% of nodes' behavior faster than other machine learning algorithms.

Author 1: Ahmed Motmi

Author 2: Samah Alhazmi

Author 3: Ahmed Abu-Khadrah

Author 4: Mousa AL-Akhras

Author 5: Fuad Alhosban

Keywords: IoT; industrial; IIoT; trust management; E-lithe; secure communication; internet of things; CoAP; datagram transport layer security

Paper 40: Machine Learning Application for Predicting Heart Attacks in Patients from Europe

Abstract: Even today, there are still a large number of people suffering from heart attacks, which have already claimed numerous lives worldwide. To examine the main components of this problem in an objective and timely manner, we chose to work with a methodology that relies on taking and learning from real and existing data for use in training and testing predictive models. This was carried out to obtain useful data for the present research work. There are in parallel different methodologies that do not quite fit the model of this work. Data was collected from the "Center for Machine Learning and Intelligent Systems" which in turn contains data from patients who have ever suffered a cardiovascular attack and from patients who never suffered the disease, all of them being patients selected from different medical institutions. With the corresponding information, it was subjected to different processes such as cleaning, preparation, and training with the data, to obtain a logistic regression type automatic learning model ready to predict whether or not a person may suffer a cardiovascular attack. Finally, a result of 87% accuracy was obtained for people who suffered a heart attack and an accuracy of 81% for people who would not suffer from this disease. This can greatly reduce the mortality rate due to infarction, by knowing the condition of a person who is unaware of his or her health situation and thus being able to take appropriate measures.

Author 1: Enrique Arturo Elescano-Avendaño

Author 2: Freddy Edson Huamán-Leon

Author 3: Gilson Andreson Vasquez-Torres

Author 4: Dayana Ysla-Espinoza

Author 5: Enrique Lee Huamaní

Author 6: Alexi Delgado

Keywords: Prediction; machine learning model; logistic regression; heart attack

Paper 41: Multi-Criteria Prediction Framework for the Prioritization of Council Candidates based on Integrated AHP-Consensus and TOPSIS Methods

Abstract: Predicting the council candidate becomes difficult due to the large number of criteria that must be known and identified. The best candidate should be chosen from among the candidates because he or she will play an important role in the organization or institution. It is critical to find the right and best candidate these days because people see and judge the outcome from the candidate in a short time with the help of social media. Perhaps the organization and institution require the best candidate criteria because they will manage and organize the community around them. This study focuses on how to prioritize council candidates using Analytic Hierarchy Process (AHP) for determine the criteria and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for prioritize the student council candidate. This proposed framework based on Multi-Criteria Decision Making (MCDM) will be used to recommend and assist students in selecting the best candidate for student council. The three criteria chosen were grade point average (GPA), Age, and Semester. Based on the results of the questionnaire and a review of the literature, these criteria were developed. The three criteria were then used to determine the most important criterion for selecting the student council. The AHP weight is used to determine and prioritize the most important criteria. TOPSIS was used to select the most qualified student council candidate. The findings show that GPA is the most important criteria in selecting the best candidate, and the TOPSIS findings support the AHP findings.

Author 1: Nurul Akhmal Mohd Zulkefli

Author 2: Muhamad Hariz Muhamad Adnan

Author 3: Mukesh Madanan

Author 4: Tariq Mohsen Hardan

Keywords: Analytic hierarchy process (AHP); technique for order of preference by similarity to ideal solution (TOPSIS); multi-criteria decision making (MCDM); student council

Paper 42: A Novel Animated CAPTCHA Technique based on Persistence of Vision

Abstract: Image-based CAPTCHA challenges have been successfully used to distinguish between humans and bots for a long time. However, image-based CAPTCHA techniques are constantly broken by hackers, forcing web developers to implement more robust security features and new approaches in CAPTCHA images. Modern-day bots can use many techniques and technologies to break CAPTCHA images automatically. These techniques include OCR, Segmentation, erosion, threshold, flood fill, etc. This led to innovative CAPTCHA systems, including those based on drag and drop, image recognition, fingerprint, mathematical problems, etc. Animated image CAPTCHAs have also been designed to show moving characters and objects and require users to recognize the characters or objects in the animation. Unfortunately, these CAPTCHA systems have also been broken successfully. This research proposes a novel animated CAPTCHA technique based on the persistence of vision, which shows text characters in multiple layers in an animated image. The proposed CAPTCHA technique has been implemented in PHP using GD library functions and tested using various popular CAPTCHA breaking tools. Further, the proposed CAPTCHA challenge has also been tested against the frame separation based breaking technique. The security analysis and usability study have demonstrated user-friendliness, vast accessibility, and robustness.

Author 1: Shafiya Afzal Sheikh

Author 2: M. Tariq Banday

Keywords: CAPTCHA; OCR; animation; segmentation; botnet; HIP; CAPTCHA usability

Paper 43: Securing Dynamic Source Routing by Neighborhood Monitoring in Wireless Adhoc Network

Abstract: Wireless Adhoc Network (WANET) significantly contributes to cost-effective network formulation due to decentralized and infrastructure-less schemes. One of the primary forms of WANET in Mobile Adhoc Network (MANET) is still evolving in research and a continued set of research problems associated with security. A review of existing security approaches shows that identifying malicious behavior in MANET is still an open-end problem irrespective of various methods. This paper introduces an improved DSR protocol mechanism of neighborhood monitoring scheme towards analyzing the malicious behavior in the presence of an unknown attacker of dynamic type. The proposed method contributes to deploying auxiliary relay nodes and retaliation nodes to control the communication process and prevent the attacker from joining the network. Using analytical research methodology, the proposed system can offer better communication performance with effective resistance from threats in MANET.

Author 1: Rajani K C

Author 2: Aishwarya P

Keywords: Mobile adhoc network; wireless adhoc network; security; attack; dynamic source routing

Paper 44: Free Hardware based System for Air Quality and CO2 Monitoring

Abstract: Due to the increase in air pollution, especially in Latin American countries of low and middle income, great environmental and health risks have been generated, highlighting that there is more pollution in closed environments. Given this problem, it has been proposed to develop a system based on free hardware for monitoring air quality and CO2, in order to reduce the levels of air pollution in a closed environment, improving the quality of life of people and contributing to the awareness of the damage caused to the environment by the hand of man himself. The system is based on V-Model, complemented with a ventilation prototype implemented with sensors and an application for its respective monitoring. The sample collected in the present investigation was non-probabilistic, derived from the reports of air indicators during 15 days with specific schedules of 9am, 1pm and 6pm. The results obtained indicated that the air quality decreased to 670 ppm, as well as the collection time decreased to 5 seconds and finally the presence of CO2 was reduced to 650 ppm after the implementation of the system, achieving to be within the standards recommended by the World Health Organization.

Author 1: Cristhoper Alvarez-Mendoza

Author 2: Jhon Vilchez-Lucana

Author 3: Fernando Sierra-Liñan

Author 4: Michael Cabanillas-Carbonell

Keywords: Air quality; air pollution; co2; control system; free hardware; v-model

Paper 45: Using HBase to Implement Speed Layer in Time Series Data Storage Systems

Abstract: In recent years, modern systems have become increasingly integrated, and the challenges are focused on delivering real-time analytics based on big data. Thus, using standard software tools to extract information from such datasets is not always possible. The Lambda Architecture proposed by Marz is an architectural solution that can manage the processing of large data volumes by combining real-time and data batch processing techniques. Choosing a suitable database management system for storing large volumes of time series data is not a trivial issue as various aspects such as low latency, high performance and the possibility of horizontal scalability must be taken into account. The new NoSQL approaches use for this purpose non-relational databases with significant advantages in terms of flexibility and performance in comparison with the traditional relational databases. With reference to this, the purpose of this paper is to analyse the general characteristics of time series data and the main activities performed by the Speed layer in a system based on the Lambda Architecture. Based on this, the use of a column-oriented NoSQL DBMS as a system for storing time series data is justified. The paper also addresses the challenges of using HBase as a system for storing and analysing time series data. These questions are related to the design of an appropriate database schema, the need to achieve balance between ease of access to the data and performance as well as considering the factors that affect the overload of individual nodes in the system.

Author 1: Milko Marinov

Keywords: Lambda architecture; speed layer; time series data; data storage system

Paper 46: Machine Learning Model for Prediction and Visualization of HIV Index Testing in Northern Tanzania

Abstract: Human Immunodeficiency Virus Acquired Immunodeficiency Syndrome (HIV AIDS) in Tanzania is still a threatening disease in society. There have been various strategies to increase the number of people to know their HIV status. Among these strategies, HIV index testing has proven to be the best modality for collecting the number of HIV contacts who might be at risk of contracting HIV from an HIV-positive person. However, the current HIV index testing is manual-based, creating many challenges, including errors, time-consuming, and expensive to operate. Therefore, this paper presents the Machine Learning model results to predict and visualise HIV index testing. The development process followed the Agile Software development methodology. The data was collected from Kilimanjaro, Arusha and Manyara regions in Tanzania. A total of 6346 samples and 11 features were collected. Then, the dataset was divided into training sets of 5075 samples and a testing set of 1270 samples (80/20). The datasets were run into Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN) algorithms. The results of the evaluation, by Mean Absolute Errors (MAE), showed that; RF MAE (1.1261), XGBoost MAE (1.2340), and ANN MAE (1.1268.); whereby the RF appeared to have the best result compared to the other two algorithms. Data visualisation shows that 17.4% of males and 82.6 of females had been notified. In addition, the Kilimanjaro region had more cases of people with HIV status from their partners. Overall, this study improved our understanding of the significance of ML in the prediction and visualisation of HIV index testing. The developed model can assist decision-makers in coming out with a suitable intervention strategy towards ending HIV AIDS in our societies. The study recommends that health centres in other regions use this model to simplify their work.

Author 1: Happyness Chikusi

Author 2: Judith Leo

Author 3: Shubi Kaijage

Keywords: Index testing; machine learning; random forest; xgboost; artificial neural network

Paper 47: Processing of Clinical Notes for Efficient Diagnosis with Dual LSTM

Abstract: Clinical records contain patient information such as laboratory values, doctor notes, or medications. However, clinical notes are underutilized because notes are complex, high-dimensional, and sparse. However, these clinical records may play an essential role in modeling clinical decision support systems. The study aimed to develop an effective predictive learning model that can process these sparse data and extract useful information to benefit the clinical decision support system for the effective diagnosis. The proposed system conducts phase-wise data modeling, and suitable text data treatment is carried out for data preparation. The study further utilized the Natutal Language Processing (NLP) mechanism where word2vec with Autoencoder is used as a clustering scheme for the topic modeling. Another significant contribution of the proposed work is that a novel approach of learning mechanism is devised by integrating Long Short Term Memory (LSTM) and Convolution Neural Network (CNN) to learn the inter-dependencies of the data sequences to predict diagnosis and patient testimony as output for the clinical decision. The development of the proposed system is carried out using the Python programming language. The study outcome based on the comparative analysis exhibits the effectiveness of the proposed method.

Author 1: Chandru A. S

Author 2: Seetharam K

Keywords: Clinical notes; natutal language processing; diagnosis; long short term memory; convolution neural network; autoencoder

Paper 48: A Smart Decision Making System for the Selection of Production Parameters using Digital Twin and Ontologies

Abstract: Currently, the industrial and economic environment is highly competitive, forcing companies to keep up with technological progress and to be efficient in terms of quality and responsiveness, not only to survive, but also to dominate the market. So, to achieve this goal, companies are always looking to master their production processes, as well as to enlarge their range of products, either by developing new products or by improving old ones. This confronts companies to many problems, including the identification of adequate and optimal production parameters for the development of their products. In this context, a decision making system based on digital twins (DT), case-based reasoning (CBR) and Ontologies is proposed. The originality of this work lies in the fact that it combines three emerging artificial intelligence tools for modeling, reasoning and decision making. Thus, this work proposes a new flexible and automated system that ensures an optimal selection of production parameters for a given complex product. An industrial case of study is developed to illustrate the effectiveness of the proposed approach.

Author 1: ABADI Mohammed

Author 2: ABADI Chaimae

Author 3: ABADI Asmae

Author 4: BEN-AZZA Hussain

Keywords: Production parameters selection; digital twin; case-based reasoning; ontologies; automation; cyber-physical systems; decision making; artificial intelligence

Paper 49: Data Mining Model for Predicting Customer Purchase Behavior in E-Commerce Context

Abstract: Nowadays e-commerce environment plays an important role to exchange commodity knowledge between consumers commonly with others. Accurately predicting customer purchase patterns in the e-commerce market is one of the critical applications of data mining. In order to achieve high profit in e-commerce, the relationship between customer and merchandise are very important. Moreover, many e-commerce websites increase rapidly and instantly and competition has become just a mouse-click away. That is why the importance of staying in the business, and improving the profit needs to accurately predict purchase behavior and target their customers with personalized services according to their preferences. In this paper, a data mining model has been proposed to enhance the accuracy of predicting and to find association rules for frequent item sets. Also, K-means clustering algorithm has been used to reduce the size of the dataset in order to enhance the runtime for the proposed model. The proposed model has used four different classifiers which are C4.5, J48, CS-MC4, and MLR. Also, Apriori algorithm to provide recommendations for items based on previous purchases. The proposed model has been tested on Northwind trader’s dataset and the results archives accuracy equal 95.2% when the number of clusters were 8.

Author 1: Orieb Abu Alghanam

Author 2: Sumaya N. Al-Khatib

Author 3: Mohammad O. Hiari

Keywords: Apriori PT algorithm; C4.5; CS-MC4; Data mining; decision tree; E-commerce; K-means

Paper 50: An Effective Analytics and Performance Measurement of different Machine Learning Algorithms for Predicting Heart Disease

Abstract: This Heart disease means any condition that affects to directly heart. Globally, Heart disease is the main reason for death. According to a survey, approximately 17.9 million people died from heart disease in 2019 (representing 32 percent of global deaths). The number of people dying is increasing at an alarming rate every day. So it is necessary to detect and prevent heart disease as soon as possible. Medical experts who work inside the field of coronary heart sickness can predict the rate of coronary heart disorder up to 69%, which is not so useful. Because of the invention of various machine learning techniques, intelligent machines can predict the chance of heart disease up to 84%, which will be helpful to prevent heart disease earlier. In this paper, for picking essential characteristics among all features in the dataset, the univariate feature selection approach was employed. One-of-a-kind machine learning algorithms like K-Nearest Neighbors, Naive Bayes, Decision Tree, Random Forest, Support Vector Machine were used to assess the performance of these algorithms and forecast which one performs best. These machine learning approaches require less time to predict disease with more precision, resulting in the loss of valued lives all around the world.

Author 1: S. M. Hasan Sazzad Iqbal

Author 2: Nasrin Jahan

Author 3: Afroja Sultana Moni

Author 4: Masuma Khatun

Keywords: Machine learning; heart disease prediction; KNN; naive bayes; decision tree; random forest; support vector machine

Paper 51: Implementation of Modified Wiener Filtering in Frequency Domain in Speech Enhancement

Abstract: The most common complaint about Digital Hearing Aids is feedback noise. Many attempts have been undertaken in recent years to successfully reduce feedback noise. A wiener filter, which calculates the wiener gain using before and after filtering SNR, is one technique to reduce background noise. Modified Noise Reduction Method (MNRM), a new way for reducing feedback noise Reduction, is presented in this work. In the Modified Noise Reduction Strategy, the advantages of a wiener filter are merged with a decision-directed approach and a twin-stage noise suppression technique The Modified Noise Reduction method can reduce the noise more successfully, according to comprehensive MATLAB programming, investigation, and findings analysis. After being modelled in MATLAB for seven distinct noise types, the SNR of the two architectures is compared.

Author 1: C. Ramesh Kumar

Author 2: M. P. Chitra

Keywords: Digital hearing aid; least mean square value; noise reduction method; power spectral density

Paper 52: A Framework for Integrating the Distributed Hash Table (DHT) with an Enhanced Bloom’s Filter in Manet

Abstract: MANET, a self-organizing, infrastructure-less, wireless network is a fast-growing technology in day-to-day life. There is a rapid growth in the area of mobile computing due to the extent of economical and huge availability of wireless devices which leads to the extensive analysis of the mobile ad-hoc network. It consists of the collection of wireless dynamic nodes. Due to this dynamic nature, the routing of packets in the MANET is a complex one. The integration of distributed hash table (DHT) in MANET is performed to enhance the overlay of routing. The node status updating in the centralized hash table creates the storage overhead. The bloom filter is a data structure that is a space-effective randomized one but it allows the false-positive rates. However, this can be able to compensate for the issue of storage overhead in DHT (Distributed hash table). Hence, to overcome the storage overhead occurring in DHT, and reduce the false positives, the Bloom's filter is integrated with the DHT initially. Furthermore, the link stability is measured by the distance among mobile nodes. The optimal node selection should be done for the transmission of packets which is the lacking factor. If it fails to select the optimal path then the removal of malicious nodes may lead to the unwanted entry of nodes into the other clustering groups. Therefore, to solve this problem, the bloom's filter is modified for enhancing the link stability. The novelty of this proposed work is the integration of Bloom's filter with the Distributed Hash Table which provides good security on transmission data by removing false-positive errors and storage overhead.

Author 1: Renisha P Salim

Author 2: Rajesh R

Keywords: Mobile ad hoc network (MANET); distributed hash table (DHT); bloom’s filter; link stability

Paper 53: Spark based Framework for Supervised Classification of Hyperspectral Images

Abstract: The advancement of remote sensing sensors acquired large amount of image data easily. Primary aspects of big data, such as volume, velocity, and variety, are represented in the acquired images. Furthermore, standard data processing approaches have different limits when dealing with such large amounts of data. As a result, good machine learning-based algorithms are required to process the data with higher accuracy and lower computational efficiency. Therefore, we propose ANOVA F-test based spectral feature selection method with a distributed implementation of this machine learning algorithm on Spark. Experimental results are obtained using the bench mark datasets acquired using AVIRIS and ROSIS sensors. The performance of Spark MLlib based supervised machine learning techniques are evaluated using the criteria viz., accuracy, specificity, sensitivity, F1-score and execution time. Added to that, we compared the execution time between distributed processing and processing with single processor. The results reveal that the proposed strategy significantly cuts down on analytical time while maintaining classification accuracy.

Author 1: N. Aswini

Author 2: R. Ragupathy

Keywords: Hyperspectral images; spark; supervised classifiers; spectral features; ANOVA F-test; distributed processing

Paper 54: Machine Learning Techniques for Sentiment Analysis of Code-Mixed and Switched Indian Social Media Text Corpus - A Comprehensive Review

Abstract: A comprehensive review of sentiment analysis for code-mixed and switched text corpus of Indian social media using machine learning (ML) approaches, based on recent research studies has been presented in this paper. Code-mixing and switching are linguistic behavior shown by the bilingual/multilingual population, primarily in spoken but also in written communication, especially on social media. Code-mixing involves combining lower linguistic units like words and phrases of a language into the sentences of other language (the base language) and code-switching involves switching to another language, for the length of one sentence or more. In code-mixing and switching, a bilingual person takes one or more words or phrases from one language and introduces them into another language while communicating in that language in spoken or written mode. People nowadays express their views and opinions on several issues on social media. In multilingual countries, people express their views using English as well as their native languages. Several reasons can be attributed to code-mixing. Lack of knowledge in one language on a particular subject, being empathetic, interjection and clarification are some to name. Sentiment analysis of monolingual social media content has been carried out for the last two decades. However, during recent years, Natural Language Processing (NLP) research focus has also shifted towards the exploration of code-mixed data, thereby, making code mixed sentiment analysis an evolving field of research. Systems have been developed using ML techniques to predict the polarity of code-mixed text corpus and to fine tune the existing models to improve their performance.

Author 1: Gazi Imtiyaz Ahmad

Author 2: Jimmy Singla

Author 3: Anis Ali

Author 4: Aijaz Ahmad Reshi

Author 5: Anas A. Salameh

Keywords: Sentiment analysis; code mixing; corpus; deep learning; machine learning; NLP; social media text

Paper 55: Hybrid Routing Topology Control for Node Energy Minimization For WSN

Abstract: Wireless sensing has become an essential feature for minimizing energy for WSN applications. The foundation of the WSN is to implicate the uniqueness of the design feature capabilities, which are tied to different applications choices of interest. The implementation of pervasive algorithms with ubiquitous Network features are depicted with changes in frequency topology bands and congestion regression of the Network. The Network would affect the parametric criteria such as bitrate, Cluster-head energy, minimum energy and bandwidth usage. Our improved hybrid Pervasive algorithms would prevent the different attacks and control with the least tolerant error since topology becomes an integral part of the design, providing efficient Routing for the Network. In order to effectively solve the problem, a hybrid tangential transform with improved topologies for effecting network parameters. The other algorithm implicates the energy-efficient with optimization of stochastic conditional inequity for different network sizes. Performance characteristics of the proposed algorithms for WSN would estimate a tolerant error with a factor of 12% on each feature of the network parameter.

Author 1: K Abdul Basith

Author 2: T. N. Shankar

Keywords: SCI (stochastic conditional inequality); LEACH; clustering; DDOS (distributed denial of service); DEEC (distributed energy efficient clustering); TETRA (terrestrial trunked radio); WSN (wireless sensor nework)

Paper 56: FNU-BiCNN: Fake News and Fake URL Detection using Bi-CNN

Abstract: Fake news (FN) has become a big problem in today's world, recognition partly to the widespread use of social media. A wide variety of news organizations and news websites post their stories on social media. It is important to verify that the information posted is genuine and obtained from reputable sources. The intensity and sincerity of internet news cannot be quantified completely and remains a challenge. We present an FNU-BiCNN model for identifying FN and fake URLs in this study by analyzing the correctness of a report and predicting its validity. Stop words and stem words with NLTK characteristics were employed during data pre-processing. Following that, we compute the TF-IDF using LSTM, batch normalization, and dense. The WORDNET Lemmatizer is used to choose the features. Bi-LSTM with ARIMA and CNN are used to train the datasets, and various machine learning techniques are used to classify them. By deriving credibility ratings from textual data, this model develops an ensemble strategy for concurrently learning the depictions of news stories, authors, and titles. To achieve greater accuracy while using Voting ensemble classifier and compared with several machine learning algorithms such as SVM, DT, RF, KNN, and Naive Bayes were tried, and it was discovered that the voting ensemble classifier achieved the highest accuracy of 99.99%. Classifiers' accuracy, recall, and F1-Score were used to assess their performance and efficacy.

Author 1: R. Sandrilla

Author 2: M. Savitha Devi

Keywords: Bi-LSTM; CNN; WORDNET; machine learning; fake news and URL; ARIMA

Paper 57: Dynamic Vehicular Communication using Gaussian Interpolation of Cluster Head Selection (GI-CHS)

Abstract: Decentralized and centralized vehicular communication is investigated in this work using Gaussian interpolation function with cluster head (CH) selection technique. The work uncovered that the best communication approach is to use both centralized and decentralized vehicular communication as combining them will achieve a much more uniform results as a function of communication radius values and vehicular speed. It is also found that vehicular speed contributes negatively to the efficiency of data communication if the relative speed of the vehicles to the communication radius is limited by their ratios. Mathematical expression is presented that relates probability of successful transmission to communication radius for both centralized and decentralized techniques with data proving the importance of the spread parameter within the Gaussian interpolation in a tabulated form, and explained to prove the adaptability of the function used. It is also shown in this work that weights affecting CH selection, thus using Gaussian interpolation is proved to be important as a weighting function in an a adaptive and dynamic vehicular ad-hoc networks (VANETS) covering both vehicle to vehicle (V2V), and vehicle to infrastructure (V2I) communication through cluster head selection.

Author 1: Mahmoud Zaki Iskandarani

Keywords: Cluster head; VANETS; adaptive routing; weighted clustering; Gaussian interpolation; V2V; V2I

Paper 58: A Secure Unmanned Aerial Vehicle Service for Medical System to Improve Smart City Facilities

Abstract: The use of drone technology and drones are currently widespread due to their increasing applications. However, there are some specific security-based challenges in the authentication process. In most drone-based applications, there are many authentication approaches, which are subject to handover delay issues with security complexities for an attack. To end these issues, the presented research has focused on developing a novel Optimized deep learning model known as Fruit Fly based UNet Drone Assisted Security (FFUDAS) to remove the malicious attacks. Moreover, the user requests are stored in the cloud, and the stored data are trained to the drones. Hereafter, the drones can deliver medicine to the requestor’s location; in that, the malicious attacks were changes the location of drones. Once the attack is identified, then the attack removal process is done. Finally, the new path location to the requested user was identified with the help of fruit fly fitness; then the medicines are delivered to the requested user’s location. Furthermore, the designed procedure is executed in an NS2 platform with required nodes. The robustness of the presented model was verified by evaluating the metrics like confidential data rate, execution time, handover delay, pack perception and data delivery rate, and energy consumption. Furthermore, to identify the effectiveness of the presented work, the presented model is compared with other existing schemes. The comparison results show that the presented model has higher throughput, less execution time and handover delay.

Author 1: Birasalapati Doraswamy

Author 2: K. Lokesh Krishna

Author 3: M. N. Giriprasad

Keywords: Drones; security; FFUDAS; malicious attack; fruit fly fitness; path identification; medicine delivery

Paper 59: A Channeled Multilayer Perceptron as Multi-Modal Approach for Two Time-Frames Algo-Trading Strategy

Abstract: FOREX (Foreign Exchanges) is a 24H open market with an enormous daily volume. Most of the used Trading strategies, used individually, are not providing accurate signals. In this paper, we are proposing an automated trading strategy that fits random market behaviors. It is based on neural networks applying triple exponential weighted moving average (EMA) as a trend indicator, Bollinger bands as a volatility indicator, and stochastic RSI as a momentum reversal indicator to prevent false indications in a short time frame. This approach is based on trend, volatility, and momentum reversal patterns combined with a market adaptive and a distributed multi-layer perceptron (MLP). It is called channeled multi-layer perceptron (CMLP) that is a neural network using channels and routines trained by previous profit/loss earned by triple EMA crossover, Bollinger Bands, and Stochastic RSI signals. Instead of using classic computations and Back-propagation for adjusting MLP parameters, we established a channeled multi-layer perceptron inspired by a multi-modal learning approach where each group of modalities (Channel) has its K_c That stands for a dynamic channel coefficient to produce a multi-processed feed-forward neural network that prevents uncertain trading signals depending on trend-volatility-momentum random patterns. CMLP has been compared to Multi-Modal GARCH-ARIMA and has proven its efficiency in unstable markets.

Author 1: Noussair Fikri

Author 2: Khalid Moussaid

Author 3: Mohamed Rida

Author 4: Amina El Omri

Author 5: Noureddine Abghour

Keywords: FOREX; neural networks; EMA; Bollinger band; stochastic RSI; momentum reversal; MLP; back-propagation; feed-forward

Paper 60: A Novel Cyber-attack Leads Prediction System using Cascaded R2CNN Model

Abstract: Novel prediction systems are required in almost all internet-connected platforms to safeguard the user information to get hacked by intermediate peoples. Finding the real impacted factors associated with the Cyber-attack probes are being considered for research. The proposed methodology is derived from various literature studies that motivated to find the unique prediction model that shows improved accuracy and performance. The proposed model is represented as R2CNN that acts as the cascaded combination of Gradient boosted regression detector with recurrent convolution neural network for pattern prediction. The given input data is the collection of various applications engaged with the wireless sensor nodes in a smart city. Each user connected with a certain number of applications that access the authorization of the device owner. The dataset comprises device information, the number of connectivity, device type, simulation time, connectivity duration, etc. The proposed R2CNN extracts the features of the dataset and forms a feature mapping that related to the parameter being focused on. The features are tested for correlation with the trained dataset and evaluate the early prediction of Cyber-attacks in the massive connected IoT devices.

Author 1: P. Shanmuga Prabha

Author 2: S. Magesh Kumar

Keywords: Cyber security in smart devices; cyber security; cyber-attacks; internet of things; IoT devices; machine learning; wireless sensor networks

Paper 61: A Secure and Robust Architecture based on Mobile Healthcare Applications for Patient Monitoring Environments

Abstract: The recent outbreak of COVID-19 pandemic realized the importance of patient monitoring environments, Mobile Healthcare Applications (MHA) plays very crucial role in the successful implementation of patient monitoring environments. Existing MHA’s in the realm of patient monitoring environments are prone to repackaging attacks; do not ensure security, application security and communication security. This paper proposes a secure and robust architecture for mobile healthcare applications in patient monitoring environments ensuring end to end security ensuring all the security properties by overcoming repackaging attacks which are very vital for success of mobile healthcare applications. We implemented our proposed protocol in Android Studio, Kotlin is designed to interoperate fully with Java. ECDH Key exchange algorithm is used for key exchange between MHA in patient’s smart phone and MHA in the hospital TPM. We created an EC key pairs (NIST P-256 aka secp256r1) at patient’s MHA and MHA of hospital TPM by using ECDH and we created a shared AES secret key. AES with GCM mode used for encryption and decryption of patient data.

Author 1: Shaik Shakeel Ahamad

Author 2: Majed Alowaidi

Keywords: Mobile healthcare applications (MHA); UICC (universal integrated circuit card); Kotlin language; android studio; ECDSA (elliptic curve digital signature algorithm); GCM mode; end to end security

Paper 62: A Novel Predictive Scheme for Confirming State of Bipolar Disorder using Recurrent Decision Tree

Abstract: Bipolar disorder is one of the most challenging illnesses where medical science is still struggling to achieve its landmark therapies. After reviewing existing prediction-based approaches towards investigating bipolar disorder, it is noted that existing approaches are more or less symptomatic and relates depression as sadness. It implies various theories that don't consider many precise indicators of confirming bipolar disorder. Therefore, this manuscript presents a novel framework capable of treating the dataset of depression and fine-tune it appropriately to subject it further to a machine learning-based predictive scheme. The proposed system subjects its dataset for a series of data cleaning operations followed by data preprocessing using a standard scale of rating bipolar level. Further usage of feature engineering and correlation analysis renders more contextual inference towards its statistical score. The proposed system also introduces a Recurrent Decision Tree that further contributes towards the predictive outcome of bipolar disorder. The outcome obtained showcases that the proposed scheme performs better than the conventional decision tree.

Author 1: Yashaswini K. A

Author 2: Aditya Kishore Saxena

Keywords: Bipolar disorder; depression; recurrent neural network; decision tree; prediction; sadness

Paper 63: Objective Type Question Generation using Natural Language Processing

Abstract: Automatic Question Generation (AQG) is a research trend that enables teachers to create assessments with greater efficiency in right set of questions from the study material. Today's educational institutions require a powerful tool to correctly assess learner’s mastery of concepts learned through study materials. Objective type questions are an excellent method of assessing a learner's topic understanding in learning process, based on Information and Communication Technology (ICT) and Intelligent Tutoring Systems (ITS).Creating a set of questions for assessment can take a significant amount of time for teachers, and obtaining questions from external sources such as assessment books or question banks may not be relevant to the content covered by students during their studies. This proposed system involves to generate the familiar objective type questions like True or False, ‘Wh’, Fill up with double blank space, match the following type question have generated using Natural Language Processing(NLP) techniquesfrom the given study material. Different rules are created to generate T/F and ‘Wh’ type questions. Dependence parser method has involved in ‘Wh’ questions. Proposed system is tested with Grade V Computer Science text book as an input. Experimental result shows that the proposed system is quite promising to generate the amount of objective type assessment questions.

Author 1: G. Deena

Author 2: K. Raja

Keywords: Intelligent tutoring system; true or false; dependency parser; natural language processing; question generation

Paper 64: IoT based Date Palm Water Management System Using Case-Based Reasoning and Linear Regression for Trend Analysis

Abstract: Palms trees (Phoenix dactylifera L.), Al Nakheel in Arabic are known to have cultural and economic importance to Gulf and Arabic-speaking countries. However, using the traditional method of cultivation, improper use, and depletion of water is perceived as the major challenge as farmers used almost two and a half times the required amount without considering numerous factors. This paper attempts to develop an implementation model of a water management system for Date Palm Trees using Case Based-Reasoning. The said model involves an IoT-based module comprised of NodeMCU, soil moisture, temperature, and humidity sensors that automate the settings of the water amount for the whole year based on palm age, temperature, air humidity, and soil moisture. CBR calculates the amount of water supplied to palm trees (based on initial knowledgebase cited from previous empirical studies) and stores it in a cloud-based database. These data and hardware status can be accessed using a mobile application. When the temperature or soil moisture sensor fails, data trends are retrieved from the database and processed using Linear Regression Analysis. The test results have shown that the proposed model helped in a significant decrease in water consumption compared to the traditional method.

Author 1: Ferddie Quiroz Canlas

Author 2: Moayad Al Falahi

Author 3: Sarachandran Nair

Keywords: Date palm tree; case-based reasoning; IoT; mobile application; NodeMCU; water management system

Paper 65: AquaStat: An Arduino-based Water Quality Monitoring Device for Fish Kill Prevention in Tilapia Aquaculture using Fuzzy Logic

Abstract: In the Philippines, Tilapia fish farming sector is vital to the economy in providing substantial employment, income and meeting local demand for protein sources of the Filipinos. However, the possible benefits that can be derived from this industry are at stake because of the sudden occurrences of fish kill events. This can be attributed to a wide variety of natural and unnatural causes such as old age, starvation, body injury, stress, suffocation, water pollution, diseases, parasites, predation, toxic algae, severe weather, and other reasons. With the identified severe effects of fish kill events to the fish farmers, consumers and the fisheries industry, advanced measures and methods must be established to alleviate the adverse effects of this phenomenon. To solve the underlying problem on water quality monitoring system to improve freshwater aquaculture, various studies were already conducted. However, these studies merely focused on the reading and gathering of water parameters. In this paper, fuzzy logic was used to come up with a model that can analyze and generate result regarding the overall quality of the water being used in Tilapia aquaculture. The water parameters considered in this paper were temperature, dissolved oxygen, and pH level. The results of the water parameter readings using the conventional method were compared to the data that were gathered by AquaStat to test its accuracy and showed no significant difference. Also, the overall water quality obtained using the conventional method was compared to the overall water quality generated by AquaStat and obtained an accurate result.

Author 1: Mark Rennel D. Molato

Keywords: Fuzzy logic; fuzzy sets; fish kill; freshwater aquaculture; Tilapia

Paper 66: Evaluation of Re-identification Risk using Anonymization and Differential Privacy in Healthcare

Abstract: In the present scenario, due to regulations of data privacy, sharing of data with other organization for research or any medical purpose becomes a big hindrance for different healthcare organizations. To preserve the privacy of patients seems like a crucial challenge for Healthcare Centre. Numerous techniques are used to preserve the privacy such as perturbation, anonymization, cryptography, etc. Anonymization is well known practical solution of this problem. A number of anonymization methods have been proposed by researchers. In this paper, an improved approach is proposed which is based on k-anonymity and differential privacy approaches. The purpose of proposed approach is to prevent the dataset from re-identification risk more effectively from linking attacks using generalization and suppression techniques.

Author 1: Ritu Ratra

Author 2: Preeti Gulia

Author 3: Nasib Singh Gill

Keywords: Data privacy; anonymization; differential privacy; re-identification risk analysis; privacy preserving data publishing

Paper 67: Implementation of QT Interval Measurement to Remove Errors in ECG

Abstract: Wireless Body Sensor Network (WBSNs) are devices that can be ported with different detection, storage, computer, but also communication capabilities. Interfacing was beneficial whenever information was collected by many sources, which may lead to erroneous sensory information. During this paper, an information nuclear fission Ensembles technique for working raw healthcare information through WBSNs during ambient cloud computer settings as described. Monitoring data were collected through various instruments and combined to provide statistics on high movements. The simulation was conducted using the low-cost Internet of Things (IoT) surveillance system on chronic kidney disease (CKD). Biosensors have been used in healthcare surveillance systems to record health problems. Patients with CKD would benefit from the developed surveillance system, which will facilitate the early diagnosis of the predominant diseases. This merged information was then sent into using the Aggregation algorithm can forecast premature cardiac illness and CKD. These groups were housed within a Cloud processing context; therefore these forecasting calculations were distributed. Another lengthy practical investigation backs that system provides application, while those findings were encouraging, with 98 percent efficiency whenever the height of that tree was equivalent with 15, total amount if estimation methods are 40, while the overall predicting job was based upon 8 attributes. We compute a mean square ECG waveform from all available leads and use a new technique to measure the QT interval. We tested this algorithm using standard and unique ECG databases. Our real-time QT interval measurement algorithm was found to be stable, accurate, and capable of tracking changing QT values.

Author 1: S. Chitra

Author 2: V. Jayalakshmi

Keywords: e-Health; QT interval; GPU; ECG signal; CKD; IoT

Paper 68: Game-based Learning Increase Japanese Language Learning through Video Game

Abstract: This research was purposed to test the effectiveness of learning the Japanese language through a video game. the video game is built for Personal Computer (PC) users to provide Japanese Language education through video games for teens and adults. The research methods used include literature studies of various books, journals, websites, and theories that can support the writing as well as defining the questions for questionnaires to collect useful data. The development of game application methodology used is Game-Based Learning with Enhanced Learning Experience and Knowledge Transfer (ELEKTRA) methodology, which consists of in-depth analysis of the target audience and learning materials. the effectiveness of video games are evaluated using pre-test and post-test methods. From this researches can be seen that video games are effective to increase the users’ knowledge of the Japanese language. also, a video game has the capability to increase the user’s interest in learning Japanese because of the visual form of the learning process that leads the user to stay engaged with the learning process.

Author 1: Yogi Udjaja

Author 2: Puti Andam Suri

Author 3: Ricky Satria Gunawan

Author 4: Felix Hartanto

Keywords: Video games; ELEKTRA; games-based learning; Japanese; JLPT N5

Paper 69: Fuzzy-set Theory to Support the Design of an Augmentative and Alternative Communication Systems for Aphasia Individuals

Abstract: This paper presents a new design of an Augmentative and Alternative Communication (AAC) systems for conveying delicate feelings or emotions of aphasia individuals, which is based on Fuzzy-set theory. Fuzzy-set theory is crucial in addressing the ambiguity of linguistic terms used and judgments made by aphasia individuals. Due to the communication difficulties of aphasia individuals, their insights were assigned in triangular fuzzy membership functions during the design process of AAC systems. In the proposed design of AAC systems, the delicate feelings or emotions were expressed as a scale, and candidate(s) of delicate feelings or emotions were shown based on their specified position. If the candidate(s) cannot properly convey the desired delicate feelings or emotions, then the corresponding fuzzy membership function can be realized by controlling its position. The proposed method has the advantage of being able to be conveyed the exact want and needs of delicate feelings or emotions during communication. Experimental result shows that conveying delicate feelings or emotions of the aphasia individual could be improved by 50 percent using the proposed design of AAC systems.

Author 1: Md. Sazzad Hossain

Keywords: Aphasia; augmentative and alternative communication; human factors; fuzzy-set theory

Paper 70: Detecting Ransomware within Real Healthcare Medical Records Adopting Internet of Medical Things using Machine and Deep Learning Techniques

Abstract: The Internet of Medical Things was immensely implemented in healthcare systems during the covid 19 pandemic to enhance the patient's circumstances remotely in critical care units while keeping the medical staff safe from being infected. However, Healthcare systems were severely affected by ransomware attacks that may override data or lock systems from caregivers' access. In this work, after obtaining the required approval, we have got a real medical dataset from actual critical care units. For the sake of research, a portion of data was used, transformed, and manifested using laboratory-made payload ransomware and successfully labeled. The detection mechanism adopted supervised machine learning techniques of K Nearest Neighbor, Support Vector Machine, Decision Trees, Random Forest, and Logistic Regression in contrast with deep learning technique of Artificial Neural Network. The methods of KNN, SVM, and DT successfully detected ransomware's signature with an accuracy of 100%. However, ANN detected the signature with an accuracy of 99.9%. The results of this work were validated using precision, recall, and f1 score metrics.

Author 1: Randa ELGawish

Author 2: Mohamed Abo-Rizka

Author 3: Rania ELGohary

Author 4: Mohamed Hashim

Keywords: Artificial neural networks; deep learning; healthcare system; internet of things; machine learning; supervised learning

Paper 71: Data Visualization of Influent and Effluent Parameters of UASB-based Wastewater Treatment Plant in Uttar Pradesh

Abstract: A rise in the population of a region implies an increase in water consumption and such a continuous increase in the usage of water worsens wastewater generation by the region. This escalation in wastewater (influent) requires the Wastewater Treatment Plants (WWTPs) to operate efficiently in order to process the demand for sewage disposal (effluent). This research paper is based upon visualizing and analyzing the parameters of influent like COD, BOD, TSS, pH, MPN and also, the parameters of effluent like COD, BOD, DO, pH and MPN of Bharwara WWTP situated in Lucknow, India which is the largest UASB-based wastewater treatment plant in Asia. We also design and implement an initial model using the machine learning based techniques to analyze as well as predict the parameters of influent and effluent of the WWTP. Model Performance is measured using Mean Squared Error (MSE) and Correlation Coefficient (R). For analyzing and designing the model, the parameters of influent and effluent have been collected over a period of 26 months on a daily basis covering the variations between seasons and climate. As a result, the model shall provide a better quality of effluent along with consuming the plant resources in an efficient manner.

Author 1: Parul Yadav

Author 2: Aditya Chaudhary

Author 3: Anand Keshari

Author 4: Nitish Kumar Chaudhary

Author 5: Priyanshu Sharma

Author 6: Kumar Saurabh

Author 7: Brijesh Singh Yadav

Keywords: Wastewater treatment plant; Bharwara STP; UASB-based plant; influent or effluent prediction; data visualization of influent and effluent; machine learning based for WWTPs

Paper 72: Forecasting Foreign Currency Exchange Rate using Convolutional Neural Network

Abstract: Foreign exchange rate forecasting has always been in demand because it is critical for foreign traders to know how their money will perform against other currencies. Traders and investors are always looking for fresh ways to outperform the market and make more money. As a result, economists, researchers and investors have done a number of studies in order to forecast trends and facts that influence the rise or fall of the exchange rate (ER). In this paper, a new Convolutional Neural Network (CNN) model with a random forest regression layer is used for future closing price prediction. The intended model has been tested using three major currency pairs: Australian Dollar against the Japanese Yen (AUD/JPY), the New Zealand Dollar against the US Dollar (NZD/USD) and the British Pound Sterling against the Japanese Yen (GBP/JPY). As a proof-of-concept, the forecast is made for 1 month, 2 months, 3 months, 4 months, 5 months, 6 months and 7 months utilizing data from January 2, 2001 to May 31, 2020 for AUD/JPY and GBP/JPY and data from January 1, 2003 to May 31, 2020 for NZD/USD. Furthermore, when compared the performance of the suggested model with the Autoregressive Integrated Moving Average (ARIMA), Multi-Layer Perceptron (MLP) and Linear Regression (LR) models and found that the proposed CNN with Random Forest model surpasses all models. The suggested model's prediction performance is assessed using R2, MAE, RMSE performance measures. The proposed model's average R2 values for three currency pairs from one to seven months are 0.9616, 0.9640 and 0.9620, demonstrating that it is the best model among them. The study's findings have ramifications for both policymakers and investors in the foreign exchange market.

Author 1: Manaswinee Madhumita Panda

Author 2: Surya Narayan Panda

Author 3: Prasant Kumar Pattnaik

Keywords: Convolutional neural network; exchange rate; R square; random forest regression method

Paper 73: New Blockchain Protocol for Partial Confidentiality and Transparency (PPCT)

Abstract: Running behind new technologies is increasingly becoming a non-circumventable requirement for organisms’ survival. This is not only a strategy to gain a competitive advantage in the market but it is a determinant key for their continuity and persistence. The Blockchain is at the heart of this technological revolution for which transparency, accessibility to the public and the sense of sharing are fundamental properties of its design. Despite its importance, leveraging this technology in an ethical and secure manner by ensuring confidentiality and privacy is a top concern. Through this work, we try to design a new approach to validate transactions within the Blockchain. Entitled "Protocol for Partial Confidentiality & Transparency PPCT", this new protocol makes possible to seek a compromise between the two requirements: Confidentiality & Transparency. It allows introducing a new notion of confidentiality that we have named partial confidentiality. Subsequently, it applies it on the transactions exchanged while ensuring the process of their validations by the different nodes of the Blockchain. In addition, and through the use of hashing and digital signature functions, this protocol also ensures integrity and authentication within its validation process. To present this work, we will first discuss the state of the art on the different current privacy approaches and our motivation behind this work. Then we will explain more about the different stages of this process, its benefits and areas for improvement.

Author 1: Salima TRICHNI

Author 2: Mohammed BOUGRINE

Author 3: Fouzia OMARY

Keywords: Blockchain; security; privacy; confidentiality; transparency; integrity; authentication; validation process

Paper 74: Image-based Automatic Counting of Bacillus cereus Colonies using Smartphone

Abstract: Substantial amounts of Bacillus cereus bacteria present in food indicates that the food is unsafe to eat, so counting B. cereus colonies in food samples is a common test for food cleanliness. Manual counting of B. cereus bacteria colonies requires approximately 2-5 minutes per Petri dish, depending on the number of colonies present. This study presents a new smartphone-based method called Bacillus Cereus Image Counting System (BCICS, “B. kiks”) for automatic counting of B. cereus colonies. BCICS uses image processing techniques including Projection Profiling, Circle Hough Transformation, Adaptive Thresholding, and Power-Law Transformation to achieve high image clarity and then uses the Connected-Component Labeling (CCL) technique to correctly count the colonies, including overlapping colonies. These techniques are built into a convenient Android smartphone application. Results of counting the colonies with BCICS were compared with results of hand counting the same dishes. The accuracy rate of each dish count was calculated, as well as the average dish accuracy across all dishes. BCICS counted total colonies with an accuracy of 90.14%, which is close to that of hand counting accuracy since hand counting itself commonly involves an error rate of 5-10%. Importantly, the application took only 3-5 seconds to count one Petri dish, which is more than 74 times faster than the time required for manual counting.

Author 1: Phongsatorn Taithong

Author 2: Siriwan Wichai

Author 3: Rattapoom Waranusast

Author 4: Panomkhawn Riyamongkol

Keywords: Bacillus cereus bacteria; colonies; automatic counting; android phone application; image processing

Paper 77: Path Optimization for Mobile Robots using Genetic Algorithms

Abstract: This article proposes a path planning strategy for mobile robots based on image processing, the visibility graphs technique, and genetic algorithms as searching/optimization tool. This proposal pretends to improve the overall execution time of the path planning strategy against other ones that use visibility graphs with other searching algorithms. The global algorithm starts from a binary image of the robot environment, where the obstacles are represented in white over a black background. After that four keypoints are calculated for each obstacle by applying some image processing algorithms and geometric measurements. Based on the obtained keypoints, a visibility graph is generated, connecting all of these along with the starting point and the ending point, as well as avoiding collisions with the obstacles taking into account a safety distance calculated by means of using an image dilation operation. Finally, a genetic algorithm is used to optimize a valid path from the start to the end passing through the navigation network created by the visibility graph. This implementation was developed using Python programming language and some modules for working with image processing ang genetic algorithms. After several tests, the proposed strategy shows execution times similar to other tested algorithms, which validates its use on applications with a limited number of ob-stacles presented in the environment and low-medium resolution images.

Author 1: Fernando Martinez Santa

Author 2: Fredy H. Martinez Sarmiento

Author 3: Holman Montiel Ariza

Keywords: Optimization; path planning; genetic algorithms; visibility graphs

Paper 78: Cryptanalysis of a Hamming Code and Logistic-Map based Pixel-Level Active Forgery Detection Scheme

Abstract: In this paper, we analyze the security of a fragile watermarking scheme for tamper detection in images recently proposed by S. Prasad et al. The chaotic functions are used in the scheme to exploit its pseudo-random behavior and its sensibility to initial condition and control parameter, but despite that, security flaws have been spotted and cryptanalysis of the scheme is conducted. Experimental results shows that the scheme could not withstand the attack and watermarked images were manipulated without triggering any alarm in the extraction scheme. In this paper, two different approaches of attacks are demonstrated and conducted to break the scheme. This work falls into the context of improving the quality of the designed cryptographic schemes taking into account several cryptanalysis techniques.

Author 1: Oussama Benrhouma

Keywords: Cryptanalysis; watermarking; tamper detection; at-tack; chaotic functions; forgery localization

Paper 79: Wifi Indoor Positioning with Genetic and Machine Learning Autonomous War-Driving Scheme

Abstract: Wifi Fingerprinting is a widely used method for indoor positioning due to its proven accuracy. However, the offline phase of the method requires collecting a large quantity of data which costs a lot of time and effort. Furthermore, interior changes in the environment can have impact on system accuracy. This paper addresses the issue by proposing a new data collecting procedure in the offline phase that only needs to collect some data points (Wi-fi reference point). To have a sufficient amount of data for the offline phase, we proposed a genetic algorithm and machine learning model to generate labeled data from unlabeled user data. The experiment was carried out using real Wi-fi data collected from our testing site and the simulated motion data. Results have shown that using the proposed method and only 8 Wi-fi reference points, labeled data can be generated from user’s live data with a positioning error of 1.23 meters in the worst case when motion error is 30%. In the online phase, we achieved a positioning error of 1.89 meters when using the Support Vector Machine model at 30% motion error.

Author 1: Pham Doan Tinh

Author 2: Bui Huy Hoang

Keywords: Wifi fingerprinting; indoor positioning; machine learning; genetic algorithm

Paper 80: Geolocation Mobile Application to Create New Routes for Cyclists

Abstract: In Peru in recent decades it has undergone unex-pected changes, often generating chaos among the population, such as the excess of vehicles that travel daily on the roads generating pollution. This has led people to seek alternatives, such as the use of bike, as a means of transportation. The objective is develop a mobile application for the creation of alternative routes for cyclists. For them we have carried out a survey of 50 people dedicated to the field of cycling as well as people who do not exercise it in order to collect data, analyze it and create mechanisms that help these users. This application was developed in Android Studio implementing free libraries to achieve its geolocation in a way that provides all the facilities for the cyclist to move. For the process of creating this application, the Scrum methodology was used, the design of the prototype is done in Adobe Photoshop. It was obtained as results of the investigation carried out in the survey that 75% of the people are satisfied with the use of the application, 60% responded defining it as very good and 100% answered yes they would recommend the application.The investigation is of importance, since it would allow as future work the reduction of environmental contamination.

Author 1: Jesus F. Lalupu Aguirre

Author 2: Laberiano Andrade-Arenas

Keywords: Android studio; cyclists; mobile application; geolo-cation; scrum

Paper 81: A Software Framework for Self-Organized Flocking System Motion Coordination Research

Abstract: We describe and analyze the basic algorithms for the self-organization of a swarm of robots in coordinated motion as a flock of agents as a strategy for the solution of multi-agent tasks. This analysis allows us to postulate a simulation framework for such systems based on the behavioral rules that characterize the dynamics of these systems. The problem is approached from the perspective of autonomous navigation in an unknown but restricted and locally observable environment. The simulation framework allows defining individually the characteristics of the basic behaviors identified as fundamental to show a flocking behavior, as well as the specific characteristics of the naviga-tion environment. It also allows the incorporation of different path planning approaches to enable the system to navigate the environment for different strategies, both geometric and reactive. The basic behaviors modeled include safe wandering, following, aggregation, dispersion, and homing, which interact to generate flocking behavior, i.e., the swarm aggregates, reach a stable formation and move in an organized fashion toward the target point. The framework concept follows the principle of constrained target tracking, which allows the problem to be solved similarly as a small robot with limited computation would solve it. It is shown that the algorithm and the framework that implements it are robust to the defined constraints and manage to generate the flocking behavior while accomplishing the navigation task. These results provide key guidelines for the implementation of these algorithms on real platforms.

Author 1: Fredy Martinez

Author 2: Holman Montiel

Author 3: Edwar Jacinto

Keywords: Flocking; formation control; motion planning; multi-robot system; obstacle avoidance; swarm

Paper 82: Trust-based Access Control Model with Quantification Method for Protecting Sensitive Attributes

Abstract: The prevailing trend of the seamless digital collec-tion has prompted privacy concerns to the organization. In enforc-ing the automation of privacy policies and laws, access control has been one of the most devoted subjects. Despite the recent advances in access control frameworks and models, there are still issues that hinder the implementation of successful access control. This paper illustrates the problem of the previous model which typically preserves data without explicitly considering the protection of sensitive attributes. This paper also highlights the drawback of the previous works which provides inaccurate calculation to specify user’s trustworthiness. Therefore, a trust-based access control (TBAC) model is proposed to protect sensitive attributes. A quantification method that provides accurate calculation of the two user properties is also proposed, namely: seniority and behaviour to specify user’s trustworthiness. Experiment have been conducted to compare the proposed quantification method and the previous quantification methods. The result shows that the proposed quantification method is stricter and accurate in specifying user’s trustworthiness as compared to the previous works. Therefore, based on the result, this study resolves the issue of specifying the user’s trustworthiness. This study also indicates that the issue of protecting sensitive attributes has been resolved.

Author 1: Mohd Rafiz Salji

Author 2: Nur Izura Udzir

Author 3: Mohd Izuan Hafez Ninggal

Author 4: Nor Fazlida Mohd. Sani

Author 5: Hamidah Ibrahim

Keywords: Access control; trust-based access control; quantifi-cation method; sensitive attributes; privacy; privacy protection

Paper 83: Feature based Entailment Recognition for Malayalam Language Texts

Abstract: Textual entailment is a relationship between two text fragments, namely, text/premise and hypothesis. It has applications in question answering systems, multi-document sum-marization, information retrieval systems, and social network analysis. In the era of the digital world, recognizing semantic variability is important in understanding inferences in texts. The texts are either in the form of sentences, posts, tweets, or user experiences. Hence understanding inferences from customer experiences helps companies in customer segmentation. The availability of digital information is ever-growing with textual data in almost all languages, including low resource languages. This work deals with various machine learning approaches applied to textual entailment recognition or natural language inference for Malayalam, a South Indian low resource language. A performance-based analysis using machine learning classification techniques such as Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, AdaBoost, and Naive Bayes is done for the MaNLI (Malayalam Natural Language Inference) dataset. Different lexical and surface-level features are used for this binary and multiclass classification. With the increasing size of the dataset, there is a drop in the performance of feature-based classification. A comparison of feature-based models with deep learning approaches highlights this inference. The main focus here is the feature-based analysis with 14 different features and its comparison, essential to any NLP classification problem.

Author 1: Sara Renjit

Author 2: Sumam Mary Idicula

Keywords: Textual entailment; natural language inference; Malayalam language; machine learning; deep learning

Paper 84: Towards Linguistic-based Evaluation System of Cloud Software as a Service (SaaS) Provider

Abstract: Cloud Software as a Service (SaaS) is a type of delivering software application by using Cloud computing Infrastructure services. Cloud SaaS used the global Internet connection to offer its services to the client consumers. The selection of Cloud SaaS provider is based on the evaluation mechanism that the Cloud SaaS consumer manage before making the service contract. In this paper, the linguistic-based evaluation of Cloud SaaS quality attributes has been proposed to help the consumer to assess the service for optimal service selection. Our proposed approach has been developed by the combinations of fuzzy logic and TOPSIS MCDM methods. The proposed approach helps the Cloud SaaS consumer to select the optimal service Cloud SaaS service provider. The case study has been proposed in order to demonstrate the proposed approach.

Author 1: Mohammed Abdulaziz Ikram

Author 2: Ryan Alturki

Author 3: Farookh K. Hussain

Keywords: Cloud services; software as a service (SaaS); eval-uation system; quality of experience (QoE); fuzzy logic; TOPSIS

Paper 85: Rectenna Design for Enhanced Node Lifetime in Energy Harvesting WSNs

Abstract: In a scenario where every possible solution is investigated for sustainability, Energy Harvesting (EH) stands as an undisputed candidate for enhancing the network lifetime in WSNs where node lifetime decides the network’s life. Radio Frequency (RF) energy is abundantly available in the ambience among all the available energy sources. Since both information and power are transmitted in an RF signal, EH is possible in the far-field region. At first, we present a novel 4-element rectangular Patch Antenna Array (PAA) design of EH rectenna. The receiving antenna is designed to pick up the radio signal in the RF range (2.45 GHz) from the free space. Then, the H-shape antenna is modified by introducing a circular slot to enhance the bandwidth. The paper compares the results of the basic parameters of the antenna, such as return loss, input impedance, bandwidth, gain, directivity, and efficiency. As a result, the modified H-shaped antenna (with circular slot) has an increased gain from 8.24 dB to 8.32 dB, with a reduced return loss from -10 dB to -16 dB and enhanced bandwidth from 64.8 MHz to 868 MHz. The high gain, large bandwidth, suitably matched impedance for a minor return loss, and high efficiency of the modified H-shaped patch antenna makes it eligible for energy harvesting application.

Author 1: Prakash K Sonwalkar

Author 2: Vijay Kalmani

Keywords: Antenna design; backscattering; beamfroming; en-ergy harvesting; sequential rule; wireless sensor networks

Paper 86: Politicians-based Deep Learning Models for Detecting News, Authors and Media Political Ideology

Abstract: Non-partisanship is one of the qualities that con-tribute to journalistic objectivity. Factual reporting alone cannot combat political polarization in the news media. News framing, agenda settings, and priming are influence mechanisms that lead to political polarization, but they are hard to identify. This paper attempts to automate the detection of two political science concepts in news coverage: politician personalization and political ideology. Politicians’ news coverage personalization is a concept that encompasses one more of the influence mechanisms. Political ideologies are often associated with controversial topics such as abortion and health insurance. However, the paper prove that politicians’ personalization is related to the political ideology of the news articles. Constructing deep neural network models based on politicians’ personalization improved the performance of political ideology detection models. Also, deep networks models could predict news articles’ politician personalization with a high F1 score. Despite being trained on less data, personalized-based deep networks proved to be more capable of capturing the ideology of news articles than other non-personalized models. The dataset consists of two politician personalization labels, namely Obama and Trump, and two political ideology labels, Democrat and Republican. The results showed that politicians’ personalization and political polarization exist in news articles, authors, and media sources.

Author 1: Khudran M. Alzhrani

Keywords: Deep neural networks; text classification; political ideology; politician personalization

Paper 87: Multi-Spectral Imaging for Fruits and Vegetables

Abstract: In the field of agriculture, fruit grading and veg-etable classification is an important and challenging task. The current fruit and vegetable classifications are done manually, which results in inconsistent performance. There is an influence of external surroundings on this manual classification. Sometimes getting an expert fruit or vegetable grader, is challenging and the performance of that person may become stagnant over some time. With the recent development in computer technology and multi-spectral camera system, it is possible to achieve an efficient fruit grading or vegetable classification system. In this manuscript, we summarize different automated fruit grading as well as vegetable classification systems, which are based on multi-spectral imaging. We have focused our analysis on four major areas such as varietal identification, fruit quality assessment, classification, and disease detection. From our analysis, we have found that the Partial Least Square Discriminant Analysis (PLS-DA) was most effective for identifying varieties of tomato seeds. For analyzing the quality of pomegranate fruits, the multiple linear regression model was the most optimal method. Multi-Layer Perceptron (MLP) classifier was the recommended method for classifying medicinal plant leaves. A Linear Discriminant Analysis (LDA) based classifier could accurately detect diseases in fruits and vegetables.

Author 1: Shilpa Gaikwad

Author 2: Sonali Tidke

Keywords: Multi-spectral imaging; fruit grading; vegetable classification; fruit quality; disease detection; fruit maturity

Paper 88: Detecting Malware Families and Subfamilies using Machine Learning Algorithms: An Empirical Study

Abstract: Machine learning algorithms have proved their effectiveness in detecting malware. This paper conducts an em-pirical study to demonstrate the effectiveness of selected machine learning algorithms in detecting and classifying Android malware using permissions features. The used dataset consists of 9000 different malicious applications from the CIC-Maldroid2020, CIC-Maldroid2017 and CIC-InvesAndMal2019 datasets collected by the Canadian Institute for Cybersecurity. Meta-Multiclass and Random Forest ensemble classifiers are used based on different machine learning classifiers to overcome the imbalance in the data classes. Moreover, a genetic attribute selection technique and SMOTE are used to classify Ransomware sub-families to handle the small size of the dataset and underfitting problem. The results show that optimization and ensemble approaches are successful in treating dataset issues, with 95% accuracy in classifying big malware families and 80% in Ransomware subfamilies.

Author 1: Esraa Odat

Author 2: Batool Alazzam

Author 3: Qussai M. Yaseen

Keywords: Malware classification; machine learning; SMOT; information security

Paper 89: Systematic Exploration and Classification of Useful Comments in Stack Overflow

Abstract: Stack Overflow is a public platform for developers to share their knowledge on programming with an engaged community. Crowdsourced programming knowledge is not only generated through questions and answers but also through comments which are commonly known as developer discussions. Despite the availability of standard commenting guidelines on Stack Overflow, some users tend to post comments not adhering to those guidelines. This practice affects the quality of the developer discussion, thus adversely affecting the knowledge-sharing process. Literature reveals that analyzing the comments could facilitate the process of learning and knowledge sharing. Therefore, this study intends to extract and classify useful comments into three categories: request clarification, constructive criticism, and relevant information. In this study, the classifi-cation of useful comments was performed using the Support Vector Machine (SVM) algorithm with five different kernels. Feature engineering was conducted to identify the possibility of concatenating ten external features with textual features. During the feature evaluation, it was identified that only TF-IDF and N-grams scores help classify useful comments. The evaluation results confirm Radial Basis Function (RBF) kernel of the SVM classification algorithm performs best in classifying useful comments in Stack Overflow regardless of the usage of the optimal combinations of hyperparameters.

Author 1: Prasadhi Ranasinghe

Author 2: Nipuni Chandimali

Author 3: Chaman Wijesiriwardana

Keywords: Stack overflow; useful comments; machine learning; SVM; classification

Paper 90: A New Index for Detecting Frequency of Unknown Underwater Weak Signals with Genetic Algorithm

Abstract: In this paper, a new index is proposed for detecting the frequency of unknown underwater signals based on the stochastic resonance theory. When the received weak signal is input into the stochastic resonance system, first, by frequency analysis, the frequency with the highest amplitude Aₘ of the output signal spectrum is considered as the pre-detection fre-quency. Then a cosine signal with the pre-detection frequency and unit amplitude is constructed. Define the pre-signal-to-noise-ratio as the logarithm of the squared amplitude Aₘ over the mean of signal amplitudes in all other frequencies. The new index is defined as the product of the pre-signal-to-noise-ratio and the correlation coefficient between the received unknown signal and the constructed cosine signal. The new index is featured by taking into account the signal characteristics in both time and frequency domain, and it will yield better signal frequency detection performance. In addition, to improve the time efficiency of the frequency detection, a method to bound the searching range, keyed to the genetic algorithm, of the stochastic resonance system parameters is proposed. The method can be used to detect the frequency of both single frequency and frequency-hopping unknown signals. With the designed new index and system parameter bounding method, the simulations and experiments for the weak underwater unknown signals are conducted. Compared to the piecewise mean value index and weighted power spectral kurtosis index, the new index yields a higher detection probability at varied input signal-to-noise ratios and signal frequencies. With bounding system parameter searching ranges, the time efficiency is improved. The main purpose of this paper is to detect the frequency of unknown underwater weak signals by stochastic resonance system with genetic algorithm. The main contributions are summarized as follows. First, the detection probability of weak signals is improved by stochastic resonance system with the proposed signal detection index than some other indexes. Second, to improve the time efficiency of the signal frequency detection, a method to bound the searching range of system parameters is proposed.

Author 1: Weixiang Yu

Author 2: Xiukui Li

Keywords: Stochastic resonance; underwater weak signal de-tection; genetic algorithm; frequency detection; frequency-hopping signal; index

Paper 91: Extraction of Point-of-Interest in Multispectral Images for Face Recognition

Abstract: Security systems in companies, airports, enter-prises, etc. face numerous challenges. Among the major ones there is objects or face recognition. The problem with the robustness of recognition systems that usually affects color images nowadays can be addressed by multispectral image acquisition in the near infrared range with cameras equipped with new high performance sensors able to take images in dark or uncontrolled environments with much more accuracy. Multispectral CMOS (Complementary Metal Oxide Semi-conductor) sensors in a single shot record several wavelengths that are isolated and allow very specific analyses. They are equipped with new acquisition methods and provide observations that are more accurate. The current generation of these imaging sensors involve scientific and technical interest because they provide much more information than those that operate in visible range; precise nature and spatio-temporal evolution of the areas need to be analyzed. In this study, multispectral images acquired by camera equipped with a hybrid sensor operating in near infrared has been used. This camera is built in the ImViA laboratory of the University of Bourgogne as part of the European project EXIST (EXtended Image Sensing Technologies). The process involved in image acquisition, image mosaicing and image demosaicing by using mosaic filters. After acquisition process the interest points be extract in these bands of images in order to know how information is shared out all over the bands. The results were satisfactory because information is spread all over the images bands and the algorithms used also have detected many interest points. Based on the results, a large database can be set up for a face recognition system building.

Author 1: Kossi Kuma KATAKPE

Author 2: Lyes AKSAS

Author 3: Diarra MAMADOU

Author 4: Pierre GOUTON

Keywords: Multispectral image; hybrid sensor; image mosaic-ing; image demosaicing; mosaic filter

Paper 92: The Effectiveness of CATA Software in Exploring the Significance of Modal Verbs in Large Data Texts

Abstract: This paper investigates the effectiveness of using and applying CATA (Computer-Aided Text Analysis) software in exploring the extent to which particular modals are significant in communicating the ideological and thematic messages of literary discourse. More specifically, the paper attempts to test the hypothesis that CATA software, including FDA (Frequency Distribution Analysis), KWICK (Key Word in Context), CA (Content Analysis), and TDA (Thematic Distribution Analysis) are effectively helpful in the linguistic and ideological analysis of modals in literary texts. To this end, the paper uses the frequency distribution analysis (FDA) and applies it to Edward Bond’s Lear as a sample representing literary texts. Two modal verbs were selected to be computationally analyzed by means of the frequency distribution analysis in order to decode the different ideologies they carry in the discourse of the selected play. These are will and must. These modal verbs were computationally displayed within their contextual, total and indicative occurrences in the play under investigation to demonstrate the way they convey particular ideologies. Findings revealed that CATA software represented in its variable of FDA is highly contributive to communicating ideologies in the play under investigation. The paper further demonstrated two findings: first, via CATA software, analysts can easily arrive at the ideological significance of the various classes of words, including modal verbs that are used in literary texts; and, second, the analysis showed that only a few occurrences out of the total number of frequencies of the modal verbs at hand are indicative in conveying the hidden ideologies of their users.

Author 1: Ayman Farid Khafaga

Keywords: CATA software; frequency distribution analysis; ideologies; modal verbs; Bond’s Lear

Paper 93: Detection of Criminal Behavior at the Residential Unit based on Deep Convolutional Neural Network

Abstract: Studies on abnormal behavior based on deep learning as a processing platform increase. Deep learning, specifically the convolutional neural network (CNN), is known for learning the features directly from the raw image. In return, CNN requires a high-performance hardware platform to accommodate its computational cost like AlexNet and VGG-16 with 62 million and 138 million parameters, respectively. Hence in this study, four CNN samplings with different architectures in detecting abnormal behavior at the gate of residential units are evaluated and validated. The forensic postures, with some other collected data, are used for the preliminary step in constructing the criminal case database. High accuracy up to 97% is obtained from the trained CNN samplings with 80% to 97% recognition rate achieved during the offline testing and 70% to 90% recognition rate recorded during the real-time testing. Results showed that the developed CNN samplings owned good performance and can be utilized in detecting and recognizing the normal and abnormal behavior at the gate of residential units.

Author 1: H. A. Razak

Author 2: Nooritawati Md Tahir

Author 3: Ali Abd Almisreb

Author 4: N. K. Zakaria

Author 5: N. F. M. Zamri

Keywords: Abnormal behavior; deep learning; convolution neural network; forensic posture; property crime

Paper 94: Teacher e-Training and Student e-Learning during the Period of Confinement Caused by Covid-19 in Case of Morocco

Abstract: The rapid advance of the new coronavirus imposes several drastic measures on the authorities to contain the virus and prevent its spread. The Ministry of Education has decreed the suspension of face-to-face classes in all schools. The pedagogical continuity, now a priority, must be carried out remotely through video conferencing, platforms, video capsules The main questions of this research are: What are the success factors of distance learning and training in Moroccan context? This raises a whole range of questions: are teachers able to adopt this new teaching method? Are the means available and adequate to ensure distance learning? What about the training of teachers to cope with this unexpected radical change? Based on the results obtained from a population of 126 teachers, we discovery that 91% of teachers said that they have adopted the online teaching but it is not really e-learning as recognized by the specialists, its objective is rather to maintain communication with the students. While 9% have not used this mode of teaching, they point out that this type of teaching does not guarantee equal opportunities for learners. We have therefore concluded that the necessary material resources must be made available to ensure the success of this type of teaching, such as computers and the Internet, as well as the necessary training for teachers to develop their skills associated with managing distance learning.

Author 1: Abdessamad El Omari

Author 2: Malika Tridane

Author 3: Said Belaaouad

Keywords: COVID-19; e-learning; e-training; change; innovation

Paper 95: Performance Evaluation of Different Raspberry Pi Models for a Broad Spectrum of Interests

Abstract: Now-a-days, Single Board Computers (SBCs), especially Raspberry Pi (RPi) devices, are extensively used due to their low cost, efficient use of energy, and successful implementation in a wide range of applications; therefore, evaluating their performance is critical to better understand the applicability of RPis to solve problems in different areas of knowledge. This paper describes a comparative and experimental study regarding the performance of five different models of the RPi family (RPi Zero W, RPi Zero 2 W, RPi 3B, RPi 3B+, and RPi 4B) in several scenarios and with different configurations. To conduct our multiple experiments on RPis, we used a self-developed and other existing open-source benchmarking tools allowing us to perform tests that mimic real-world needs, assessing important factors including CPU frequency and temperature during stressful activities, processor performance when executing CPU-intensive processes such as audio and file compressions as well as cryptographic operations, memory and microSD storage performance when executing read and write operations, TCP throughput in different WiFi bands, and TCP latency to send a specific payload from a source to a destination. Our experimental results showed that the RPi 4B significantly outperformed the other SBCs tested. In addition, our research indicated that the RPi Zero 2 W overclocked, RPi 3B, and RPi 3B+ had similar performance. Finally, the RPi Zero 2 W showed a much higher capacity than its predecessor, the RPi Zero W, and seems to be a perfect replacement when upgrading, since they have the same form factor and are physically interchangeable. With this study, we aim to guide researchers and hobbyists in selecting adequate RPis for their projects.

Author 1: Eric Gamess

Author 2: Sergio Hernandez

Keywords: Performance evaluation; benchmarks; raspberry pi; single board computer