IJACSA Vol. 10 Issue 5 (2019)

1

Analyzing Personality Traits and External Factors for Stem Education Awareness using Machine Learning

Author 1: Sang C Suh Author 2: Anusha Upadhyaya B.N Author 3: Ashwin Nadig N.V

The purpose of the paper is to present the personality traits and the factors that influence a student to pursue STEM education using machine learning techniques. STEM courses have high regard because they play a vital role in global technology, inventions and the economy. Educational Data Mining helps us to identify patterns and relationships in a large educational database. On the other hand, Machine Learning facilitates decision making process by enabling learning from the dataset. A survey comprising of an extensive variety of questions regarding STEM education was conducted and the opinions of students from various backgrounds and disciplines were collected. A dataset was generated based on the responses from students. Machine Learning algorithms (one class-SVM and KNN) applied on this dataset emphasizes variety of courses offered, research-oriented learning, problem-solving approach, a good career with high paying job are some of the factors which may influence a student to choose STEM course.

Educational Data Mining (EDM) Science Technology Engineering Management (STEM) Machine Learning (ML) K-Nearest Neighbor (KNN) One class–Support Vector Machine (one class - SVM)

Abstract doi.org/10.14569/IJACSA.2019.0100501 PDF

2

High-Speed FPGA-based of the Particle Swarm Optimization using HLS Tool

Author 1: Ali Al Bataineh Author 2: Amin Jarrah Author 3: Devinder Kaur

The Particle Swarm Optimization (PSO) is a heuristic search method inspired by different biological populations on their swarming or collaborative behavior. This novel work has implemented PSO for the Travelling Salesman Problem (TSP) in high-level synthesis to reduce the computational time latency. The high-level synthesis design generates an estimation of the hardware resources needed to implement the PSO algorithm for TSP on FPGA. The targeted FPGA of this algorithm is the Xilinx Zynq family. The algorithm has been implemented for getting the best route between 5 given cities with given distances. The research has used 7 number of particles for a different number of iterations for generating the best route between those 5 cities. The overall latency has been reduced due to the applied optimization techniques. This paper also implemented and parallelized the same algorithm on CPU Intel I7 Processor; the result shows the FPGA implementation gives better results than CPU on the comparison of performance.

FPGA High Level Synthesis Particle Swarm Optimization Travelling Salesman Problem (TSP)

Abstract doi.org/10.14569/IJACSA.2019.0100502 PDF

3

Exploring Factors Associated with Voucher Program for Speech Language Therapy for the Preschoolers of Parents with Communication Disorder using Weighted Random Forests

Author 1: Haewon Byeon Author 2: Sulki Cha Author 3: KyoungYuel Lim

It is necessary to identify the demand level of consumers and recognize the support target priority based on it in order to provide efficient services with a limited budget. This study provided baseline data for spreading the use of consumer-oriented voucher service by exploring factors associated with the demand of the Voucher Program for Speech Language Therapy for preschool children. This study were analyzed 212 guardians living with children (≤5 years old) who resided in Seoul from Aug 11 to Oct 9, 2015. The outcome variable was defined as the demand (i.e., required and not required) of the Voucher Program for Speech Language Therapy. The results of the developed prediction model were compared with the results of a decision tree based on classification and regression tree (CART). The prediction performance of the developed model was evaluated using a confusion matrix. Among the 212 subjects, 112 (52.8%) responded that the Voucher Program for Speech Language Therapy was necessary. The weighted random forest-based model predicted five variables (i.e., whether preschooler caregiving services were used or not, economic activity after childbirth, the awareness of Seoul’s welfare counselor operation, mean monthly living expenses, and whether welfare related information was obtained) as the variables associated with the demand of the Voucher Program for Speech Language Therapy and the accuracy was 72.1%. It is needed to develop systematic policies to expand consumer-oriented language therapy services based on the developed prediction model for the Voucher Program for Speech Language Therapy.

Weighted random forests CART speech language therapy prediction model voucher program

Abstract doi.org/10.14569/IJACSA.2019.0100503 PDF

4

ZigBee Radio Frequency (RF) Performance on Raspberry Pi 3 for Internet of Things (IoT) based Blood Pressure Sensors Monitoring

Author 1: Puput Dani Prasetyo Adi Author 2: Akio Kitagawa

Wireless Sensor Network has grown rapidly, e.g. using the Zigbee RF module and combined with the Raspberry Pi 3, a reason at this research is building a Wireless Sensor Network (WSN). this research discusses how sensor nodes work well and how Quality of Service (QoS) from the Sensor node being analyzed and the role of Raspberry Pi 3 as an internet gateway will sending a blood pressure data to the database and displayed in real-time on the internet, from this research it is expected that patients can check the blood pressure from home and don’t need to the Hospital even data can be quickly and accurately received by Hospital Officers, doctors, and medical personnel. the purpose of this research is make a prototype to providing a blood pressure (mmHg) real-time data from systolic and diastolic data patient’s that determine patients suffering from symptoms of certain diseases, i.e, anemia, symptoms of hypertension and even more chronic diseases. this research discusses how sensor nodes work well and how Quality of Service (QoS) from the Sensor node being analyzed and the role of Raspberry Pi 3 as an internet gateway will sending a blood pressure data to the database and displayed in real-time on the internet. Furthermore, Zigbee has the task of sending Blood pressure (mmHg) data in real-time to the database and then sent to the internet from Zigbee end-device communication to ZigBee coordinator. Zigbee communication at a distance of 5 meters, RSSI simulations show a value of -29 dBm and the experiment shows a value of -40 dBm, at a distance of 100 m, RSSI shows a value of -55 dBm (simulation) and -86 dBm (experiment).

Zigbee Raspberry Pi 3 IoT blood pressure

Abstract doi.org/10.14569/IJACSA.2019.0100504 PDF

5

Storage Consumption Reduction using Improved Inverted Indexing for Similarity Search on LINGO Profiles

Author 1: Muhammad Jaziem bin Javeed Author 2: Nurul Hashimah Ahamed Hassain Malim

Millions of compounds which exist in huge datasets are represented using Simplified Molecular-Input Line- Entry System (SMILES) representation. Fragmenting SMILES strings into overlapping substrings of a defined size called LINGO Profiles avoids the otherwise time-consuming conversion process. One drawback of this process is the generation of numerous identical LINGO Profiles. Introduced by Kristensen et al, the inverted indexing approach represents a modification intended to deal with the large number of molecules residing in the database. Implementing this technique effectively reduced the storage space requirement of the dataset by half, while also achieving significant speedup and a favourable accuracy value when performing similarity searching. This report presents an in-depth analysis of results, with conclusions about the effectiveness of the working prototype for this study.

Simplified Molecular-Input Line-Entry System (SMILES) LINGO profiles similarity searching inverted indexing

Abstract doi.org/10.14569/IJACSA.2019.0100505 PDF

6

A Framework for Iris Partial Recognition based on Legendre Wavelet Filter

Author 1: Muktar Danlami Author 2: Sapiee Jamel Author 3: Sofia Najwa Ramli Author 4: Mustafa Mat Deris

An increasing need for biometrics recognition system has grown substantially to address the issues of recognition and identification especially in highly dense areas such as airport, train stations and for financial transaction. Evidences of these can be seen in some airports and also the implementation of these technologies in our mobile phones. Among the most popular biometric technologies include facial, fingerprints and iris recognition. The iris recognition is considered by many researchers to be the most accurate and reliable form of biometric recognition, because iris can neither be surgically operated with a chance of losing slight nor change due to ageing. However, presently most iris recognition system available can only recognize iris image with frontal-looking and high-quality images. Angular image and partially capture image cannot be authenticated with existing method of iris recognition. This research investigates the possibility of developing a framework for recognition partially captured iris image. The research also adopts the Legendre wavelet filter for the iris feature extraction. Selected iris images from CASIA, UBIRIS and MMU database were used to test the accuracy of the introduced framework. A threshold for the minimum iris image required was established.

Iris recognition partial recognition wavelet Legendre wavelet filter biometric

Abstract doi.org/10.14569/IJACSA.2019.0100506 PDF

7

The Implementation of Software Anti-Ageing Model towards Green and Sustainable Products

Author 1: Zuriani Hayati Abdullah Author 2: Jamaiah Yahaya Author 3: Siti Rohana Ahmad Ibrahim Author 4: Sazrol Fadzli Author 5: Aziz Deraman

Software ageing is a phenomenon that normally occurs in a long running software. Progressive degradation of software performance is a symptom that shows software is getting aged and old. Researchers believe that the ageing phenomenon can be delayed by applying anti-ageing techniques towards the software or also known as software rejuvenation. Software ageing factors are classified into two categories: internal and external factors. This study focuses on external factors of software ageing, and are categorized into three main factors: environment, human and functional. These three factors were derived from empirical study that been conducted involving fifty software practitioners in Malaysia. The anti-ageing model (SEANA model) is proposed to support in preventing the software from prematurely aged, thus prolong its usage and sustainable in their environment. SEANA model is implemented in collaboration with a government agency in Malaysia to verify and validate the model in real environment. The prototype of SEANA model was developed and applied in the real case study. Furthermore, the anti-ageing guideline and actions are suggested for ageing factors to delay the ageing phenomenon in application software and further support the greenness and sustainability of software products.

Software ageing factor ageing prevention software anti-ageing model SEANA model SeRIS Prototype System Green And Sustainable Product Emprirical Study

Abstract doi.org/10.14569/IJACSA.2019.0100507 PDF

8

Understanding Customer Voice of Project Portfolio Management Software

Author 1: Maruthi Rohit Ayyagari Author 2: Issa Atoum

Project Portfolio Management (PPM) has gained success in many projects due to its large number of features that covers effective scheduling, risk management, collaboration, and third-party software integrations to mention a few. A broad range of PPM software is available; however, it is essential to select the PPM with minimum usage issues over time. While many companies use surveys and market research to get users feedback, the PPM product software reviews carry the voice of users; the positive and negative sentiments of the PPM software reviews. This paper collected 4,775 reviews of ten PPM software from Capttera.com. Our approach has these phases- text preprocessing, sentiment analysis, summarization, and categorizations. The software reviews are filtered and cleaned, then negative sentiments of user reviews are summarized into a set of factors that identify issues of adopted PPM software. We report the most important issues of PPM software which were related to missing technological features and lack of training. Results using Latent Dirichlet Allocation (LDA) model showed that the top ten common issues are related to software complexity and lack of required features.

Project Portfolio Management (PPM) software reviews sentiment analytics text summarization LDA

Abstract doi.org/10.14569/IJACSA.2019.0100508 PDF

9

Analysis of the Emotions’ Brainwaves

Author 1: Witman Alvarado-Díaz Author 2: Brian Meneses-Claudio Author 3: Avid Roman-Gonzalez

Currently in Peru, patients with degenerative diseases, such as Amyotrophic Lateral Sclerosis (ALS) have lost of communication ability. Many researchers’ papers that establish basic communication system for these patients. It is also essential to know their feelings or state of mind through their emotions, in this study, we present an analysis of electroencephalographic signals (EEG) applied to emotions such as fear, tenderness, happiness and surprised; it was used linear discriminant analysis (LDA) to get the identification and classification of the 4 emotions with a success rate of 63.36% on average.

Electroencephalogram EEG emotions amyotrophic lateral sclerosis degenerative diseases classification learner

Abstract doi.org/10.14569/IJACSA.2019.0100509 PDF

10

Multi-Agent Architecture of Intelligent and Distributed Platform of Governance, Risk and Compliance of Information Systems

Author 1: Soukaina Elhasnaoui Author 2: Saadia Drissi Author 3: Hajar Iguer Author 4: Hicham Medromi

Governance, risk management and compliance of information technologies (IT GRC) is the responsibility of the company’s executives. The IT GRC responds to the important concerns of information systems managers, to ensure the necessary changes in the Information System (IS) over time, and enable it to meet the needs of risk mitigation, regulatory compliance, value creation and strategic alignment. Like a large number of organizations' activities, the IT GRC has to find a solution that is equipped through IS applications. Although these tools do exist, they are never developed by considering the IT GRC processes as a whole. We respond to this lack of consideration by proposing an intelligent and distributed platform of risk, governance and compliance of information systems that deploys a variety of IT GRC best practices and frameworks and makes an intelligent choice under constraints and parameters of the best framework to evaluate the objectives and processes in question. EAS-COM (communication system dedicated to the IT GRC platform) is our second proposal in this work: it ensures end-to-end communication between the different layers of the proposed IT GRC platform. This approach is based on Multi-Agent System (MAS) intelligence to manage the interactions between the distributed systems of the IT GRC platform.

IT Governance risk and compliance information system multi agent systems

Abstract doi.org/10.14569/IJACSA.2019.0100510 PDF

11

Comparison of Accuracy between Convolutional Neural Networks and Naïve Bayes Classifiers in Sentiment Analysis on Twitter

Author 1: P.O. Abas Sunarya Author 2: Rina Refianti Author 3: Achmad Benny Mutiara Author 4: Wiranti Octaviani

The needs and demands of the community for the ease of accessing information encourage the increasing use of social media tools such as Twitter to share, deliver and search for information needed. The number of large tweets shared by Twitter users every second, making the collection of tweets can be processed into useful information using sentiment analysis. The need for a large number of tweets to produce information encourages the need for a classifier model that can perform the analysis process quickly and provide accurate results. One algorithm that is currently popular and is widely used today to build classifier models is Deep Learning. Sentiment analysis in this research was conducted on English-language tweets on the topic "Turkey Crisis 2018" by using one of the Deep Learning algorithms, Convolutional Neural Network (CNN). The resulting of CNN classifier model will then be compared with the Naïve Bayes Classifier (NBC) classifier model to find out which classifier model can provide better accuracy in sentiment analysis. The research methods that will be carried out in this research are data retrieval, pre-processing, model design and training, model testing and visualization. The results obtained from this research indicate that the CNN classifier model produces an accuracy of 0.88 or 88% while the NBC classifier model produces an accuracy of 0.78 or 78% in the testing phase of the data test. Based on these results it can be concluded that the classifier model with Deep Learning algorithm produces better accuracy in sentiment analysis compared to the Naïve Bayes classifier model.

Sentiment-analysis convolutional neural network deep learning Naïve Bayes classifier

Abstract doi.org/10.14569/IJACSA.2019.0100511 PDF

12

Digital Legacy: Posterity Rights Analysis and Proposed Model for Digital Memorabilia Adoption using Machine Learning

Author 1: Amit Sudan Author 2: Dr. Munish Sabharwal

The paper informs about the digital legacy and its related concepts of posterity rights and digital memorabilia. It also deals with the right to exercise the digital posterity concerning the social networking profiles (SNP) on social networking sites (SNS). Digital Memorabilia is the compendium of people’s social profiles and the digital artifacts accumulated in the name of people in online or virtual world, it can give people an online space to connect to and be remembered online even after their demise, showing the many dimensions of their real world personality. The paper proposes a model using multiple logistic regression technique of machine learning to predict the users that will opt for a digital memorial dependent upon different factors such as age, frequency of using SNPs, awareness about digital assets and digital legacy, awareness about privacy rights concerning digital assets and awareness about rights to posterity.

Digital assets digital legacy digital posterity digital executers digital memorabilia SNP (Social Networking Profiles) SNS (Social Networking Sites)

Abstract doi.org/10.14569/IJACSA.2019.0100512 PDF

13

Smart Sustainable Agriculture (SSA) Solution Underpinned by Internet of Things (IoT) and Artificial Intelligence (AI)

Author 1: Eissa Alreshidi

The Internet of Things (IoT) and Artificial Intelligence (AI) have been employed in agriculture over a long period of time, alongside other advanced computing technologies. However, increased attention is currently being paid to the use of such smart technologies. Agriculture has provided an important source of food for human beings over many thousands of years, including the development of appropriate farming methods for different types of crops. The emergence of new advanced IoT technologies has the potential to monitor the agricultural environment to ensure high-quality products. However, there remains a lack of research and development in relation to Smart Sustainable Agriculture (SSA), accompanied by complex obstacles arising from the fragmentation of agricultural processes, i.e. the control and operation of IoT/AI machines; data sharing and management; interoperability; and large amounts of data analysis and storage. This study firstly, explores existing IoT/AI technologies adopted for SSA and secondly, identifies IoT/AI technical architecture capable of underpinning the development of SSA platforms. As well as contributing to the current body of knowledge, this research reviews research and development within SSA and provides an IoT/AI architecture to establish a Smart, Sustainable Agriculture platform as a solution.

Smart Agriculture Internet of Things IoT Artificial Intelligence AI Fragmentation Smart Sustainable Agriculture solutions

Abstract doi.org/10.14569/IJACSA.2019.0100513 PDF

14

Reconstruction of Fingerprint Shape using Fractal Interpolation

Author 1: Abdullah Bajahzar Author 2: Hichem Guedri

One of the severe problems in a fingerprint-based system is retaining the fingerprint images. In this paper, we propose a method to minimize the fingerprint images size and retain the reference points. The method is divided into three parts, the first part is about digital image preprocessing that allows us to eliminate the noise, improve the image, convert it into a binary image, detect the skeleton and locate the reference point. The second part concerns the detection of critical points by the Douglas-Peucker method. The final part presents the methodology for the fingerprint curves reconstruction using the fractal interpolation curves. The experimental result shows the accuracy of this reconstruction method. The relative error (ER) is between 2.007% and 5.627% and the mean squared error (MSE) is between 0.126 and 0.009 at a small iterations number. On the other hand, for a greater number of iterations, the ER is between 0.415% and 1.64% and MSE is between 0.000124 and 0.0167. This clearly indicates that the interpolated curves and the original curves are virtually identical and exceedingly close.

Fingerprint images enhancement thresholding process thinning algorithms minutiae extraction Douglas-Peucker algorithm fractal interpolation iterated function system (IFS)

Abstract doi.org/10.14569/IJACSA.2019.0100514 PDF

15

Analytical and Comparative Study of Different Types of Two-Leg Chopping Up Regulator

Author 1: Walid Emar Author 2: Omar A. Saraereh

The main focus of this article is to analyze and simulate the two-leg parallel connection of a chopping up regulator with flattering inductive smoothers or with an interphasing centre-tap transformer supplied by a three-phase diode rectifier and a DC link in between. The article deals with the problem of reducing total harmonic distortion, minimizing THD and EMI with low switching frequency. The Simulated three phase a.c. load model is added at the end to investigate the current and voltage harmonics. The main objective of this paper is the investigation of the problem and active impact of replacing flattering inductive smoothers used to reduce voltcurrent fluctuating waveforms of the chopping up regulator by new topology known as interphasing centre-tap transformer with magnetic coupling. The comparison of these two variations of the study is then done based on their technical parameters and economical investment viewpoint. The considered technical parameters are to be current distribution into individual legs, amount of voltcurrent ripple and area of discontinuous currents. The investment costs governed by the material requirements are essential for transformer and smoother production design. The outcome of using the interphasing centre-tap transformer is successive cancelation of voltcurrent fluctuating waveforms generated at the output of the chopping up regulator. This is proved by an experiment with 35 in input and power chopping up400-V/90-A.Software simulations in Simplorer and Matlab/Simulink or software program and regimen prototypes have been arranged to confirm the results.

Chopping up regulator with a flattering inductive smoother magnetic coupling connection with interphasing centre-tap transformer

Abstract doi.org/10.14569/IJACSA.2019.0100515 PDF

16

CWNN-Net: A New Convolution Wavelet Neural Network for Gender Classification using Palm Print

Author 1: Elaraby A Elgallad Author 2: Wael Ouarda Author 3: Adel M. Alimi

The human hand is one of the body parts with special characteristics that are unique to every individual. The distinctive features can give some information about an individual, thus, making it a suitable body part that can be relied upon for biometric identification and, specifically, gender recognition. Several studies have suggested that the hand has unique traits that help in gender classification. Human hands form part of soft biometrics as they have distinctive features that can give information about a person. Nevertheless, the information retrieved from the soft biometrics can be used to identify an individual’s gender. Furthermore, the soft biometrics can be combined with the main biometrics characteristics that can improve the quality of biometric detection. Gender classification using hand features, such as palm contributes significantly to the biometric identification domain and, hence, presents itself as a valuable research topic. This study explores the use of Discrete Wavelet Transform (DWT) in gender identification, with SqueezeNet acting as a tool for unsheathing features, and Support Vector Machine (SVM) operating as discriminative classifier. Inference is made using mode voting approach. Notably, the two datasets that were crucial for the fulfillment of the study were the 11k database and CASIA. The outcome of the tests substantiated the use of voting technique for gender recognition.

Deep learning feature extraction gender voting

Abstract doi.org/10.14569/IJACSA.2019.0100516 PDF

17

The Method of Computer-Aided Design of a Bread Composition with Regard to Biomedical Requirements

Author 1: Natalia A Berezina Author 2: Andrey V. Artemov Author 3: Igor A. Nikitin Author 4: Alexander A. Budnik

A method for efficient software implementation of bread optimized multicomponent mixtures has been developed. These polycomposite mixtures have a chemical composition that meets the modern physiological standards of nutrition for the elderly people. To implement the developed algorithm a high-level programming language Object Pascal was used using the IDE Borland Delphi 7.0. An unconventional raw material was selected, which allows to provide necessary requirements to the quality indicators of the finished bread in all modeled mixtures. Modeling the composition of flour mixtures for gerodietic nutrition using the software made it possible to obtain compositions with a specific ratio of prescripted components, balanced in accordance with the intended purpose.

Modeling polycomposite mixture bread gerodietic nutrition quality

Abstract doi.org/10.14569/IJACSA.2019.0100517 PDF

18

Quality of Service and Power Consumption Optimization on the IEEE 802.15.4 Pulse Sensor Node based on Internet of Things

Author 1: Puput Dani Prasetyo Adi Author 2: Akio Kitagawa

The Purpose of this research is to determine the Quality of Service (QoS) Zigbee or IEEE 802.15.4 sensor Node use the indicators, i.e. the Receiver Signal Strength and PathLoss (attenuation (-dB)) at the time of communication of the sensor node end device to the sensor Router node or Coordinator sensor node (sink). The factor power consumption sensor node is important to maintain the lifetime sensor node, The Sensor data in this research is the pulse sensor. The development of the Wireless Sensor Network communication system is in multi-hop communication, with efforts to obtain low power consumption on each sensor node. This study utilizes the Routing Protocol for Low Power and Lossy Network (RPL) method with position management on the sensor node on DODAGs consequently, that the average power consumption value for each sensor node is low. The benefit of the Sensor node is to send pulse sensor data from various nodes that are interconnected at different distances in multi-hop so that power consumption and Quality of Services (QoS) can be identified from the sensor node. From the research results, the average PathLoss value of IEEE 802.15.4 or Zigbee in free space is obtained by comparing the various simulation values and field experiments at a distance of 50 m at -75.4 dB and the Average Receiver Signal Strength (RSS) with a comparison of Equation and Experiments in the field with parameters The minimum Power Transmitter is 0 dBm and the Power Transmitter is maximum +20 dBm at a distance of 50m at - 66.6 dBm. Therefore, Pulse Sensor data will be displayed on the Web Page and stored in the MySQL database using Raspberry PI 3 as the Internet Gateway.

RPL RSS Pathloss Zigbee Pulse DODAGs IoT

Abstract doi.org/10.14569/IJACSA.2019.0100518 PDF

19

Segmentation of Touching Arabic Characters in Handwritten Documents by Overlapping Set Theory and Contour Tracing

Author 1: Inam Ullah Author 2: Mohd Sanusi Azmi Author 3: Mohamad Ishak Desa Author 4: Yazan M. Alomari

Segmentation of handwritten words into characters is one of the challenging problem in the field of OCR. In presence of touching characters, make this problem more difficult and challenging. There are many obstacles/challenges in segmentation of touching Arabic handwritten text. Although researches are busy in solving the problem of segmentation of these touching characters but still there exist unsolved problems of segmentation of touching offline Arabic handwritten characters. This is due to large variety of characters and their shapes. So in this research, a new method for segmentation of touching Arabic Handwritten character has been developed. The main idea of the proposed method is to segment the touching characters by identifying the touching point by overlapping set theory and ending points of the Arabic word by applying some standard morphology operation methods. After identifying all the points, segmentation method is applied to trace the boundaries of characters to separate these touching characters. Experiments were conducted on touching characters taken from different data sets. The results show the accuracy of the proposed method.

Offline handwritten characters touching characters segmentation overlapping set theory morphological operation

Abstract doi.org/10.14569/IJACSA.2019.0100519 PDF

20

Pedestrian Safety with Eye-Contact between Autonomous Car and Pedestrian

Author 1: Kohei Arai Author 2: Akihito Yamashita Author 3: Hiroshi Okumura

Method for eye-contact between autonomous car and pedestrian is proposed for pedestrian safety. The method allows to detect the pedestrian who would like to across a street through eye-contact between an autonomous driving car and the pedestrian. Through experiment, it is found that the proposed method does work well for finding such pedestrians and for noticing a sign to the pedestrians from the autonomous driving car with a comprehensive representation of face image displayed onto front glass of the car.

Autonomous driving car eye-contact self driving car pedestrian safety Yolo OpenCV GazeRecorder

Abstract doi.org/10.14569/IJACSA.2019.0100520 PDF

21

Tennis Player Training Support System based on Sport Vision

Author 1: Kohei Arai Author 2: Toshiki Nishimura Author 3: Hiroshi Okumura

Sports vision based tennis player training support system is proposed. In sports, gaze, dynamic visual acuity, eye movement and viewing place are important. In sports vision, Static eyesight, Dynamic visual acuity, Contrast sensitivity, Eye movement, Deep vision, Instant vision, Cooperative action of eye, hand and foot, and Peripheral field are have to be treated. In particular for the tennis, all of the items are very important. Furthermore, trajectory of gaze location and tennis racket stroke gives some instructions for skill-up of tennis play. Therefore, sports vision based tennis player training system is proposed. Through experiment, it is found that the proposed system does work well for improvement of tennis players’ skills.

Sport vision static eyesight dynamic visual acuity contrast sensitivity eye movement deep vision instant vision cooperative action of eye hand and foot peripheral field

Abstract doi.org/10.14569/IJACSA.2019.0100521 PDF

22

A Low Power Consuming Model of Parallel Programming for HPC System

Author 1: Mohammed Nawaf Altouri Author 2: Abdullah M. Algarni

For most of the past five decades, the growing computational power of supercomputers has come primarily from a doubling of clock frequency every 18 months. Over this time period, the clock rate increased by six orders of magnitude, while the number of processors increased by three orders of magnitude. The major challenge caused by the increasing scale and complexity of HPC systems is the massive power consumption. Due to constraints on heat and the power requirements of today's microprocessors, vendors have shifted to putting multiple processors (cores) on a chip. The number of cores per chip is expected to continue increasing exponentially over the next decade. One expected strategy is the correct usage of parallel programming models that decrease power consumption and increase system performance through massive parallelism (concurrency). In the current study, we have proposed a Hybrid MVAPICH-2 + CUDA (HMC) parallel programming model that outperformed other state-of-the-art dual and tri hierarchy level approaches with respect to power consumption and execution time. Moreover, the HMC model was evaluated by implementing the matrix multiplication benchmarking application. Consequently, it can be considered a leading model for the emerging Exascale computing system.

HPC parallel computation power consumption hybrid programming MVAPIC2 CUDA

Abstract doi.org/10.14569/IJACSA.2019.0100522 PDF

23

Effective Framework of Pedagogy

Author 1: Tallat Naz Author 2: Momeen Khan Author 3: Khalid Mahmood

Learning paths drive learners to proficiency by using a selected sequence of training activities under time constraints. Therefore, learners can regulate learning and give feedback for pedagogy improvements. Studying learning path evaluation provides a useful conceptual reference to enhance pedagogically. This paper proposes an approach based on the Plan-Do-Check-Act improvement cycle to systematically evaluate learning paths in learning management systems. The framework is a valuable resource that consolidates existing practices in learning management evaluation. Our approach integrates learning styles, learning profile, along with cognitive activities. The proposed framework was compared with current learning path methods. Results were competitive compared with related works.

Learning management system learning styles learning path Plan-Do-Check-Act (PDCA)

Abstract doi.org/10.14569/IJACSA.2019.0100523 PDF

24

Comparative Performance Analysis of RPL for Low Power and Lossy Networks based on Different Objective Functions

Author 1: Mah Zaib Jamil Author 2: Danista Khan Author 3: Adeel Saleem Author 4: Kashif Mehmood Author 5: Atif Iqbal

The Internet of Things (IoT) is an extensive network between people-people, people-things and things-things. With the overgrown opportunities, then it also comes with a lot of challenges proportional to the number of connected things to the network. The IPv6 allows us to connect a huge number of things. For resource-constrained IoT devices, the routing issues are very thought-provoking and for this purpose an IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) is proposed. There are multi-HOP paths connecting nodes to the root node. Destination Oriented Directed Acyclic Graph (DODAG) is created taking into account different parameters such as link costs, nodes attribute and objective functions. RPL is flexible and it can be tuned as per application demands, therefore, the network can be optimized by using different objective functions. This paper presents a novel energy efficient analysis of RPL by performing a set of simulations in COOJA simulator. The performance evaluation of RPL is compared by introducing different Objective functions (OF) with multiple metrics for the network.

ETX ELT HOP internet of things IP networks network performance routing RPL

Abstract doi.org/10.14569/IJACSA.2019.0100524 PDF

25

Towards Effective Service Discovery using Feature Selection and Supervised Learning Algorithms

Author 1: Heyam H Al-Baity Author 2: Norah I. AlShowiman

With the rapid development of web service technologies, the number and variety of web services available on the internet are rapidly increasing. Currently, service registries support human classification, which has been observed to have certain limitations, such as poor query results with low precision and recall rates. With the huge amount of available web services, efficient web service discovery has become a challenging issue. Therefore, to support the effective application of web services, automatic web service classification is required. In recent years, many researchers have approached web service classification problems by applying machine learning methods to automatically classify web services. The ultimate goal of our work is to construct a classifier model that can accurately classify previously unseen web services into the proper categories. This paper presents an intensive investigation on the impact of incorporating feature selection methods (filter and wrapper) on the performance of four state-of-the-art machine learning classifiers. The purpose of employing feature selection is to find a subset of features that maximizes classification accuracy and improves the speed of traditional machine learning classifiers. The effectiveness of the proposed classification method has been evaluated through comprehensive experiments on real-world web service datasets. The results demonstrated that our approach outperforms other state-of-the-art methods.

Web service discovery Web Service Description Language (WSDL) supervised machine learning classification feature selection

Abstract doi.org/10.14569/IJACSA.2019.0100525 PDF

26

An Advanced Emergency Warning Message Scheme based on Vehicles Speed and Traffic Densities

Author 1: Mustafa Banikhalaf Author 2: Saleh Ali Alomari Author 3: Mowafaq Salem Alzboon

In intelligent transportation systems, broadcasting Warning Messages (WMs) by Vehicular Ad hoc Networks (VANETs) communication is a significant task. Designing efficient dissemination schemes for fast and reliable delivery of WMs is still an open research question. In this paper, we propose a novel messaging scheme, Advanced Speed and Density Warning Message (ASDWM). ASDWM is a broadcast-based scheme that meets design objectives and achieves high saved rebroadcast and reachability, as well as low end-to-end latency of WM delivery. The ASDWM uses vehicle speeds and vehicles density degrees to help emergency vehicles to send WM according to a road condition, adaptively. Simulation results demonstrate the effectiveness and superiority of the ASDWM over its counterparts.

Warning message the broadcast storm problem emergency vehicles

Abstract doi.org/10.14569/IJACSA.2019.0100526 PDF

27

Domain and Schema Independent Semantic Model Verbalization: A Conceptual Overview

Author 1: Kaneeka Vidanage Author 2: Noor Maizura Mohamad Noor Author 3: Rosmayati Mohemad Author 4: Zuriana Abu Bakar

Semantic Web-based technologies have become extremely popular and its a success that has spread across many domains, additional to the computer science domain. Nevertheless, the reusability aspects associated with the created and available semantic knowledge models are very low. The main bottleneck associated with this issue is, the difficulty associated in understanding the complex schema of a knowledge model created and barriers associated with querying the knowledge models using SPARQL or SQWRL query formulations. This research emphasizes on proposing a verbalizer which can go beyond existing Controlled Natural Language (CNL) type verbalizers and to verbalizer knowledge stored in a knowledge model file written in either RDF or OWL format, despite its domain and schematics.

Ontology OWL RDF Verbalize Schema

Abstract doi.org/10.14569/IJACSA.2019.0100527 PDF

28

A Modified Adaptive Thresholding Method using Cuckoo Search Algorithm for Detecting Surface Defects

Author 1: Yasir Aslam Author 2: Santhi N Author 3: Ramasamy N Author 4: K. Ramar

There are various mathematical optimization problems that can be effectively solved by meta-heuristic algorithms. The improvement of these algorithms is that they carry out iterative search processes which resourcefully act upon exploration and exploitation in spatial domain containing global and local optima. An innovative robust Cuckoo Optimization Algorithm (COA) with adaptive thresholding is proposed to solve the problem of detection and estimation of surface defects on metal coating surfaces. The proposed method is developed through implementing changes to COA and improved the performance. For improving capability of local search as well to keep the global search effect, the enhanced methods such as level set is associated with the proposed method. Also, the method adapts dynamic step size, adaptively changing with the search process for improving the rate of convergence and the ability of local search. The algorithm performance is scrutinized from the experimental analysis and results. Also, the segmentation effectiveness is further enhanced by adapting suitable methods for preprocessing and post processing. The comparison and analysis of the results accomplished with the proposed method and results of earlier methods shows superior performance of the proposed method.

Thresholding surface defect optimization image processing coated surface

Abstract doi.org/10.14569/IJACSA.2019.0100528 PDF

29

Secure Data Provenance in Internet of Things based Networks by Outsourcing Attribute based Signatures and using Bloom Filters

Author 1: Muhammad Shoaib Siddiqui Author 2: Atiqur Rahman Author 3: Adnan Nadeem Author 4: Ali M. Alzahrani

With the dawn of autonomous organization and network and service management, the integration of existing networks with Internet of Things (IoT) based networks is becoming a reality. With minimal human interaction, the security of IoT data moving through the network becomes prone to attacks. IoT networks require a secure provenance mechanism, which is efficient and lightweight because of the scarce computing and storage resources at the IoT nodes. In this paper, we have proposed a secure mechanism to sign and authenticate provenance messages using Ciphertext-Policy Attribute Based Encryption (CP-ABE) based signatures. The proposed technique uses Bloom filters to reduce storage requirements and an outsourced ABE mechanism to use lessen the computational requirements at the IoT devices. The proposed technique helps in reducing the storage requirements and computation time in IoT devices. The performance of the proposed mechanism is evaluated and the results show that the proposed solution is best suited for resourced constrained IoT network.

Data provenance bloom filter ciphertext policy attribute based encryption IoT

Abstract doi.org/10.14569/IJACSA.2019.0100529 PDF

30

Query Expansion based on Explicit-Relevant Feedback and Synonyms for English Quran Translation Information Retrieval

Author 1: Nuhu Yusuf Author 2: Mohd Amin Mohd Yunus Author 3: Norfaradilla Wahid

Search engines are commonly present as information retrieval applications that help to retrieve relevant information from different domain areas. The crucial part of improving the quality of search engine is based on query expansion, which expands the query with additional information to match additional important documents. This paper presents a query expansion approach that utilizes explicit relevant feedback with word synonyms and semantic relatedness. We describe the possibility and demonstrations based on the experimental work pertain to search engines where relevant judgment and word synonyms can improve search quality. In order to show the level of improving the proposed approach, we compared the results obtained from the experiments based on Yusuf Ali, Arberry and Sarwar Quran datasets. The proposed approach shows improvement over other methods.

Query expansion search engine relevant feedbacks explicit relevant feedback synonyms information retrieval

Abstract doi.org/10.14569/IJACSA.2019.0100530 PDF

31

Modelling and Implementation of Proactive Risk Management in e-Learning Projects: A Step Towards Enhancing Quality of e-Learning

Author 1: Haneen Hijazi Author 2: Bashar Hammad Author 3: Ahmad Al-Khasawneh

The introduction of e-Learning to higher education institutions has been evolving drastically. However, the quality of e-Learning becomes a central issue in order to provide all stakeholders with the necessary confidence to compete with traditional learning methods. Risk management plays a vital role in the successful implementation of e-Learning projects and in attaining high-quality e-Learning courses. Little research has been conducted about implementing risk management in e-Learning projects. This work proposes a quality assurance framework for e-Learning projects. This framework comprises a proactive risk management model that integrates risk management into the e-Learning process. This integration helps in obtaining high-quality e-Learning courses by preventing negative e-Learning risks from being materialized. The model is verified to evaluate its effectiveness through a Renewable Energy Course that was converted from a traditional face-to-face into e-Learning course. Quantitative and qualitative measures are performed to analyze the data collected through the implementation of the project. The results show that the proposed model is managed to mitigate the majority of probable risk factors leading to high-quality e-Courses development and delivery.

e-Learning technology-enhanced learning quality proactive risk management risk factors higher educatio

Abstract doi.org/10.14569/IJACSA.2019.0100531 PDF

32

Design and Development of an Industrial Solver for Integrated Planning of Production and Logistics

Author 1: Yassine El Khayyam Author 2: Brahim Herrou

Faced with an increasingly hard competition, an increasingly unstable economic environment and ever-increasing customer requirements, companies should optimize costs and lead times not only at their level but also at the entire supply chain to which they belong. In such situation, an integrated supply chain management is necessary. In this paper, we discuss one of the essential building blocks of the integrated supply chain management, which is the integrated planning of the sup-ply chain. We introduce a new method for integrated planning of production and logistics, which is the MLRP (Manufacturing and Logistics Requirement Planning). This method allows supply chain planners to determine in advance, for the entire planning horizon, the manufacturing orders, the supplier’s commands and the transport orders as well as vehicles routing for distribution of finished products and for the collection of components/raw materials. We will also discuss in this article the design and development of the solver which execute the MLRP method, this solver is the SMLRP that will be used to implement the proposed method on the different encountered industrial cases.

MRP VRP production planning transports planning integration MLRP

Abstract doi.org/10.14569/IJACSA.2019.0100532 PDF

33

Novel Joint Subcarrier and Power Allocation Method in SWIPT for WSNs Employing OFDM System

Author 1: Saleemullah Memon Author 2: Kamran Ali Memon Author 3: Zulfiqar Ali Zardari Author 4: Muhammad Aamir Panhwar Author 5: Sijjad Ali Khuhro Author 6: Asiya Siddiqui

In recent research trends, simultaneous wireless information and power transfer (SWIPT) has proved to be an innovative technique to deal with limited energy problems in energy harvesting (EH) technologies for wireless sensor networks (WSNs). In this paper, a method of subcarrier and power allocation for both EH and information decoding (ID) operations is proposed under orthogonal frequency division multiplexing (OFDM) systems, with an improved the quality of service (QoS) parameters. This proposed method assigns one group of subcarriers for ID and remaining group of subcarriers is assigned for EH, despite of applying any splitting schemes. We achieved maximum EH under the ID and power constraints with an effective algorithm for the first time incorporating the dual decomposition technique which deals with power and subcarrier allocation problem jointly. The obtained simulation outcomes in relation to power allocation ratio, subcarrier allocation ratio and energy harvested (EH) at the destination node proved better when compared to the schemes that contain water filling, time switching (TS) or power splitting (PS) approaches under different target transmission rates and transmitter and receiver distances.

Simultaneous wireless information & power transfer (SWIPT) Energy harvesting (EH) Information decoding (ID) power allocation subcarrier allocation

Abstract doi.org/10.14569/IJACSA.2019.0100533 PDF

34

Optimization of a Three-Phase Tetrahedral High Voltage Transformer used in the Power Supply of Microwave

Author 1: Mouhcine Lahame Author 2: Mohammed Chraygane Author 3: Hamid Outzguinrimt Author 4: Rajaa Oumghar

This article deals with the optimization of a three-phase tetrahedral-type high voltage transformer, sized to supply three voltage-doubling cells and three magnetrons per phase. The optimization method used is based on an algorithm implemented in Matlab/Simulink to study the influence of transformer geometrical parameters on the electrical operation of the power supply. This study will allow to find reduced volume of transformer respecting the current constraints imposed by the magnetrons manufacturer. The choice of optimal solution is done by calculation of magnetrons powers in order to respect the nominal operation.

Optimization tetrahedral voltage-doubling transformer magnetrons

Abstract doi.org/10.14569/IJACSA.2019.0100534 PDF

35

LBPH-based Enhanced Real-Time Face Recognition

Author 1: Farah Deeba Author 2: Hira Memon Author 3: Fayaz Ali Dharejo Author 4: Aftab Ahmed Author 5: Abddul Ghaffar

Facial recognition has always gone through a consistent research area due to its non-modelling nature and its diverse applications. As a result, day-to-day activities are increasingly being carried out electronically rather than in pencil and paper. Today, computer vision is a comprehensive field that deals with a high level of programming by feeding the input images/videos to automatically perform tasks such as detection, recognition and classification. Even with deep learning techniques, they are better than the normal human visual system. In this article, we developed a facial recognition system based on the Local Binary Pattern Histogram (LBPH) method to treat the real-time recognition of the human face in the low and high-level images. We aspire to maximize the variation that is relevant to facial expression and open edges so to sort of encode edges in a very cheap way. These highly successful features are called the Local Binary Pattern Histogram (LBPH).

Face recognition feature extraction Local Binary Pattern Histogram (LBPH)

Abstract doi.org/10.14569/IJACSA.2019.0100535 PDF

36

Visualizing Code Bad Smells

Author 1: Maen Hammad Author 2: Sabah Alsofriya

Software visualization is an effective way to support human comprehension to large software systems. In software maintenance, most of the time is spent on understanding code in order to change it. This paper presents a visualization approach to help maintainers to locate and understand code bad smells. Software maintainers need to locate and understand these bad smells in order to remove them via code refactoring. Object oriented code elements are visualized as well as their bad smells if they exist. The proposed visualization shows classes as building and bad smell as letter avatars based on the initials of the names of bad smells. These avatars are shown as warning signs on the buildings. A framework is proposed to automatically analyze code to identify bad smells and to generate the proposed visualizations. The evaluation of the proposed visualizations showed they reduce the comprehension time needed to understand bad smells.

Software visualization program comprehension data modeling bad smells

Abstract doi.org/10.14569/IJACSA.2019.0100536 PDF

37

Novel Carrier based PWM Techniques Reduce Common Mode Voltage for Six Phase Induction Motor Drives

Author 1: Ngoc Thuy Pham Author 2: Nho Van Nguyen

This paper proposes a novel pulse width modulation (CBPWM) technique for reducing the common mode voltage for a six-phase induction motor (SPIM) drive. This proposed CBPWM technique relies on setting up offset functions and the phase shift of carrier wares. Common mode voltage occurs under the effect of DC power Vd always in Vd/6 limits. Some ways of designing the offset function are proposed; these proposed strategies permit to reduce either the mean value or the instantaneous value of the common mode voltage. Features of proposal CBPWM solutions have been compared. Simulation and experimental results demonstrate the feasibility of the proposed solution.

Six-phase induction motor six-phase voltage source inverter common mode voltage carrier based pulse width modulation

Abstract doi.org/10.14569/IJACSA.2019.0100537 PDF

38

Performance Analysis of Machine Learning Techniques on Software Defect Prediction using NASA Datasets

Author 1: Ahmed Iqbal Author 2: Shabib Aftab Author 3: Umair Ali Author 4: Zahid Nawaz Author 5: Laraib Sana Author 6: Munir Ahmad Author 7: Arif Husen

Defect prediction at early stages of software development life cycle is a crucial activity of quality assurance process and has been broadly studied in the last two decades. The early prediction of defective modules in developing software can help the development team to utilize the available resources efficiently and effectively to deliver high quality software product in limited time. Until now, many researchers have developed defect prediction models by using machine learning and statistical techniques. Machine learning approach is an effective way to identify the defective modules, which works by extracting the hidden patterns among software attributes. In this study, several machine learning classification techniques are used to predict the software defects in twelve widely used NASA datasets. The classification techniques include: Naïve Bayes (NB), Multi-Layer Perceptron (MLP). Radial Basis Function (RBF), Support Vector Machine (SVM), K Nearest Neighbor (KNN), kStar (K*), One Rule (OneR), PART, Decision Tree (DT), and Random Forest (RF). Performance of used classification techniques is evaluated by using various measures such as: Precision, Recall, F-Measure, Accuracy, MCC, and ROC Area. The detailed results in this research can be used as a baseline for other researches so that any claim regarding the improvement in prediction through any new technique, model or framework can be compared and verified.

Software defect prediction software metrics data mining machine learning classification class imbalance

Abstract doi.org/10.14569/IJACSA.2019.0100538 PDF

39

Experimental Evaluation of the Virtual Environment Efficiency for Distributed Software Development

Author 1: Pavel Kolyasnikov Author 2: Evgeny Nikulchev Author 3: Iliy Silakov Author 4: Dmitry Ilin Author 5: Alexander Gusev

At every software design stage nowadays, there is an acute need to solve the problem of effective choice of libraries, development technologies, data exchange formats, virtual environment systems, characteristics of virtual machines. Due to the spread of various kinds of devices and the popularity of Web platforms, lots of systems are developed not for the universal installation on a device (box version), but for a specific architecture with the subsequent provision of web services. Under these conditions, the only way for estimating the efficiency parameters at the design stage is to conduct various kinds of experiments to evaluate the parameters of a particular solution. Using the example of the Web platform of digital psychological tools, the methods for experimental parameter evaluation were developed in the article. The mechanisms and technologies for improving the efficiency of the Vagrant and Docker cloud virtual environment were also proposed in the paper. A set of basic criteria for evaluating the effectiveness of the configuration of the virtual development environment has been determined to be rapid deployment; increase in the speed and decrease in the volume of resources used; increase in the speed of data exchange between the host machine and the virtual machine. The results of experimental estimates of the parameters that define the formulated efficiency criteria are given as: processor utilization involved (percentage); the amount of RAM involved (GB); initialization time of virtual machines (seconds); time to assemble the component completely (Build) and to reassemble the component (Watch) (seconds). To improve the efficiency, a file system access driver based on the NFS protocol was studied in the paper.

Distributed software development virtual development environment increase development efficiency virtual machines vagrant Docker NFS webpack

Abstract doi.org/10.14569/IJACSA.2019.0100539 PDF

40

Prediction of Crude Oil Prices using Hybrid Guided Best-So-Far Honey Bees Algorithm-Neural Networks

Author 1: Nasser Tairan Author 2: Habib Shah Author 3: Aliya Aleryani

The objective of this paper is the use of new hybrid meta-heuristic method called Guided Best-So-Far Honey Bees Inspired Algorithm with Artificial Neural Network (ANN) on the Prediction of Crude Oil Prices of Kingdom of Saudi Arabia (KSA). Very high volatility of crude oil prices is one of the main hurdles for the economic development; therefore, it’s the need of the hour to predict crude oil prices, especially for oil-rich countries such as KSA. Hence, in this paper, we are proposing a hybrid algorithm, named: Guided Best-So-Far Artificial Bee Colony (GBABC) algorithm. The proposed algorithm has been trained and tested with ANN for finding the optimal weight values to increase the exploration and exploitation process with balance quantities to obtain the accurate prediction of crude oil prices. The KSA crude oil prices of the five years 2013 to 2017 have been used to train ANN with different topologies and learning parameters of the proposed method for the prediction of the crude oil prices of the next day. The simulation results have been very promising and encouraging of the proposed algorithm when compared and analyzed with ABC, GABC (Gbest Guided ABC) and Best-So-Far ABC methods for prediction purpose. In most cases, the actual prices and predicted crude oil KSA prices are very close, which were obtained by the proposed GBABC method based on the optimal weight values of ANN and minimum prediction error.

Bio inspired best so far crude oil prices KSA

Abstract doi.org/10.14569/IJACSA.2019.0100540 PDF

41

Designing Model of Serious Game for Flood Safety Training

Author 1: Nursyahida Mokhtar Author 2: Amirah Ismail Author 3: Zurina Muda

Serious games have the potential to increase motivation among users in the aspect of safety training. Additionally, serious games can also positively impact training outcomes when the knowledge and skills acquired during a serious game training are transferred to a real-world application. The development of a serious game is based on the game elements and theories determined according to the goals or objectives of the game being developed. There are existing serious games that have been used for training but less usage of scenarios and feedback element render the game less effective for training purposes. Besides that, existing serious games for training purposes fail in delivering domain content to achieve the game objectives since they are more focused on entertainment. This is because the games do not involve experts in providing game domain content. The objective of this paper is to design a serious game model for flood safety training. Preliminary study and literature review are used in this study as the research method. The result of this study is a model of a serious game for flood safety training. In conclusion, this study focuses on the design of a serious game model for flood safety training that includes the elements of serious game identified and adapted to psychology readiness based on the flood training module by Malaysian Defense Force (APM). This makes the serious game more attractive and can give intrinsic motivation to players. For future studies, every single element serious game and theory of psychology readiness in the model developed in this study will be validated with the expert game and expert psychology.

Serious game model flood safety training flood awareness intrinsic motivation psychology readiness

Abstract doi.org/10.14569/IJACSA.2019.0100541 PDF

42

Comparison of Reducing the Speckle Noise in Ultrasound Medical Images using Discrete Wavelet Transform

Author 1: Asim ur Rehman Khan Author 2: Farrokh Janabi-Sharifi Author 3: Mohammad Ghahramani Author 4: Muhammad Ahsan Rehman Khan

Speckle noise in ultrasound (US) medical images is the prime factor that undermines its full utilization. This noise is added by the constructive / destructive interference of sound waves travelling through hard- and soft-tissues of a patient. It is therefore generally accepted that the noise is unavoidable. As an alternate researchers have proposed several algorithms to somewhat undermine the effect of speckle noise. The discrete wavelet transform (DWT) has been used by several researchers. However, the performance of only a few transforms has been demonstrated. This paper provides a comparison of several DWT. The algorithm comprises of a pre-processing stage using Wiener filter, and a post-processing stage using Median filter. The processed image is compared with the original image on four metrics: two are based on full-reference (FR) image quality assessment (IQA), and the remaining two are based on no-reference (NR) IQA metrics. The FR-IQA are peak signal-to-noise ratio (PSNR) and mean structurally similarity index measure (MSSIM). The two NR-IQA techniques are blind pseudo-reference image (BPRI), and blind multiple pseudo-reference images (BMPRI). It has been demonstrated that some of these wavelet transforms outperform others by a significant margin.

Discrete wavelet transform image quality assessment ultrasound medical image

Abstract doi.org/10.14569/IJACSA.2019.0100542 PDF

43

BHA-160: Constructional Design of Hash Function based on NP-hard Problem

Author 1: Ali Al Shahrani

Secure hash function is used to protect the integrity of the message transferred on the unsecured network. Changes on the bits of the sender’s message are recognized by the message digest produced by the hash function. Hash function is mainly concerned with data integrity, where the data receiver needs to verify whether the message has been altered by eavesdropping by checking the hash value appended with the message. To achieve this purpose, we have to use a secure hash function that is able to calculate the hash value of any message. In this paper, we introduce an alternative hash function based on NP-hard problem. The chosen NP-hard problem is known as Braid Conjugacy problem. This problem has proved to be secure against cryptanalysis attacks.

Hash function integrity message cryptanalysis attack NP-hard problem

Abstract doi.org/10.14569/IJACSA.2019.0100543 PDF

44

Variable Reduction-based Prediction through Modified Genetic Algorithm

Author 1: Allemar Jhone P. Delima Author 2: Ariel M. Sison Author 3: Ruji P. Medina

Due to the massive influence in the use of prediction models in different sectors of society, many researchers have employed hybrid algorithms to increase the accuracy level of the prediction model. The literature suggests that the use of Genetic Algorithms (GAs) can sufficiently improve the performance of other prediction models; thus, this study. This paper introduced a new avenue of prediction integrating GA with the novel Inversed Bi-segmented Average Crossover (IBAX) operator paired with rank-based selection function to the KNN algorithm. The 70% of data from 597 records of student-respondents in the evaluation of the faculty instructional performance from the four State Universities and Colleges (SUC) in Caraga Region, Philippines were used as training set while the 30% was used for testing. The simulation result showed that the use of the proposed prediction model with the integration of the modified GA outperformed the KNN prediction model where GA with average crossover and roulette wheel selection function was used. The KNN where k value is three (3) was identified to be the optimal model for prediction with the 95.53% prediction accuracy compared to KNN with 1, 5, and 7 k values.

Enhanced prediction model IBAX operator modified genetic algorithm prediction accuracy enhancement

Abstract doi.org/10.14569/IJACSA.2019.0100544 PDF

45

IoT Testing-as-a-Service: A New Dimension of Automation

Author 1: Babur Hayat Malik Author 2: Myda Khalid Author 3: Maliha Maryam Author 4: M. Nauman Ali Author 5: Sheraz Yousaf Author 6: Mudassar Mehmood Author 7: Hammad Saleem

Internet of Things (IoT) systems has become a global trend enhancing the capabilities smart computing era involving a variety of distributed end-devices and multi- scalable applications. The collaborative nature of IoT systems connected through the Internet increases the heterogeneity of coming data streams that need to be processed for correct decision making in a real-time environment. The processing of huge data streams for remotely distributed IoT systems create loops for data breaches and open new challenges for security and scalability of system testing. Thus, the testing of IoT systems is becoming the necessity, requires automated testing framework due to the amount of IoT devices and processing of data events is prone to error by traditional software testing. An automated IoT testing service based framework is purposed in this paper, to test the distributed IoT systems by reducing cost and scalability issues of software testing. The infrastructure of IoT systems demands a large number of platforms be developed which requires systematic testing approach. Therefore, the purposed automated IoT testing as a service model performs distributed interoperability testing, oneM2M based conformance testing, security testing of distributed systems and validating semantics/syntactic testing of IoT devices in a systematic approach. Lastly, to provide more strength to the work we discussed and analyze existing IoT testing models to evaluate our proposed model.

Testing automation IoT interoperability testing conformance testing security testing semantic testing

Abstract doi.org/10.14569/IJACSA.2019.0100545 PDF

46

Assessment of Technology Transfer from Grid power to Photovoltaic: An Experimental Case Study for Pakistan

Author 1: Umer Farooq Author 2: Habib Ullah Manzoor Author 3: Aamir Mehmood Author 4: Awais Iqbal Author 5: Rida Younis Author 6: Amina Iqbal Author 7: Fan Yang Author 8: Muhammad Arshad Shehzad Hassan Author 9: Nouman Faiz

Pakistan is located on the world map where enough solar irradiance value strikes the ground that can be harnessed to vanish the existing blackout problems of the country. Government is focusing towards renewable integration, especially solar photovoltaic (PV) technology. This work is focused to assess the techno-economic viability of different PV technologies with aim of recommending the most optimum type for domestic sector in high solar irradiance region of the country. For this purpose, standalone PV systems are installed using monocrystalline (m-Si), polycrystalline (p-Si), and amorphous crystalline (a-Si) modules on the rooftop at 31.4 oN latitude position. The performance of PV modules is evaluated based on, average output power, normalized power output efficiency, module conversion efficiency, and performance ratio. Results elaborated that m-Si module is the optimum type for the application with 23.01% average normalized power output efficiency. Economics of the system has also been evaluated in terms of the price of power value produced by PV modules with respect to the consumption of that power value from grid source in base case. Integration of such type of domestic PV systems are a need of time to make the future sustainable.

Solar energy photovoltaic technologies module efficiency power demand satisfaction economics

Abstract doi.org/10.14569/IJACSA.2019.0100546 PDF

47

MHealth for Decision Making Support: A Case Study of EHealth in the Public Sector

Author 1: Majed Kamel Al-Azzam Author 2: Malik Bader Alazzam Author 3: Majida Khalid al-Manasra

This paper seeks to explore factors that determine the acceptance of the MHealth application patients. The research relied on (UTAUT2) Unified Theory of Acceptance and Use of Technology to assess the level of acceptance of a new mobile health application by patients. The study involved conducting test surveys across medical hospitals in Jordan with the goal of collecting data from hospital visitors and their patients concerning their intention to use the new mobile health application. 98 questionnaires were collected and 44 valid responses drawn from them for onward data analysis. The UTAUT2 research model was the most appropriate one for conducting the evaluation on MHealth’s user acceptance. Its results would support the government’s goal of building m-health solutions that meet user needs. The model also enhances the roles of DSS in facilitating adoption of MHealth applications. This study provides a theoretical framework for pursuing future research work on the rates of adoption of m-health applications by patients.

Mobile health application UTAUT1 UTAUT2 trust factors

Abstract doi.org/10.14569/IJACSA.2019.0100547 PDF

48

Sea Lion Optimization Algorithm

Author 1: Raja Masadeh Author 2: Basel A. Mahafzah Author 3: Ahmad Sharieh

This paper suggests a new nature inspired metaheuristic optimization algorithm which is called Sea Lion Optimization (SLnO) algorithm. The SLnO algorithm imitates the hunting behavior of sea lions in nature. Moreover, it is inspired by sea lions' whiskers that are used in order to detect the prey. SLnO algorithm is tested with 23 well-known test functions (Benchmarks). Optimization results show that the SLnO algorithm is very competitive compared to Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Sine Cosine Algorithm (SCA) and Dragonfly Algorithm (DA).

Optimization Metaheuristic optimization algorithms Benchmarks Sea Lion Optimization Algorithm (SLnO)

Abstract doi.org/10.14569/IJACSA.2019.0100548 PDF

49

Towards a Real Time Energy Management Strategy for Hybrid Wind-PV Power System based on Hierarchical Distribution of Loads

Author 1: Abdelhadi Raihani Author 2: Tajeddine Khalili Author 3: Mohamed Rafik Author 4: Mohammed Hicham Zaggaf Author 5: Omar Bouattane

Energy management is a crucial aspect for achieving energy efficiency within a Hybrid Renewable energy power station. Load being unbalanced through the day, a reasonable power management can avoid energy dissipation and unnecessary grid solicitation. This article presents an energy management strategy in a real case scenario of a hybrid wind-solar power station in the ENSET campus. The approach manages energy provided by wind turbines and multiple photovoltaic panels, using a power bank as backup source. in this study actual data involving wind speed, solar radiation, load profile and energy generation was collected. Different scenarios were simulated in order to synthesize an efficient energy management and load balancing system with possible load forecasting capability. In all the simulated scenarios the study emphasizes a minimal solicitation of the grid.

Energy management hybrid renewable energy sources grid injection loads distribution energy forecasting load forecasting

Abstract doi.org/10.14569/IJACSA.2019.0100549 PDF

50

Interaction between Learning Style and Gender in Mixed Learning with 40% Face-to-face Learning and 60% Online Learning

Author 1: Anthony Anggrawan Author 2: Nurdin Ibrahim Author 3: Suyitno Muslim Author 4: Christofer Satria

Student learning styles are important factors that have a strong impact on student performance in learning outcomes. That is why each learning method will produce different learning outcomes for students who have different learning styles. According to the previous study concluded that mixed learning produces learning outcomes that are superior to online and face-to-face learning models, but the questions are how is the difference between learning outcomes between student learning styles in mixed learning, and whether there is an interaction between mixed learning models and student learning styles towards learning outcomes. This study provides a scientific answer solution, by conducting experimental research of mix learning with a mixture of 40% face-to-face material learning and 60% online material learning for the subject of Algorithms and Programming. Based on 2-way ANOVA, T, and SCHEFFE tests towards student learning outcomes in this study, it is found: there are differences in learning outcomes between students who have different learning styles, the learning outcomes of male students achieve better learning outcomes than female students, and there is an interaction between student gender and student learning styles towards learning outcomes, where with further tests, it was found that there is no difference in learning outcomes based on student learning styles of all students except students who have a visual learning style with male sex achieving superior learning outcomes than students who have auditory and kinesthetic learning styles.

Online face-to-face mixed learning algorithm and programming learning outcome interaction

Abstract doi.org/10.14569/IJACSA.2019.0100550 PDF

51

Frequency Reconfigurable Vivaldi Antenna with Switched Resonators for Wireless Applications

Author 1: Rabiaa Herzi Author 2: Mohamed-Ali Boujemaa Author 3: Fethi Choubani Author 4: Ali Gharsallah

In this paper, a frequency reconfigurable Vivaldi antenna with switched slot ring resonators is presented. The principle of the method to reconfigure the Vivaldi antenna is based on the perturbation of the surface currents distribution. Switched ring resonators that act as a bandpass filter are printed in specific positions on the antenna metallization. This structure has the ability to reconfigurate between wideband mode and four narrow-band modes which cover significant wireless applications. Combination of the bandpass filters and tapered slot antenna characteristics achieve an agile antenna capable to operate in UWB mode from 2 to 8 GHz and to generate multi-narrow bands at 3.5 GHz, 4GHz, 5.2 GHz, 5.5 GHz, 5.8 GHz and 6.5 GHz. The measurement and simulation results show good agreement. This antenna is an appropriate solution for wireless applications which require reconfigurable Wideband multi-narrow bands antenna.

Frequency reconfigurable Vivaldi Antenna (VA) Ultra-Wideband (UWB) slot ring resonator wireless applications

Abstract doi.org/10.14569/IJACSA.2019.0100551 PDF

52

Accuracy Performance Degradation in Image Classification Models due to Concept Drift

Author 1: Manzoor Ahmed Hashmani Author 2: Syed Muslim Jameel Author 3: Hitham Alhussain Author 4: Mobashar Rehman Author 5: Arif Budiman

Big data is playing a significant role in the current computing revolution. Industries and organizations are utilizing their insights for Business Intelligence by using Deep Learning Networks (DLN). However, dynamic characteristics of BD introduce many critical issues for DLN; Concept Drift (CD) is one of them. CD issue appears frequently in Online Supervised Learning environments in which data trends change over time. The problem may even worsen in a BD environment due to the veracity and variability factors. The CD issue may render the DLN inapplicable by degrading the accuracy of classification results in DLN which is a very serious issue that needs to be addressed. Therefore, these DLN need to quickly adapt to changes for maintaining the accuracy level of the results. To overcome classification accuracy, we need some dynamical changes in the existing DLN. Therefore, in this paper, we examine some of the existing Shallow Learning and Deep Learning models and their behavior before and after the Concept Drift (in experiment 1) and validate the pre-trained Deep Learning network (ResNet-50). In future work, this experiment will examine the most recent pre-trained DLN (Alex Net, VGG16, VGG19) and identify their suitability to overcome Concept Drift using fine-tuning and transfer learning approaches.

Pre-trained networks deep learning concept drift fine tuning transfer learning

Abstract doi.org/10.14569/IJACSA.2019.0100552 PDF

53

Study and Design of a Magnetic Levitator System

Author 1: Brian Meneses-Claudio Author 2: Zeila Torres Santos Author 3: Avid Roman-Gonzalez

Magnetic levitation is one of the mechanisms that is at the forefront of technology. It is used in its most basic form in educational teaching, where the principles of physics converge that have as their principle electromagnetism and the fields created by existing poles that repel according to a quantity of initial current, giving instructive ideas of how the theoretical formulas work, giving life to a practical visual system. The current use on a large scale are the Maglev trains of Japan or superconductivity, being the realization of the quantum effects visualized at the moment of cooling the sample. The electronic circuit tends to be stable because, when using a high-power current, a Triac is needed to compensate the electrical flow provided by the operational amplifier and, therefore, stabilize with the photodiode when activated with the Led diode. Our purpose is to create a circuit that identifies the values of the electronic components that allow reaching equilibrium, with input and output variables that indicate the position and height of the object to be levitated.

Magnetic levitator electromagnet electronic circuit differential potential

Abstract doi.org/10.14569/IJACSA.2019.0100553 PDF

54

Detection of Suspicions of Varicose Veins in the Legs using Thermal Imaging

Author 1: Brian Meneses-Claudio Author 2: Witman Alvarado-Diaz Author 3: Avid Roman-Gonzalez

Varicose veins also known as venous insufficiency, are dilated veins due to an accumulation of blood that occurs in different parts of the body, the most common are in the legs, in addition to having a higher index in women for clothing style that they use. Varicose veins are classified by grades ranging from I to IV and can cause pain, itching, cramps and even ulcers if they are treated in time. Not all varicose veins can be visible superficially, many of them begin inside of the skin. According to the WHO (World Health Organization) 10% of the world population has varicose veins. That is why the detection of suspicions of varicose veins in the legs was raised in this research work, first a thermal image will be obtained using the FLIR ONE Pro thermal camera following a necessary protocol of distance and temperature range. The thermal image is processed in MATLAB to identify the segments of the histogram of the thermal image, to obtain the area of the highest temperature indicating the presence of varicose vein in the subject's leg. The segmentation of the areas with the highest temperature was obtained as a result to be overlaid on the real image, showing the real image with the varicose vein segment found in the thermal image processing.

Thermal image varicose veins detection image processing image segmentation

Abstract doi.org/10.14569/IJACSA.2019.0100554 PDF

55

Skyline Path Queries for Location-based Services

Author 1: Nishu Chowdhury Author 2: Mohammad Shamsul Arefin

A skyline query finds objects that are not dominated by another object from a given set of objects. Skyline queries help us to filter unnecessary information efficiently and provide us clues for various decision making tasks. In this paper, we consider skyline queries for location-based services and proposed a framework that can efficiently compute all non-dominated paths in road networks. A path p is said to dominate another path q if p is not worse than q in any of the k dimensions and p is better than q in at least one of the k dimensions. Our proposed skyline framework considers several features related to road networks and return all non-dominated paths from the road networks. In our work, we compute skylines considering two different perspectives: business perspective and individual user’s perspective. We have conducted several experiments to show the effectiveness of our method. From the experimental results, we can say that our system can perform efficient computation of skyline paths from road networks.

Skyline queries trip planning location-based services

Abstract doi.org/10.14569/IJACSA.2019.0100555 PDF

56

IoT-Enabled Door Lock System

Author 1: Trio Adiono Author 2: Syifaul Fuada Author 3: Sinantya Feranti Anindya Author 4: Irfan Gani Purwanda Author 5: Maulana Yusuf Fathany

This paper covers the design of a prototype for IoT and GPS enabled door lock system. The aim of this research is to design a door lock system that does not need manual input from user for convenience purpose while also remaining secure. The system primarily consists STM32L100 microcontroller as its core, TIP102 transistor that controls 12 VDC solenoid, and Xbee module to communicate with the smart home’s host and receive status regarding user’s GPS position. The system is tested by measuring the user’s distance from the predetermined location using GPS coordinate captured by an Android application, which serves to test whether the system is able to operate as intended and measure the device’s power usage. The test result shows that the device is able to work based on GPS coordinate data received, using 42.3 mA and 587 mA current in idle and active modes, respectively.

Internet of Things smart home smart lock

Abstract doi.org/10.14569/IJACSA.2019.0100556 PDF

57

Low-Cost and Portable Ground Station for the Reception of NOAA Satellite Images

Author 1: Antony E Quiroz-Olivares Author 2: Ntalia I. Vargas-Cuentas Author 3: Guillermo W. Zarate Segura Author 4: Avid Roman-Gonzalez

Currently, in Peru, the study of satellite images is increasing because it has the Earth observation satellite PeruSat-1. However, the cost of implementing a ground station is very high; for this reason, it is baffling that each university has its station. In the present work, the design and implementation of a low-cost portable earth station for the reception of meteorological satellite images is proposed in an automatic way, using accessible electronic devices such as Raspberry Pi 3b +, Software Defined by Radio (SDR) and an antenna double cross four dipoles, in this way encourage the study of satellite images in schools and universities. The results obtained show the viability of this project.

Software defined by radio Raspberry Pi meteorological images antenna dipoles

Abstract doi.org/10.14569/IJACSA.2019.0100557 PDF

58

Experience in Asteroid Search using Astrometrica Software

Author 1: Junior Ascencio-Moran Author 2: Jhon Calero-Juarez Author 3: Maria del Carmen Pajares-Acuña Author 4: Avid Roman-Gonzalez

The present work of this research consists of the analysis of telescopic images provided by the International Astronomical Search Collaboration (IASC) to find asteroids that can be named. The concern in searching for asteroids helps the scientific community that promotes the collaboration of young students and astronomy fans get experience in finding asteroids through campaigns related to these. The Space Generation Advisory Council (SGAC) campaign in partnership with IASC has found around 1500 asteroids since the beginning of October 2006 as each year more than 1000 teams from different countries participate. The Astrometrica software was used which is in charge of receiving the images in FITS format. The configuration of the selected telescope is carried out so that they are later analyzed in greater detail. Finally, a clean and precise Minor Planet Center (MPC) report is made, which is what the campaign requires so that it can go on to a preliminary phase and subsequently be accepted by the international astronomical union. The asteroids that become named will be registered in the catalog of official minor planets of the world. In the campaign related to this study, one finds 28 possible asteroids.

SGAC IASC INTI-Lab UCH MPC asteroids

Abstract doi.org/10.14569/IJACSA.2019.0100558 PDF

59

Size Reduction and Performance Enhancement of Pi Shaped Patch Antenna using Superstrate Configuration

Author 1: Pir Saadullah Shah Author 2: Shahryar Shafique Qureshi Author 3: Muhammad Haneef Author 4: Sohail Imran Saeed

Patch antennas are modern elements of today’s world communication technology. They appear to have unique characteristics and features with their unique power with handling capabilities and lighted structure. This paper focuses on superstrate configuration of patch antenna with defected ground plane and Pi Slotted radiating patch. The three different cases were taken in terms of wavelength distance to observe the performance characteristics of patch structure. The antenna designed in this study can be used for S and C band applications.

Radiating patch ground plane slotted bandwidth gain directivity

Abstract doi.org/10.14569/IJACSA.2019.0100559 PDF

60

Speech Recognition System based on Discrete Wave Atoms Transform Partial Noisy Environment

Author 1: Mohamed Walid Author 2: Bousselmi Souha Author 3: Cherif Adnen

Automatic speech recognition is one of the most active research areas as it offers a dynamic platform for human-machine interaction. The robustness of speech recognition systems is often degraded in real time applications, which are often accompanied by environmental noises. In this work, we have investigated the efficiency of combining wave atoms transform (WAT) with Mel-Frequency Cepstral Coefficients (MFCC) using Support Vector Machine (SVM) as classifier in different noisy conditions. A full experimental evaluation of the proposed model has been conducted using Arabic speech database (ARADIGIT) and corrupted with “NOISEUS database” noises at different levels of SNR ranging from -5 to 15dB. The results of Simulation have indicated that the proposed algorithm has improved the recognition rate (99.9%) at 15 dB of SNR. A comparative study was conducted by applying the proposed WAT-MFCC features to multilayer perceptron (MLP) and hidden Markov model (HMM) in order to prove the efficiency and the robustness of the proposed system.

WAT SVM HMM thresholding noise MFCC MLP

Abstract doi.org/10.14569/IJACSA.2019.0100560 PDF

61

Intelligent Scheduling of Bag-of-Tasks Applications in the Cloud

Author 1: Preethi Sheba Hepsiba Author 2: Grace Mary Kanaga E

The need of efficient provision resources in cloud computing is imperative in meeting the performance requirements. The design of any resource allocation algorithm is dependent on the type of workload. BoT (Bag-of-Tasks) which is made up of batches of independent tasks are predominant in large scale distributed systems such as the cloud and efficiently scheduling BoTs in heterogeneous resources is a known NP-Complete problem. In this work, the intelligent agent uses reinforcement learning to learn the best scheduling heuristic to use in a state. The primary objective of BISA (BoT Intelligent Scheduling Agent) is to minimize makespan. BISA is deployed as an agent in a cloud testbed and synthetic workload and different configurations of a private cloud are used to test the effectiveness of BISA. The normalized makespan is compared against 15 batch mode and immediate mode scheduling heuristics. At its best, BISA produces a 72% lower average normalized makespan than the traditional heuristics and in most cases comparable to the best traditional scheduling heuristic.

Bag-of-tasks applications intelligent agent reinforcement learning scheduling

Abstract doi.org/10.14569/IJACSA.2019.0100561 PDF

62

Four-Class Motor Imagery EEG Signal Classification using PCA, Wavelet and Two-Stage Neural Network

Author 1: Md. Asadur Rahman Author 2: Farzana Khanam Author 3: Md. Kazem Hossain Author 4: Mohammad Khurshed Alam Author 5: Mohiuddin Ahmad

Electroencephalogram (EEG) is the most significant signal for brain-computer interfaces (BCI). Nowadays, motor imagery (MI) movement based BCI is highly accepted method for. This paper proposes a novel method based on the combined utilization of principal component analysis (PCA), wavelet packet transformation (WPT), and two-stage machine learning algorithm to classify four-class MI EEG signal. This work includes four-class MI events by an imaginary lifting of the left hand, right hand, left foot, and Right Foot. The main challenge of this work is to discriminate the similar lobe EEG signal pattern such as left foot VS left hand. Another critical problem is to identify the MI movements of two different feet because their activation level is very low and show an almost similar pattern. This work firstly uses the PCA to reduce the signal dimensions of the left and right lobe of the brain. Then, WPT is used to extract the feature from the different class EEG signal. Finally, the artificial neural network is trained into two stages – 1st stage identifies the lobe from the signal pattern and the 2nd stage identifies whether the signal is of MI hand or MI foot movement. The proposed method is applied to the 4-class MI movement related EEG signals of 15 participants and found excellent classification accuracy (>74% on average). The outcomes of the proposed method prove its effectiveness in practical BCI implementation.

Brain-computer interface electroencephalogram motor imagery principal component analysis wavelet packet transformation artificial neural network classification

Abstract doi.org/10.14569/IJACSA.2019.0100562 PDF

63

A Calibrating Six-Port Compact Circuit using a New Technique Program

Author 1: Traii Moubarek Author 2: Mohannad Almanee Author 3: Ali Gharsallah

In this paper, a calibration of six-port reflectometer using a new technique program is presented. It has been shown that a calibration procedure is based on explicit method, the method that capturing the output wave forms of six-port junction and determines the complex relationship between the two waves present at the input from the value of four outputs. The number of calibrating standards and the computation effort required are the most important parameters in selecting a calibration technique. Comparison between the results obtained from the new calibration method program with measurement results show the validity of the method proposed. This calibration technique can be used in general six-port direct digital receiver.

Calibration technique digital receiver explicit method reflectometer S parameters

Abstract doi.org/10.14569/IJACSA.2019.0100563 PDF

64

Hybrid Concatenated LDPC Codes with LTE Modulation Schemes

Author 1: Mohanad Alfiras Author 2: Wael A. H. Hadi Author 3: Amjad Ali Jassim

In a communication system, the LDPC code is considered as a good performance error correcting code which reaches near Shannon limit. In this paper a hybrid LDPC code is proposed, the hybrid term here refers to the serial concatenation of parallel LDPC codes group and a single serial LDPC code. The outer two parallel LDPC codes encoder represents outer encoder where the single LDPC encoder represents the inner encoder. This study also emphases on the performance of a hybrid coding system in consideration with three modulation schemes. The modulation schemes include quadrature phase shift keying (QPSK) and two types of quadrature amplitude modulation; 16-QAM and 64-QAM. These modulation schemes are selected due to their importance in modern communication applications, such as long term evolution (LTE); such schemes are the standard modulation schemes used with LTE system. This study investigates different LDPC code rates such as 1/2 and 1/3 and simulates the AWGN communication channel using MATLAB. The simulation results show improvement in bit error rate (BER) when using 1/3 LDPC code rate in the designed system rather than 1/2, but it also increases the system complexity. In the end, all simulation results, the comparison between different cases of LDPC code rates and system performance are summarized.

Coding modulation Hybrid concatenation low density parity check

Abstract doi.org/10.14569/IJACSA.2019.0100564 PDF

65

Cloud Computing Adoption in Small and Medium- Sized Enterprises (SMEs) of Asia and Africa

Author 1: Babur Hayat Malik Author 2: Jazba Asad Author 3: Sabila Kousar Author 4: Faiza Nawaz Author 5: Zainab Author 6: Farania Hayder Author 7: Sehresh Bibi Author 8: Amina Yousaf Author 9: Ali Raza

Cloud computing is a rapidly emerging technology over the last few years that has abolished the burden of purchasing heavy hardware and licensed software. Cloud computing has been advantageous to Small and Medium-sized Enterprises (SMEs), but still numerous SMEs have not adopted cloud computing to delve into its appealing benefits. Asia and Africa vary notably regarding their innovative capability. Asia has been competent to advance and sustain world leadership in technological innovations whereas Africa has not developed significantly in these terms. A seldom comparative study has been implemented on the reasons for the innovation gap between these two continents. This article examines and compares the cloud computing adoption from a Geo-regional framework; Asia and Africa. A comparative study is used to organize the findings from China in Asia, and Nigeria in Africa. The article identifies the probable benefits, usage of cloud computing and level of cloud computing adoption amid SMEs in Nigeria and China. The paper explores the margin that subsists amongst the level of cloud computing adoption in SMEs of these two countries and specifies challenges particular to each country intercepting the complete cloud computing adoption and proposes solutions for Nigerian SMEs to beat these challenges. Furthermore, the article contributes proof-supported intrusion for cloud service providers, the government and the capitalism to enhance the cloud computing adoption amid SMEs to eventually determine the enterprises for the probable financial advantage.

Cloud computing adoption Asia Africa small and medium-sized enterprises analysis

Abstract doi.org/10.14569/IJACSA.2019.0100565 PDF

66

Exploratory Analysis of the Total Variation of Electrons in the Ionosphere before Telluric Events Greater than M7.0 in the World During 2015-2016

Author 1: Alva Mantari Alicia Author 2: Zarate Segura Guillermo Wenceslao Author 3: Sotomayor Beltran Carlos Author 4: Brian Meneses-Claudio Author 5: Roman-Gonzalez Avid

This exploratory observational study analyzes the variation of the total amount of vertical electrons (vTEC) in the ionosphere, 17 days before telluric events with grades greater than M7.0 between 2015 and 2016. Thirty telluric events have been analyzed with these characteristics. The data was obtained from 55 satellites and 300 GPS receivers that were downloaded from the Center for Orbit Determination in Europe (CODE). The variations are considered significant only if it is outside the "normal" ranges considered after the statistical analysis performed. The data was downloaded by a program developed in our laboratory. The downloaded data was processed and maps of variations of vTEC generated with a periodicity of 2 hours. The analysis area was considered to be a circular one with a radius of 1000km centered on the epicenter of each earthquake. Variation of vTEC was found during 2015-2016 in 100% of the earthquakes in the range from day 1 to day 17 days before the event, over the circular area of 1000 km radius centered on the epicenter of the earthquake. Of these in 96.55% there is positive variations, and a negative ones exist in 68.97% of the events. If we observe in the range from day 3 to 17 before the event, a variation was recorded in 100% of the cases, and from day 8 to day 17 before the event in 93.10% of the cases, it is important to emphasize that while the evidence in a period before the event is more likely to find evidence to develop early warning tool for earthquake prevention. This study explores the variation of vTEC as precursor events to each earthquake during 2015-2016, it is a preliminary analysis that shows us the feasibility of analyzing this information as a preamble for an exhaustive association study later. The final objective is to calculate the risk of telluric events which would benefit the population worldwide.

Total number of electrons ionosphere earthquakes prevention risk

Abstract doi.org/10.14569/IJACSA.2019.0100566 PDF

67

Fast and Efficient In-Memory Big Data Processing

Author 1: Babur Hayat Malik Author 2: Maliha Maryam Author 3: Myda Khalid Author 4: Javaria Khlaid Author 5: Najam Ur Rehman Author 6: Syeda Iqra Sajjad Author 7: Tanveer Islam Author 8: Umair Ahmed Butt Author 9: Ali Raza Author 10: M. Saad Nasr

With the passage of time, the data is growing exponentially and the mostly endured areas are social media networks, media hosting applications, and servers. They have thousands of Tera-bytes of data and the efficient systems, however, they are as yet confronting issue to oversee such volume of information and its size is growing each day. Data systems retrieve information with less time of In-memory. Instead of each factor data systems are required to define good usage of cache and fast memory access with help of optimization. The proposed technique to solve this problem can be the optimal indexing technique with better and efficient utilization of Cache and having less overhead of DRAM with the goal that energy can also be saved for the high-end servers.

Big data processing indexing techniques R-tree B-tree X-tree hashing inverted index graph query tree

Abstract doi.org/10.14569/IJACSA.2019.0100567 PDF

68

Comparing Hybrid Tool for Static and Dynamic Object-Oriented Metrics

Author 1: Babur Hayat Malik Author 2: Javaria Khalid Author 3: Hafsa Arif Author 4: Ayesha Sadiqa Author 5: Amara Tanveer Author 6: Asia Mumtaz Author 7: Zartashiya Afzal Author 8: Samreen Azhar Author 9: Muhammad Numan Ali

Software metrics are created and used by the distinctive programming associations intended for assessing, guaranteeing program excellence, activity, and software recovery. Software metrics have turned into a basic part of programming growth and are utilized in each period of the product development life cycle. Software metrics essentially measure programming items like plan source code and help us in taking technical and administrative choices. The desire of this examination is to play out the relative investigation of static and dynamic metrics. In any case, software quality characteristics, for example, performance, execution time and dependability rely upon the dynamic exercises of the product artifact. Due to every one of these variables, we favor dynamic metrics instead of customary static metrics. With the assistance of customary static metrics, we are not capable to analyze different actualities of programming. There are various types of this OO static and dynamic equipments. In this paper we have played out a similar investigation of different OO static and dynamic metrics tools and find out the hybrid too is counted as best one extraction of both, static and dynamic characteristics from mobile Android applications. The source code and a Docker compartment is utilized by open source tool in only three phases pre-static, static and dynamic examination.

Software metrics static metrics dynamic metrics Object Oriented (OO)

Abstract doi.org/10.14569/IJACSA.2019.0100568 PDF

69

Comparison of Agile Method and Scrum Method with Software Quality Affecting Factors

Author 1: Muhammad Asaad Subih Author 2: Babur Hayat Malik Author 3: Imran Mazhar Author 4: Izaz-ul-Hassan Author 5: Usman Sabir Author 6: Tamoor Wakeel Author 7: Wajid Ali Author 8: Amina Yousaf Author 9: Bilal-bin-Ijaz Author 10: Hadiqa Nawaz Author 11: Muhammad Suleman

The software industry used software development lifecycle (SDLC) to design, develop, produce high quality, reliable and cost-effective software products. To develop an application, project team used some methodology which may include artifacts and pre-defining specific deliverables. There are different SDLC process models such as waterfall, iterative, spiral and agile model available to develop a quality product. In this paper we focus only on agile software development model, and Scrum model and their techniques. There are many papers and books written on agile methodologies. We will also use their knowledge in this paper. To collect data for comparison of agile method with software quality affecting factors, an online questionnaire survey was conducted. The survey sample consisted of software developers with several years of industry experience using agile methodologies. The main purpose of this study is to compare soft-ware quality affecting factors with agile and scrum model.

Component SDLC Software Quality Affecting Factors Agile methodologies Scrum

Abstract doi.org/10.14569/IJACSA.2019.0100569 PDF

70

Reengineering Framework to Enhance the Performance of Existing Software

Author 1: Jaswinder Singh Author 2: Kanwalvir Singh Dhindsa Author 3: Jaiteg Singh

Term reengineering refers to improve the quality of the system. Continues maintenance and aging degrade the performance of the software system. Right approach and methodology must be adapted to perform reengineering. With lack of right approach and methodology, reengineering itself will be costly and time-consuming. For the process of reengineering main concerns include when to reengineer, how to estimate cost, the right approach for reengineering, and how to validate software enhancement. This research paper proposed a framework to identify the need for reengineering, to estimate the cost of reengineering, and to validate software quality improvement. Research work used the agile methodology to perform tasks of reengineering. Reengineering needs are identified using prediction based decision tree approach. Reengineering is applied using the agile Scrum methodology. Cost estimation is done using story point estimation. Performance analyses are done using complexity measures analysis of the internal design metrics and mean time to execute metric. The research used various automated tools like CKJM ver1.9, Rapid Miner studio ver7.1, and Net beans7.3 framework.

Reengineering maintenance decision tree agile methodology scrum

Abstract doi.org/10.14569/IJACSA.2019.0100570 PDF

71

Dynamic Bandwidth Allocation in LAN using Dynamic Excess Rate Sensing

Author 1: Muhammad Abubakar Muhammad Author 2: Muhammad Azhar Mushatq Author 3: Abid Sultan Author 4: Muhammad Afrasayab

Today human and information processing system both need rapid access to anything they want on the internet. To fulfill these needs more and more internet service providers with a large amount of bandwidth are introducing themselves in the market. For these providers, a lot of bandwidth is free during off-peak hours while during peak hours the total available bandwidth might be insufficient. The primary purpose of our research is to divide and distribute the excessive bandwidth among the users during off-peak hours to attain the maximum user satisfaction. In order to do this dynamic excess rate (DER) scheme and its frame work is proposed in this paper.

DER ISPs PIR DBA MRT CIR

Abstract doi.org/10.14569/IJACSA.2019.0100571 PDF

72

SentiNeural: A Depression Clustering Technique for Egyptian Women Sentiments

Author 1: Doaa Mohey ElDin Author 2: Mohamed Hamed N. Taha Author 3: Nour Eldeen M. Khalifa

Online Sentiments Analysis is a trending research domain of study which is based on natural language processing, artificial intelligence, and computational linguistics. Negation sentiments usually are not included in sentiment’s analysis process. The depression analysis can be improved by negative sentiments processing. The negation sentiments may contribute to classify the depression problems and its causes. The proposed clustering technique can detect female sentiments from the sentiment’s text through cause’s classification, and the written sentiment style. The combination of sentiment analysis and neural network is a promising solution for creating a new clustering algorithm. According to Egypt Independent Journal in 2018, 7% of Egyptians suffer from mental illness reported by the Public Health Ministry in Egypt. But the real statistics is more than the mentioned percentage which causes major social problems such as divorce, avoiding responsibilities, or non-marriage. This paper will address the real statistics and cluster the depression causes and social status for each sentiment. Online women sentiments are the essential focus of this research. The proposed technique consists of two algorithms clustering for user’s sex and classification algorithm for causes and responsibilities of women. The proposed clustering algorithm can recognize automatically for the sentiments user sex (females or males) and the level of depression automatically. The neural network clustering approach will produce accurate analysis results. The hardness of depression analysis implicitly and explicitly demonstrated in the different classifications for sentiments. This paper introduces a new technique for clustering sentiments and evaluating Egyptian women depression based on social sentiments.

Sentiment analysis negation handling depression analysis neural network clustering

Abstract doi.org/10.14569/IJACSA.2019.0100572 PDF

73

Bayesian Network Analysis for the Questionnaire Investigation on the Needs at Fuji Shopping Street Town under the View Point of Service Engineering

Author 1: Tsuyoshi Aburai Author 2: Akane Okubo Author 3: Daisuke Suzuki Author 4: Kazuhiro Takeyasu

Shopping streets at local city in Japan became old and are generally declining. In this paper, the area rebirth and/or regional revitalization of shopping street are handled. Fuji city in Japan is focused. Four big festivals are held at Fuji city (two for Fuji Shopping Street Town and two for Yoshiwara Shopping Street Town). Many people visit these festivals including residents in that area. Therefore a questionnaire investigation to the residents and visitors is conducted during these periods in order to clarify residents and visitors’ needs for the shopping street, and utilize them to the plan building of the area rebirth and/or regional revitalization of shopping street. There is a big difference between Fuji Shopping Street Town and Yoshiwara Shopping Street Town. Therefore Fuji Shopping Street Town is focused in this paper. These are analyzed by using Bayesian Network. These are analyzed by sensitivity analysis and odds ratio is calculated to the results of sensitivity analysis in order to obtain much clearer results. The analysis utilizing Bayesian Network enabled us to visualize the causal relationship among items. Furthermore, sensitivity analysis brought us estimating and predicting the prospective visitors. Sensitivity analysis is performed by back propagation method. These are utilized for constructing a much more effective and useful plan building. Fruitful results are obtained. To confirm the findings by utilizing the new consecutive visiting records would be the future works to be investigated.

Fuji city area rebirth regional vitalization Bayesian network back propagation service engineering

Abstract doi.org/10.14569/IJACSA.2019.0100573 PDF

74

Alerts Clustering for Intrusion Detection Systems: Overview and Machine Learning Perspectives

Author 1: Wajdi Alhakami

The tremendous amount of the security alerts due to the high-speed alert generation of high-speed networks make the management of intrusion detection computationally expensive. Evidently, the high-level rate of wrong alerts disproves the Intrusion Detection Systems (IDS) performances and decrease its capability to prevent cyber-attacks which lead to tedious alert analysis task. Thus, it is important to develop new tools to understand intrusion data and to represent them in a compact forms using, for example, an alert clustering process. This hot topic of research is studied here and an understandable taxonomy followed by a deep survey of main published works related to intrusion alert management is presented in this paper. The second part of this work exposes different useful steps for designing a unified IDS system on the basis of machine learning techniques which are considered one of the most powerful tools for solving certain problems related to alert management and outlier detection.

Intrusion detection systems alert clustering taxon-omy survey machine learning

Abstract doi.org/10.14569/IJACSA.2019.0100574 PDF

75

Feature based Algorithmic Analysis on American Sign Language Dataset

Author 1: Umair Muneer Butt Author 2: Basharat Husnain Author 3: Usman Ahmed Author 4: Arslan Tariq Author 5: Iqra Tariq Author 6: Muhammad Aadil Butt Author 7: Dr. Muhammad Sultan Zia

Physical disability is one of the factor in human beings, which cannot be ignored. A person who can’t listen by nature is called deaf person. For the representation of their knowledge, a special language is adopted called ‘Sign-Language’. American Sign Language (ASL) is one of the most popular sign language that is used for learning process in deaf persons. For the representation of their knowledge by deaf persons, a special language is adopted ‘Sign-Language’. American Sign Language contains a set of digital images of hands in different shapes or hand gestures. In this paper, we present feature based algorithmic analysis to prepare a significant model for recognition of hand gestures of American Sign Language. To make a machine intelligent, this model can be used to learn efficiently. For effective machine learning, we generate a list of useful features from digital images of hand gestures. For feature extraction, we use Matlab 2018a. For training and testing, we use weka-3-9-3 and Rapid Miner 9 1.0. Both application tools are used to build an effective data modeling. Rapid Miner outperforms with 99.9% accuracy in auto model.

Hand gesture recognition pre-processing weka rapid miner HOG LBP auto model

Abstract doi.org/10.14569/IJACSA.2019.0100575 PDF

76

A Comprehensive Survey on the Performance Analysis of Underwater Wireless Sensor Networks (UWSN) Routing Protocols

Author 1: Tariq Mahmood Author 2: Faheem Akhtar Author 3: Sher Daudpota Author 4: Khalil ur Rehman Author 5: Saqib Ali Author 6: Fawaz Mahiuob Mokbal

The probe of innovative technologies is a furious issue of the day for the improvement of underwater wireless sensor network devices. The undersea is a remarkable and mystical region which is still unexplored and inaccessible on earth. Interest has been increasing in monitoring the medium of underwater for oceanographic data collection, surveillance application, offshore exploration, disaster prevention, commer-cial, scientific investigation, attack avoidance, and other military purposes. In underwater milieus, the sensor networks face a dangerous situation due to intrinsic water nature. However, significant challenges in this concern are high power consumption of acoustic modem, high propagation latency in data transmission, and dynamic topology of nodes due to wave movements. Routing protocols working in UWSN has low stability period due to increased data flooding which causes nodes to expire quickly due to unnecessary data forwarding and high energy consumption. The quick energy consumption of nodes originates large coverage holes in the core network. To keep sensor nodes functional in an underwater network, dedicated protocols are needed for routing that maintain the path connectivity. The path connectivity consumes more energy, high route updated cost with a high end to end delay for the retransmission of packets. So, in this paper, we are providing a comprehensive survey of different routing protocols employed in UWSN. The UWSN routing protocols are studied and evaluated related to the network environment and quality measures such as the end to end delay, dynamic network topology, energy consumption and packet delivery ratio. The merits and demerits of each routing protocol are also highlighted.

Underwater Wireless Sensor Networks (UWSN) routing protocols end-to-end delay energy consumptions

Abstract doi.org/10.14569/IJACSA.2019.0100576 PDF

77

A Novel Framework for Drug Synergy Prediction using Differential Evolution based Multinomial Random Forest

Author 1: Jaspreet Kaur Author 2: Dilbag Singh Author 3: Manjit Kaur

An efficient prediction of drug synergy plays a significant role in the medical domain. Examination of different drug-drug interaction can be achieved by considering the drug synergy score. With an rapid increase in cancer disease, it becomes difficult for doctors to predict significant amount of drug synergy. Because each cancer patient’s infection level varies. Therefore, less or more amount of drug may harm these patients. Machine learning techniques are extensively used to estimate drug synergy score. However, machine learning based drug synergy prediction approaches suffer from the parameter tuning problem. To overcome this issue, in this paper, an efficient Differential evolution based multinomial random forest (DERF) is designed and implemented. Extensive experiments by considering the existing and the proposed DERF based machine learning models. The comparative analysis of DERF reveals that it outperforms existing techniques in terms of coefficient of determination, root mean squared error and accuracy.

Machine learning random forest drug synergy

Abstract doi.org/10.14569/IJACSA.2019.0100577 PDF

78

Intruder Attacks on Wireless Sensor Networks: A Soft Decision and Prevention Mechanism

Author 1: Iftikhar Hussain Author 2: Samman Zahra Author 3: Abrar Hussain Author 4: Hayat Dino Bedru Author 5: Shahzad Haider Author 6: Diana Gumzhacheva

Because of the wide-ranging of applications in a variety of fields, such as medicine, environmental studies, robotics, warfare and security, and so forth, the research on wireless sensor networks (WSNs) has attracted much attention recently. WSNs offer economical, flexible, scalable and pragmatic solutions in many situations. Sensor nodes are tiny and have a limited, non-rechargeable battery source, small memory/computational abilities and low transmitter power. Energy resources are vital as once the battery is depleted, the node is no longer usable. Multiple medium access control (MAC) protocols are designed to increase the life cycle of a node by minimizing its unnecessary energy consumption. In some critical applications like the surveillance of enemy movements on a battlefield, opponents deploy adversary nodes to disturb the performance of WSNs by mainly depleting the battery sources of legitimate nodes. In this work, an intrusion detection mechanism has been adapted to detect different kinds of intruders’ attacks in MAC protocols of WSN’s. A soft decision mechanism has been implemented to detect collision and exhaus-tion attacks. A preventative mechanism has also been introduced, which helps a node to avoid these intrusive attacks. Results show how the lifetime of a node increases and network performance also increases with better throughput and reduced delay.

MAC protocols S-MAC wireless sensor networks intrusion detection

Abstract doi.org/10.14569/IJACSA.2019.0100578 PDF

79

Deep Learning Approaches for Data Augmentation and Classification of Breast Masses using Ultrasound Images

Author 1: Walid Al-Dhabyani Author 2: Mohammed Gomaa Author 3: Hussien Khaled Author 4: Aly Fahmy

Breast classification and detection using ultrasound imaging is considered a significant step in computer-aided diagno-sis systems. Over the previous decades, researchers have proved the opportunities to automate the initial tumor classification and detection. The shortage of popular datasets of ultrasound images of breast cancer prevents researchers from obtaining a good performance of the classification algorithms. Traditional augmentation approaches are firmly limited, especially in tasks where the images follow strict standards, as in the case of medical datasets. Therefore besides the traditional augmentation, we use a new methodology for data augmentation using Generative Adversarial Network (GAN). We achieved higher accuracies by integrating traditional with GAN-based augmentation. This paper uses two breast ultrasound image datasets obtained from two various ultrasound systems. The first dataset is our dataset which was collected from Baheya Hospital for Early Detection and Treatment of Women’s Cancer, Cairo (Egypt), we name it (BUSI) referring to Breast Ultrasound Images (BUSI) dataset. It contains 780 images (133 normal, 437 benign and 210 malignant). While the Dataset (B) is obtained from related work and it has 163 images (110 benign and 53 malignant). To overcome the shortage of public datasets in this field, BUSI dataset will be publicly available for researchers. Moreover, in this paper, deep learning approaches are proposed to be used for breast ultrasound classification. We examine two different methods: a Convolutional Neural Network (CNN) approach and a Transfer Learning (TL) approach and we compare their performance with and without augmentation. The results confirm an overall enhancement using augmentation methods with deep learning classification methods (especially transfer learning) when evaluated on the two datasets.

Generative Adversarial Networks (GAN) Convolu-tional Neural Network (CNN) deep learning breast cancer Trans-fer Learning (TL) data augmentation ultrasound (US) imaging cancer diagnosis

Abstract doi.org/10.14569/IJACSA.2019.0100579 PDF

80

Feature Fusion for Negation Scope Detection in Sentiment Analysis: Comprehensive Analysis over Social Media

Author 1: Nikhil Kumar Singh Author 2: Deepak Singh Tomar

Negation control for sentiment analysis is essential and effective decision support system. Negation control include identification of negation cues, scope of negation and their influence within it. Negation can either shift or change the polarity score of opinionated word. This paper present a framework for feature fusion of text feature extraction, negation cue and scope detection technique for enhancing the performance of recent sen-timent classifier for negation control. Explore text feature POS, BOW and HT with negation cue and scope detection techniques for classification technique over social media data set. This paper has included the evaluation of sentiment classification (Support vector machine, Navies Bayes, Linear Regression and Random Forest) and Nine feature fusion over presented prepossessing framework. This paper yield interesting result about collective response of feature fusion for negation scope detection and clas-sification technique. Feature Fusion vector significantly increase the polarity classification accuracy of sentiment classification technique. POS with Grammatical dependency tree can detect negation with better accuracy as compared to other feature fusion.

Sentiment analysis feature fusion negation cues scope detection conjunction analysis punctuation mark gram-matical dependency tree Navies Bayes linear regression random forest SVM

Abstract doi.org/10.14569/IJACSA.2019.0100580 PDF

81

Use of Blockchain in Healthcare: A Systematic Literature Review

Author 1: Sobia Yaqoob Author 2: Muhammad Murad Khan Author 3: Ramzan Talib Author 4: Arslan Dawood Butt Author 5: Sohaib Saleem Author 6: Fatima Arif Author 7: Amna Nadeem

Blockchain is an emerging field which works on the concept of a digitally distributed ledger and consensus algorithm removing all the threats of intermediaries. Its early applications were related to the finance sector but now this concept has been extended to almost all the major areas of research includ-ing education, IoT, banking, supplychain, defense, governance, healthcare, etc. In the field of healthcare, stakeholders (provider, patient, payer, research organizations, and supply chain bearers) demand interoperability, security, authenticity, transparency, and streamlined transactions. Blockchain technology, built over the internet, has the potential to use the current healthcare data into peer to peer and interoperable manner by using a patient-centric approach eliminating the third party. Using this technology, applications can be built to manage and share secure, transparent and immutable audit trails with reduced systematic fraud. This study reviews existing literature in order to identify the major issues of various healthcare stakeholders and to explore the features of blockchain technology that could resolve identified issues. However, there are some challenges and limitations of this technology which are needed to be focused on future research.

Issues healthcare blockchain systematic review

Abstract doi.org/10.14569/IJACSA.2019.0100581 PDF

82

Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification

Author 1: Nelly Elsayed Author 2: Anthony S Maida Author 3: Magdy Bayoumi

Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We empirically show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better performance on many time series datasets without further changes to the model. Our empirical study showed that the proposed GRU-FCN model also outperforms the state-of-the-art classification performance in many univariate time series datasets without additional supporting algorithms requirement. Furthermore, since the GRU uses simpler architecture than the LSTM, it has fewer training parameters, less training time, smaller memory storage requirements, and simpler hardware implementation, compared to the LSTM-based models.

GRU-FCN LSTM fully convolutional neural net-work time series classification

Abstract doi.org/10.14569/IJACSA.2019.0100582 PDF

83

Impact Study and Evaluation of Higher Modulation Schemes on Physical Layer of Upcoming Wireless Mobile Networks

Author 1: Heba Haboobi Author 2: Mohammad R Kadhum

In this paper, the higher modulation formats (128 and 256) Quadrature Amplitude Modulation (QAM), for mod-ulation/demodulation the digital signal of the currently used Orthogonal Frequency Division Multiplexing (OFDM) system, is proposed, explored and evaluated at a wireless transmission system. The proposed modulation schemes are utilized to study the impact of adding extra bits for each transmitted sample on system performance in terms of the channel capacity, Bit Error Rate (BER) and Signal to Noise Ratio (SNR). As such, the key purpose of this research is to identify the advantages and disadvantages of using higher modulation schemes on the physical layer (PHY) of future mobile networks. In addition, the trade-off relation between the achieved bit rate and the required power of the receiver is examined in the presence of the Additive White Gaussian Noise (AWGN) and Rayleigh noise channels. Besides, the currently employed waveform (OFDM) is considered herein as an essential environment to test the effect of receiving additional complex numbers on the constellations table. Thus, investigate the ability to recognize both the phase and amplitude of intended constellations for the upcoming design of wireless transceivers. Moreover, a MATLAB simulation is employed to evaluate the proposed system mathematically and physically in an electrical back-to-back transmission system.

Orthogonal Frequency Division Multiplexing (OFDM) Quadrature Amplitude Modulation (QAM) Bit Error Rate (BER) Signal to Noise Ratio (SNR) Bandwidth (BW) Additive White Gaussian Noise (AWGN) Rayleigh noise physical layer (PHY)

Abstract doi.org/10.14569/IJACSA.2019.0100583 PDF

84

Assuring Non-fraudulent Transactions in Cash on Delivery by Introducing Double Smart Contracts

Author 1: Ngoc Tien Thanh Le Author 2: Quoc Nghiep Nguyen Author 3: Nguyen Ngoc Phien Author 4: Nghia Duong-Trung Author 5: Thai Tam Huynh Author 6: The Phuc Nguyen Author 7: Ha Xuan Son

The adoption of decentralized cryptocurrency plat-forms is growing fast, thanks to the implementation of Blockchain technology and smart contracts. It encourages the novel frame-works in a wide range of applications including finance and payment methods such as cash on delivery. However, a large number of smart contracts developed for cash on delivery suffer from fraudulent transactions which enable malicious participants to break the signed contracts without sufficient penalties. A shipper will involve in the system and place a mortgage to ensure reliability. A buyer also pledges an amount of money when making the order. Our process not only ensures the interests of a seller but also prevents a fraud shipper. The penalties will be made in two scenarios: (i) the buyer refuses to receive the commodities without any reliable reasons; and (ii) the shipper attempts to make any modification on the delivered goods during transportation. To help developers create more secure and reliable cash on delivery system, we introduce double smart contracts, a framework rooted in Blockchain technology and Ethereum, to tackle those mentioned problems. We also contribute our solution as an open source software that developers can easily add to their implementation to enhance functionality.

Cash on Delivery (COD) Blockchain smart con-tract Ethereum e-commerce online payment

Abstract doi.org/10.14569/IJACSA.2019.0100584 PDF

85

Use of Blockchain in Governance: A Systematic Literature Review

Author 1: Asad Razzaq Author 2: Muhammad Murad Khan Author 3: Ramzan Talib Author 4: Arslan Dawood Butt Author 5: Noman Hanif Author 6: Sultan Afzal Author 7: Muhammad Razeen Raouf

Blockchain is a distributed network based ledger that is secured by the methods of cryptographic proof. It enables the creation of self-executable digital contracts i.e. smart contracts. This technology is working in collaboration with major areas of research including governance, IoT, health, banking and education. It has anticipated revolutionary ways, which helps us to overcome the problems of governance such as human error, voting, privacy of data, security and food safety. In governance, there is a need to ameliorate the services and facilities with the assistance of blockchain technology. This paper aims to explore the issues of governance which can be resolved with the assistance of Blockchain features. Furthermore this paper also provides the future work directions.

Blockchain governance voting security privacy

Abstract doi.org/10.14569/IJACSA.2019.0100585 PDF

86

Swarm Robotics and Rapidly Exploring Random Graph Algorithms Applied to Environment Exploration and Path Planning

Author 1: Cindy Calderon-Arce Author 2: Rebeca Solis-Ortega

We propose an efficient scheme based on a swarm robotics approach for exploring unknown environments. The initial goal is to trace a map which is later used to find optimal paths. The algorithm minimizes distance and danger. The proposed scheme consists in three phases: exploration, mapping and path optimization. A cellular automata approach is used for the simulation of the fist two phases. For the exploration phase, a stigmergy approach is applied in order to allow for swarm communication in a implicit way. For the path planning phase a hybrid method is proposed. First an adapted Rapidly-exploring Random Graph algorithm is used and then a scalarized multiobjective technique is applied to find the shortest path.

Swarm robotics cellular automata path planning Rapidly-exploring Random Graph (RRG) scalarized multiobjective optimization

Abstract doi.org/10.14569/IJACSA.2019.0100586 PDF

87

Social Media Cyberbullying Detection using Machine Learning

Author 1: John Hani Author 2: Mohamed Nashaat Author 3: Mostafa Ahmed Author 4: Zeyad Emad Author 5: Eslam Amer Author 6: Ammar Mohammed

With the exponential increase of social media users, cyberbullying has been emerged as a form of bullying through electronic messages. Social networks provides a rich environment for bullies to uses these networks as vulnerable to attacks against victims. Given the consequences of cyberbullying on victims, it is necessary to find suitable actions to detect and prevent it. Machine learning can be helpful to detect language patterns of the bullies and hence can generate a model to automatically detect cyberbullying actions. This paper proposes a supervised machine learning approach for detecting and preventing cyberbullying. Several classifiers are used to train and recognize bullying actions. The evaluation of the proposed approach on cyberbullying dataset shows that Neural Network performs better and achieves accuracy of 92.8% and SVM achieves 90.3. Also, NN outperforms other classifiers of similar work on the same dataset.

Cyberbullying machine learning neural network

Abstract doi.org/10.14569/IJACSA.2019.0100587 PDF

88

A Blockchain-based Value Added Tax (VAT) System: Saudi Arabia as a Use-Case

Author 1: Ahmad Alkhodre Author 2: Toqeer Ali Author 3: Salman Jan Author 4: Yazed Alsaawy Author 5: Shah Khusro Author 6: Muhammad Yasar

Businesses need trust to confidently perform trade among each other. Centralized business models are the only mature solutions available to perform trades over the Internet. However, they have many problems which includes but are not limited to the fact that these create bottleneck on the server as well as requires trusted third parties. Recently, decentralized solutions have gained significant popularity and acceptance for future businesses. The wide acceptance of such systems is indeed due to the trust management among various untrusted business stakeholders. Many solutions have been proposed in this regard to provide de-centralized infrastructure for various business models. A standard solution that is acceptable to the industry is still in demand. Hyperledger umbrella Blockchain projects, that are supported by IBM and many other industry big players are gaining popularity due to its efficient and pluggable design. In this study, the author present the idea of utilizing Blockchain to design a Value-Added Tax (VAT) system for Saudi Arabia’s newly introduced tax system. The reason to select this business model for VAT is twofold. First, it provides an untampered distributed ledger, which cannot be deceived by any party. Each transaction in the system cannot go unnoticed by the smart contract. Sec-ondly, it provides a transparent record, and updates all involved parties regarding each activity performed by stakeholders. The newly proposed system will provide a transparent database of VAT transactions according to our smart contract design and at each stage of supply chain, tax will be deducted and stored on peer-to-peer network via consensus process. The author believes that the proposed solution will have significant impact on VAT collection in the Kingdom of Saudi Arabia.

VAT hyperledger blockchain consensus decen-tralized network

Abstract doi.org/10.14569/IJACSA.2019.0100588 PDF

89

Navigation Application with Safety Features

Author 1: Andrew Usama Author 2: Moustafa Waly Author 3: Habiba Elwany Author 4: Mohamed H. ElGazzar Author 5: Monica Medhat Author 6: Youssef Mobarak

In 2017, the number of car accidents that occurred was astronomically high, even though, infrastructural road sys-tems are being continuously built and renewed to make it more efficient. But a significant problem which still remains is that a staggering number of accidents is exactly what should be avoided. In order to address this issue, this paper will serve to survey and discuss some of the solutions proposed, both software and hardware, for this problem. This will include some of the implemented safety features while also exploring how to make the system more interactive and smooth to meet user needs.

Traffic safety navigation systems neural networks

Abstract doi.org/10.14569/IJACSA.2019.0100589 PDF

90

Value-Driven use Cases Triage for Embedded Systems: A Case Study of Cellular Phone

Author 1: Neunghoe Kim Author 2: Younkyu Lee Author 3: Vijayan Sugumaran Author 4: Soojin Park

A well-defined and prioritized set of use cases enables the enhancement of an entire system by focusing on more important use cases identified in the previous iteration. These use cases are given more opportunities to be refined and tested. Until now, use case prioritization has been done from a user perspective, and through balanced measurement of actors/ objects usage. Lack of cost consideration for realization, however, renders it ineffective for economic purposes. Hence, this study incorporates the ‘value’ concept, based on cost benefit analysis, in use case prioritization for embedded systems. The use case satisfaction level is used as the surrogate for ‘benefit’, and the complexity of implementation for ‘cost’. Based on the value, use cases are prioritized. As a proof-of-concept, we apply our value-based prioritization method to the development of a camera system in a cellular phone.

Value-based software engineering use case triage embedded system cost-benefit analysis

Abstract doi.org/10.14569/IJACSA.2019.0100590 PDF