IJACSA Volume 8 Issue 12 - thesai.org

IJACSA Volume 8 Issue 12

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: Impact of Different Data Types on Classifier Performance of Random Forest, Naïve Bayes, and K-Nearest Neighbors Algorithms

Abstract: This study aims to evaluate impact of three different data types (Text only, Numeric Only and Text + Numeric) on classifier performance (Random Forest, k-Nearest Neighbor (kNN) and Naïve Bayes (NB) algorithms). The classification problems in this study are explored in terms of mean accuracy and the effects of varying algorithm parameters over different types of datasets. This content analysis has been examined through eight different datasets taken from UCI to train models for all three algorithms. The results obtained from this study clearly show that RF and kNN outperform NB. Furthermore, kNN and RF perform relatively the same in terms of mean accuracy nonetheless kNN takes less time to train a model. The changing numbers of attributes in datasets have no effect on Random Forest, whereas Naïve Bayes mean accuracy fluctuates up and down that leads to a lower mean accuracy, whereas, kNN mean accuracy increases and ends with higher accuracy. Additionally, changing number of trees has no significant effects on mean accuracy of the Random forest, however, the time to train the model has increased greatly. Random Forest and k-Nearest Neighbor are proved to be the best classifiers for any type of dataset. Thus, Naïve Bayes can outperform other two algorithms if the feature variables are in a problem space and are independent. Besides Random forests, it takes highest computational time and Naïve Bayes takes lowest. The k-Nearest Neighbor requires finding an optimal number of k for improved performance at the cost of computation time. Similarly, changing the number of attributes that effect Naïve Bayes and k-Nearest Neighbor performance nevertheless not the Random forest. This study can be extended by researchers who use the parametric method to analyze results.

Author 1: Asmita Singh

Author 2: Malka N. Halgamuge

Author 3: Rajasekaran Lakshmiganthan

Keywords: Big data; random forest; Naïve Bayes; k-nearest neighbors algorithm

Paper 2: Cluster Formation and Cluster Head Selection Approach for Vehicle Ad-Hoc Network (VANETs) using K-Means and Floyd-Warshall Technique

Abstract: Vehicular Ad-hoc Network (VANETs) is the specific form of Mobile ad-hoc networking (MANETs) in which high dynamic nodes are utilized in carrying out the operations. They are mainly used in urban areas for safety traveling. Clustering algorithms are used for clustering the vehicles that are in the range of the network as VANET consists of a great amount of traffic. A clustering head node is used specified through a procedure to collect all information from the surroundings. This study introduced a new method for cluster head selection by using the K-Mean and Floyd-Warshall algorithms. The proposed technique first divided the points for vehicle groups while the Floyd-Warshall algorithm calculated all pairs of shortest distance for every vehicle within the defined cluster. A vehicle with the smallest average distance among a cluster is chosen as the cluster head. The Floyd-Warshall algorithm overall selects a centralized vehicle as a cluster head, hence its stability time will improve significantly.

Author 1: Iftikhar Hussain

Author 2: Chen Bingcai

Keywords: Vehicular Ad-hoc Network (VANETs); Mobile ad-hoc networking (MANETs); K-Mean; clustering; cluster head selection; Floyd-Warshall

Paper 3: State-of-the-Art and Open Challenges in RTS Game-AI and Starcraft

Abstract: This paper presents a review of artificial intelligence for different approaches used in real-time strategy games. Real-time strategy (RTS) based games are quick combat games in which the objective is to dominate and destroy the opposing enemy such as Rome-total war, Starcraft, the age of empires, and command & conquer, etc. In such games, each player needs to utilize resources efficiently, which includes managing different types of soldiers, units, equipment’s, economic status, positions and the uncertainty during the combat in real time. Now the best human players face difficulty in defeating the best RTS games due to the recent success and advancement of deep mind technologies. In this paper, we explain state-of-the-art and challenges in artificial intelligence (AI) for RTS games and Starcraft, describing problems and issues carried out by RTS based games with some solutions that are addressed to them. Finally, we conclude by emphasizing on game ‘CIG & AIIDE’ competitions along with open research problems and questions in the context of RTS Game-AI, where some of the problems and challenges are mostly considered improved and solved but yet some are open for further research.

Author 1: Khan Adil

Author 2: Feng Jiang

Author 3: Shaohui Liu

Author 4: Worku Jifara

Author 5: Zhihong Tian

Author 6: Yunsheng Fu

Keywords: Real Time Strategy (RTS); Game-AI; Starcraft; MMOG; AIIDE; CIG; MOBA

Paper 4: Intelligent Classification of Liver Disorder using Fuzzy Neural System

Abstract: In this study, designed an intelligent model for liver disorders based on Fuzzy Neural System (FNS) models is considered. For this purpose, fuzzy system and neural networks (FNS) are explored for the detection of liver disorders. The structure and learning algorithm of the FNS are described. In this study, we utilized dataset extracted from a renowned machine learning data base (UCI) repository. 10 folds cross-validation approach was explored for the design of the system. The designed algorithm is accurate, reliable and faster as compared to other traditional diagnostic systems. We highly recommend this framework as a specialized training tool for medical practitioners.

Author 1: Mohammad Khaleel Sallam Ma’aitah

Author 2: Rahib Abiyev

Author 3: Idoko John Bush

Keywords: Artificial neural networks; fuzzy systems; fuzzy neural systems; liver disorders

Paper 5: Training an Agent for FPS Doom Game using Visual Reinforcement Learning and VizDoom

Abstract: Because of the recent success and advancements in deep mind technologies, it is now used to train agents using deep learning for first-person shooter games that are often outperforming human players by means of only screen raw pixels to create their decisions. A visual Doom AI Competition is organized each year on two different tracks: limited death-match on a known map and a full death-match on an unknown map for evaluating AI agents, because computer games are the best test-beds for testing and evaluating different AI techniques and approaches. The competition is ranked based on the number of frags each agent achieves. In this paper, training a competitive agent for playing Doom’s (FPS Game) basic scenario(s) in a semi-realistic 3D world ‘VizDoom’ using the combination of convolutional Deep learning and Q-learning by considering only the screen raw pixels in order to exhibit agent’s usefulness in Doom is proposed. Experimental results show that the trained agent outperforms average human player and inbuilt game agents in basic scenario(s) where only move left, right and shoot actions are allowed.

Author 1: Khan Adil

Author 2: Feng Jiang

Author 3: Shaohui Liu

Author 4: Aleksei Grigorev

Author 5: B.B. Gupta

Author 6: Seungmin Rho

Keywords: Visual reinforcement learning; Deep Q-learning; FPS; CNN; computational intelligence; Game-AI; VizDoom; agent; bot; DOOM

Paper 6: Development of an Improved Algorithm for Image Processing: A Proposed Algorithm for Optimal Reduction of Shadow from the Image

Abstract: Shadow detection is the most important aspect in the field of image processing. It has become essential to develop such algorithms that are capable of processing the images with the maximum efficiency. Therefore, the research has aimed to propose an algorithm that effectively processes the image on the basis of shadow reduction. An algorithm has been proposed, which was based on RGB (red, green, and blue) and HIS (hue, saturation and intensity) model. Steps for Shadow detection have been defined. Median filter and colour saturation have been widely used to process the outcomes. Algorithm has proved efficient for the detection of shadow from the images. It was found efficient when compared with two previously developed algorithms. 87% efficiency has been observed, implementing the proposed algorithm as compared to the algorithms implemented previously by other researchers. The study proved to make a supportive effort in the development of optimized algorithm. It has been suggested that the market requires such practices that can be used to improve the working conditions of the image processing paradigm.

Author 1: Yahia S. AL-Halabi

Keywords: Image; processing; shadow; algorithm; detection filter; luminance; morphological processing

Paper 7: An Automatic Dysarthric Speech Recognition Approach using Deep Neural Networks

Abstract: Transcribing dysarthric speech into text is still a challenging problem for the state-of-the-art techniques or commercially available speech recognition systems. Improving the accuracy of dysarthric speech recognition, this paper adopts Deep Belief Neural Networks (DBNs) to model the distribution of dysarthric speech signal. A continuous dysarthric speech recognition system is produced, in which the DBNs are used to predict the posterior probabilities of the states in Hidden Markov Models (HMM) and the Weighted Finite State Transducers framework was utilized to build the speech decoder. Experimental results show that the proposed method provides better prediction of the probability distribution of the spectral representation of dysarthric speech that outperforms the existing methods, e.g., GMM-HMM based dysarthric speech recogniztion approaches. To the best of our knowledge, this work is the first time to build a continuous speech recognition system for dysarthric speech with deep neural network technique, which is a promising approach for improving the communication between those individuals with speech impediments and normal speakers.

Author 1: Jun Ren

Author 2: Mingzhe Liu

Keywords: Dysarthric speech recognition; deep neural networks; hidden markov models

Paper 8: Internet Orchestra of Things: A Different Perspective on the Internet of Things

Abstract: The Internet of Things (IoT) is defined as a global network that links together living and/or non-living entities, such as people, animals, software, physical objects or devices. These entities can interact with each other, gather, provide or transmit information to the IoT. Although the Internet of Things is a relatively new concept, various platforms are already available. Some of them are open platforms, enabling both the integration of people, systems, and objects from the physical and virtual world, and the visualization of data. For example, there are already some IoT platforms used, like Google Cloud Platform, Microsoft Azure IoT Hub, Amazon Web Services IoT Platform, IBM Watson IoT Platform, Nimbits, Open.Sen.se, ThingWorx, and ThingSpeak. But what if things could not only “work” and “speak”, but also “sing”? We propose a game in which the things connected to IoT can play in real time different sounds, according to the values of some monitored parameters. These things can be grouped in the IoT platform to create a virtual orchestra and make music. Besides this game allowing the creation of great songs, it can be widely used to explain the new ideas behind the fast emerging areas of the Internet of Things. In addition to many technical challenges, it is also worth considering the effect the IoT concept will have on people, society, and economy as a whole.

Author 1: Cristina Turcu

Author 2: Cornel Turcu

Keywords: Internet of Things; music; game; education; RFID; robot

Paper 9: Deep Learning-Based Recommendation: Current Issues and Challenges

Abstract: Due to the revolutionary advances of deep learning achieved in the field of image processing, speech recognition and natural language processing, the deep learning gains much attention. The recommendation task is influenced by the deep learning trend which shows its significant effectiveness and the high-quality of recommendations. The deep learning based recommender models provide a better detention of user preferences, item features and users-items interactions history. In this paper, we provide a recent literature review of researches dealing with deep learning based recommendation approaches which are preceded by a presentation of the main lines of the recommendation approaches and the deep learning techniques. We propose also classification criteria of the different deep learning integration model. Then we finish by presenting the recommendation approach adopted by the most popular video recommendation platform YouTube which is based essentially on deep learning advances.

Author 1: Rim Fakhfakh

Author 2: Anis Ben Ammar

Author 3: Chokri Ben Amar

Keywords: Recommender system; deep learning; neural network; YouTube recommendation

Paper 10: A Comparative Study of Forensic Tools for WhatsApp Analysis using NIST Measurements

Abstract: One of the popularly used features on Android smartphone is WhatsApp. WhatsApp can be misused, such as for criminal purposes. To conduct investigation involving smartphone devices, the investigators need to use forensic tools. Nonetheless, the development of the existing forensic tool technology is not as fast as the development of mobile technology and WhatsApp. The latest version of smartphones and WhatsApp always comes up. Therefore, a research on the performance of the current forensic tools in order to handle a case involving Android smartphones and WhatsApp in particular need to be done. This research evaluated existing forensic tools for performing forensic analysis on WhatsApp using parameters from NIST and WhatsApp artifacts. The outcome shows that Belkasoft Evidence has the highest index number, WhatsApp Key/DB Extractor has superiority in terms of costs, and Oxygen Forensic has superiority in obtaining WhatsApp artifact.

Author 1: Rusydi Umar

Author 2: Imam Riadi

Author 3: Guntur Maulana Zamroni

Keywords: Whatsapp; acquisition; NIST parameters; artifact

Paper 11: Big Data Processing for Full-Text Search and Visualization with Elasticsearch

Abstract: In this paper, the task of using Big Data to identify specific individuals on the indirect grounds of their interaction with information resources is considered. Possible sources of Big Data and problems related to its processing are analyzed. Existing means of data clustering are considered. Available software for full-text search and data visualization is analyzed, and a system based on Elasticsearch engine and MapReduce model is proposed for the solution of user verification problem.

Author 1: Aleksei Voit

Author 2: Aleksei Stankus

Author 3: Shamil Magomedov

Author 4: Irina Ivanova

Keywords: Big Data processing; verification; elasticsearch; MapReduce; data clustering

Paper 12: A New Approach for Grouping Similar Operations Extracted from WSDLs Files using K-Means Algorithm

Abstract: Grouping similar operations is an effective solution to the various problems, especially those related to research because the services will be classified by joint operations. Searching for a particular operation returns, as a result, all services with this same operation, but also the problems related to the substitution (such as, during a call failure or a malfunction). A list of similar operations is returned to the client. He chooses an operation, based on non-functional criteria. In this work, our goal is to study the functional similarity between operations, and thus constituting groups of similar operations, while benefiting from the K-means algorithm.

Author 1: Rekkal Sara

Author 2: Amrane Fatima

Author 3: Loukil Lakhdar

Keywords: Web services; WSDL; inputs; outputs; similarity; syntax analysis; semantic analysis; Hungarian maximum matching; K-means

Paper 13: Predicting Future Gold Rates using Machine Learning Approach

Abstract: Historically, gold was used for supporting trade transactions around the world besides other modes of payment. Various states maintained and enhanced their gold reserves and were recognized as wealthy and progressive states. In present times, precious metals like gold are held with central banks of all countries to guarantee re-payment of foreign debts, and also to control inflation. Moreover, it also reflects the financial strength of the country. Besides government agencies, various multi-national companies and individuals have also invested in gold reserves. In traditional events of Asian countries, gold is also presented as gifts/souvenirs and in marriages, gold ornaments are presented as Dowry in India, Pakistan and other countries. In addition to the demand and supply of the commodity in the market, the performance of the world’s leading economies also strongly influences gold rates. We predict future gold rates based on 22 market variables using machine learning techniques. Results show that we can predict the daily gold rates very accurately. Our prediction models will be beneficial for investors, and central banks to decide when to invest in this commodity.

Author 1: Iftikhar ul Sami

Author 2: Khurum Nazir Junejo

Keywords: Gold rates; prediction; forecasting; linear regression; neural networks; ARMA Model

Paper 14: Leisure Technology for the Elderly: A Survey, User Acceptance Testing and Conceptual Design

Abstract: The Alzheimer’s disease damages neuronal and synaptic system due to the high level of amyloid beta in the brain. It is the common cause of dementia which is more common to afflict the elderly where they will gradually loss their memory and communication skills as well as deterioration of thinking and reasoning ability. Hence, it is crucial for elderly people to monitor their cognitive performance consistently and continuously to detect the Alzheimer’s symptoms, such as dementia or Mild Cognitive Impairment. There are many technologies that have been established in healthcare for its detection; however, such technologies, mostly medical treatments could not be self-catered by elderly on daily basis and in fact the use of this technology incurs cost each time. Therefore, this study looks at an alternative technology called leisure technology that allows access to the elderly every day at home in an enjoyable and relaxing manner. The aim of this study is to study applications of leisure activities that could stimulate brain cognitive function to be turned to a leisure technology application. Prior to proposing the conceptual design of this application, a user acceptance study of leisure technology among elderly people has been conducted. This study involves interviews and survey through distribution of questionnaires. The survey results shows that 90% of the participants stated that there was an improvement in cognitive abilities after using leisure technology and 98.4% of the participants stated that they could adapt to leisure technology. On the other hand, the outcomes from the interview show that they agreed that different types of leisure technology provide heterogeneous benefits, which can improve their cognitive abilities. Finally, this study proposes a conceptual design for leisure technology application that elderly people can adapt to.

Author 1: Chow Sook Theng

Author 2: Saravanan Sagadevan

Author 3: Nurul Hashimah Ahamed Hassain Malim

Keywords: Leisure technology; user acceptance; cognitive ability; elderly

Paper 15: Machine Learning based Predictive Model for Screening Mycobacterium Tuberculosis Transcriptional Regulatory Protein Inhibitors from High-Throughput Screening Dataset

Abstract: In view of the essential role played by dosRS in the survival of Mycobacterium in the infected granuloma cells, dosRS transcriptional regulatory proteins were considered as a validated target for high throughput screening (HTS). However, the cost and time factor involved in screening large compound libraries are an important hurdle in identifying lead compounds. Therefore, the use of computational machine learning techniques to build a predictive model for screening putative drug-like molecule has gained significance. In this regard, a target-based predictive model using machine learning approaches was built to develop fast and efficient virtual screening procedures to screen anti-dosRS molecules. In the present study, we have used various structural and physiochemical attributes of compounds from HTS dataset to train and build a chemoinformatics predictive model based on four state-of-art supervised classifiers (Random forest, SMO, J48, and Naïve Bayes). The trained model was applied to test dataset for validating the robustness, accuracy, and sensitivity of the predictive model in screening active anti-dosRS molecules. The Cost-Sensitive Classifier (CSC) with Random Forest (RF) algorithm based predictive model showed a high sensitivity (100%) and specificity (83.13%) to identify active and inactive molecules, respectively from assay dataset (ID: 1159583). CSC-RF proved to more robust and efficient in classifying active molecule from an imbalanced dataset with highest Balancing Classification Rate (BCR) (91.57%) and maximum Area under the Curve (AUC) value (0.999).

Author 1: Syed Asif Hassan

Author 2: Tabrej Khan

Keywords: Mycobacterium; dosRS-transcriptional regulatory proteins; High Throughput Screening (HTS); virtual screening; machine learning algorithms; classification; predictive chemoinformatics model

Paper 16: A Machine Learning Model to Predict the Onset of Alzheimer Disease using Potential Cerebrospinal Fluid (CSF) Biomarkers

Abstract: Clinical studies in the past have shown that the pathology of Alzheimer’s disease (AD) initiates, 10 to 15 years before the visible clinical symptoms of cognitive impairment starts to appear in AD diagnosed patients. Therefore, early diagnosis of the AD using potential early stage cerebrospinal fluid (CSF) biomarkers will be valuable in designing a clinical trial and proper care of AD patients. Therefore, the goal of our study was to generate a classification model to predict earlier stages of the AD using specific early-stage CSF biomarkers obtained from a clinical Alzheimer dataset. The dataset was segmented into variable sizes and classification models based on three machine learning (ML) algorithms, such as Sequential Minimal Optimization (SMO), Naïve Bayes (NB), and J48 were generated. The efficacy of the models to accurately predict the cognitive impairment status was evaluated and compared using various model performance parameters available in Weka software tool. The current findings show that J48 based classification model can be effectively employed for classifying cognitive impaired Alzheimer patient from normal healthy individuals with an accuracy of 98.82%, area under curve (AUC) value of 0.992 and sensitivity & specificity of 99.19% and 97.87%, respectively. The sample size (60% training and 40% independent test data) showed significant improvement in T-test with J48 algorithm when compared with other classifiers tested on Alzheimer dataset.

Author 1: Syed Asif Hassan

Author 2: Tabrej Khan

Keywords: Alzheimer disease; early-stage biomarker; machine learning algorithm; classification model; accuracy; sensitivity

Paper 17: Performance vs. Power and Energy Consumption: Impact of Coding Style and Compiler

Abstract: Reaching a balance between performance and energy consumption has always been a difficult objective to achieve for energy and power-aware applications. The work presented in this paper investigates the impact of using different coding styles to achieve a balance between performance and energy efficiency. The research also studies how different compilers may affect not only the performance of the code but also the energy consumption. The research demonstrates and concludes the process of choosing the right combination of the coding style and compiler, the combination which works best with the nature of the application and the target hardware, is necessary if the balance between performance and energy is a software design goal. The study addresses some experimental aspects of the impact of coding style and choice of the compiler on energy and performance efficiency. It also shows how different coding practices for the same problem could produce different performance and energy consumption rates.

Author 1: Hesham H M Hassan

Author 2: Ahmed Shawky Moussa

Author 3: Ibrahim Farag

Keywords: Energy consumption; energy efficiency; power-aware; performance; coding styles; coding practice; compilers

Paper 18: Factors Influencing the Adoption of ICT by Teachers in Primary Schools in Saudi Arabia

Abstract: Information and communication technology (ICT) has become part of everyday life for the many people in business, entertainment, education and many other areas of human activity. Students in primary school are just beginning to learn and accept new ideas, show a maturing creativity, develop critical thinking and decision making skills. ICT enriches all these processes. In education, the successful integration of ICT into learning and teaching depends on teachers’ attitudes and their ability to use communication technologies, not just competently, but with skill and imagination. Experience is required with the medium, however, but ICT use in education has been largely ignored in Saudi Arabia. The study described here investigated the factors influencing the adoption of ICT as a teaching tool by teachers at Saudi Arabian primary schools. Analysis of the data showed computer literacy and confidence with technology registered a significant positive effect on the study, participants’ effort expectancy, which in turn positively influenced their behavioural intention to adopt ICT. On the other hand, Saudi culture, social conditions, system quality, and other obstacles discourage the uptake of ICT by primary school teachers. The findings of this study will assist the Saudi government to enhance the positive factors and eliminate or reduce the negative factors to ensure successful adoption of ICT in primary education by teachers.

Author 1: Sami Alshmrany

Author 2: Brett Wilkinson

Keywords: Information and communication technology (ICT); primary education; Saudi Arabia; computer literacy; behavioural influence

Paper 19: Low Power Low Jitter 0.18 CMOS Ring VCO Design with Strategy based on EKV3.0 Model

Abstract: In this paper, the design of micro-power CMOS ring VCO with minimum jitter intended for a concept of frequency synthesizer in biotelemetry systems is studied. A design procedure implemented in MATLAB is described for a circuit realization with TSMC 0.18µm CMOS technology. This conventional design methodology based on EKV3.0 model is clearly suited to the challenges of analog circuits design with reduced channel width. Measures realized with ADS confirmed methodology capability to circuit sizing respecting the specifications of application. The designed ring VCO operates at a central frequency of 433MHz in ISM band with an amplitude of oscillation equal to 500 mV. The integration area was intrinsic (without buffers and without external capacitances). The simulated phase noise is about -108 dBc/Hz at 1MHz, the value of rms jitter is 44.8 ps and the power consumption of the designed VCO is 6.37 mW @ 433 MHz.

Author 1: Amine AYED

Author 2: Hamadi GHARIANI

Keywords: Ring VCO; jitter; power consumption; EKV model; MATLAB

Paper 20: Bio-NER: Biomedical Named Entity Recognition using Rule-Based and Statistical Learners

Abstract: The purpose of extracting of Bio-Medical Entities is to recognize the particular entities, whether word or phrases, from the unstructured data contained in the text. This work proposes different approaches and methods, i.e. Machine Learning Hybrid Classification, Rule Based Non-tested Generalized Exemplars and Partial Decision Tree (PART) Learners for Bio-Medical Named Entity Recognition. The Prime objective is to consider, preferably, simple characteristics, such as, affixes and context. In addition, orthographic, Parts of Speech (POS) tags and N-grams are given secondary importance as for as their comparison with affixes and context is concerned. Further, for the very purpose of Bio-medical Diseased Named Recognition, proposal of Rule Based Classifiers along with the Statistical Machine Learning is given. Also, this paper proposes the blend of both preceding methods that jointly construct Hybrid Classification algorithm. Precision, Recall and F-measure – standard metrics- has been put into practice for the evaluation. The results prove that the technique used has far better performance results than the method used before - state-of-art Disease NER (Named Entity Recognition).

Author 1: Pir Dino Soomro

Author 2: Sanotsh Kumar

Author 3: Banbhrani

Author 4: Arsalan Ali Shaikh

Author 5: Hans Raj

Keywords: Bio-medical text mining; machine learning; named entity recognition; naive bayesian; rule-based classifier; information extraction

Paper 21: Distributed GPU-Based K-Means Algorithm for Data-Intensive Applications: Large-Sized Image Segmentation Case

Abstract: K-means is a compute-intensive iterative algorithm. Its use in a complex scenario is cumbersome, specifically in data-intensive applications. In order to accelerate the K-means running time for data-intensive application, such as large sized image segmentation, we use a distributed multi-agent system accelerated by GPUs. In this K-means version, the input image data are divided into subsets of image data which can be performed independently on GPUs. In each GPU, we offloaded the data assignment and the K-centroids recalculation steps of the K-means algorithm for a massively parallel processing. We have implemented this K-means version on the Nvidia GPU with Compute Unified Device Architecture. The distributed multi-agent system was written with Java Agent Development framework.

Author 1: Hicham Fakhi

Author 2: Omar Bouattane

Author 3: Mohamed Youssfi

Author 4: Hassan Ouajji

Keywords: Distributed computing; GPU computing; K-means; image segmentation

Paper 22: Chi-Square Automatic Interaction Detection Modeling for Predicting Depression in Multicultural Female Students

Abstract: This study developed a depression prediction model for female students from multicultural families by using a decision tree model based on Chi-squared automatic interaction detection (CHAID) algorithm. Subjects of the study were 9,024 female students between 12 and 15 years old among the children of surveyed marriage immigrants. Outcome variables were classified as presence of depression. Explanatory variables included sex, residing area, experience of career counseling, experience of social discrimination, experience of Korean language education, experience of using a multicultural family support center, Korean reading, Korean speaking, Korean writing, Korean listening, Korean society adjustment education experience, needs of Korean society adjustment education, needs of Korean language education, and rejoined entry. In the CHAID algorithm analysis, female students from multicultural families who experienced social discrimination within the past one year and had ordinary Korean speaking skill posed the highest risk of depression. It is necessary to pay social level interests to the mental health of adolescents from multicultural families for achieving successful social integration based on the results of this study.

Author 1: Haewon Byeon

Keywords: CHAID; data mining; multicultural family; risk factors; depression

Paper 23: Teaching Programming to Students in other Fields

Abstract: It is a fact that programming is difficult to learn. On the other hand, programming skills are essential for each program in the field of computing and must be covered in the curriculum, regardless of the profile. Our experience in the last 3-4 years shows a noticeable downward trend in students’ results in computer science and similar programs. In this article, we comment on the reasons that have led to such a decline and we are looking for solutions by experimenting with motivated students from other areas of knowledge and comparing their progress in mastering basic concepts and mechanisms of programming with that of computer specialists.

Author 1: Ivaylo Donchev

Author 2: Emilia Todorova

Keywords: Programming curricula; objects-first; teaching programming; object-oriented; education; programming; problem solving skills; politology

Paper 24: A Proposed Hybrid Effective Technique for Enhancing Classification Accuracy

Abstract: The automatic prediction and detection of breast cancer disease is an imperative, challenging problem in medical applications. In this paper, a proposed model to improve the accuracy of classification algorithms is presented. A new approach for designing effective pre-processing stage is introduced. Such approach integrates K-means clustering algorithm with fuzzy rough feature selection or correlation feature selection for data reduction. The attributes of the reduced clustered data are merged to form a new data set to be classified. Simulation results prove the enhancement of classification by using the proposed approach. Moreover, a new hybrid model for classification composed of K-means clustering algorithm, fuzzy rough feature selection and discernibility nearest neighbour is achieved. Compared to previous studies on the same data, it is proved that the presented model outperforms other classification models. The proposed model is tested on breast cancer dataset from UCI machine learning repository.

Author 1: Ibrahim M. El-Hasnony

Author 2: Hazem M. El-Bakry

Author 3: Omar H. Al-Tarawneh

Author 4: Mona Gamal

Keywords: Data mining; bioinformatics; fuzzy rough feature selection; correlation feature selection and data classification

Paper 25: A New Parallel Matrix Multiplication Algorithm on Tree-Hypercube Network using Iman1 Supercomputer

Abstract: The tree-hypercube (TH) interconnection network is relatively a new interconnection network, which is constructed from tree and hypercube topologies. TH is developed to support parallel algorithms for solving computation and communication intensive problems. In this paper, we propose a new parallel multiplication algorithm on TH network to present broadcast communication operation for TH using store-and-forward technique, namely, one-to-all broadcast operation which allows a message to be transmitted through the shortest path from the source node to all other nodes. The proposed algorithm is implemented and evaluated in terms of running time, efficiency and speedup with different data size using IMAN1. The experimental results show that the runtime, efficiency and the speedup of the proposed algorithm decrease as a number of processors increases for all cases of matrices size of 1000?1000, 2000?2000, and 4000?4000.

Author 1: Orieb AbuAlghanam

Author 2: Mohammad Qatawneh

Author 3: Hussein A. al Ofeishat

Author 4: Omar Adwan

Author 5: Ammar Huneiti

Keywords: MPI; supercomputer; tree-hypercube; matrix multiplication

Paper 26: Fuzzy Logic Energy Management Strategy of a Hybrid Renewable Energy System Feeding a Typical Tunisian House

Abstract: This paper proposes an energy management strategy for hybrid power system HPS which is composed of a photovoltaic generator, wind turbine, fuel cell generator and NaS battery storage device, feeding a type house. This strategy is based on Fuzzy Logic Control technique. The hybrid power system is sized to provide the energy demand of the inhabitants of the house and if there is an extra power generation, it would be sold to the grid. Using Simulink, we develop the different scenarios in order to use the fuel cell or battery during critical periods. The methodology developed was applied under the climatic conditions (wind speed, solar irradiation and temperature) measured at a site located in the northeast of Tunisia.

Author 1: Sameh ZENNED

Author 2: Houssem CHAOUALI

Author 3: Abdelkader MAMI

Keywords: Energy management strategy; hybrid power system; photovoltaic generator; wind turbine; fuel cell generator; nas battery; fuzzy logic control technique

Paper 27: Recommender System for Journal Articles using Opinion Mining and Semantics

Abstract: Till date, the dominant part of Recommender Systems (RS) work focusing on single domain, i.e. for films, books and shopping and so on. However, human inclinations may traverse over numerous areas. Thus, utilization practices on related things from various domains can be valuable for RS to make recommendations. Academic articles, such as research papers are the way to express ideas and thoughts for the research community. However, there have been a lot of journals available which recognize these technical writings. In addition, journal selection procedure should consider user experience about the journals in order to recommend users most relevant journal. In this work of journal recommendation system, the data about the user experience targeting various aspects of journals has been gathered which addresses user experience about any journal. In addition, data set of archive articles has been developed considering the user experience in this regard. Moreover, the user experience and gathered data of archives are analyzed using two different frameworks based on semantics in order to have better consolidated recommendations. Before submission, we offer services on behalf of the research community that exploit user reviews and relevant data to suggest suitable journal according to the needs of the author.

Author 1: Anam Sardar

Author 2: Javed Ferzund

Author 3: Muhammad Asif Suryani

Author 4: Muhammad Shoaib

Keywords: Recommendation system; journal recommendation system; user opinion; sementic similarity; text analysis

Paper 28: The Computation of Assimilation of Arabic Language Phonemes

Abstract: The computational phonology is fairly a new science that deals with studying phonological rules under the computation point of view. Computational phonology is based on the phonological rules, which are the processes that are applied to phonemes to produce another phoneme under specific phonetic environment. A type of these phonological processes is the assimilation process, which its rules reform the involved phonemes regarding the place of articulation, the manner of articulation, and/or voicing. Thus, assimilation is considered as a consequence of phonological coarticulation. Arabic, like other natural languages, has systematic phonemes’ changing rules. This paper aims to automate the assimilation rules of the Arabic language. Among several computational approaches that are used for automating phonological rules, this paper uses Artificial Neural Network (ANN) approach, and thus, contributes the using of ANN as a computational approach for automating the assimilation rules in the Arabic language. The designed ANN-based system of this paper has been defined and implemented by using MATLAB software, in which the results show the success of this approach and deliver an experience for later similar work.

Author 1: Ayad Tareq Imam

Author 2: Jehad Ahmad Alaraifi

Keywords: Computational phonology; phonological rules; assimilation; phonological coarticulation; artificial neural networks; MATLAB

Paper 29: Quantifying Integrity Impacts in Security Risk Scoring Models

Abstract: Organizations are attacked daily by criminal hackers. Managers need to know what kinds of cyber-attacks they are exposed to, for taking defense activities. Attackers may cause several kinds of damages according to the knowledge they have on organizations’ configuration and of systems’ vulnerabilities. One possible result of attacks is damaging the database. Estimations of attacks’ impacts on database integrity are not found in literature, besides intuitive managers’ assessments. The aim of this work is defining a quantitative measure, which takes into consideration the known vulnerabilities threatening on database integrity and proving its feasibility. In this work a quantitative integrity impact measure is defined, formulated, illustrated and evaluated. The proposed measure is based on the real database configuration. The superiority of the measure over current practices is illustrated.

Author 1: Eli Weintraub

Keywords: Security; cyber-attack; risk score; vulnerability; database integrity

Paper 30: Harmonics Measurement in Computer Laboratory and Design of Passive Harmonic Filter using MATLAB

Abstract: In this paper the harmonics measurement for computer loads is analyzed and passive filters are designed for mitigating those harmonics. The filters are designed to meet the IEEE standard 519-1992 which is recommended for harmonic current limits. Personal computers are non-linear loads that generate harmonics due to non-sinusoidal current present at entrance of power supply. In this work the personal computers in laboratory are taken as domestic load and harmonics generated by them cannot be ignored which are simulated using MATLAB/Simulink. The purpose is developing analytical method for the design of the passive harmonic filter that absorbs current harmonics caused by computer loads. The findings of this study would be supportive to make the source current free from harmonics thereby reducing the THD. Simulation results of proposed design method of passive filters shows attractive results for harmonic reduction with profit of upgrade of power factor. Design of passive harmonic filters by using non active power can be simple cost effective solution for systems.

Author 1: Muhammad Usman Keerio

Author 2: Muhammad Shahzad Bajwa

Author 3: Abdul Sattar Saand

Author 4: Munwar Ayaz memon

Keywords: Power Quality (PQ); personal computers; Total Harmonic Distortion (THD); passive filter; MATLAB/Simulink

Paper 31: Analysis of Energy Saving Approaches in Cloud Computing using Ant Colony and First Fit Algorithms

Abstract: Cloud computing is a style of technology that is increasingly used every day. It requires the use of an important amount of resources that is dynamically provided as a service. The growth of energy consumption associated to the process of resource allocation implemented in the cloud computing is an important issue that needs to be taken into consideration. Better performance will be acquired by allowing the same required workload to be performed using a lower number of servers, which could bring to important energy savings. So it is a requirement to adopt efficient techniques in order to save and minimize energy consumed clouds such as virtual machines migration. This paper analyzes two algorithms: First Fit and Ant Colony which address the use of virtual machine migration approaches to improve the cloud performance in terms of reducing the consumed energy.

Author 1: Alaa Ahmed

Author 2: Mostafa Ibrahim

Keywords: Cloud computing; VM migration; first fit; ant colony; energy savaging

Paper 32: TLM-2 Base Protocol Analysis for Model-Driven Design

Abstract: The system-on-chip design cost is not only dependent on implementation and manufacturing techniques, but also on the used methodologies and design tools. In recent years, transaction level modelling (TLM) and more specifically the SystemC TLM-2 library has become the standard in writing a system-level specification. Even though TLM-2 based models are more abstract than registry-level ones, they are very challenging to develop. They are often written manually and from scratch. In this paper, we expose a more elaborate and modular structure of transaction level models based on more predictable semantics. This work will be our first stone of the building of a model-driven design, a methodology that has proven itself in software engineering.

Author 1: Salaheddine Hamza Sfar

Author 2: Rached Tourki

Keywords: Electronic system level design; systemC; transaction level modelling; model-driven engineering

Paper 33: Multicast Routing with Load Balancing in Multi-Channel Multi-Radio Wireless Mesh Networks

Abstract: By an increasing expansion of multimedia services and group communication applications, the need for multicast routing to respond to multicast requests in wireless mesh networks is felt more than before. One of the main challenges in multi-channel multi-radio wireless mesh networks is the efficient use of the capacity of channels as well as load balance in network. In this paper, we proposed an algorithm for building a multicast tree, namely, Load balanced Multicast routing with Genetic Algorithm (LM-GA). The purpose of this algorithm is to construct a multicast tree for requested sessions in Multi-Radio Multi-Channel Wireless Mesh Networks (MCMR WMNs) regarding load balance in channels through minimizing the maximum amount of channels utilization. The results show the efficiency of LM-GA in distribution of load in the channels of the network with finding near-optimal solutions, and also an increase in the network performance while avoiding creation of bottlenecks.

Author 1: Atena Asami

Author 2: Majid Asadi Shahmirzadi

Author 3: Sam Jabbehdari

Keywords: Wireless mesh network; multi-radio; multi-channel; multicast routing; channels load balancing; genetic algorithm

Paper 34: Unsupervised Video Surveillance for Anomaly Detection of Street Traffic

Abstract: Intelligent transportation systems enables the analysis of large multidimensional street traffic data to detect pattern and anomaly, which otherwise is a difficult task. Advancement in computer vision makes great contribution in the progress of video based traffic surveillance system. But still there are some challenges which need to be solved like objects occlusion, behavior of objects. This paper developed a novel framework which explores multidimensional data of road traffic to analyze different patterns of traffic and anomaly detection. This framework is implemented on road traffic dataset collected from different areas of the city.

Author 1: Muhammad Umer Farooq

Author 2: Najeed Ahmed Khan

Author 3: Mir Shabbar Ali

Keywords: Kalman filter; Gaussian mixture model; DBSCAN clustering; similarity matrix; occlusion; computer vision; traffic surveillance; Intelligent Transport Systems (ITS)

Paper 35: Browser-Based DDoS Attacks without Javascript

Abstract: Recently, browser-based distributed denial of service (DDoS) attacks, in which a malicious JavaScript program is distributed through an advertisement network, and runs in the background of the web browser, were observed. In this paper, we address a question whether browser-based DDoS attacks can be realized without JavaScript. We construct new browser-based DDoS attacks based only on HTML functions, and compare them with the existing JavaScript-based DDoS attacks in efficiency.

Author 1: Ryo Kamikubo

Author 2: Taiichi Saito

Keywords: Browser; denial of service (DoS); distributed denial of service (DDoS); attacks; HTML; JavaScript; botnets; networks

Paper 36: A Method for Analyzing and Designing Microservice Holistically

Abstract: Microservice is a new architecture that is getting attention in the development of service systems. However, microservice is still at the early stage and the acceptance of this architecture is overwhelming. Microservice architecture is a promising architecture in delivering loosely coupled, decentralized, and scalable system that utilizes the latest technology, such as container and cloud computing. However, the traditional method for analyzing and designing system will not be able to fully utilize the capability of the microservice architecture. Therefore, a new method for analyzing and designing the microservice holistically is being proposed in this paper. The Design Science Research methodology has been adopted in designing the proposed method. The artifact, which is the result of the research, is the proposed method. The proposed method has shown its potential in being used to analyze and design the microservice holistically and to benefit from the microservice architecture capabilities.

Author 1: Ahmad Tarmizi Abdul Ghani

Author 2: Mohd. Shanudin Zakaria

Keywords: Microservice; service design; promise theory; viable system model; Viplan method

Paper 37: Capacitated Vehicle Routing Problem Solving using Adaptive Sweep and Velocity Tentative PSO

Abstract: Vehicle Routing Problem (VRP) has become an integral part in logistic operations which determines optimal routes for several vehicles to serve customers. The basic version of VRP is Capacitated VRP (CVRP) which considers equal capacities for all vehicles. The objective of CVRP is to minimize the total traveling distance of all vehicles to serve all the customers. Various methods are used to solve CVRP, among them the most popular way is splitting the task into two different phases: assigning customers under different vehicles and then finding optimal route of each vehicle. Sweep clustering algorithm is well studied for clustering nodes. On the other hand, route optimization is simply a traveling salesman problem (TSP) and a number of TSP optimization methods are applied for this purpose. In Sweep, cluster formation staring angle is identified as an element of CVRP performance. In this study, a heuristic approach is developed to identify appropriate starting angle in Sweep clustering. The proposed heuristic approach considers angle difference of consecutive nodes and distance between the nodes as well as distances from the depot. On the other hand, velocity tentative particle swarm optimization (VTPSO), the most recent TSP method, is considered for route optimization. Finally, proposed adaptive Sweep (i.e., Sweep with proposed heuristic) plus VTPSO is tested on a large number of benchmark CVRP problems and is revealed as an effective CVRP solving method while outcomes compared with other prominent methods.

Author 1: M. A. H. Akhand

Author 2: Zahrul Jannat Peya

Author 3: Kazuyuki Murase

Keywords: Capacitated vehicle routing problem; Sweep clustering and velocity tentative particle swarm optimization

Paper 38: Comparative Analysis of ANN Techniques for Predicting Channel Frequencies in Cognitive Radio

Abstract: Demand of larger bandwidth increases the spectrum scarcity problem. By using the concepts of Cognitive radio we can achieve an efficient spectrum utilization. The cognitive radio allows the unlicensed user to share the licensed user band. To sense the accessibility of vacant channel and allocation of licensed user band is provided by Machine learning techniques because this decision need to be very fast and accurate. It is based on certain factors (such as Power, Bandwidth, antenna parameters, etc.). In this paper, we used neural network to propose this decision of resource allocation more accurately by providing bandwidth, power, antenna gain, azimuth, angle of elevation and location as a supplements factors to increase the predicting accuracy of Available channel frequencies for secondary user in particular bands. The comparative analysis is done between artificial neural network techniques to determine the maximum decision accuracy in order to design a suitable neural network structure and the system to make fast prediction for available channels. The dataset is divided in to cellular 850 MHZ and Advanced wireless service 1900/2100 MHZ bands. In both bands, Feed Forward networks performs better as compared to Elman and Radial basis network for predicting the best available channel to accommodate the secondary user. It will considerably increase overall QoS and decrease interference, hence making Cognitive radio system reliable.

Author 1: Imran Khan

Author 2: Shaukat Wasi

Author 3: Adnan Waqar

Author 4: Saima Khadim

Keywords: Cognitive radio; machine learning; artificial neural network; frequencies band; feed forward neural network; Elman; Radial basis

Paper 39: Motivators and Demotivators of Agile Software Development: Elicitation and Analysis

Abstract: Motivators and demotivators are key factors in software productivity. Both are also critical to the success of Agile software development. Literature reports very diverse and multidimensional critical factors affecting the quality of Agile software development, thus, there is a need to extract and map required factors systematically for wider implications. The classification of anticipated factors and sub-factors is also desired to simplify their identification and definition. The reported research focuses on the systematic mapping of motivators and demotivators in Agile software development. A systematic mapping literature study has been performed to shed light on scattered critical factors for software engineers, affecting productivity and understanding of Agile viewpoints. Additionally, this study categorizes the extracted motivators as organization, people and technical. Whereas, the sub-factors’ categorization has been concentrated, which contributes to the motivators at grass root level. This research alleviates the problems of identification, definition and classification of the critical factors in agile software development for both practitioners and researchers.

Author 1: Shahbaz Ahmed Khan Ghayyur

Author 2: Salman Ahmed

Author 3: Adnan Naseem

Author 4: Abdul Razzaq

Keywords: Agile methodology; systematic mapping; motivators; demotivators; Agile teams; Agile software development

Paper 40: D-MFCLMin: A New Algorithm for Extracting Frequent Conceptual Links from Social Networks

Abstract: Massive amounts of data in social networks have made researchers look for ways to display a summary of the information provided and extract knowledge from them. One of the new approaches to describe knowledge of the social network is through a concise structure called conceptual view. In order to build this view, it is first needed to extract conceptual links from the intended network. However, extracting these links for large scale networks is very time consuming. In this paper, a new algorithm for extracting frequent conceptual link from social networks is provided where by introducing the concept of dependency, it is tried to accelerate the process of extracting conceptual links. Although the proposed algorithm will be able to accelerate this process if there are dependencies between data, but the tests carried out on Pokec social network, which lacks dependency between its data, revealed that absence of dependency, increases execution time of extracting conceptual links only up to 15 percent.

Author 1: Hamid Tabatabaee

Keywords: Social network analysis; frequent conceptual link; data mining; graph mining

Paper 41: Iterative Learning Control for Trajectory Tracking of Single-link Flexible Arm

Abstract: This paper focuses on the issue of tracking the trajectory of a flexible arm. The purpose is to ensure the flexible arm follows the desired path in the joint space. To achieve our objective, we have three problems to solve: modeling, control, and trajectory planning. As in the case of rigid robots, the Euler-Lagrange formulation remains valid with the exception of dividing the flexible arm into a finite number of elements to model the deformation. The iterative learning control scheme can be used to achieve perfect tracking throughout the movement period, a sufficient condition based on the bounded real lemma that guarantees the convergence error between iteration is given. All the results are presented in terms of linear matrix inequalities synthesis (LMIs).

Author 1: Marouen Mejerbi

Author 2: Sameh Zribi

Author 3: Jilani Knani

Keywords: Single-link flexible arm; finite element; trajectory tracking; iterative learning control; linear matrix inequality; bounded real lemma

Paper 42: Biometrics Recognition based on Image Local Features Ordinal Encoding

Abstract: In the present informational era, with the continue extension of embedded computing systems, the demand of faster and robust image descriptors is an important issue. However, image representation and recognition is an open problem. The aim of the paper is to embrace ordinal measurements for image analysis and to apply the concept for a real problem, such as biometric identification. Biometrics provides a robust solution for the identity management process and is increasingly more present in our life. To explore the textural discriminative information of images, the paper proposes a new feature extraction technique, namely, Image Local Features Ordinal Encoding.

Author 1: Simina Emerich

Author 2: Bogdan Belean

Keywords: Biometrics; image local features; ordinal measurements; iris; dorsal hand veins

Paper 43: Creation and Usability Evaluating of E-Learning Contents for Automobile Repair Block Painting

Abstract: Due to the fact that paintwork in the automobile repair industry requires individual correspondence, work by human hands is indispensable. Although the skills of expert engineers have a great influence on the finish, learning these skills require a lot of experience and time. In Japan, the number of young people in the automobile mechanic and automobile repair industry is drastically decreasing due to the declining birthrates, the trend of young people turning away from driving cars, and the diversification of occupation options. Moreover, the aging of the mechanics and repair technicians has been progressing, and the average age of the mechanics and repair technicians remaining in this industry has been increasing every year. In the near future, there is a high possibility that the shortage of human resources supporting this industry will become apparent. In this study, we aimed to construct a self-study support system for young engineers engaged in automobile repair painting to support skill acquisition, using e-learning teaching materials utilizing motion analysis data on block painting by solid paint done by experienced engineers. Furthermore, the usability of the teaching materials was clarified from the viewers’ characteristics obtained by publishing the teaching materials. The e-learning teaching materials which secured a certain number of repeaters had a possibility to be effective teaching material. At the same time, several tasks such as the shortening of playback time of the teaching material time were also highlighted.

Author 1: Shigeru Ikemoto

Author 2: Yuka Takai

Author 3: Hiroyuki Hamada

Author 4: Noriaki Kuwahara

Keywords: Automobile repair; block painting; expert; e-learning; usability

Paper 44: The Use of a Simplex Method with an Artificial basis in Modeling of Flour Mixtures for Bakery Products

Abstract: Modeling of flour mixtures for bakery products of increased biological value is done. The problem is solved by a simplex method with an artificial basis related to numerical optimization methods for solving linear programming problems. A mathematical model of the composition of a polycomponent flour mixture has been constructed. The model is taking into account the minimal amount of essential amino acids. An automated scientific research system for modeling the composition of flour mixtures with specified functional characteristics was developed and implemented. The composition of flour mixes for bakery products has been optimized according to the target values of the amino acid score and biological value. Application of the developed software package allows creating prescription compounds for rye-wheat bread with a 6.12-17.66% higher biological value than traditional bakery products.

Author 1: Natalia A. Berezina

Author 2: Andrey V. Artemov

Author 3: Igor A. Nikitin

Author 4: Igor V. Zavalishin

Author 5: Andrey N. Ryazanov

Keywords: Modeling; simplex method; polycomponent flour mixture; bakery products; biological value; quality

Paper 45: A Cascaded H-Bridge Multilevel Inverter with SOC Battery Balancing

Abstract: In this paper, we present a single phase 5 levels H-Bridge multilevel inverter (CHMLI) with battery balancing technique. Each single full bridge is directly connected to a battery inside the power bank. The different combinations and batteries wiring sets offer the possibility to control the batteries discharge. The cascaded H-Bridge multilevel inverter is first described and the discharge is studied in normal conditions under different stress scenarios. State of charge (SOC) balancing technique is then achieved using an equalization algorithm controlling the different switching combination inside the power bank. Results of the simulation model with and without the SOC balancing is presented using Matlab.

Author 1: Khalili Tajeddine

Author 2: Raihani Abdelhadi

Author 3: Bouattane Omar

Author 4: Ouajji Hassan

Keywords: Cascaded H-Bridge; multilevel inverter; battery discharge; SOC balancing

Paper 46: Relevance of Energy Efficiency Gain in Massive MIMO Wireless Network

Abstract: The massive MIMO and energy efficiency (EE) analysis for the next generation technology are the hottest topics in wireless network research. This paper explains about massive MIMO wireless networks and EE for manifold channel which is an evolution massive MIMO. This research will help to design and implement a practical system of next generation network based on massive MIMO where efficient processing provides EE gain. In order to approach this research, different types of manifolds are considered with efficient techniques that depend on the rank of the channel matrix. Employing the specific manifold that helps to analyze the rate of the feedback increases not only the overall performance of the MIMO system but also the EE. We studied the convergence techniques used for optimizing quantization errors which have influences with manifold feedback. Here, we have focused on relevant areas which are very important to analyze EE gain in the future massive network. According to the selected results obtained in this research, many challenges will be possible to make useful proposals.

Author 1: Ahmed Alzahrani

Author 2: Vijey Thayananthan

Author 3: Muhammad Shuaib Qureshi

Keywords: Massive MIMO; manifolds; EE gain; feedback; convergence; quantization

Paper 47: A Smartwatch Centric Social Networking Application for Alzheimer People

Abstract: In recent years, people are increasingly interacting with an overwhelming of devices especially wearable devices. These later have initiated new ways in human connections with the world. The basic concept of these devices is that they can be worn instead of being carried. They have pervasive and unobtrusive presence. Furthermore, they can be used for helping people with serious medical conditions, like the Alzheimer people. In this context, an application that allows Alzheimer relatives to locate and track the patient by connecting the application with GPS smartwatch that is worn by the patient is proposed. A safety area is predefined by the relative in order to be notified once the patient gets beyond this area. When there is no connection with the GPS watch for any reason and the patient cannot be tracked, the relatives can send a broadcast message to all application users who wish to help and participate in such social and humanitarian work.

Author 1: Henda Chorfi Ouertani

Author 2: Ahlam Al-Mutairi

Author 3: Fatimah Al-Shehri

Author 4: GhadahAl-Hammad

Author 5: Maram Al-Suhaibani

Author 6: Munira Al-Holaibah

Author 7: Nouf Al-Saleh

Keywords: Smartwatch; Alzheimer; broadcast; tracking; social application

Paper 48: Text Summarization of Multi-Aspect Comments in Social Networks in Persian Language

Abstract: Now-a-days, there are increasingly huge amount of user generated comments on the web. The user generated comments usually contains useful and essential information reflecting public’s or customers’ opinions. Since the information in the comments could be used for decision making, production or service improvement, and achieving user satisfaction, the systematic analysis of these comments is an essential need in so many domains including e-commerce, production, and social network analysis. However, the analysis of large volume of comments is a difficult and time-consuming task. Therefore, the need for a system which can convert this massive volume of comments to a useful and efficient summary is felt more and more. Text summarization leads to using more resources at higher speeds and getting richer information. According to numerous studies conducted in the field of multi-document summarization, few studies can be found that have been focused on the user generated comments in Persian language. In this paper, we propose a novel approach to summarize huge amount of comments in Persian, which is enough close to a human summarization. Our approach is based on semantic and lexical similarities and uses a graph-based summarization. We also propose a clustering to deal with multiple aspects (subjects) in a corpus of comments. According to the experiments, the summaries extracted by the proposed approach reached an average score of 8.75 out of 10, which improves the state-of-the-art summarizer’s score about 14 percent.

Author 1: Hossein Shahverdian

Author 2: Hassan Saneifar

Keywords: Text mining; comments analysis; summarization; graph summarization; Persian language

Paper 49: A Decision Support System for Early-Stage Diabetic Retinopathy Lesions

Abstract: Retina is a network layer containing light-sensitive cells. Diseases that occur in this layer, which performs the eye-sight, threaten our eye-sight directly. Diabetic Retinopathy is one of the main complications of diabetes mellitus and it is the most significant factor contributing to blindness in the later stages of the disease. Therefore, early diagnosis is of great importance to prevent the progress of this disease. For this purpose, in this study, an application based on image processing techniques and machine learning, which provides decision support to specialist, was developed for the detection of hard exudates, cotton spots, hemorrhage and microaneurysm lesions which appear in the early stages of the disease. The meaningful information was extracted from a set of samples obtained from the DIARETDB1 dataset during the system modeling process. In this process, Gabor and Discrete Fourier Transform attributes were utilized and dimension reduction was performed by using Spectral Regression Discriminant Analysis algorithm. Then, Random Forest and Logistic Regression and classifier algorithms’ performances were evaluated on each attribute dataset. Experimental results were obtained using the retinal fundus images provided from both DIARETDB1 dataset and the department of Ophthalmology, Ataturk Training and Research Hospital in Ankara.

Author 1: Kemal AKYOL

Author 2: Safak BAYIR

Author 3: Baha SEN

Keywords: Early stage diabetic retinopathy lesions; feature extraction; important features; image recognition; classification; decision support system; computer aided analysis

Paper 50: Examining the Impact of Feature Selection Methods on Text Classification

Abstract: Feature selection that aims to determine and select the distinctive terms representing a best document is one of the most important steps of classification. With the feature selection, dimension of document vectors are reduced and consequently duration of the process is shortened. In this study, feature selection methods were studied in terms of dimension reduction rates, classification success rates, and dimension reduction-classification success relation. As classifiers, kNN (k-Nearest Neighbors) and SVM (Support Vector Machines) were used. 5 standard (Odds Ratio-OR, Mutual Information-MI, Information Gain-IG, Chi-Square-CHI and Document Frequency-DF), 2 combined (Union of Feature Selections-UFS and Correlation of Union of Feature Selections-CUFS) and 1 new (Sum of Term Frequency-STF) feature selection methods were tested. The application was performed by selecting 100 to 1000 terms (with an increment of 100 terms) from each class. It was seen that kNN produces much better results than SVM. STF was found out to be the most successful feature selection considering the average values in both datasets. It was also found out that CUFS, a combined model, is the one that reduces the dimension the most, accordingly, it was seen that CUFS classify the documents more successfully with less terms and in short period compared to many of the standard methods.

Author 1: Mehmet Fatih KARACA

Author 2: Safak BAYIR

Keywords: Feature selection; text classification; text mining; k-Nearest Neighbors; support vector machines

Paper 51: Integration of Wearable Smart Sensor for Improving e-Healthcare

Abstract: Analyzing health conditions using sensors is one of the daily activities in a healthcare organization. The purpose of this research is to improve the e-healthcare formulated through the integration of wearable smart sensors and miniaturized devices. In this research, monitoring glucose level of the diabetic is considered as an example of the non-linear problem in which we show that accuracy and efficiency of e-healthcare can be achieved through Multiple-input, multiple-output (MIMO) system. In this novel technique, Pn-manifolds, which are the non-linear mathematical approach, provide the flexible rate and enhance the accuracy and efficiency of the medical systems in the e-healthcare services.

Author 1: Vijey Thayananthan

Author 2: Abdullah Basuhail

Keywords: Smart sensors; miniaturized devices; e-healthcare applications; MIMO; manifolds

Paper 52: Fish Image Segmentation Algorithm (FISA) for Improving the Performance of Image Retrieval System

Abstract: The image features (local, global) pay vital role in image retrieval system. The effectiveness of these image features depends on the application domain, i.e., in some domains the global features generate better results while in others the local features give good results. Different species of fishes have different color, texture, and shape features in their body parts (head, abdomen, and tail). Previously most of the work, in fish image domain has been done using global features. This work claims that fish image retrieval system using local features can generate better results as compared to global features. This is because of the fact that fish image has different features in its body parts. In this research, a fish image segmentation algorithm is proposed to extract fish object from its background and then separate fish object into three distinguished body parts, i.e. head, abdomen, and tail. The proposed algorithm was tested on a subset of “QUT_fish_data” data set containing 369 fishes of various sizes of 30 species. The experimental results showed an accuracy of 87.5% on fish image segmentation and demonstrated the effectiveness of local features over global features.

Author 1: Amanullah Baloch

Author 2: Mushstaq Ali

Author 3: Faqir Gul

Author 4: Sadia Basir

Author 5: Ibrar Afzal

Keywords: Fish body parts segmentation; local and global features; object extraction; image retrieval system; image features

Paper 53: Recent Approaches to Enhance the Efficiency of Ultra-Wide Band MAC Protocols

Abstract: Ultra-wide band (UWB) is a promising radio technology to transmit huge data in short distances between different digital devices or between individual components of a personal computer. Due to the magnificent features of UWB technology, it finds vast research and application interests, such as Wireless Personal Area Networks (WPANs), Wireless Sensor Networks (WSNs), Wireless Body Area Networks (WBANs) as a special case of WSNs, and Wireless Area Networks (WLANs) as well. In this article, we study the assumptions and performance metrics related to recent schemes of Medium Access Control (MAC) Protocols employed in UWB applications that aim to improve its performance. Also, we compare the different approaches used in the recent works based on 10 parameters: application domain, cast type, protocol centralization, number of hops, mobility, number of used channels, uniformity, priority, and analytical approach. Finally, we introduce different approaches to improve UWB applications.

Author 1: Mohamed Ali Ahmed

Author 2: H. M. Bahig

Author 3: Hassan Al-Mahdi

Keywords: Ultra-wide band (UWB); Wireless Personal Area Network (WPAN); Wireless Sensor Network (WSN); Wireless Body Area Network (WBAN); Medium Access Control (MAC); performance metrics

Paper 54: Web Unique Method (WUM): An Open Source Blackbox Scanner for Detecting Web Vulnerabilities

Abstract: The internet has provided a vast range of benefits to society, and empowering people in a variety of ways. Due to incredible growth of Internet usage in past 2 decades, everyday a number of new Web applications are also becoming a part of World Wide Web. The distributed and open nature of internet attracts hackers to interrupt the smooth services of web applications. Some of the famous web application vulnerabilities are SQL Injection, Cross Site Scripting (XSS) and Cross Site request Forgery (CSRF). We believe that in order to encounter these vulnerabilities; the web application vulnerabilities scanner should have strong detection and prevention rules to ease the problem. At present, a number of web application vulnerabilities scanners have been proposed by research community, such as ZED Attack Proxy (ZAP) by AWASP, Wapiti by sourceforge.net and w3af by w3af.org. However, these scanners cannot challenge all web vulnerabilities. This research proposed and develop a vulnerability scanning tool WUM (web unique method) to detection and prevention of all the major instance vulnerabilities and demonstrates how to detect unauthorized access by finding vulnerabilities. With the efficient use of this tool, the developers are able to find potentially vulnerable web application. WUM generated a high level of accuracy and compatibility, which is elaborated underneath. The result of the experiment shows proposed vulnerability scanner tool WUM which gives less false positive and detect more vulnerabilities in comparison of well-known black box scanners.

Author 1: Muhammad Noman khalid

Author 2: Muhammad Iqbal

Author 3: Muhammad Talha Alam

Author 4: Vishal Jain

Author 5: Hira Mirza

Author 6: Kamran Rasheed

Keywords: Automated vulnerability detection; black-box scanners; web vulnerabilities crawling; security scanner

Paper 55: Comparative Performance Analysis for Generalized Additive and Generalized Linear Modeling in Epidemiology

Abstract: Most environmental-epidemiological researches emphasize modeling as the causal link of different events (e.g., hospital admission, death, disease emergency). There has been a particular concern in the use of the Generalized Linear Models (GLMs) in the field of epidemiology. However, recent studies in this field highlighted the use of non-parametric techniques, especially the Generalized Additive Models (GAMs). The aim of this work is to compare performance of both methods in the field of epidemiology. Comparison is done in terms of sharpening the relation between the predictors and the response variable as well as in predicting outbreaks. The most suitable method is then adopted to elucidate the impact of bioclimatic factors on the emergence of the zoonotic cutaneous leishmaniasis (ZCL) disease in Central Tunisia. Monthly epidemiologic and bioclimatic data from July 2009 to June 2016 are used in this study. Akaike information criterion, R-squared and F-statistic are used to compare model performance, while the root mean square error is used for checking predictive accuracy for both models. Our results show the potential of GAM model to provide a better assessment of the nonlinear relations and to give a high predictive accuracy compared to GLMs. The results also stress the inaccurate estimation of risk factors when linear trends are used to model nonlinear structured data.

Author 1: Talmoudi Khouloud

Author 2: Bellali Hedia

Author 3: Ben-Alaya Nissaf

Author 4: Saez Marc

Author 5: Malouche Dhafer

Author 6: Chahed Mohamed Kouni

Keywords: Generalized linear model; generalized additive model; zoonotic cutaneous leishmaniasis; Central Tunisia

Paper 56: A Firefly Algorithm for the Mono-Processors Hybrid Flow Shop Problem

Abstract: Nature-inspired swarm metaheuristics become one of the most powerful methods for optimization. In discrete optimization, the efficiency of an algorithm depends on how it is adapted to the problem. This paper aims to provide a discretization of the Firefly Algorithm (FF) for the scheduling of a specific manufacturing system, which is the mono processors two-stage hybrid flow shop (HFS). This kind of manufacturing system appears in several fields as the operating theatre scheduling problem. Results of proposed discrete firefly algorithm are compared to results of other methods found in the literature. Computational results with different numbers of fireflies and on a standard HFS benchmark of about 55 cases, generating about 1900 instances demonstrates that the proposed discretized metaheuristic reaches the best makespan.

Author 1: Latifa DEKHICI

Author 2: Khaled BELKADI

Keywords: Firefly algorithm; hybrid flow shop; metaheuristics; discrete optimization

Paper 57: Cross-Lingual Sentiment Classification from English to Arabic using Machine Translation

Abstract: Cross-lingual sentiment learning is becoming increasingly important due to the multilingual nature of user-generated content on social media and the scarce resources for languages other than English. However, cross-lingual sentiment learning is a challenging task due to the different distribution between translated data and original data and due to the language gap, i.e. each language has its own ways to express sentiments. This work explores the adaptation of English resources for sentiment analysis to a new language, Arabic. The aim is to design a light model for cross-lingual sentiment classification from English to Arabic, without any manual annotation effort which, at the same time, is easy to build and does not require deep linguistic analysis. The ultimate goal is to find an optimal baseline model and to determine the relation between the noise in the translated data and the accuracy of sentiment classification. Different configurations of several factors are investigated including feature representation, feature reduction methods, and the learning algorithms to find the optimal baseline model. Experiments show that a good classification model can be obtained from translated data regardless of the artificial noise added by machine translation. The results also show a significant cost to automation, and thus the best path to future enhancement is through the inclusion of language-specific knowledge and resources.

Author 1: Adel Al-Shabi

Author 2: Aisah Adel

Author 3: Nazlia Omar

Author 4: Tareq Al-Moslmi

Keywords: Cross-lingual sentiment classification; English to Arabic; machine translation

Paper 58: An Improved Homomorphic Encryption for Secure Cloud Data Storage

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

Author 1: Mohd Rahul

Author 2: Hesham A. Alhumyani

Author 3: Mohd Muntjir

Author 4: Minakshi Kambojl

Keywords: Clouds; cloud computing; issues; security; homomorphic encryption; RSA; EIGamal; Paillier

Paper 59: Multivariate Statistical Analysis on Anomaly P2P Botnets Detection

Abstract: Botnets population is rapidly growing and they become a huge threat on the Internet. Botnets has been declared as Advanced Malware (AM) and Advanced Persistent Threat (APT) listed attacks which is able to manipulate advanced technology where the intricacy of threats need for continuous detection and protection. These attacks will be almost exclusive for financial gain. P2P botnets act as bots that use P2P technology to accomplish certain tasks. The evolution of P2P technology had generated P2P botnets to become more resilient and robust than centralized botnets. This poses a big challenge on detection and defences. In order to detect these botnets, a complete flow analysis is necessary. In this paper, we proposed anomaly detection through chi-square multivariate statistical analysis which currently focuses on time duration and time slot. This particular time is considered to identify the existence of botserver. We foiled both of host level and network level to make coordination within a P2P botnets and the malicious behaviour each bot exhibits for making detection decisions. The statistical approach result show a high detection accuracy and low false positive that make it as one of the promising approach to reveal botserver.

Author 1: Raihana Syahirah Binti Abdullah

Author 2: Faizal M. A.

Author 3: Zul Azri Muhamad Noh

Keywords: P2P botnets; anomaly-based; chi-square; multivariate; statistical-based

Paper 60: Image noise Detection and Removal based on Enhanced GridLOF Algorithm

Abstract: Image noise removal is a major task in image processing where noise can harness any information inferred from the image especially when the noise level is high. Although there exists many outlier detection approaches used for this task, more enhancements are needed to achieve better performance specifically in terms of time. This paper proposes a new algorithm to detect and remove noise from images depending on an enhanced version of GridLOF algorithm. The enhancement aims to reduce the time and complexity of the algorithm while attaining comparable accuracy. Simulation results on a set of different images proved that proposed algorithm achieves the standard accuracy.

Author 1: Ahmed M. Elmogy

Author 2: Eslam Mahmoud

Author 3: Fahd A. Turki

Keywords: Outlier detection; image noise removal; LOF; GridLOF

Paper 61: An Optimized Salahaddin University New Campus IP-Network Design using OPNET

Abstract: Salahaddin University is the oldest and the biggest university in Kurdistan region. It involves 14 colleges and 3 academic centers. The new university campus that will be established on an area of 10km2 provides a challenge of designing, efficient and robust networking infrastructure due to increased demand on data and data processing applications like FTP (File Transfer Protocol) which is a vital protocol in an academic environment. At access layer (college level) Wireless Local Area Network (WLAN) is employed to provide Wi-Fi to the end user for ultimate mobility. At backbone level four scenarios have been proposed and tested for a proposed university campus. These scenarios used to connect each college Wi-Fi router to Cisco core switch (6509). The first scenario uses optical fiber cable 1000Base-LX (Gigabit- Ethernet), while in the second scenario the Virtual Local Area Network (VLAN) based core switch is used to connect (Gigabit- Ethernet) cables. The third scenario uses FDDI (Fiber Distributed Data Interface) technology. In the fourth scenario, a combination of the VLAN based core switch and FDDI is presented. In the four scenarios, the core switch is connected to the main router Cisco (7507) which connects the campus network to the cloud. The network performance and behavior have been studied by calculating network load throughput and delay. The system has been implemented using OPNET (Optimized Network Engineering Tool) simulator modular 14.5. The simulation results show that the fourth scenario gives minimum delay while maximum data transfer (throughput) is achieved by the fourth scenario.

Author 1: Ammar. O. Hasan

Author 2: Raghad Z.Yousif

Author 3: Rakan S.Rashid

Keywords: Fiber Distributed Data Interface (FDDI); Optimized Network Engineering Tool (OPNET); File Transfer Protocol (FTP); Virtual Local Area Networks (VLAN); campus network

Paper 62: Rating Prediction with Topic Gradient Descent Method for Matrix Factorization in Recommendation

Abstract: In many online review sites or social media, the users are encouraged to assign a numeric rating and write a textual review as feedback to each product that they have bought. Based on users’ history of feedbacks, recommender systems predict how they assesses the unpurchased products to further discover the ones that they may like and buy in future. A traditional approach to predict the unknown ratings is matrix factorization, while it uses only the history of ratings included in the feedbacks. In recent researches, its ignorance of textual reviews is pointed out to be the drawback that brings mediocre performance. In order to solve such issue, we propose a method of rating prediction which uses both the ratings and reviews, including a new first-order gradient method for matrix factorization, named Topic Gradient Descent (TGD). The proposed method firstly derives the latent topics from the reviews via Latent Dirichlet Allocation. Each of the topics is characterized by a probability distribution of words and is assigned to correspond to a latent factor. Secondly, to predict the ratings of the users, it uses matrix factorizaiton which is trained by the proposed TGD method. In the training process, the updating step of each latent factor is dynamically assigned depending on the stochastic proportion of its corresponding topic in the review. In evaluation, we both use YELP challenge dataset and per-category Amazon review datasets. The experimental results show that the proposed method certainly converges the squared error of the prediction, and improves the performance of traditional matrix factorization up to 12.23%.

Author 1: Guan-Shen Fang

Author 2: Sayaka Kamei

Author 3: Satoshi Fujita

Keywords: Gradient descent; matrix factorization; Latent Dirichlet Allocation; information recommendation

Paper 63: Enhanced K-mean Using Evolutionary Algorithms for Melanoma Detection and Segmentation in Skin Images

Abstract: Nowadays, Melanoma has become one of the most significant public health concerns. Malignant Melanoma (MM) is considered the most rapidly spreading type of skin cancer. In this paper, we have built models for detection, segmentation, and classification of Melanoma in skin images using evolutionary algorithms. The first step was to enhance the K-mean algorithm by using two kinds of Evolutionary Algorithms: a Genetic Algorithm and the Particle Swarm Algorithm. Then the Enhanced Algorithms and the default k-mean separately were used to do detection and segmentation of skin cancer images. Then a feature extraction step was applied on the segmented images. Finally, the classification step was done by using two predictive models. The first model was built using a Neural Network backpropagation and the other one using some threshold values for some selected features. The results showed a high accuracy using Neural Back-propagation for the Enhanced K-mean by using a Genetic Algorithm, which achieved 87.5%.

Author 1: Asmaa Aljawawdeh

Author 2: Esraa Imraiziq

Author 3: Ayat Aljawawdeh

Keywords: Melanoma; genetic algorithm; K-mean; particle swarm optimization; classification; segmentation

Paper 64: Survey and Classification of Methods for Building a Semantic Annotation

Abstract: Though Arabic is one of the five most spoken languages, little work has been done on building Arabic semantic resources. Currently, there is no agreed-upon method for building such a reliable Arabic semantic resource. The purpose of this paper is to present a comprehensive survey of different methods for building or enriching Arabic semantic resources; to study and analyze each method; and to categorize the methods according to their properties. This work should contribute to the definition of new methods and help researchers on Arabic semantics to fit their work in the panel of existing ones.

Author 1: Georges Lebbos

Author 2: Abd El Salam Al Hajjar

Author 3: Gilles Bernard

Author 4: Mohammad Hajjar

Keywords: Lexical semantics; WordNet; Arabic WordNet; Arabic corpus; synset; Arabic semantic resources; translation-based methods; ontologies

Paper 65: SAFFRON: A Semi-Automated Framework for Software Requirements Prioritization

Abstract: Due to dynamic nature of current software development methods, changes in requirements are embraced and given proper consideration. However, this triggers the rank reversal problem which involves re-prioritizing requirements based on stakeholders’ feedback. It incurs significant cost because of time elapsed in large number of human interactions. To solve this issue, a Semi-Automated Framework for soFtware Requirements priOritizatioN (SAFFRON) is presented in this paper. For a particular requirement, SAFFRON predicts appropriate stakeholders’ ratings to reduce human interactions. Initially, item-item collaborative filtering is utilized to estimate similarity between new and previously elicited requirements. Using this similarity, stakeholders who are most likely to rate requirements are determined. Afterwards, collaborative filtering based on latent factor model is used to predict ratings of those stakeholders. The proposed approach is implemented and tested on RALIC dataset. The results illustrate consistent correlation, similar to state of the art approaches, with the ground truth. In addition, SAFFRON requires 13.5-27% less human interaction for reprioritizing requirements.

Author 1: Syed Ali Asif

Author 2: Zarif Masud

Author 3: Rubaida Easmin

Author 4: Alim Ul Gias

Keywords: Requirement prioritization; rank reversal problem; model-based collaborative filtering

Paper 66: An Approach for External Preference Mapping Improvement by Denoising Consumer Rating Data

Abstract: In this study, denoising data was advocated in sensory analysis field to remove the existing noise in consumer rating data before processing to External Preference Mapping (EPM). This technique is a data visualization used to understand consumers sensory profiles by relating their preferences towards products to external information about sensory characteristics of the perceived products. The output is a perceptual map which visualizes the optimal products and aspects that maximize consumers likings. Hence, EPM is considered as a decision tool to support the development or improvement of products and respond to market requirements. In fact, the stability of the map is affected by the high variability of judgments that make consumer rating data very noisy. This may lead to mismatch between products features and consumers’ preferences then distorted results and wrong decisions. To remove the existing noise, the use of some filtering methods is proposed. Regularized Principal Component Analysis (RPCA) and Stein’s Unbiased Risk Estimate (SURE), based respectively on hard and soft thresholding rules, were applied to consumer rating data to separate the signal to noise and maintain only useful information about the given liking scores. As a way to compare the EPM obtained from each strategy, a sampling process was conducted to randomly select samples from noisy and cleaned data, then perform their corresponding EPM. The stability of the obtained maps was evaluated using an indicator that computes and compares distances between them before and after denoising. The effectiveness of this methodology was evaluated by a simulation study and a potential application was shown on real dataset. Results show that recorded distances after denoising are lower than those before in almost cases for both RPCA and SURE. However, RPCA outperforms SURE. The corresponding map is made more stable where level lines are seen smoothed and products are better located on liking zones. Hence, noise removal reduces variability in data and brings closer preferences which improves the quality of the visualized map.

Author 1: Ibtihel Rebhi

Author 2: Dhafer Malouche

Keywords: Data denoising; Regularized Principal Component Analysis; Stein’s Unbiased Risk Estimate; sensory analysis; external preference mapping stability

Paper 67: Web Usability and User Trust on E-commerce Websites in Pakistan

Abstract: Web usability is an integral part of e-commerce. Users are less prone to the websites which are difficult to navigate and slow in response time. E-commerce business is growing aggressively on daily basis, but lack of user trust can impede this growth. Success of online business is largely dependent on getting user’s trust. There are different techniques and models to measure web usability and user trust level, but they are not covering all aspects of web usability. So we proposed a new enhanced SUPR-Q model with six (6) parameters, such as Usability, Effectiveness, Efficiency, Learnability, Satisfaction and Security. We performed an experiment with one hundred twenty (120) participants to measure the web usability and user’s trust on two famous e-commerce websites of Pakistan (daraz.pk & homeshopping.pk). We divided our participants into two equal groups, such as Random and Regular group on the basis of their previous shopping exposure. Our results shows that usability score of Regular group who did shopping most frequently were better than the Random group which was less exposed with shopping experience. Regular group was more satisfied from both websites with the score of 46.8% on daraz.pk and 44.8% on homshopping.pk as compared to Random group. Both groups showed higher usability score on daraz.pk which was 45.2% in case of Regular group and 40% in case of Random group due to the higher effectiveness and efficiency of web interface. The overall results showed that trust on e-commerce website plays vital role in user’s satisfaction and purchasing.

Author 1: Rohail Shehzad

Author 2: Zulqurnan Aslam

Author 3: Nadeem Ahmad

Author 4: Muhammad Waseem Iqbal

Keywords: Web usability; e-commerce; user trust; Pakistan; random; regular

Paper 68: Performance Evaluation of SIFT and Convolutional Neural Network for Image Retrieval

Abstract: Convolutional Neural Network (NN) has gained a lot of attention of the researchers due to its high accuracy in classification and feature learning. In this paper, we evaluated the performance of CNN used as feature for image retrieval with the gold standard feature, aka SIFT. Experiments are conducted on famous Oxford 5k data-set. The mAP of SIFT and CNN is 0.6279 and 0.5284, respectively. The performance of CNN is also compared with bag of visual word (BoVW) model. CNN achieves better accuracy than BoVW.

Author 1: Varsha Devi Sachdeva

Author 2: Junaid Baber

Author 3: Maheen Bakhtyar

Author 4: Ihsan Ullah

Author 5: Waheed Noor

Author 6: Abdul Basit

Keywords: Computer vision; SIFT; CNN; image retrieval; precision; recall

Paper 69: MulWiFi: Flexible Policy Enforcement in Multi-Radio High-Speed WiFi Networks

Abstract: As data rates in 802.11 Wireless LANs (WLANs) scale to Gbps, it becomes increasingly challenging for a single radio resource to meet the goals of high MAC efficiency, service differentiation, and adaptability to diverse network scenarios. We present MulWiFi, a system that uses a cen-tralized controller to manage multiple off-the-shelf radios in a single device for addressing challenges in high-speed WLANs. MulWiFi allows flexible policy enforcement based on ap-plication requirements and channel state information at each radio. MulWiFi offers the ability to (a) customize the MAC based on application requirements and network scenarios, (b) assign different roles to radios, (c) improve MAC throughput efficiency at high data rates, and (d) combine fragmented channels. We demonstrate the early promise of MulWiFi through three case studies and discuss future opportunities and challenges.

Author 1: Kamran Nishat

Author 2: Zartash Afzal Uzmi

Author 3: Ihsan Ayyub Qazi

Keywords: WLAN; IEEE 802.11; QoS; multi-radio; experimental analysis; testbed