IJACSA Volume 11 Issue 7 - thesai.org

IJACSA Volume 11 Issue 7

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: Dependency Evaluation and Visualization Tool for Systems Represented by a Directed Acyclic Graph

Abstract: There is a dearth of data visualization tools for displaying college degree-planning information, especially course prerequisite and complex academic requirement information. The existing methods for exploring degree plans involve a painstaking what-if analysis of static data presented in a convoluted format. In this paper, we present a data visualization tool, named as Dependency Evaluation and Visualization (DEV) chart, to visualize course prerequisite structure and a dynamic flowchart to guide students and advisors through all possible degree requirement completions. DEV chart uses an adjacency matrix of a directed acyclic graph to store a course structure for a degree into a database. Since DEV chart is created dynamically by updating data associated with each node of the directed graph, it provides a mechanism for adding an alert system when prerequisite conditions are not met, and hence the user can visualize the available courses at each step. Similarly, DEV chart can be used with project planning where nodes represent tasks and edges represent their dependencies.

Author 1: Sobitha Samaranayake

Author 2: Athula Gunawardena

Keywords: Data visualization; degree planning; dynamic flowchart; prerequisite structure; adjacency matrix

Paper 2: “Dr.J”: An Artificial Intelligence Powered Ultrasonography Breast Cancer Preliminary Screening Solution

Abstract: Breast cancer ranks top incidence rate among all malignant tumors for women, globally. Early detection through regular preliminary screening is critical to decreasing the breast cancer’s fatality rate. However, the promotion of preliminary screening faces major limitations of human diagnosis capacity, cost, and technical reliability in China and most of the world. To meet these challenges, we developed a solution featuring an innovative division of labor model by incorporating artificial intelligence (AI) with ultrasonography and cloud computing. The objective of this research was to develop a solution named “Dr.J”, which applies AI to process real-time video live feed from ultrasonography, which is physically safe and more suitable for Asian women. It can automatically detect and highlight the suspected breast cancer lesions and provide BI-RADS (Breast Imaging-Reporting and Data System) ratings to assist human diagnosis. “Dr.J” does not require its frontline operators to have prior medical or IT background and thus significantly lowers manpower threshold for preliminary screening promotion. Furthermore, its cloud computing platform can store detailed breast cancer data such as images and BI-RADS ratings for further essential needs in medical treatment, research and health management, etc. as well as establishing a hierarchy medical service network for this disease. Therefore, “Dr.J” significantly enhances the availability and accessibility of preliminary screening service for breast cancer at grassroots.

Author 1: Zhenzhong Zhou

Author 2: Xueqin Xie

Author 3: Alex L. Zhou

Author 4: Zongjin Yang

Author 5: Muhammad Nabeel

Author 6: Yongjie Deng

Author 7: Zhongxiong Feng

Author 8: Xiaoling Zheng

Author 9: Zhiwen Fang

Keywords: Breast cancer preliminary screening; lesions detection; ultrasonography; artificial intelligence; deep learning; cloud computing; BI-RADS

Paper 3: Porting X Windows System to Operating System Compliant with Portable Operating System Interface

Abstract: Now-a-days graphical interface is very important for any operating system, even the embedded ones. Adopting existing solutions will be much easier than developing your own. Moreover, a lot of software may be reused in this case. This article is devoted to X Window System adaptation for Portable Operating System Interface (POSIX) compliant real-time operating system Baget. Many encountered problems come from the tight connection between X and Linux, therefore it is expected to encounter these issues during usage of X on non-Linux systems. Discussed problems include, but not limited to the absence of dlopen, irregular file paths, specific device drivers. Instructions and recommendations to solve these issues are given. A comparison between XFree86 and Xorg implementations of X is discussed. Although synthetic tests show Xorg performance superiority, XFree86 consumes fewer system resources and is easier to port.

Author 1: Andrey V Zhadchenko

Author 2: Kirill A. Mamrosenko

Author 3: Alexander M. Giatsintov

Keywords: X Window System; X11; X.Org Server; Xorg; XFree86; Portable Operating System Interface (POSIX); graphics; Realtime Operating System (RTOS)

Paper 4: Developing Web-based Support Systems for Predicting Poor-performing Students using Educational Data Mining Techniques

Abstract: The primary goal of educational systems is to enrich the quality of education by maximizing the best results and minimizing the failure rate of poor-performing students. Early predicting student performance has become a challenging task for the improvement and development of academic performance. Educational data mining is an effective discipline of data mining concerned with information integrated into the education domain. The study is of this work is to propose techniques in educational data mining and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models was conducted. Subsequently, high performing models were developed to get higher performance. The hybrid random forest named Hybrid RF produces the most successful classification. For the context of intervention and improving the learning outcomes, a novel feature selection method named MICHI, which is the combination of mutual information and chi-square algorithms based on the ranked feature scores is introduced to select a dominant set and improve performance of prediction models. By using the proposed techniques of educational data mining, and academic performance prediction system is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental results and evaluation surveys report the effectiveness and usefulness of the developed academic prediction system. The system is used to help educational stakeholders for intervening and improving student performance.

Author 1: Phauk Sokkhey

Author 2: Takeo Okazaki

Keywords: Academic performance prediction systems; educational data mining; dominant factors; feature selection methods; prediction models; student performance

Paper 5: Network Reconfiguration for Minimizing Power Loss by Moth Swarm Algorithm

Abstract: This paper presents a network reconfiguration approach for minimizing power loss of the distribution system based on moth swarm algorithm (MSA). The MSA is a recent metaheuristic inspired from the navigational technique of moths in the dark for finding food sources. For searching optimal solution, MSA used three different mechanisms of generating new solutions consisting of Lévy-flights, Gaussian walks and spiral flight. The effectiveness of MSA is validated on two distribution systems consisting of the 33-nodes and 69-nodes. The simulation results are compared to particle swarm optimization and other available approaches in the literature. The calculated results on the test systems show that MSA can be an effective and reliable tool for the NR problems.

Author 1: Thuan Thanh Nguyen

Author 2: Duong Thanh Long

Keywords: Network reconfiguration; moth swarm algorithm; power loss; particle swarm optimization; distribution system

Paper 6: Reduction of the Humidity Contained in the Harvest Cereals by the Means of in High Frequency Electromagnetic Field Processing

Abstract: The new environmental friendly microwave technologies represents an important concern in the environmental policies. The use of microwave energy for the processing of different agricultural products presents the advantage of a green technology which allow a uniform distribution of electromagnetic and thermal field with a short relatively time of the process. In the paper is studied the microwave drying technology used in the drying process of oat seeds. In this sense the experiments were carried out for different working conditions of the equipment with respect to applied microwave power and obtained temperatures. A numerical model associated to the problem and solved by the means of finite element method is used. These allows us to obtain the electromagnetic field distribution through simulation inside the microwave dryer. The simulations were performed in order to obtain good quality products that may be used for seeding and food industry. The approached method is flexible so as it can be applied to all cereals.

Author 1: Cornelia Emilia Gordan

Author 2: Ioan Mircea Gordan

Author 3: Vasile Darie ?oproni

Author 4: Carmen Otilia Molnar

Author 5: Mircea Nicolae Arion

Author 6: Francisc Ioan Hathazi

Keywords: High frequency electromagnetic field; numerical simulation; microwave processing; oat drying; agricultural seeds

Paper 7: Optimization of Production Processes using BPMN and ArchiMate

Abstract: This article aims to map and optimize production processes through the graphical form using syntax combination of BPMN and ArchiMate. In the first phase, the existing business processes of the manufacturing company in the Czech Republic were analyzed. In the second phase, the optimization of produc-tion processes was subsequently proposed. These optimizations were based on a combination of two ArchiMate and BPMN syntaxes with implementing ERP systems, enabling the design to utilize more efficient modern technology. The as-is-to-be process was documented in BPMN and ArchiMate, and a process-based simulation tool was used to quantify the effects of process improvement.

Author 1: Hana Tomaskova

Keywords: Production processes; graphic modelling; BPMN; ArchiMate

Paper 8: Cluster based Detection and Reduction Techniques to Identify Wormhole Attacks in Underwater Wireless Sensor Networks

Abstract: Underwater Wireless Sensor Networks (UWSN) is widely used in variety of applications but none of the applications have taken network security into considerations. Deployment of underwater network is a challenging task and because of the hash underwater environment, the network is vulnerable to large class of security attacks. Recent research on underwater communication focuses mainly on energy efficiency, network connectivity and maximum communication range. The nature of underwater sensor network makes it more attractive for the attackers. One of the most serious problems in underwater networks is wormhole attack. In this research work we concentrate on providing security to the underwater network against wormhole attacks. We introduce the wormhole attack in the network and propose a solution to detect this attack in underwater wireless networks. Energy Efficient Hybrid Optical - Acoustic Cluster Based Routing Protocol (EEHRCP) is incorporated and using the round trip time and other characteristics of wormhole attack, the presence of the wormhole attack in the network is identified. The simulation results depicts that the proposed wormhole detection mechanism increases throughput by 26%, reduces energy consumption by 3%, reduces end to end delay by 13% and increases packet delivery ratio by 3%.

Author 1: Tejaswini R Murgod

Author 2: S Meenakshi Sundaram

Keywords: Underwater communication; wormhole attack; round trip time; EEHRCP

Paper 9: Effect of Multi-Frequency Beam Alignment on Non-Line-of-Site Vehicle to Infrastructure Communication using CI Model (CI-NLOS-V2I)

Abstract: Investigation of the effect of beam alignment for milimeter wave (mmWave) transmission in the case of Vehicle-to-Infrastructure communication (V2I) is carried out. The investigation covered varying transmission-reception (TX-RX) distances. The effect of carrier frequency variation using different antenna angles and gains is also analyzed. The results showed convergence of path loss (PL) values regardless of angle or antenna gain (dBi). The investigation also proved that shadow fading (SF), which is related to standard deviation () and exponent number (n) is a main contributor to the observed high path loss values in the case of misalignment. It is also noted that the path loss values decreases as a function of frequency per same travelled distance, which is related to the exponent number. This work highlights the importance of antenna alignment and that V2I communication can be very much optimized if and when auto-antenna alignment is used, and the importance of multi-antenna arrays.

Author 1: Mahmoud Zaki Iskandarani

Keywords: Intelligent transportation systems; autonomous vehicles; connected vehicles; mmWave; channel model; path loss; CI Model; NLOS; V2I; V2V

Paper 10: A Cyber-Physical Approach to Resilience and Robustness by Design

Abstract: Modern critical infrastructures (e.g. Critical Energy Infrastructures) are increasingly evolving into complex and distributed networks of Cyber-Physical Systems. Although the cyber systems provide great flexibility in the operation of critical infrastructure, it also introduces additional security threats that need to be properly addressed during the design and development phase. In this landscape, resilience and robustness by design are becoming fundamental requirements. In order to achieve that, new approaches and technological solutions have to be developed that guarantee i) the fast incident/attack detection; and ii) the adoption of proper mitigation strategies that ensure the continuity of service from the infrastructure. The “Double Virtualization” emerged recently as a potential strategy/approach to ensure the robust and resilient design and management of critical energy infrastructures based on Cyber-Physical Systems. The presented approach exploits the separation of the virtual capabilities/functionalities of a device from the physical system and/or platform used to run/execute them while allowing to dynamically (re-) configure the system in the presence of predicted and unpredicted incidents/accidents. Internet-based technologies are used for developing and deploying the envisioned approach.

Author 1: Giovanni Di Orio

Author 2: Guilherme Brito

Author 3: Pedro Malo

Author 4: Abhinav Sadu

Author 5: Nikolaus Wirtz

Author 6: Antonello Monti

Keywords: Double virtualization; critical energy infrastructures; cyber-physical systems; resilience

Paper 11: Text Messages: A Computer-Mediated Discourse Analysis

Abstract: This study explores the discourse of text messages from a microlinguistic perspective by means of concordance analysis. It aims at sorting the dominant phonological, lexical and grammatical features that mark texting as a peculiar asynchronous mode of computer-mediated communication. Also, it investigates how technology reshapes texters’ linguistic habits as long as spatio-temporal constraints are imposed. The study goes beyond the description of linguistic features as it takes at its core the explanation of the functions performed by each of these features. Findings showed that most of the phonological, lexical and grammatical features of the discourse of text messages were consciously employed to save space and to speed up communication. Furthermore, the study demonstrated that though the discourse of text messages is space-bound and visually decontextualized, it proved to be cohesive, adaptable and interactive in order to perform common language functions such as greetings, expressing attitudes, congratulations, showing involvement, asking for information and demonstrating social solidarity. Finally, based on textual evidence, findings showed that texters created a set of orthographical surrogates to recompense the absence of verbal and para-verbal cues due to specific technological affordances.

Author 1: Waheed M. A. Altohami

Keywords: Text messages; computer-mediated communication; discourse; technological affordances

Paper 12: Flood Damage Area Detection Method by Means of Coherency Derived from Interferometric SAR Analysis with Sentinel-A SAR

Abstract: Flood damage area detection method by means of coherency derived from interferometric SAR analysis with Sentinel-A SAR is proposed. One of the key issues for flooding area detection is to estimate it as soon as possible. The flooding area due to heavy rain, typhoon, severe storm, however, is usually covered with clouds. Therefore, it is not easy to detect with optical imagers onboard remote sensing satellite. On the other hand, Synthetic Aperture Radar: SAR onboard remote sensing satellites allows to observe the flooding area even if it is cloudy and rainy weather conditions. Usually, flooding area shows relatively small back scattering cross section due to the fact that return signal from the water surface is quite small because of dielectric loss. It, however, is not clear enough of the flooding area detected by using return signal of SAR data from the water surface. The proposed method uses coherency derived from interferometric SAR analysis. Through experiment, it is found that the proposed method is useful to detect the flooding area clearly.

Author 1: Kohei Arai

Author 2: Hiroshi Okumura

Author 3: Shogo Kajiki

Keywords: Flooding area detection; Synthetic Aperture Radar: SAR; interferometric SAR analysis; coherency; back scattering cross section; remote sensing satellite

Paper 13: Barley Quality Estimation Method with UAV Mounted NIR Camera Data based on Regressive Analysis

Abstract: Barley quality estimation method with Unmanned Aerial Vehicle: UAV based Near Infrared: NIR camera data based on regressive analysis is proposed. The proposed method allows to predict barley quality, anthocyanin, β-glucan and water contents in the harvested “Daishimochi” of barley grains before the harvest. The prediction method proposed here is based on regression analysis with the Near Infrared: NIR camera data mounted on UAV which allows to estimate barley quality, anthocyanin, β-glucan and water contents in the harvested “Daishimochi” of barley grains before the harvest.. This is the first original attempt for the prediction in the world. Through experiment, it is found that water content (%), Anthocyanin content (mg Cy3G/100 g), Anthocyanin content (mg Cy3G/100 g: which corresponds to dry matter), and barley β-glucan (%) can be predicted before the harvest with high R2 value (more than 0.99). Therefore, farmers can control fertilizer and water supply for improvement of the Daishimochi barley grain quality.

Author 1: Kohei Arai

Author 2: Eisuke Kisu

Author 3: Kazuhiro Nagafuchi

Keywords: Unmanned Aerial Vehicle: UAV; Near Infrared: NIR camera; Daishimochi; anthocyanin; ß-glucan and water contents; barley quality

Paper 14: Enterprise Architecture “As-Is” Analysis for Competitive Advantage

Abstract: In the telecommunication market, it is essential to ensure that the infrastructure and resources of the internet service provider can adapt and grow. In contrast, provide the best quality of data services and offering the best packages for their customers. It is essential to ensure that an internet service provider company remain competitive and agile so that it can provide better products and services promptly to the market. At iiNET, raising awareness of how having an enterprise-wide understanding and view of how the business processes run and all the existing technology within the organisation is vital in ensuring their adaptability and growth in the telecom industry. This paper discusses the challenges which IINET is currently facing and how an enterprise architecture solution is proposed to provide iiNET with the strategic advantage it needs to overcome those challenges. The existing EA frameworks are discussed and analysed to select the best fit for iiNET’s EA solution. Finally, the “As-Is” architecture at iiNET is explained as the findings for this EA implementation phase.

Author 1: Eithar Mohamed Mahmoud Nasef

Author 2: Nur Azaliah Abu Bakar

Keywords: Enterprise architecture; internet service provider; competitive advantage; “As-Is” analysis

Paper 15: A Novel ASCII Code-based Polybius Square Alphabet Sequencer as Enhanced Cryptographic Cipher for Cyber Security Protection (APSAlpS-3CS)

Abstract: For all industries, cybersecurity is regarded as one of the major areas of concern that needs to be addressed. Data and information in all forms should be safeguarded to avoid leakage of information, data theft, and robbery through intruders and hackers. This paper proposes a modification on the traditional 5x5 Polybius square in cryptography, through dynamically generated matrices. The modification is done through shifting cell elements for every encrypted character using a secret key and its ASCII decimal code equivalents. The results of the study revealed that the modified Polybius cipher offers a more secure plaintext-ciphertext conversion and is difficult to break, as evident in the frequency analysis. In the proposed method, each element produced in the digraphs exhibits a wider range of possible values. However, with the increase of process in the encryption and decryption, the modified Polybius cipher obtained a longer execution time of 0.0031ms, being identified as its tradeoff. The unmodified Polybius cipher, however, obtained an execution time of 0.0005ms. Future researchers may address the execution time tradeoff of the modified Polybius cipher.

Author 1: Jan Carlo T. Arroyo

Author 2: Ariel Roy L. Reyes

Author 3: Allemar Jhone P. Delima

Keywords: Cryptography; ciphers; ciphertext; modified polybius cipher; plaintext

Paper 16: An Efficient Convolutional Neural Network for Paddy Leaf Disease and Pest Classification

Abstract: Improving the quality and quantity of paddy production is very important since rice is the most consumed staple food for billion people around the world. Early detection of the paddy diseases and pests at different stages of growth is very crucial in paddy production. However, the current manual method in detecting and classifying the paddy diseases and pests requires a very knowledgeable farmer and time consuming. Thus, this study attempts to utilize an effective image processing and machine learning technique to detect and classify the paddy diseases and pests more accurately and less time processing. To accomplish this study, 3355 images comprises of 4 classes paddy images which are healthy, brown spot, leaf blast, and hispa was used. Then the proposed five layers of CNN technique is used to classify the images. The result shows that the proposed CNN technique is outperform and achieved the accuracy rate up to 93% as compared to other state-of-art comparative models.

Author 1: Norhalina Senan

Author 2: Muhammad Aamir

Author 3: Rosziati Ibrahim

Author 4: N. S. A. M Taujuddin

Author 5: W.H.N Wan Muda

Keywords: Convolutional neural network; image classification; paddy classification; paddy disease and pest

Paper 17: Enhancement of Two-Tier ATM Security Mechanism: Towards Providing a Real-Time Solution for Network Issues

Abstract: In the current scenario, the crime rate has tremendously increased with respect to the Automatic Teller Machine (ATM). During the last few years, criminals are becoming more sophisticated and paid more attention to ATMs. The majority of ATMs in India are working on a single authentication technique. The attacks, such as skimming, shimming, card cloning, card swapping, shoulder surfing, etc. works due to the use of minimal authentication in ATMs. So, the concern about the security of ATMs is reached to its peak level. Nowadays, banks have moved towards the two-tier authentication level. Recently in India, some banks have adopted the One Time Password (OTP) mechanism along with a UID number to perform the transaction in ATMs. In such a case, dependency on the cellular network for OTP is also a significant concern. To overcome these types of issues researcher proposed a two-tier authentication mechanism. The paper addresses the recent problems and their solution with the help of a two-way authentication method. To resolve the network issue, the researcher also proposed a novel technique, i.e., Security Question-based verification mechanism.

Author 1: Syed Anas Ansar

Author 2: Satish Kumar

Author 3: Mohd. Waris Khan

Author 4: Amitabha Yadav

Author 5: Raees Ahmad Khan

Keywords: ATM-fraud; security: Unique Identifier (UID); shoulder surfing; shimming; trapping

Paper 18: A Novel Pre-Class Learning Content Approach for the Implementation of Flipped Classrooms

Abstract: The nascent recognition of computing in curriculum across countries is also accompanied by several pedagogic inefficiencies especially concerning insufficient time available for teacher-student interaction. In this paper, a flipped classroom concept was identified as an effective approach to teaching students at various levels in the academia including Higher Education. Preparing the pre-class content and considering the format used to deliver it has not gained much consideration. There are several ways in which this content could be provided to students to prepare them before an in-class activity where a flipped-classroom approach can be implemented. The present study analyzed the success of the flipped classroom concept based on a comparative analysis of the two types of flipped classroom pre-class content delivery methods: online videos and online PowerPoint slides. Evaluation was performed using paired T-test. The results show that the two approaches have significantly different means and huge differences between them. The students preferred online videos to online PowerPoint (ppt) methods underlining the importance of the proposed flipped classroom approach.

Author 1: Soly Mathew Biju

Author 2: Ayodeji Olalekan Salau

Author 3: Joy Nnenna Eneh

Author 4: Vincent Egoigwe Sochima

Author 5: Izuchukwu ThankGod Ozue

Keywords: Flipped classroom; active learning; online videos; student-centered approach; increased interaction; pre-class content

Paper 19: Handwriting Recognition using Artificial Intelligence Neural Network and Image Processing

Abstract: Due to increased usage of digital technologies in all sectors and in almost all day to day activities to store and pass information, Handwriting character recognition has become a popular subject of research. Handwriting remains relevant, but people still want to have Handwriting copies converted into electronic copies that can be communicated and stored electronically. Handwriting character recognition refers to the computer's ability to detect and interpret intelligible Handwriting input from Handwriting sources such as touch screens, photographs, paper documents, and other sources. Handwriting characters remain complex since different individuals have different handwriting styles. This paper aims to report the development of a Handwriting character recognition system that will be used to read students and lectures Handwriting notes. The development is based on an artificial neural network, which is a field of study in artificial intelligence. Different techniques and methods are used to develop a Handwriting character recognition system. However, few of them focus on neural networks. The use of neural networks for recognizing Handwriting characters is more efficient and robust compared with other computing techniques. The paper also outlines the methodology, design, and architecture of the Handwriting character recognition system and testing and results of the system development. The aim is to demonstrate the effectiveness of neural networks for Handwriting character recognition.

Author 1: Sara Aqab

Author 2: Muhammad Usman Tariq

Keywords: Support vector machine; neural network; artificial intelligence; handwriting processing

Paper 20: Tai Chi Care: An Exergaming Software using Microsoft Kinect V2 for Blind or Low Vision Person during Confinement

Abstract: Blind or low vision people need to practice activities for their mental and physical health to minimize the risk of suffering from articulation pain but they have problems due to difficulties and inaccessibility of displacement especially during the COVID-19 pandemic where everyone in this world was asked to stay at home during confinement. To solve these problems, we have developed a software tool for a care Tai Chi exergaming to encourage them to practice exercise at home using body tracking by Microsoft Kinect V2 and audio feedback. This software acts as a Tai Chi treatment, teaches four poses, and has a customized audio feedback to help person to understand each pose and generates progress graphs to evaluate the success of these exercises. We used the SDK libraries of the Kinect to obtain 3D joint position from sensors of the Kinect to calculate the angles and distances between joints to help the person to position in front of the Kinect, evaluate the different gestures of flexions and extensions of knees and elbows of each exercises, and body balance direction to avoid falling risk. These exercises have been evaluated with persons who are blind or low vision to improve feasibility and feedback.

Author 1: Marwa Bouri

Author 2: Ali Khalfallah

Author 3: Med Salim Bouhlel

Keywords: Tai Chi; COVID-19; visual impaired; physical exercise; exergaming; audio feedback; Kinect; body tracking

Paper 21: Optimized Machine Learning based Classifications of Staging in Gynecological Cancers using Feature Subset through Fused Feature Selection Process

Abstract: After diagnosing the cancer, the next step is to identify the staging of the cancer to start with the appropriate treatment plans. There are different kinds of gynaecological cancers and this research lays emphasis on cervical and ovarian cancer types with their staging classifications. The cervical and ovarian cancers data from SEER registry are used in this work. This work intends to propose an optimized classification method for staging prediction in gynaecological cancers through fused feature selection process that aimed to provide an optimal feature subset. The fused feature selection process includes the hybridization of relief filter approach with wrapper method of genetic algorithm to produce revised feature subset of data as an outcome. Accordingly, this work attained an improved feature subset through fused feature selection process for precise classification of cervical and ovarian cancer stages by identifying their significant features. The predictive models are established with 10-fold cross validation using major classification algorithms like C5.0, Random Forest and KNN. The classification results are attained for the respective types of cervical, ovarian cancer stages and the stage-wise classification based on patients age also obtained through this proposed method. The results portrayed that the women in the age group of 45 and above are more critical with the incidence of cervical and ovarian cancer types. Random Forest method has shown progressive accuracy rate with progressive percentage of other performance outcomes. Also, this work recognized that the best and optimal feature subset selection could condense the complexity of the predictive model.

Author 1: B Nithya

Author 2: V Ilango

Keywords: Ovarian cancer; cervical cancer; diagnosis; gynaecological cancers; staging; feature selection; machine learning; classification

Paper 22: A Systematic Review on Practical Considerations, Recent Advances and Research Challenges in Underwater Optical Wireless Communication

Abstract: Underwater Optical Wireless Communication (UOWC) has gained significant attraction in many underwater activities because of its high bandwidth as compared to radio frequency and acoustic technologies. Underwater Optical Wireless Communication (UOWC) has high stature in underwater observation, exploration and monitoring applications. However, due to complex nature of ocean water, several practical challenges exist in deployment of UOWC links. Qualitative and effective research has been carried out in UOWCs from last few decades. Ambition behind this research systematic study is to provide a comprehensive survey on latest research in UOWCs. Herein, we provide a brief discussion on major research challenges, limitations and development in UOWCs. We provide a periodical review on UOWC issues and potential challenges highlighted in previous studies. In this paper, we have also investigated research methods to gain attention of research fraternity towards future technologies and challenges on the basis of existing approaches. Thus, it is our foremost requirement to provide state-of-the-art analysis of existing UOWCs. Significant deliberation has been provided with recent bibliography.

Author 1: Syed Agha Hassnain Mohsan

Author 2: Md. Mehedi Hasan

Author 3: Alireza Mazinani

Author 4: Muhammad Abubakar Sadiq

Author 5: Muhammad Hammad Akhtar

Author 6: Asad Islam

Author 7: Laraba Selsabil Rokia

Keywords: Component; underwater optical wireless communication; underwater technologies; research questions; 5G/6G

Paper 23: Predicting Cervical Cancer using Machine Learning Methods

Abstract: In almost all countries, precautionary measures are less expensive than medical treatment. The early detection of any disease gives a patient better chances of successful treatment than disease discovery at an advanced stage of its development. If we do not know how to treat patients, any treatment we can provide would be useful and would provide a more comfortable life. Cervical cancer is one such disease, considered to be fourth among the most common types of cancer in women around the world. There are many factors that increase the risk of cervical cancer, such as age and use of hormonal contraceptives. Early detection of cervical cancer helps to raise recovery rates and reduce death rates. This paper aims to use machine learning algorithms to find a model capable of diagnosing cervical cancer with high accuracy and sensitivity. The cervical cancer risk factor dataset from the University of California at Irvine (UCI) was used to construct the classification model through a voting method that combines three classifiers: Decision tree, logistic regression and random forest. The synthetic minority oversampling technique (SMOTE) was used to solve the problem of imbalance dataset and, together with the principal component analysis (PCA) technique, to reduce dimensions that do not affect model accuracy. Then, stratified 10-fold cross-validation technique was used to prevent the overfitting problem. This dataset contains four target variables–Hinselmann, Schiller, Cytology, and Biopsy–with 32 risk factors. We found that using the voting classifier, SMOTE and PCA techniques helped raise the accuracy, sensitivity, and area under the Receiver Operating Characteristic curve (ROC_AUC) of the predictive models created for each of the four target variables to higher rates. In the SMOTE-voting model, accuracy, sensitivity and PPA ratios improved by 0.93 % to 5.13 %, 39.26 % to 46.97 % and 2 % to 29 %, respectively for all target variables. Moreover, using PCA technology reduced computational processing time and increasing model efficiency. Finally, after comparing our results with several previous studies, it was found that our models were able to diagnose cervical cancer more efficiently according to certain evaluation measures.

Author 1: Riham Alsmariy

Author 2: Graham Healy

Author 3: Hoda Abdelhafez

Keywords: Cervical cancer; machine learning; voting method; risk factors; SMOTE; PCA

Paper 24: Students’ Perception of the Effect of Cognitive Factors in Determining Success in Computer Programming: A Case Study

Abstract: The reliance on science and technology by both countries and corporate entities is increasingly evident as the evolving trend of digitization not only pervades every facet of life but also assumes a dominant role. Correspondingly, the significance of producing competent computer science and information technology (IT) graduates becomes highly imperative. Already, in most developed and developing countries, there has been an increasing demand for these competencies such as network engineers, programmers, and other IT-related specialists. Although these competencies are equally valuable, programming skills constitute the core of the strength of every other IT-related competence. Nevertheless, programming is reported in the literature to be one of the most difficult courses to students. Moreover, the level of performance in programming is said to be significantly low with an attendant high rate of students’ dropout. There is a concerted research effort toward addressing the challenge of poor academic performance by attempting to answer the question of what factors affect academic performance in general. However, there is scanty literature on the factors that affect the ability to understand the concept of programming in specific. This paper, therefore, reports a case study investigation of students’ perception of the effect of cognitive factors as the determinant of success in computer programming. The findings showed that performance in introductory programming is impacted by a range of interrelated cognitive factors including self-efficacy and the love for technology.

Author 1: Jotham Msane

Author 2: Bethel Mutanga Murimo

Author 3: Tarirai Chani

Keywords: Cognitive factors; performance; programming; self-efficacy

Paper 25: Malware Analysis in Web Application Security: An Investigation and Suggestion

Abstract: Malware analysis is essentially used for the identification of malware and its objectives. However, the present era has seen the process of malware analysis being used for enhancing security methods for different domains of technology. This study has attempted to analyze the current situation and status of malware analysis in web application security through some objectives. These objectives helps the authors to analyze the purpose, used methodology of malware analysis in web application security previously as well as authors select and find a prioritized technique of malware analysis through a hybrid multi criteria decision making procedure called fuzzy-Analytical Hierarchy Process. This fuzzy-AHP methodology helps the authors to find and recommend a most prioritized malware analysis techniques and type as well as suggest a ranking of various malware analysis techniques that used in web application security frequently for experts and developers use. Furthermore, second section of paper forecast the attack statistics and publication statistics of malwares and malware analysis in web application security respectively for understanding the sensitivity of topic and need of investigation. The proposed tactic intends to be an effective reckoner for web developers and facilitate in malware analysis for securing web applications. Additionally, the study also forecast the publication and attack scenario of malware and malware analysis for web application security that gives a complimentary overview of domain.

Author 1: Abhishek Kumar Pandey

Author 2: Fawaz Alsolami

Keywords: Malware analysis; web application; application security; fuzzy-AHP; forecasting

Paper 26: Lightweight Security Mechanism over MQTT Protocol for IoT Devices

Abstract: Security is one of the main concerns with regard to the Internet of Things (IoT) networks. Since most IoT devices are restricted in resource and power consumption, it is not easy to implement robust security mechanisms. There are different methods to secure network communications; however, they are not applicable to IoT devices. In addition, most authentication methods use certificates in which signing and verifying certificates need more computation and power. The main objective of this paper is to propose a lightweight authentication and encryption mechanism for IoT constrained devices. This mechanism uses ECDHE-PSK which is the Transport Layer Security (TLS) authentication algorithm over Message Queuing Telemetry Transport (MQTT) Protocol. This authentication algorithm provides a Perfect Forward Secrecy (PFS) feature that makes an improvement in security. It is the first time that this TLS authentication algorithm is implemented and evaluated over the MQTT protocol for IoT devices. To evaluate resource consumption of the proposed security mechanism, it was compared with the default security mechanism of the MQTT protocol and the ECDHE-ECDSA that is a certificate-based authentication algorithm. They were evaluated in terms of CPU utilization, execution time, bandwidth, and power consumption. The results show that the proposed security mechanism outperforms the ECDHE-ECDSA in all tests.

Author 1: Sanaz Amanlou

Author 2: Khairul Azmi Abu Bakar

Keywords: Internet of Things (IoT); MQTT; Pre-Shared Keys (PSK); elliptic curve cryptography; Diffie-Hellman Ephemeral (DHE); Digital Signature Algorithm (DSA); Perfect Forward Secrecy (PFS); authentication; power consumption; wireless sensors

Paper 27: Factors Affecting SME Owners in Adopting ICT in Business using Thematic Analysis

Abstract: In Malaysia, Small Medium Enterprise (SME) has become the main contributor for the income generation and employment thus are expected to increase country’s GDP growth. Hence, it is important for the SME owners to ensure the sustainability of their business in today’s business settings that has moved to digital businesses in which technology is used to create new value in business models, customer experiences and the internal capabilities that support its core operations. Yet, there are still local SMEs who did not fully utilized the advantages of adopting Information and Communications Technology (ICT) in their business operation and transactions. This paper presents an interview done with 12 SME owners that operates their businesses in Kuala Lumpur and Selangor. The study is to gain an understanding on the factors affecting SME owners in adopting ICT in their business by using the Thematic Analysis method. The outcome shows that there are two central themes that affect ICT usage in SME which are the (1) Internal Factor and (2) External Factor. Further, we identified two (2) components that effect the Internal Factor, namely Company (capital, company’s age, less skilled workers and family business) and SME Owners (time, education, perceptions and experiences) and another two (2) components that affect the External Factor, namely Technology (high cost, complicated, system’s security and stability) and Regulators (government’s initiatives, training skills and no urgency). Hence, the result is important to the SME owners and management as well as the government or the authorities to resolve these issues in order to increase the ICT usage among the SME owners in Malaysia.

Author 1: Anis Nur Assila Rozmi

Author 2: Puteri N.E. Nohuddin

Author 3: Abdul Razak Abdul Hadi

Author 4: Mohd Izhar A. Bakar

Author 5: A. Imran Nordin

Keywords: Small Medium Enterprise (SME); Information and Communications Technology (ICT); thematic analysis; internal factors; external factor

Paper 28: Emotional Impact for Predicting Student Performance in Intelligent Tutoring Systems (ITS)

Abstract: Current Intelligent Tutoring Systems (ITS) provide better recommendations for students to improve their learning. These recommendations mainly involve students’ performance prediction, which remains problematic for ITS, despite the significant improvements made by prediction methods such as Matrix Factorization (MF). The present contribution therefore aims to provide a solution to this prediction problem by proposing an approach that combines Multiple Linear Regression (Modelling Emotional Impact) and a Weighted Multi-Relational Matrix Factorization model to take advantage of both student cognitive and emotional faculties. This approach takes into account not only the relationships that exist between students, tasks and skills, but also students’ emotions. Experimental results on a set of pedagogical data collected from 250 students show that our approach significantly improves the results of Student Performance Prediction.

Author 1: Kouame Abel Assielou

Author 2: Cissé Théodore Haba

Author 3: Bi Tra Gooré

Author 4: Tanon Lambert Kadjo

Author 5: Kouakou Daniel Yao

Keywords: Intelligent tutoring system; student performance prediction; matrix factorization; emotional impact; achievement emotions

Paper 29: Applying Aspect Oriented Programming in Distributed Application Engineering

Abstract: Aspect-oriented programming is an emerging programming paradigm that stretches during the development phases in different domains. Many researchers have focused on the use of this paradigm in web service composition in different research axis. However, none of them use together aspect-oriented programming and design by contract to deal with the adaptation of the parameters in the web service composition process. This paper proposes a web service composition algorithm based on the planning graph using both Aspect-oriented programming and design by contract concept. The aspect-oriented Programming approach provides explicit support for separation of crosscutting concerns in web services composition whereas the design by contract approach allows the processing of parameters execution in pre-condition and post-condition mode by using contracts in order to ensure correct service execution with adaptation to external parameters without touching in properties which can be dealt with re-construction of the composite service. Future development of this planning graph will include the introduction of the dynamic way of aspect oriented programming and add comparison results.

Author 1: Fatiha Khalifa

Author 2: Samira Chouraqui

Keywords: Aspect oriented programming; design by contract; web service composition; parameters adaptation

Paper 30: Object Detection using Template and HOG Feature Matching

Abstract: In the present era, the applications of computer vision is increasing day by day. Computer vision is related to the automatic recognition, exploration and extraction of the necessary information from a particular image or a group of image sets. This paper addresses the method to detect the desired object from an image. Usually, a template of the desired object is used in detection through a matching technique named Template Matching. But it works well when the template image is cropped from the original one, which is not always invariant due to various transformations in the test images. To cope with this difficulty and to develop a generalized approach, we investigate in detail another technique which is known as HOG (Histogram of Oriented Gradient) approach. In HOG, the image is divided into overlapping blocks of template size and then compare each block’s normalized HOG with the normalized HOG of the template to find the best match of the object. We perform experiments with a large number of images and have found satisfactory performance.

Author 1: Marjia Sultana

Author 2: Tasniya Ahmed

Author 3: Partha Chakraborty

Author 4: Mahmuda Khatun

Author 5: Md. Rakib Hasan

Author 6: Mohammad Shorif Uddin

Keywords: Computer vision; template matching; HOG; feature extraction

Paper 31: A Compact Broadband and High Gain Tapered Slot Antenna with Stripline Feeding Network for H, X, Ku and K Band Applications

Abstract: In this paper, a planar travelling wave tapered slot antenna with compact size is proposed for wireless communication applications. The prototype of antenna is developed on Roger RT/Duroid 5880 laminate with tan δ = 0.0009, a relative permittivity of 2.2 while working in the range of 6GHz – 21GHz. The simple feeding technique transits with radial cavity and the opening taper profile. The antenna dimensions of the antenna have been designed in such a manner so as to enable impedance matching. The parametric study of the variables is carried out by various scrupulous simulations. The designed characteristic antenna has achieved an impedance bandwidth in the broadband spectrum of 111.11% at the minimum 10-dB return loss and peak realized gain of 7dBi is obtained for a resonant frequency of 19.6GHz. The simulated results are in good agreement with experimental results and hence make the antenna suitable for H ( 6 - 8 GHz), X (8 - 12 GHz), Ku (12 - 18 GHz) and K (18 - 26 GHz) and future wireless communication applications.

Author 1: Permanand Soothar

Author 2: Hao Wang

Author 3: Chunyan Xu

Author 4: Zaheer Ahmed Dayo

Author 5: Badar Muneer

Author 6: Kelash Kanwar

Keywords: Tapered slot antenna (TSA); compact; radial cavity; broadband impedance bandwidth; peak realized gain; etched slots

Paper 32: QUES: A Quality Estimation System of Arabic to English Translation

Abstract: Estimating translation quality is a problem of growing importance as it has many potential applications. The quality of translation from Arabic to English is especially difficult to evaluate due to the languages being distant languages: different in syntax and low in lexical similarity. We propose a feature-based framework for estimating the quality of Arabic to English translations at the sentence level. The proposed method works without reference translations, considers both fluency and adequacy of translations, and does not imply assumptions on the source of translation (humans, machines, or post-edited machine translations); thus, making the solution applicable to increasingly more situations. This research solves the translation quality estimation problem by treating it as a supervised machine learning problem. The proposed model utilizes regression algorithms (SVR and Linear Regression) to predict quality scores of unseen translated texts at runtime. This is accomplished by training models on a labeled parallel corpus and mapping extracted features to the quality label. The prediction models succeeded in predicting fluency and adequacy of translations with a Mean Absolute Error of 0.84 and 1.02, respectively. Furthermore, we show that in a similar setting of our approach, fluency of an Arabic to English translated sentence on its own, is an appropriate indication of a translation’s overall quality.

Author 1: Manar Salamah Ali

Author 2: Anfal Alatawi

Author 3: Bayader Alsahafi

Author 4: Najwa Noorwali

Keywords: Translation quality estimation; translation adequacy; translation fluency; supervised machine learning

Paper 33: Classification of Freshwater Zooplankton by Pre-trained Convolutional Neural Network in Underwater Microscopy

Abstract: Zooplankton is enormously diverse and fundamental group of microorganisms that exists in almost every freshwater body, determining its ecology and play a vital role in food chain. Considering the significance of zooplankton, the study of freshwater zooplankton is very essential which intensely relies on the classification of images. However, the routine manual analysis and classification is laborious, time consuming and expensive, and poses a significant challenge to experts. Thus, for recent decade much research is focused on the development of underwater imaging technologies and intelligent classification system of zooplankton. This work presents devotion to observation of freshwater zooplankton by designed underwater microscope and modeling the system for automatic classification among four different taxa. Unlike most of the existing zooplankton image classification systems, this model is trained on a comparatively small dataset collected from freshwater by designed underwater microscope. Transfer learning of pre-trained AlexNet Convolutional Neural Network (CNN) model proved to be a potential approach in the system design. Among four networks trained over two datasets, the best overall classification accuracy of up to 93.1%, comparable to other existing systems was achieved on test dataset (92.5% for Calanoid and Cyclopoid (Female), 90% for Cyclopoid (Male) and 97.5% for Daphnia). Graphical User Interface (GUI) of the model constructed on MATLAB, makes it easy for the users to collect images for building database, train network and to classify images of different taxa. Moreover, the designed system is adaptable to the addition of more classes in the future.

Author 1: Song Hong

Author 2: Syed Raza Mehdi

Author 3: Hui Huang

Author 4: Kamran Shahani

Author 5: Yangfang Zhang

Author 6: Junaidullah

Author 7: Kazim Raza

Author 8: Mushtaq Ali Khan

Keywords: AlexNet; automatic image classification; Convolutional Neural Networks (CNN); freshwater zooplankton; transfer learning; underwater microscope

Paper 34: An Efficient Binary Clonal Selection Algorithm with Optimum Path Forest for Feature Selection

Abstract: Feature selection is an important step in different applications such as data mining, classification, pattern recognition, and optimization. Until now, finding the most informative set of features among a large dataset is still an open problem. In computer science, a lot of metaphors are imported from nature and biology and proved to be efficient when applying them in an artificial way to solve a lot of problems. Examples include Neural Networks, Human Genetics, Flower Pollination, and Human Immune system. Clonal selection is one of the processes that happens in the human immune system while recognizing new infections. Mimicking this process in an artificial way resulted in a powerful algorithm, which is the Clonal Selection Algorithm. In this paper, we tried to explore the power of the Clonal Selection Algorithm in its binary form for solving the feature selection problem, we used the accuracy of the Optimum-Path Forest classifier, which is much faster than other classifiers, as a fitness function to be optimized. Experiments on three public benchmark datasets are conducted to compare the proposed Binary Clonal Selection Algorithm in conjunction with the Optimum Path Forest classifier with other four powerful algorithms. The four algorithms are Binary Flower Pollination Algorithm, Binary Bat Algorithm, Binary Cuckoo Search, and Binary Differential Evolution Algorithm. In terms of classification accuracy, experiments revealed that the proposed method outperformed the other four algorithms and moreover with a smaller number of features. Also, the proposed method took less average execution time in comparison with the other algorithms, except for Binary Cuckoo Search. The statistical analysis showed that our proposal has a significant difference in accuracy compared with the Binary Bat Algorithm and the Binary Differential Evolution Algorithm.

Author 1: Emad Nabil

Author 2: Safinaz Abdel-Fattah Sayed

Author 3: Hala Abdel Hameed

Keywords: Feature selection; artificial immune system; clonal selection algorithm; optimization; optimum path forest

Paper 35: A Machine Learning Approach for Recognizing the Holy Quran Reciter

Abstract: Mainly, the holy Quran is the holy book for all Muslims. Reading the holy Quran is a special reading with rules. Reading the Holy Quran is called recitation. One of the Muslim essential activities is reading or listening to the Holy Quran. In this paper, a machine learning approach for recognizing the reader of the holy Quran (reciter) is proposed. The proposed system contains basic traditional phases for a recognition system, including data acquisition, pre-processing, feature extraction, and classification. A dataset is created for ten well-known reciters. The reciters are the prayer leaders in the holy mosques in Mecca and Madinah. The audio dataset set is analyzed using the Mel Frequency Cepstral Coefficients (MFCC). Both the K nearest neighbor (KNN) classifier, and the artificial neural network (ANN) classifier are applied for classification purpose. The pitch is used as features which are utilized to train the ANN and the KNN for classification. Two chapters from the Holy Quran are selected in this paper for system validation. Excellent accuracy is achieved. Using the ANN, the proposed system gives 97.62% accuracy for chapter 18 and 96.7% accuracy for chapter 36. On the other hand, the proposed system gives 97.03% accuracy for chapter 18 and 96.08% accuracy for chapter 36 by using the KNN.

Author 1: Jawad H Alkhateeb

Keywords: Holy Quran audio analysis; MFCC; KNN; ANN; Machine learning

Paper 36: Modeling and Performance Analysis of an Adaptive PID Speed Controller for the BLDC Motor

Abstract: Brushless Direct Current (BLDC) motor is the most popular useable motor for automation and industry. For good performance of the BLDC motor hunger driving circuit but the driving circuit is costly, complex control mechanism, various parameter dependency and low torque. The Proportional Integral (PI), Proportional Integral Derivative (PID), fuzzy logic, adaptive, Quantity Feedback Theory (QFT), Pulse Width Modulation (PWM) controller are the common types of control method existing for the BLDC motor. This research explores some well-working experiments and identified the PID controller as far more applicable controller. For well efficacious and useful in getting satisfied control performance if the adaptability is implemented. This research proposed a combined method using PID and PID auto tuner, having the ability to improve the system adaptability, given the method named as adaptive PID controller. To verify the performance, MATLAB simulation platform was used, and a benchmark system was developed based on the actual BLDC motor parameters, auxiliary systems, and mathematically solved parameters. All work has done by using MATLAB/ Simulink.

Author 1: Md Mahmud

Author 2: S. M. A. Motakabber

Author 3: A. H. M. Zahirul Alam

Author 4: Anis Nurashikin Nordin

Author 5: A. K.M. Ahasan Habib

Keywords: QFT; PWM; BLDC motor; PID controller; adaptive; adaptive PID controller; APIDC

Paper 37: Fast Side Information Generation for High-Resolution Videos in Distributed Video Coding Applications

Abstract: Distributed video coding (DVC) is an attractive and promising scheme that suits the constrained video applications, such as wireless sensor networks or wireless surveillance systems. In DVC, estimation of fast and consistent side information (Տį) is a critical issue for instant and real-time decoding. This issue becomes even more serious for high-resolution videos. Therefore, to minimise the side information estimation computational complexity, in this work, a computationally low complex DVC codec is proposed, which uses a simple phase interpolation (Phase-I) algorithm. It performs faster for all resolutions videos, and significant results are achieved for high-resolution videos with a large group of pictures (GOP). For the proposed technique, the computation time rapidly decreases with an increase in resolution. It performs 221% to 280% faster from conventional frame interpolation method for high-resolution videos and large GOP at the cost of little degradation in the visual quality of estimated side information.

Author 1: Shahzad Khursheed

Author 2: Nasreen Badruddin

Author 3: Varun Jeoti

Author 4: Manzoor Ahmed Hashmani

Keywords: Fast side information algorithm; phase-based interpolation (Phase-I); DVC; DVC decoder for high-resolution videos; real-time DVC decoding; real-time side information

Paper 38: Level of Depression in Tuberculosis Patients of Los Olivos Health Centers

Abstract: Tuberculosis is a contagious infectious disease, caused by Mycobacterium Tuberculosis, transmitted through its release into the air when a sick person coughs, sneezes or talks, so it can be inhaled by another person and infect it, it is necessary for patients to adopt family, work and social distancing to avoid infections, causing a risk of developing different levels of depression, which is detrimental due to its negative influence on decision-making. The frequency of depression in society is high, as is the predisposition of patients diagnosed with Tuberculosis due to the sudden change in their lifestyle, which is why it was proposed to determine the level of depression in tuberculosis patients at health centers from Los Olivos district, this study will also allow to know the most frequent physical and psychological reactions, in addition to the most predominant sex. To obtain the information, the corresponding permits were obtained and the Patient Health Questionnaire 9 (PHQ-9), an international and nationally validated standardized instrument, was applied; the data was processed in the statistical software SPSS 24.0, and the graphics were subsequently extracted; where the following obtained results were reflected: 100% of the participants had some level of depression, the most prevalent being the level of moderate depression with 35.56%, being more present in the female population with 21.11% , it was also shown that 48.9% of patients almost always have little interest or pleasure in doing things.

Author 1: Katherine Trinidad-Carrillo

Author 2: Ruth Santana-Cercado

Author 3: Katherine Castillo-Nanez

Author 4: Brian Meneses-Claudio

Author 5: Hernan Matta-Solis

Keywords: Tuberculosis; depression; patient health questionnaire 9; health centers; tuberculosis lifestyle

Paper 39: How Entrepreneurs Utilize Accelerators: A Demographic Factor Analysis in Turkey using Regression

Abstract: This study examines entrepreneurs participating into eight accelerator programs located in Istanbul, Turkey. Business accelerators are a new kind of incubation program built in particular to help technology entrepreneurs and assist them reach to the next level. In total eight accelerator programs are researched in this study. A survey is developed for this study and applied to entrepreneurs attending these eight accelerator programs. In this survey, the effectiveness of these programs are measured according to the demographics of entrepreneurs. The aim of this research is to analyze how entrepreneurs use the services given by the accelerator program. In relation to entrepreneurs’ age, gender, work experience, educational status and family background, several hypotheses have been identified for assessing the value of supports given in these accelerator programs. The data of this research have been examined via SPSS using Mann-Whitney and Kruskal-Wallis methods. According to the results of these tests, a regression model called Generalized Linear Mixed Model (GLMM) has been developed. This study adds to the literature by examining accelerator supports and facilities so that accelerators can set apart their programs in line with the requests of the entrepreneurs.

Author 1: Ceren Cubukcu

Author 2: Sevinc Gulsecen

Keywords: Accelerators; e-business; startups; regression

Paper 40: Learning Analytics Tool Adoption by University Students

Abstract: Learning analytics refers to a systematic process involving measuring, collecting, analyzing and reporting data about learners with the aim of fully understanding how best learning environments can be optimized to increase efficiency. The aim of this study is to understand the factors contributing to the learning analytics adoption by university students in North Cyprus. Participants comprised of students from three universities in North Cyprus. 718 valid questionnaires involving items from the adopted UTAUT (Unified Theory of Acceptance and Use of Technology) model was used in the study. The results have shown that there was a weak negative correlation between Performance Expectancy and Technology Use Intention implying that when students are aware of how a technology operates and if it satisfies their requirements, then they will be ready to adopt learning analytics. There was also a negative weak correlation between Effort Expectancy and Technology Use Intention. A positive weak correlation between Social Influence and Technology Use Intention was observed while there was a negative weak correlation between Technology Use Intention and Technology Use Behavior implying that when a students have intentions of using learning analytics, they show a positive behavior towards the technology. The study also shows that there was also moderate positive correlation between Technology Anxiety and Technology User Behavior. This study is considered to be of great benefit and practical implementation to researchers, instructors, students, universities and the ministry of education.

Author 1: Seren Basaran

Author 2: Ahmed Mohamed Daganni

Keywords: Higher education; learning analytics; learning tools; North Cyprus; students; technology

Paper 41: Effective Voice Frame Shrinking Method to Enhance VoIP Bandwidth Exploitation

Abstract: The traditional telecommunication system (e.g. landline telephone system) are increasingly being replaced by Voice over Internet Protocol (VoIP) systems because of the very low or free rate. However, one of the main handicaps of VoIP adoption is the inefficient bandwidth exploitation issue. A key approach to handle this issue is packet multiplexing. This article proposes a new VoIP packet payload compression method that enhances bandwidth exploitation over Internet Telephony Transport Protocol (ITTP) protocol. The proposed method is called payload shrinking over ITTP (ITTP-PS). As the name implies, the proposed ITTP-PS method shrinks the VoIP packet payload based on a certain mechanism. The ITTP-PS method has two entities, namely, sender ITTP-PS (S-ITTP-PS) and receiver ITTP-PS (R-ITTP-PS). The main function of the S-ITTP-PS entity is to shrink the VoIP packet payload, while the main function of the R-ITTP-PS entity is restoring the VoIP packet payload to its normal size. To perform the R-ITTP-PS entity function, the ITTP-PS method will reemploy the flag bits in the IP protocol header. The ITTP-PS method has been implemented and compared with traditional ITTP protocol without shrinking the VoIP packet payload. The comparison based on the VoIP packet payload shrinking ratio and isochronous calls capacity improvement ratio. The result showed that the VoIP packet payload shrinking ratio has enhanced by up to around 20%, while the isochronous calls capacity improvement ratio has enhanced by up to around 9.5%. Therefore, enhancing the VoIP bandwidth exploitation over ITTP protocol.

Author 1: Qusai Shambour

Author 2: Sumaya N. Alkhatib

Author 3: Mosleh M. Abualhaj

Author 4: Yousef Alrabanah

Keywords: VoIP; VoIP protocols; ITTP protocol; payload compression; bandwidth exploitation

Paper 42: Development and Analysis of a Zeta Method for Low-Cost, Camera-based Iris Recognition

Abstract: Iris recognition is an alternative authentication method. Many studies have tried to improve iris recognition as a biometric-based alternative for secure authentication. Iris segmentation is an important part of iris recognition because it defines the image region that is used for subsequent processing such as feature extraction and matching, hence directly affects the overall iris recognition performance. This work focuses on the development of an authentication system using localization methods and half-polar normalization of the iris. The proposed Zeta method uses a new model of eye segmentation and normalization that can be used simultaneously on both eyes, considering different iris patterns in those two eyes. There are seven variants of the proposed and tested Zeta method: Zeta-v1, Zeta-v2, Zeta-v3, Zeta-v4, Zeta-v5, Zeta-v6, and Zeta-v7. Overall, the method achieved an average segmentation time performance of 0.0138427 seconds. The most accurate rate was by the Zeta-v1 method, with a value threshold of 100% on the wrong rejection rate and 94.9% on the correct acceptance rate.

Author 1: Eko Ihsanto

Author 2: Jeffry Kurniawan

Author 3: Diyanatul Husna

Author 4: Alfan Presekal

Author 5: Kalamullah Ramli

Keywords: Iris recognition; iris segmentation; Zeta; authentication; biometric; pattern recognition

Paper 43: Virtual Machine Escape in Cloud Computing Services

Abstract: It’s of axioms; every progress that is devised in the field of facilitating daily life through technology is matched by many complications in terms of the methods that led to the creation of these inventions and how to maintain their sustainability, consistency, and development. In digital world that became not only as axiom of its nature, but it is now one of the main inherent features that define digital technology. Whereas Major international companies are in a big race to produce the new development and invention of their products to be supplied to markets, and all of that should be conquered within not more than a year. The immersion in that big race has to be armed with patience and deep breath.

Author 1: Hesham Abusaimeh

Keywords: Cloud computing; virtual machine escape; cloud security; impact of VM escape; VM escape counter measures; VM escape nature

Paper 44: The Language of Persuasion in Courtroom Discourse: A Computer-Aided Text Analysis

Abstract: This paper uses a Computer-Aided Text Analysis (CATA) and a Critical Discourse Analysis (CDA) to investigate the language of persuasion in courtroom discourse. More specifically, the paper tries to explore the extent to which a computer-aided text analysis contributes to decoding the various persuasive strategies employed to control, defend or accuse within the framework of courtroom discourse. Two research questions are tackled in this paper: first, what are the strategies of persuasion employed in the selected data? Second, how can a computer-aided text analysis reveal these persuasive tools that influence the attitudes of recipients? By means of the adopted computer-assisted textual analysis, four CDA strategies are discussed in this study: questioning, repetition, emotive language, and justification. The paper reveals that language in courtroom discourse can be used to persuade or biased to manipulate. In both cases, a triadic relationship between language, law, and computer is emphasized.

Author 1: Bader Nasser Aldosari

Author 2: Ayman F. Khafaga

Keywords: Computer-aided text analysis; legal discourse; persuasion; critical discourse analysis; power; control

Paper 45: Differential Evolution-based Approach for Tone-Mapping of High Dynamic Range Images

Abstract: Recently, high dynamic range (HDR) imaging has received significant attention from research community as well as the industrial companies due to valuable applications of HDR images in better visualization and analysis. However, HDR images need to be converted to low dynamic range (LDR) images for viewing on standard LDR display screens. Several tone-mapping operators have been proposed for the conversion, however, so far, no significant works have been reported employing artificial intelligence to achieve better enhancement of the output images. In this paper, we present an optimization-based approach, to enhance the quality of the tone-mapped LDR images using metaheuristics. More specifically, the optimization process is based on the differential evolution (DE) algorithm which takes tone-mapping function of an existing histogram-based method as initial guess and refines the histogram bins iteratively leading to progressive enhancement of the quality of LDR image. The final results produced by the proposed optimized histogram-based approach (OHbA) showed better performance compared to the existing state-of-the-art tone-mapping algorithms.

Author 1: Ahmed Almaghthawi

Author 2: Farid Bourennani

Author 3: Ishtiaq Rasool Khan

Keywords: HDR image; LDR image; metaheuritics; differential evolution; tone-mapping; histogram

Paper 46: Self Organising Fuzzy Logic Classifier for Predicting Type-2 Diabetes Mellitus using ACO-ANN

Abstract: In today’s digital world, a dataset with large number of attributes has a curse of dimensionality where the computation time grows exponentially with the number of dimensions. To overcome the problem of computation time and space, appropriate method of feature selection can be developed using metaheuristic approaches. The aim of this work is to investigate the use of ant colony optimization with the help of neural network to select near optimal feature subset and integrate it with the self-organizing fuzzy logic classifier for improving the recognition rate. The proposed fuzzy classifier derives prototype from the collected data through an offline training process and uses it to develop a fuzzy inference system for classification. Once trained, it can continuously learn from streaming data and later adapts the changing facts by updating the system structure recursively. The developed model is not based on predefined parameters used in the data generation model but is derived from the empirically observed data.

Author 1: Ratna Patil

Author 2: Sharvari Tamane

Author 3: Kanishk Patil

Keywords: Ant colony optimization; feature selection; fuzzy logic classifier; self organizing; type-2 diabetes mellitus

Paper 47: Modeling of a Tourism Group Decision Support System using Risk Analysis based Knowledge Base

Abstract: The increasing number of tourist destination becomes the main factor for export earning, job vacancy, business development, and infrastructure. The problem that occurs is the difference in regional income (GDP) that is quite significant in each region. Thus, it is necessary for the government to make a decision or policy in increasing tourist visits, mainly in Bali. In this case, choosing the most efficient decision from a number of decisions is for the government, tourists, community leaders, academics, and entrepreneurs in the tourism sector, especially in Bali. It is important to have a modeling decision support group (GDSS). GDSS modeling by integrating a knowledge-based (KB) risk analysis can determine decisions, extract information, and identify problems in the tourism sector especially, tourism objects in each region, more specifically. Problem identification in risk analysis modeling is determining decisions in handling risks and finding solutions from alternative tourism decisions that are potentially enlarged and knowledge gained from each decision-maker (DM). The process of identifying knowledge starts with comparing the assessment criteria on each tourism object and knowledge of tourism decision-makers. The results of GDSS modeling are subsequently integrated into knowledge-based risk analysis so that a decision is obtained in the form of an impact or risk and solution or recommendation in developing the specified tourism object. The purpose of combining the result is to understand the impacts or risks that may arise, and recommendations recommended so that the impacts or risks can be avoided.

Author 1: Putu Sugiartawan

Author 2: Sri Hartati

Author 3: Aina Musdholifah

Keywords: GDSS modeling; risk analysis; tourism site; knowledge base; Bali tourism

Paper 48: A Hybrid Document Features Extraction with Clustering based Classification Framework on Large Document Sets

Abstract: As the size of the document collections are increasing day-by-day, finding an essential document clusters for classification problem is one of the major problem due to high inter and intra document variations. Also, most of the conventional classification models such as SVM, neural network and Bayesian models have high true negative rate and error rate for document classification process. In order to improve the computational efficacy of the traditional document classification models, a hybrid feature extraction-based document cluster approach and classification approaches are developed on the large document sets. In the proposed work, a hybrid glove feature selection model is proposed to improve the contextual similarity of the keywords in the large document corpus. In this work, a hybrid document clustering similarity index is optimized to find the essential key document clusters based on the contextual keywords. Finally, a hybrid document classification model is used to classify the clustered documents on large corpus. Experimental results are conducted on different datasets, it is noted that the proposed document clustering-based classification model has high true positive rate, accuracy and low error rate than the conventional models.

Author 1: S Anjali Devi

Author 2: S Siva Kumar

Keywords: Classification; document feature extraction; document similarity

Paper 49: Super-Resolution using Deep Learning to Support Person Identification in Surveillance Video

Abstract: Recently, video surveillance systems have been perceived as important technical tools that play a fundamental role in protecting people and assets. In particular, the recorded surveillance video sequences are used as evidence to solve violation, theft and criminal cases. Therefore, the identification of the person present on the crime scene becomes a critical task. In this paper, we proposed a Deep learning-based Super-Resolution system that aims to enhance the faces images captured from surveillance video in order to support suspect identification. The proposed system relies on an image processing technique called Super-Resolution that consists of recovering high-resolution images from low-resolution ones. More specifically, we used the Very-Deep Super-Resolution (VDSR) neural network to enhance the image quality. The proposed model was trained with CelebA faces dataset and used to enhance the resolution of the QMUL-SurvFace dataset. It yielded a Peak Signal-to-Noise Ratio (PSNR) improvement of 7% and Structural Similarity Index (SSIM) improvement of 3%. Most importantly, it increased the face recognition rate by 45.7%.

Author 1: Lamya Alkanhal

Author 2: Deena Alotaibi

Author 3: Nada Albrahim

Author 4: Sara Alrayes

Author 5: Ghaida Alshemali

Author 6: Ouiem Bchir

Keywords: Deep learning; image processing; super-resolution; surveillance video

Paper 50: A Method for Predicting Human Walking Patterns using Smartphone’s Accelerometer Sensor

Abstract: Recently, the techniques for monitoring and recognizing human walking patterns have become one of the most important research topics, especially in health applications related to fitness and disease progression. This paper aims at combining machine learning techniques with Smartphone sensors readings (i.e. accelerometer sensor) in order to develop a smart model capable of classifying walking patterns into different categories (fast, normal, slow, very slow or very fast) along with variable of gender, male or female and sensor place, waist, hand or leg. In this paper, we use several machine learning algorithms including: Neural Network, KNN, Random forest, and Tree to train and test extracted data from Smartphone sensors. The results indicate that Smartphone sensor can be exploited in developing a reliable model for identifying the human walking patterns based on accelerometer readings. In addition, results show that Random forest is the best performing classifiers with an accuracy of (92.3%) and (91.8%) when applied on waist datasets for both males and females respectively.

Author 1: Zaid T. Alhalhouli

Keywords: Smartphone’s; accelerometer sensor; walking patterns; machine learning classifiers

Paper 51: Household Overspending Model Amongst B40, M40 and T20 using Classification Algorithm

Abstract: The family economy is a critical indicator of the well-being of a family institution. It can be seen by the total income and how well the household finances is managed. In Malaysia, the household income level is categorized as B40, M40 and T20. These categories can also indicate the poverty level of the household. Overspending is a phenomenon where the monthly expenses are more than the household's total income, which affects economic wellbeing. Finding important factors that affect the spending patterns among the household can reveal the causes of overspending. It will assist the government in mitigating such problems. Availability of 4 million household expenditure records obtained from the survey conducted in 2016 by the Department of Statistics Malaysia eases the aim of this study to develop a household overspending model by using machine learning. The model is developed using 12 household demographic attributes with 14451 household records. The attributes are the number of households, area, state, strata, race, highest certificate, marital status, gender, housing, income, total expenditure, and category as attributes class. The model development employs five machine learning algorithms namely decision tree, Naïve Bayes, Neural network, Support Vector Machines, Nearest Neighbour. The results show that the decision tree through J48 algorithm has produced the easiest rule to be interpreted. The model shows four attributes which were income, state, races and number of households that highly influence the overspending problem. Based on the research finding, it can be concluded that these attributes are essential for improving the indicator measure for Malaysian Family Wellbeing Index in the aspect of overspending.

Author 1: Zulaiha Ali Othman

Author 2: Azuraliza Abu Bakar

Author 3: Nor Samsiah Sani

Author 4: Jamaludin Sallim

Keywords: Overspending; classification; poverty; household

Paper 52: A Hybrid Recommender System to Enrollment for Elective Subjects in Engineering Students using Classification Algorithms

Abstract: One of the main problems that engineering university students face is making the correct decision regarding the lines of elective subjects to enroll based on available information (preferences, syllabus, schedules, subject content, possible academic performance, teacher, curriculum, and others). Under these circumstances, this research work seeks to develop a Hybrid Recommender System. For this, a model based on the Content-based approach of all the subjects that has been studied is developed (using Natural Language Processing and the statistical measures Term Frequency and Inverse Term Frequency), giving it appropriate relevance with the grades that the student has achieved. In addition, a model based on a Collaborative Filtering approach is developed, establishing relationships between different students, identifying similar academic behaviors. Thus, the system will recommend to the student in which lines of elective subjects to enroll to obtain better results in the academic field. The given recommendation will be obtained from machine learning models (XGBoost and k-NN) based on the similarity between the contents of each subject with respect to the line of elective subject and based on the academic relationship between all the students. To achieve the objective, data from engineering students between 2011 and 2016 has been analyzed. The results obtained indicate that the recommendations reach a MAP-k of 82.14% and a precision of 91.83%.

Author 1: Jerson Erick Herrera Rivera

Keywords: Hybrid; recommender system; academic performance; term frequency; inverse term frequency; natural language processing; k-NN; XGBoost; MAP-k

Paper 53: Method for Automatically Processing Outliers of a Quantitative Variable

Abstract: In data analysis processes, the treatment of outliers in quantitative variables is very critical as it affects the quality of the conclusions. However, despite the existence of very good tools for detecting outliers, dealing with them is not always straightforward. Indeed, statisticians recommend modeling the process underlying outliers to identify the best way to deal with them. In the context of Data Science and Machine Learning, the identification of processes that generate outliers remains problematic because this work requires a visual human interpretation of certain statistical tools. The techniques proposed so far, are systematic imputations by a central tendency characteristic, usually the arithmetic mean or median. Although adapted to the framework of Data Science and Machine Learning, these different approaches cause a fundamental problem, that of modifying the distribution of the initial data. The purpose of our paper is to propose an algorithm that allows the automatic processing of outliers by a software while preserving the distributional structure of the treated variable, whatever the law of probability is. The method is based on the moustache box theory developed by John Tukey. The procedure is tested with existing real data. All treatments are performed with the R programming language.

Author 1: NIANGORAN Aristhophane Kerandel

Author 2: MENSAH Edoété Patrice

Author 3: ACHIEPO Odilon Yapo M

Author 4: DIAKO Doffou Jérome

Keywords: Outliers; boxplot; exploratory data analysis; Programming R; data science

Paper 54: Analysis of the Use of Technological Tools in University Higher Education using the Soft Systems Methodology

Abstract: This article analyzes the professional training of students according to the current situation. Students are experiencing a new modality of study due to the Covid-19 and specialists have to evaluate which would be the best solutions in order that students achieve greater understanding, because they are one of the most affected today. Therefore, we will be able to analyze in a detailed way each one of the causes that our problem presents to evaluate and thus to be able to obtain the different points of view of those who are involved in this problem. In this study we will apply the methodology of the soft systems with a systemic approach and a holistic vision to analyze the situation presented by all those involved. Having as results that it is necessary to evaluate in a better way the solutions that are given to higher education institutions, since it should have as main objective the achievement of a better teaching towards the students and thus opting for the use of good methodologies of learning.

Author 1: Alexandra Ramos Bernaola

Author 2: Marianne Aldude Tipula

Author 3: Jose Estrada Moltalvo

Author 4: Valeria Señas Sandoval

Author 5: Laberiano Andrade-Arenas

Keywords: Soft system; involved; university; virtual classroom; students

Paper 55: Effective Opinion Words Extraction for Food Reviews Classification

Abstract: Opinion mining (known as sentiment analysis or emotion Artificial Intelligence) holds important roles for e-commerce and benefits to numerous business and organizations. It studies the use of natural language processing, text analysis, computational linguistics, and biometrics to provide us business valuable insights into how people feel about our product brand or service. In this study, we investigate reviews from Amazon Fine Food Reviews dataset including about 500,000 reviews and propose a method to transform reviews into features including Opinion Words which then can be used for reviews classification tasks by machine learning algorithms. From the obtained results, we evaluate useful Opinion Words which can be informative to identify whether the review is positive or negative.

Author 1: Phuc Quang Tran

Author 2: Ngoan Thanh Trieu

Author 3: Nguyen Vu Dao

Author 4: Hai Thanh Nguyen

Author 5: Hiep Xuan Huynh

Keywords: Review classification; opinion words; machine learning; important features; Amazon

Paper 56: Novel Design and Implementation of a Vehicle Controlling and Tracking System

Abstract: The purpose of this project is to build a system that will quickly track the location of a stolen vehicle, thereby reducing the cost and effort of police. Moreover, the vehicle’s computer system can be controlled remotely by the owners of the vehicle or police. More precisely, the goal of this work is to design a, develop remote control of the vehicle, and find the locations with Latitude (LAT) and Longitude (LONG).

Author 1: Hasan K. Naji

Author 2: Iuliana Marin

Author 3: Nicolae Goga

Author 4: Cristian Taslitschi

Keywords: Vehicle controlling; smart system; tracking system; microcontroller; messaging; GSM; GBS

Paper 57: An Intelligent Approach for Detecting Palm Trees Diseases using Image Processing and Machine Learning

Abstract: Today’s palm trees diseases which cause a huge loss in production are extremely hard to detect either because these diseases are hidden inside the texture of the palm itself and cannot be seen by naked eyes or because it appears on its leaves which are hardly examined due to how far they really are from the ground. In this paper we’re interested in detecting three of the most common diseases threatening palms today, Leaf Spots, Blight Spots and Red Palm Weevil. Diagnosis of these diseases are done by capturing normal and thermal images of palm trees then, image processing techniques were applied to the acquired images. Two classifiers were used, CNN to differentiate between Leaf Spots and Blight Spots diseases and SVM for Red Palm Weevil pest. The results for CNN and SVM algorithms showed a success rate of accuracy ratio 97.9% and 92.8% respectively, these results are considered to be the best results in this domain as far as we know. The paper also includes the first gathered thermal images dataset for palms infected with Red Palm Weevil and healthy palms as well.

Author 1: Hazem Alaa

Author 2: Khaled Waleed

Author 3: Moataz Samir

Author 4: Mohamed Tarek

Author 5: Hager Sobeah

Author 6: Mustafa Abdul Salam

Keywords: Machine learning; deep learning; image processing; leaf spots; blight spots; red palm weevil

Paper 58: Entropy-Based k Shortest-Path Routing for Motorcycles: A Simulated Case Study in Jakarta

Abstract: Traffic congestion is a serious problem in rapidly developing urban areas like Jakarta, Indonesia’s capital city. To avoid the congestion, motorcycles assisted with navigation apps are popular solution. However, the existing navigation apps do not take into account traffic data. This paper proposes an open-source navigation app for motorcycle by taking into account the traffic data and wide road to avoid congestion. The propose navigation app uses entropy-balanced k shortest paths (EBkSP) algorithm to suggest different routes to different users to prevent further congestion. Tests show that the proposed route planning system in the app gives routes that are significantly shorter than motorcycle routes planned by Google Maps. The EBkSP algorithm also distributes vehicles more evenly among routes than the random kSP algorithm and does so in a practical amount of computing time.

Author 1: Muhamad Asvial

Author 2: M. Faridz Gita Pandoyo

Author 3: Ajib Setyo Arifin

Keywords: Traffic congestion; motorcycle; navigation apps; EBkSP

Paper 59: Identity Attributes Metric Modelling based on Mathematical Distance Metrics Models

Abstract: Internet has brought a lot of security challenges on the interaction, activities, and transactions that occur online. These include pervasion of privacy of individuals, organizations, and other online actors. Relationships in real life get affected by online mischievous actors with intent to misrepresent or ruin the characters of innocent people, leading to damaged relationships. Proliferation of cybercrime has threatened the value and benefits of internet. Identity theft by fraudsters with intent to steal assets in real space or online has escalated. This study has developed a metrics model based on distance metrics in order to quantify the credential identity attributes used in online services and activities. This is to help address the digital identity challenges, bring confidence to online activities and ownership of assets. The application forms and identity tokens used in the various sectors to identify online users were used as the sources of the identity attributes in this paper. The corpus toolkits were used to mine and extract the identity attributes from the various forms of identity tokens. Term weighting schemes were used to compute the term weight of the identity attributes. Other methods used included Shannon Entropy and the Term Frequency-Inverse Document Frequency scheme (TF*IDF). Standardization of data using data normalization method has been applied. The results show that using the Cosine Similarity Measure, we can identify the identity attributes in any given identity token used to identify individuals and entities. This will help to attach the legitimate ownership to the digital identity attributes. The developed model can be used to uniquely identify an online identity claimant and help address the security challenge in identity management systems. The proposed model can also identify the key identity attributes that could be used to identify an entity in real or cyber spaces.

Author 1: Felix Kabwe

Author 2: Jackson Phiri

Keywords: Mathematical modeling; Cosine Similarity Measure; text frequency; inverse document frequency; cyber space; term weight; internet; digital identity; trust model; normalization; text mining

Paper 60: Design Optimization of Power and Area of Two-Stage CMOS Operational Amplifier Utilizing Chaos Grey Wolf Technique

Abstract: Low Power Dissipation is an emerging challenge in the current electronics industry. Area shrinking has found the most prominent place and is the foundation of every constricted size in the utilization of CMOS circuits in Integrated Circuit Manufacturing. Functionality in terms of rapidity, dissipation of power, etc. are strongly influenced by the dimensions of transistors in many CMOS Integrated Circuits. The significant formulation parameters in CMOS circuit design to perform optimization of the above-mentioned parameters, and various techniques were projected earlier to a maximum extent possible. Latency, Power, and Dimension are significant parameters in the design of CMOS based IC design. Most analog circuit reduction in terms of size as parameter typically describes solitary or many objectives-controlled optimization issues. The eminent challenges with regards to size and power dissipation can be described as problems that are typically encountered under certain conditions. In this study, the design of a two-stage CMOS Differential Amplifier applying the nature-inspired Grey Wolf Algorithm for optimizing the area and power is utilized. To enhance the formulation terms concerning important considerations such as the amount incurred, strength, and functionality; a computerized formulation approach is used. This formulated design proposal will meet specifications such as positive and negative Slew Rate, Unity Gain Bandwidth and Phase Margin, etc. Chaos theory can be induced into the Grey Wolf Optimization Algorithm (CGWO) with the help of speeding global convergence metric i.e. Speed. The results obtained from CGWO are then analyzed with the functionality of other prevailing optimization techniques employed in the analog circuit sizing. Depending on the investigations, CGWO functions reduce the dimensions of the circuit and analyze the prevailing techniques by achieving a healthier rate of convergence and power dissipation with low value.

Author 1: Telugu Maddileti

Author 2: Govindarajulu Salendra

Author 3: Chandra Mohan Reddy Sivappagari

Keywords: CMOS; CGWO; optimization technique; operational amplifier; aspect ratio; power dissipation

Paper 61: BERT+vnKG: Using Deep Learning and Knowledge Graph to Improve Vietnamese Question Answering System

Abstract: A question answering (QA) system based on natural language processing and deep learning is a prominent area and is being researched widely. The Long Short-Term Memory (LSTM) model that is a variety of Recurrent Neural Network (RNN) used to be popular in machine translation, and question answering system. However, that model still has certainly limited capabilities, so a new model named Bidirectional Encoder Representation from Transformer (BERT) emerged to solve these restrictions. BERT has more advanced features than LSTM and shows state-of-the-art results in many tasks, especially in multilingual question answering system over the past few years. Nevertheless, we tried applying multilingual BERT model for a Vietnamese QA system and found that BERT model still has certainly limitation in term of time and precision to return a Vietnamese answer. The purpose of this study is to propose a method that solved above restriction of multilingual BERT and applied for question answering system about tourism in Vietnam. Our method combined BERT and knowledge graph to enhance accurately and find quickly for an answer. We experimented our crafted QA data about Vietnam tourism on three models such as LSTM, BERT fine-tuned multilingual for QA (BERT for QA), and BERT+vnKG. As a result, our model outperformed two previous models in terms of accuracy and time. This research can also be applied to other fields such as finance, e-commerce, and so on.

Author 1: Truong H. V Phan

Author 2: Phuc Do

Keywords: Bidirectional Encoder Representation from Transformer (BERT); knowledge graph; Question Answering (QA); Long Short-Term Memory (LSTM); deep learning; Vietnamese tourism; natural language processing

Paper 62: A New Strategy for the Morphological and Colorimetric Recognition of Erythrocytes for the Diagnosis of Forms of Anemia based on Microscopic Color Images of Blood Smears

Abstract: The detection of red blood cells based on morphology and colorimetric appearance is very important in improving hematology diagnostics. There are automatons capable of detecting certain forms, but these have limitations with regard to the formal identification of red blood cells because they consider certain cells to be red blood cells when they are not and vice versa. Other automata have limitations in their operation because they do not cover a sufficient area of the blood smear. In spite of their performance, biologists have very often resorted to the manual analysis of blood smears under an optical microscope for a morphological and colorimetric study. In this paper, we present a new strategy for semi-automatic identification of red blood cells based on their isolation, their automatic color segmentation using Otsu's algorithm and their morphology. The algorithms of our method have been implemented in the programming environment of the scientific software MATLAB resulting in an artificial intelligence application. The application, once launched, allows the biologist to select a region of interest containing the erythrocyte to be characterized, then a set of attributes are computed extracted from this target red blood cell. These attributes include compactness, perimeter, area, morphology, white and red proportions of the erythrocyte, etc. The types of anemia treated in this work concern the iron-deficiency, sickle-cell or falciform, thalassemia, hemolytic, etc. forms. The results obtained are excellent because they highlight different forms of anemia contracted in a patient.

Author 1: J. Nango ALICO

Author 2: Sie OUATTARA

Author 3: Alain CLEMENT

Keywords: Erythrocyte; anemia; iron-deficiency; falciform; thalassemia; hemolytic; recognition; morphology; color; segmentation; histogram; Otsu

Paper 63: Enhanced Artificial Intelligence System for Diagnosing and Predicting Breast Cancer using Deep Learning

Abstract: Breast cancer is the leading cause of death among women with cancer. Computer-aided diagnosis is an efficient method for assisting medical experts in early diagnosis, improving the chance of recovery. Employing artificial intelligence (AI) in the medical area is very crucial due to the sensitivity of this field. This means that the low accuracy of the classification methods used for cancer detection is a critical issue. This problem is accentuated when it comes to blurry mammogram images. In this paper, convolutional neural networks (CNNs) are employed to present the traditional convolutional neural network (TCNN) and supported convolutional neural network (SCNN) approaches. The TCNN and SCNN approaches contribute by overcoming the shift and scaling problems included in blurry mammogram images. In addition, the flipped rotation-based approach (FRbA) is proposed to enhance the accuracy of the prediction process (classification of the type of cancerous mass) by taking into account the different directions of the cancerous mass to extract effective features to form the map of the tumour. The proposed approaches are implemented on the MIAS medical dataset using 200 mammogram breast images. Compared to similar approaches based on KNN and RF, the proposed approaches show better performance in terms of accuracy, sensitivity, spasticity, precision, recall, time of performance, and quality of image metrics.

Author 1: Mona Alfifi

Author 2: Mohamad Shady Alrahhal

Author 3: Samir Bataineh

Author 4: Mohammad Mezher

Keywords: Traditional Convolutional Neural Network (TCNN); Supported Convolutional Neural Network (SCNN); shift; scaling; cancer detection; mammogram; histogram equalization; adaptive median filter

Paper 64: A Dynamic Two-Layers MI and Clustering-based Ensemble Feature Selection for Multi-Labels Text Classification

Abstract: Multi-label text classification deals with the issue that arises from each sample being related to multiple labels. The text data suffers from high dimensionality. In order to resolve this issue, a feature selection (FS) method can be implemented for efficiently removing the noisy, irrelevant, and redundant features. Multi-label FS is a powerful tool for solving the high-dimension problem. With regards to handling correlation and high dimensionality problems in multi-label text classification, this paper investigates the various heterogeneous FS ensemble schemes. In addition, this paper proposes an enhanced FS method called dynamic multi-label two-layers MI and clustering-based ensemble feature selection algorithm (DMMC-EFS). The proposed method considers the: 1) dynamic global weight of feature, 2) heterogeneous ensemble, and 3) maximum dependency and relevancy and minimum redundancy of features. This method aims to overcome the high dimensionality of multi-label datasets and acquire improved multi-label text classification. We have conducted experiments based on three benchmark datasets: Reuters-21578, Bibtex, and Enron. The experimental results show that DMMC-EFS has significantly outperformed other state-of-the-art conventional and ensemble multi-label FS methods.

Author 1: Adil Yaseen Taha

Author 2: Sabrina Tiun

Author 3: Abdul Hadi Abd Rahman

Author 4: Masri Ayob

Author 5: Ali Sabah

Keywords: Multi-label text classification; high dimensionality; filtering method; ensemble clustering; ensemble MI feature selection

Paper 65: ARIMA Model for Accurate Time Series Stocks Forecasting

Abstract: With the increasing of historical data availability and the need to produce forecasting which includes making decisions regarding investments, in addition to the needs of developing plans and strategies for the future endeavors as well as the difficulty to predict the stock market due to its complicated features, This paper applied and compared auto ARIMA (Auto Regressive Integrated Moving Average model). Two customize ARIMA(p,D,q) to get an accurate stock forecasting model by using Netflix stock historical data for five years. Between the three models, ARIMA (1,1,33) showed accurate results in calculating the MAPE and holdout testing, which shows the potential of using the ARIMA model for accurate stock forecasting.

Author 1: Shakir Khan

Author 2: Hela Alghulaiakh

Keywords: ARIMA; forecasting; prediction analysis; time series; stocks forecasting; data mining; big data

Paper 66: M2C: A Massive Performance and Energy Throttling Framework for High-Performance Computing Systems

Abstract: At the Petascale level of performance, High-Performance Computing (HPC) systems require significant use of supercomputers with the extensive parallel programming approaches to solve the complicated computational tasks. The Exascale level of performance having 1018 calculations per second is another remarkable achievement in computing with a fathomless influence on everyday life. The current technologies are facing various challenges while achieving ExaFlop performance through energy-efficient systems. Massive parallelism and power consumption are vital challenges for achieving ExaFlop performance. In this paper, we have introduced a novel parallel programming model that provides massive performance under power consumption limitations by parallelizing data on the heterogeneous system to provide coarse grain and fine-grain parallelism. The proposed dual-hierarchical architecture is a hybrid of MVAPICH2 and CUDA, called the M2C model, for heterogeneous systems that utilize both CPU and GPU devices for providing massive parallelism. To validate the objectives of the current study, the proposed model has been implemented using bench-marking applications including linear Dense Matrix Multiplication. Furthermore, we conducted a comparative analysis of the proposed model by existing state-of-the-art models and libraries such as MOC, kBLAS, and cuBLAS. The suggested model outperforms existing models while achieving massive performance in HPC clusters and can be considered for emerging Exascale computing systems.

Author 1: Muhammad Usman Ashraf

Author 2: Kamal M. Jambi

Author 3: Amna Arshad

Author 4: Rabia Aslam

Author 5: Iqra Ilyas

Keywords: High performance computing; Exascale computing; compute unified device architecture

Paper 67: Systematic Review Study of Decision Trees based Software Development Effort Estimation

Abstract: The role of decision trees in software development effort estimation (SDEE) has received increased attention across several disciplines in recent years thanks to their power of predicting, their ease of use, and understanding. Furthermore, there are a large number of published studies that investigated the use of a decision tree (DT) techniques in SDEE. Nevertheless, in reviewing the literature, a systematic literature review (SLR) that assesses the evidence stated on DT techniques is still lacking. The main issues addressed in this paper have been divided into five parts: prediction accuracy, performance comparison, suitable conditions of prediction, the effect of the methods employed in association with DT techniques, and DT tools. To carry out this SLR, we performed an automatic search over five digital libraries for studies published between 1985 and 2019. In general, the results of this SLR revealed that most DT methods outperform many techniques and show an improvement in accuracy when combined with association rules (AR), fuzzy logic (FL), and bagging. Additionally, it has been observed a limited use of DT tools: it is therefore suggested for researchers to develop more DT tools to promote the industrial utilization of DT amongst professionals.

Author 1: Assia Najm

Author 2: Abdelali Zakrani

Author 3: Abdelaziz Marzak

Keywords: Systematic literature review; decision tree; regression tree; software development effort estimation

Paper 68: Genetic Algorithms for the Multiple Travelling Salesman Problem

Abstract: We consider the multiple travelling salesman Problem (MTSP) that is one of the generalization of the travelling salesman problem (TSP). For solving this problem genetic algorithms (GAs) based on numerous crossover operators have been described in the literature. Choosing effective crossover operator can give effective GA. Generally, the crossover operators that are developed for the TSP are applied to the MTSP. We propose to develop simple and effective GAs using sequential constructive crossover (SCX), adaptive SCX, greedy SCX, reverse greedy SCX and comprehensive SCX for solving the MTSP. The effectiveness of the crossover operators is demonstrated by comparing among them and with another crossover operator on some instances from TSPLIB of various sizes with different number of salesmen. The experimental study shows the promising results by the crossover operators, especially CSCX, for the MTSP.

Author 1: Maha Ata Al-Furhud

Author 2: Zakir Hussain Ahmed

Keywords: Multiple travelling salesman problem; NP-hard; genetic algorithm; sequential constructive crossover; adaptive; greedy; comprehensive

Paper 69: Stage Identification and Classification of Lung Cancer using Deep Convolutional Neural Network

Abstract: The performance of lung segmentation is highly dependent on disease prediction task. Challenges for prediction and segmentation raise the need of using multiple learning techniques. Current models initially perform image segmentation in all CT scan images and then classify it as malicious or benign. This consumes more time since it segments both normal and abnormal CT’s. So, due to improper segmentation of images the region of interest will be inaccurate and results in false classification of images. Therefore, by initially checking the CT which has malignancy and then segmenting those lesions will provide more accuracy in segmentation of cancerous nodules thereby helps to identify the stage of cancer the patient is suffering from. The aim is to improve the current cancer detection techniques using DCNN by filtering out malignant CT scan from the medical dataset and segmenting those images for stage identification. Segmentation is done using UNET++ architecture and stage identification is done by considering the “size” (T) parameter from the globally recognized standard named “TNM staging” for classifying the spread of each malignant nodule as T1-T4. 99.83 % accuracy is achieved in lung cancer classification using VGG-16 which yields better results for both segmentation and stage identification too.

Author 1: Varsha Prakash

Author 2: Smitha Vas.P

Keywords: Computer Aided Diagnosis (CAD); Deep Convolutional Neural Network (DCNN); pulmonary nodule; segmentation; benign; malignant; staging

Paper 70: Classification Model of Municipal Management in Local Governments of Peru based on K-means Clustering Algorithms

Abstract: The K-means algorithm groups datasets into different groups, defines a fixed number of clusters, iteratively assigning data to the clusters formed by adjusting the centers in each cluster. K-means algorithm uses an unsupervised learning method to discover patterns in an input data set. The purpose of the research is to propose a municipal management classification model in the municipalities of Peru using a K-means clustering algorithm based in 58 variables obtained from the areas of human resources, heavy machinery and operating vehicles, information and communication technologies, municipal planning, municipal finances, local economic development, social services, solid waste management, cultural, recreational and sports facilities, public security, disaster risk management, environmental protection and conservation of all the municipalities of the 24 departments of Peru and the constitutional province of Callao. The results of the application of the K-means algorithm show that 32% of the municipalities made up of the municipal governments of Amazonas, Apurímac, Huancavelica, Huánuco, Ica, Lambayeque, Loreto and San Martin; are in Cluster 1; the 8% in Cluster 2 with the municipal governments of Ancash and Cusco; in the third Cluster the 28% with the municipal governments of the constitutional Province of Callao, Madre de Dios, Moquegua, Pasco, Tacna, Tumbes and Ucayali and in Cluster 4, 32% composed of the municipal governments of Arequipa, Ayacucho, Cajamarca, Junín, La Libertad, Lima, Piura and Puno Region.

Author 1: Jose Morales

Author 2: Nakaday Vargas

Author 3: Mario Coyla

Author 4: Jose Huanca

Keywords: K-means; cluster; municipality; model; municipal management

Paper 71: Dynamic SEIZ in Online Social Networks: Epidemiological Modeling of Untrue Information

Abstract: The epidemic propagation of untrue information in online social networks leads to potential damage to society. This phenomenon has attracted attention to researchers on a faster spread of false information. Epidemic models such as SI, SIS, SIR, developed to study the infection spread on social media. This paper uses SEIZ, an enhanced epidemic model classifies the overall population in four classes (i.e. Susceptible, Exposed, Infected, Skeptic). It uses probabilities of transition from one state to another state to characterize misinformation from actual information. It suffers from two limitations i.e. the rate of change of population and state transition probabilities considered constant for the entire period of observation. In this paper, a dynamic SEIZ computes the rate of change of population at fixed intervals and the predictions based on the new rates periodically. Research findings on Twitter data have indicated that this model gives more accuracy by early indications of being untrue information.

Author 1: Akanksha Mathur

Author 2: Chandra Prakash Gupta

Keywords: Information diffusion; epidemic models; SEIZ; rumor detection

Paper 72: An Artificial Intelligent based System to Automate Decision Making in Assembly Solution Design

Abstract: Nowadays, competitiveness between industries has become very strong. Thus, industries are faced to serious challenges in terms of products qualities, time development and production cost. As assembly operations difficulties cause a big part of production problems, the integration of assembly selection since the earlier product life cycle phases has become a necessity for every company in order to survive. However, despite the large number of approaches that have been proposed in order to achieve this integration goal, many other problems are still present. It is in this context that a flexible and automated decision making system is proposed. It is based on ontologies and also on the Case Based Reasoning (CBR) and Rule Based Reasoning (RBR) concepts. Indeed, this system is an automation of the integrated DFMMA approach, in particular its assembly solution selection methodology. The developed system permits to designers avoiding the redundancy in the works by benefiting from their previous studies and their experience. In addition to that, it facilitates and automates the assembly solution selection even if the number of assembly alternatives is high. Finally, to illustrate the efficacy of the proposed system, a case of study is developed in the end of the work.

Author 1: ABADI Chaimae

Author 2: MANSSOURI Imad

Author 3: ABADI Asmae

Keywords: Assembly selection; product assembly; ontologies; CBR & RBR; flexible and automated; decision making system; artificial intelligence

Paper 73: IDP: A Privacy Provisioning Framework for TIP Attributes in Trusted Third Party-based Location-based Services Systems

Abstract: Location-Based Services (LBS) System is rapidly growing due to radio communication services with wireless mobile devices having a positioning component in it. LBS System offers location-based services by knowing the actual user position. A mobile user uses LBS to access services relevant to their locations. In order to provide Point of Interest (POI), LBS confronts numerous privacy related challenges in three different formats including Non-Trusted Third Party (NTTP), Trusted Third Party (TTP), and Mobile Peer-to-Peer (P2P). The current study emphasized the TTP based LBS system where the Location server does not provide full privacy to mobile users. In TTP based LBS system, a user’s privacy is concerned with personal identity, location information, and time information. In order to accomplish privacy under these concerns, state-of-the-art existing mechanisms have been reviewed. Hence, the aim to provide a promising roadmap to research and development communities for the right selection of privacy approach has achieved by conducting a comparative survey of the TTP based approaches. Leading to these privacy attributes, the current study addressed the privacy challenge by proposing a new privacy protection model named “Improved Dummy Position” (IDP) that protects TIP (Time, Identity, and Position) attributes under TTP LBS System. In order to validate the privacy level, a comparative analysis has been conducted by implementing the proposed IDP model in the simulation tool, Riverbed Modeler academic edition. The different scenarios of changing query transferring rate evaluate the performance of the proposed model. Simulation results demonstrate that our IDP could be considered as a promising model to protect user’s TIP attributes in a TTP based LBS system due to better performance and improved privacy level. Further, the proposed model extensively compared with the existing work.

Author 1: Muhammad Usman Ashraf

Author 2: Kamal M. Jambi

Author 3: Rida Qayyum

Author 4: Hina Ejaz

Keywords: Location Based Services (LBS); Trusted Third Party (TTP); privacy protection goals; mobile user privacy; Improved Dummy Position (IDP); Sybil Query

Paper 74: Survey on Homomorphic Encryption and Address of New Trend

Abstract: Encryption is the process of disguising text to ensure the confidentiality of data transmitted from one party to another. Homomorphic encryption is one of the most important encryption-related processes which allows performing operation over encrypted data. Using different public key algorithms, homo-morphic encryption can be implemented in any scheme. There are many encryption algorithms to secure operations and data stor-age, which after calculations can obtain the same results. While there is a considerable contribution and enhancement in the field of homomorphic encryption for various performance metrics, there is still an necessity to clarify the applications dealing with this technology. Recently, many distinguished research papers have been filed to address the need for various applications of homomorphic encryption. Recently, many distinguished research papers have been filed to address the need for various applications of homomorphic encryption. Example of these applications but not limited to : Vehicle to Vehicle (v2v) secure communication, cloud security, Vehicular ad-hoc networks (VANET), Blockchain, E-Voting, Data mining with privacy preserving and healthcare sector. This article aims to introduce a literature survey to close the gap in homomorphic encryption systems and their applications in the protection of privacy. We focus on above-mentioned applications and present our recommendations for future work.

Author 1: Ayman Alharbi

Author 2: Haneen Zamzami

Author 3: Eman Samkri

Keywords: Homomorphic encryption; cloud computing; V2V; VANET; blockchain

Paper 75: Convolutional Neural Network and Topic Modeling based Hybrid Recommender System

Abstract: In today’s personalized business environment, or-ganizations are providing bulk of information regarding their products and services. Recommender system has various accom-plishment on exploiting auxiliary information in matrix factor-ization. To handle data sparsity problem most recommender systems utilized deep learning techniques for in-depth analysis of item content to generate more accurate recommendations. However, these systems still have a research gap on how to handle user reviews effectively. Reviews that were written by users contain a large amount of information that can be utilized for more accurate predictions. This paper proposes a Hybrid Model to address the sparsity problem, convolutional neural network and topic modeling for recommender system, which extract the contextual features of both items and users by utilizing Deep Learning Convolutional Neural Network (CNN) along with Topic Modeling (Lda2vec) technique to generate latent factors of user and item. Topic Modeling is used to capture important topics from side information and deep learning is used to provide contextual information. To demonstrate the effectiveness of the research, an extensive experimental sets were performed on four public datasets (Amazon Instant Video, Kindle store, Health and Personal Care, Automotive). Results demonstrate that the proposed model outperformed the other state of the art approaches.

Author 1: Hira Kanwal

Author 2: Muhammad Assam

Author 3: Abdul Jabbar

Author 4: Salman Khan

Author 5: Kalimullah

Keywords: Recommender system; collaborative filtering; Lda2vec; Convolutional Neural Network (CNN); data sparsity problem; user reviews

Paper 76: Data Rate Limit in Low and High SNR Regime for Nakagami-q Fading Wireless Channel

Abstract: Adequate data rate is always desired in wireless communication channels. Previously, few fading models were used to model wireless communication channels and to perform analysis on them. In this paper, analyses of data rate limit of single-input single-output (SISO) wireless communication system over Nakagami-q fading channels are presented. The calculation of capacity has been carried out using small and large limit argument approximations. The analytical solution for channel capacity is presented using small and large limit argument approximations. Where small and large limit argument approx-imations correspond low and high signal-to-noise ratio (SNR) regime. Behavior of channel capacity with respect to SNR and fading parameter respectively has been investigated deeply. The comparison of the channel capacity behavior for both low SNR and high SNR regime and have also been done and analyzed. It has found that the channel capacity increased with increasing SNR in low SNR regime. The channel capacity also behave in the same manner in high SNR regime as well.

Author 1: Md. Mazid-Ul-Haque

Author 2: Md. Sohidul Islam

Keywords: Wireless communication; Nakagami-q fading; SISO channel capacity; low SNR regime; high SNR regime

Paper 77: DeepScratch: Scratch Programming Language Extension for Deep Learning Education

Abstract: Visual programming languages make programming more accessible for novices, which open more opportunities to innovate and develop problem-solving skills. Besides, deep learning is one of the trending computer science fields that has a profound impact on our daily life, and it is important that young people are aware of how our world works. In this study, we partially attribute the difficulties novices face in building deep learning models to the used programming language. This paper presents DeepScratch, a new programming language extension to Scratch that provides powerful language elements to facilitate building and learning about deep learning models. We present the implementation process of DeepScratch, and explain the syntactical definition and the lexical definition of the extended vocabulary. DeepScratch provides two options to implement deep learning models: training a neural network based on built-in datasets and using pre-trained deep learning models. The two options are provided to serve different age groups and educational levels. The preliminary evaluation shows the usability and the effectiveness of this extension as a tool for kids to learn about deep learning.

Author 1: Nora Alturayeif

Author 2: Nouf Alturaief

Author 3: Zainab Alhathloul

Keywords: Deep learning; visual programming languages; pro-gramming education; formal language definitions; neural networks

Paper 78: Enhancing Disease Prediction on Imbalanced Metagenomic Dataset by Cost-Sensitive

Abstract: Imbalanced datasets usually appear popularly to many real-world applications and studies. For metagenomic data, we also face the same issue where the number of patients is greater than the number of healthy individuals or vice versa. In this study, we propose a method to handle the imbalanced datasets issues by Cost-sensitive approach. The proposed method is evaluated on an imbalanced metagenomic dataset related to Inflammatory bowel disease to do prediction tasks. Our method reaches a noteworthy improvement on prediction performance with deep learning algorithms including a MultiLayer Perceptron and a Convolutional Neural Neural Network with the proposed cost-sensitive for Metagenome-based Disease Prediction tasks.

Author 1: Hai Thanh Nguyen

Author 2: Toan Bao Tran

Author 3: Quan Minh Bui

Author 4: Huong Hoang Luong

Author 5: Trung Phuoc Le

Author 6: Nghi Cong Tran

Keywords: Cost-sensitive; imbalanced datasets; disease predic-tion; deep learning

Paper 79: Design of Efficient Power Supply for the Proper Operation of Bio-Mimetic Soft Lens

Abstract: Soft Robotics is one of the emerging and top-notched researched fields in Robotics which collaborate and Interact with Human Machine Interface (HMI). Several power electronics and electrical devices are used for the proper operation of these robots, among them high voltage power supply plays a vital role. Several approaches are used for the design of the high voltage power supply but still there is a deficiency in the design of the power supply which fulfill our desires level (highly efficient and less complex). This paper presents the efficient power supply for the control of bio-mimetic lens. The proposed power supply is designed by the use of boost converter, single phase inverter and the cock-croft Walton Voltage Multiplier. The work employs the use of power electronics for the achievement of the efficient high voltage power supply and boost the level of voltage up to 5 kV. Numerical simulations are performed for the comprehensive testing of the proposed model. Simulink is used for designing of the high voltage supply for simulation work. More-over the results are verified with the designing of laboratory setup. The experimental results are close to the simulation results with an error less than 3%. This proof the validity of proposed high voltage power supply.

Author 1: Saad Hayat

Author 2: Sheeraz Ahmed

Author 3: Malik Shah Zeb Ali

Author 4: Muhammad Qaiser Khan

Author 5: Muhammad Salman Khan

Author 6: Muhammad Usama

Author 7: Zeeshan Najam

Author 8: Asif Nawaz

Keywords: Cock croft walton multiplier; EOG; elastomers; bio mimetic lens; template

Paper 80: Viral and Bacterial Pneumonia Diagnosis via Deep Learning Techniques and Model Explainability

Abstract: Pneumonia is one of the most serious diseases for infants and young children, people older than age 65, and people with health problems or weakened immune systems. From nu-merous studies, scientists have found that a variety of organisms, including bacteria, viruses, and fungi, can be the cause of the disease. Coronavirus pandemic (COVID-2019) which comes from a type of pneumonia has been causing hundreds of thousands of deaths and is still progressing. Machine learning approaches are applied to develop models for medicine but they still work as a black-box are difficult to interpret output generated by machine learning models. In this study, we propose a method for image-based diagnosis for Pneumonia leveraging deep learning techniques and interpretability of explanation models such as Local Interpretable Model-agnostic Explanations and Saliency maps. We experiment on a variety of sizes and Convolutional neural network architecture to evaluate the efficiency of the proposed method on the set of Chest x-ray images. The work is expected to provide an approach to distinguish between healthy individuals and patients who are affected by Pneumonia as well as differentiate between viral Pneumonia and bacteria Pneumonia by providing signals supporting image-based disease diagnosis approaches.

Author 1: Hai Thanh Nguyen

Author 2: Toan Bao Tran

Author 3: Huong Hoang Luong

Author 4: Trung Phuoc Le

Author 5: Nghi Cong Tran

Keywords: Interpretability; pneumonia; x-rays images; bacte-rial and viral pneumonia; image-based disease diagnosis

Paper 81: Abandoned Object Detection using Frame Differencing and Background Subtraction

Abstract: Tracking objects over fixed surveillance cameras are widely used for security purposes in public areas such as train stations, airports, parking areas, and public transportation for the prevention of terrorism. Once the object is accurately detected in the image scene, we can use various visual algorithms to find a number of applications. In this paper, we introduce a model for tracking the multiple objects along with detecting the abandoned luggage in the real time environment. In our model, we used the initial frames to model the background scene. Next, we used the motion model that is background subtraction to detect and track moving objects such as the owner and the luggage. The proposed model also maintains the position history of moving objects followed by the frame differencing technique to find out the luggage history and detect the abandoned luggage by a human. We have used PETS2006 and PETS2007 dataset for the testing of the proposed system in various indoor and outdoor environments with varying lighting conditions.

Author 1: Mohiu Din

Author 2: Aneela Bashir

Author 3: Abdul Basit

Author 4: Sadia Lakho

Keywords: Object detection; video surveillance; tracking; back-ground subtraction; frame differencing; motion model

Paper 82: Single and Ensemble Classification for Predicting User’s Restaurant Preference

Abstract: Classification is one of the most attractive and powerful data mining functionalities. Classification algorithms are applied to real-world problems to produce intelligent prediction models. Two main categories of classification algorithms can be adopted for generating prediction models: Single and Ensemble classification algorithms. In this paper, both categories are utilized to generate a novel prediction model to predict restaurant category preferences. More specifically, the central idea espoused in this paper is to construct an effective prediction model, using Single and Ensemble classification algorithms, to assist people to determine the best relevant place to go based on their demographic data, income level and place preferences. Therefore, this paper introduces a new application of classification task. According to the reported experimental results, an effective Restaurant Category Preferences Prediction Model (RCPPM) could be generated using classification algorithms. In addition, Bagging Homogeneous Ensemble classification produced the most effective RCPPM.

Author 1: Esra’a Alshdaifat

Author 2: Ala’a Al-shdaifat

Keywords: Classification; data mining; ensemble algorithms; restaurant preferences

Paper 83: A Multi-Class Neural Network Model for Rapid Detection of IoT Botnet Attacks

Abstract: The tremendous number of Internet of Things (IoT) devices and their widespread use have made our lives considerably more manageable and safer. At the same time, however, the vulnerability of these innovations means that our day-to-day existence is surrounded by insecure devices, thereby facilitating ways for cybercriminals to launch various attacks by large-scale robot networks (botnets) through IoT. In consideration of these issues, we propose a neural network-based model to detect IoT botnet attacks. Furthermore, the model provides multi-classification, which is necessary for taking appropriate countermeasures to understand and stop the attacks. In addition, it is independent and does not require specific equipment or software to fetch the required features. According to the con-ducted experiments, the proposed model is accurate and achieves 99.99%, 99.04% as F1 score for two benchmark datasets in addition to fulfilling IoT constraints regarding complexity and speed. It is less complicated in terms of computations, and it provides real-time detection that outperformed the state-of-the-art, achieving a detection time ratio of 1:5 and a ratio of 1:8.

Author 1: Haifaa Alzahrani

Author 2: Maysoon Abulkhair

Author 3: Entisar Alkayal

Keywords: Internet of Things (IoT); IoT botnets; IoT security; intrusion detection system; deep learning; neural network

Paper 84: Vehicle Counting using Deep Learning Models: A Comparative Study

Abstract: Recently, there has been a shift to deep learning architectures for better application in vehicle traffic control systems. One popular deep learning library used for detecting vehicle is TensorFlow. In TensorFlow, the pre-trained model is very efficient and can be transferred easily to solve other similar problems. However, due to inconsistency between the original dataset used in the pre-trained model and the target dataset for testing, this can lead to low-accuracy detection and hinder vehicle counting performance. One major obstacle in retraining deep learning architectures is that the network requires a large corpus training dataset to secure good results. Therefore, we propose to perform data annotation and transfer learning from an existing model to construct a new model for vehicle detection and counting in the real world urban traffic scenes. Then, the new model is compared with the experimental data to verify the validity of the new model. Besides, this paper reports some experimental results, comprising a set of innovative tests to identify the best detection algorithm and system performance. Furthermore, a simple vehicle tracking method is proposed to aid the vehicle counting process in challenging illumination and traffic conditions. The results showed a significant improvement of the proposed system with the average vehicle counting of 80.90%.

Author 1: Azizi Abdullah

Author 2: Jaison Oothariasamy

Keywords: CNN; transfer learning; deep learning; object de-tection; vehicle detection

Paper 85: Predicting Customer Retention using XGBoost and Balancing Methods

Abstract: Customer retention is considered as one of the important concerns for many companies and financial institutions like banks, telecommunication service providers, investment ser-vices, insurance and retail sectors. Recent marketing indicators and metrics show that attracting and gaining new customers or subscribers is much more expensive and difficult than retaining existing ones. Therefore, losing a customer or a subscriber will negatively impact the growth and the profitability if the company. In this work, we propose a customer retention model based on one of the most powerful machine learning classifiers which is XGBoost. The latter classifier is experimented when combined wit different oversampling methods to improve its performance in the used imbalanced dataset. The experimental results show very promising results compared to other well-known classifiers.

Author 1: Atallah M. AL-Shatnwai

Author 2: Mohammad Faris

Keywords: Customer retention; churn prediction; oversam-pling; XGBoost

Paper 86: Proposal for a Software Architecture as a Tool for the Fight Against Corruption in the Regional Governments of Peru

Abstract: This paper covers the problem of corruption in Peru, with an emphasis on regional governments, and presents a proposal for an anti-corruption software application architecture for those levels of government. The design of the proposal starts from the analysis of corruption encompassing statistical studies, trust evolution, government management, legal situation and incidents in information technology. Also, aspects of the budget allocation, crime data, political party financing data, management resources, contracting processes, integration systems and citizen participation are presented, for the subsequent presentation of the data structure and resources for the software application architecture. The methodology used is of an exploratory documentary type. In addition, a systemic approach and development are considered in three layers: data persistence, logical process, and presentation; considering the interrelationships that must exist between them for the development of the proposed architecture.

Author 1: Martin M. Soto-Cordova

Author 2: Samuel Leon-Cardenas

Author 3: Kevin Huayhuas-Caripaza

Author 4: Raquel M. Sotomayor-Parian

Keywords: Software architecture; anti-corruption; regional government; local government; corruption perception index

Paper 87: Ontology-based Course Teacher Assignment within Universities

Abstract: Educational institutions suffer from the enormous amount of data that keeps growing continuously. These data are usually scattered and unorganised, and it comes from different resources with different formats. Besides, modernization vision within these institutions aims to reduce human action and replace it with automatic devices interactions. To have the full benefit from these data and use it within the modern systems, they have to be readable and understandable by machines. Those data and knowledge with semantic descriptions make an easy way to monitor and manage decision processes within universities to solve many educational challenges. In this study, an educational ontology is developed to model the semantic courses and academic profiles in universities and use it to solve the challenge of assigning the most appropriate academic teacher to teach a specific course.

Author 1: Ghadeer Ashour

Author 2: Ahmad Al-Dubai

Author 3: Imed Romdhani

Keywords: Semantic; university ontology; academic profile; syllabus; course-teacher assignment