		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
January 2021 | Vol. 99 No.01

Title:	SECURITY REQUIREMENTS TEMPLATE-BASED APPROACH TO IMPROVE THE WRITING OF COMPLETE SECURITY REQUIREMENTS
Author:	NURIDAWATI MUSTAFA, MASSILA KAMALRUDIN, SAFIAH SIDEK
Abstract:	Writing quality security requirements contributes to the success of secure software development. It has been a common practice to include security requirements in a software system after the system is defined. Thus, incorporating security requirements at a later stage of software development will increase the risks of security vulnerabilities in software development. However, the process of writing security requirements is tedious and complex. Although significant work can be found in the field of requirements elicitation, less attention has been given for writing complete security requirements. It is still a challenge and tedious process for requirements engineers (REs) to elicit and write complete security requirements that are derived from natural language. This is due to their tendency to misunderstand the real needs and the security terms used by inexperienced REs leading to incomplete security requirements. Motivated from these problems, we have developed a prototype tool, called SecureMEReq to improve the writing of complete security requirements. This tool provides four important key-features, which are (1) extraction of security requirements components from client-stakeholders; (2) validation of security requirements probability density and security requirements syntax density; (3) checking the security requirements and key-structure components; and (4) validation of completeness prioritization. To do this, we used our pattern libraries: SecLib and SRCLib to support the automation process of elicitation, especially in writing the security requirements. To evaluate our approach and tool, we have conducted completeness tests to compare the completeness of writing security requirements through the results provided by SecureMEReq and manual writing. Our evaluation results show that our prototype tool is capable to facilitate the writing of complete security requirements and useful in assisting the REs to elicit the security requirements.
Keywords:	Tool Security Requirements, Template-Based Approach, Security Requirements Completeness, Template-Based Density, Syntax Density
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	FACTORS INFLUENCING CONSUMER ATTITUDE AND CORPORATE IMAGE ON DONATION DECISIONS THROUGH CROWDFUNDING PLATFORM
Author:	ANGGRAINI JUNIA, LA MANI
Abstract:	The main purpose of this study is to examine the factors that influence the consumer attitude and corporate image in making donation decisions through crowdfunding platforms. One crowdfunding platform in Indonesia is Kitabisa.com in this platform, fundraising is done on social media Instagram, by doing one of the campaign #OrangBaik, is a fundraising campaign to collect funds and contributor with the people who matter and people who donate are given the name #OrangBaik. This study uses a quantitative approach to data collection, and uses a survey method. The research has a total sample of 100 respondents who are active followers on Instagram @kitabisacom. In managing the results, the study uses the Slovin formula to represent the entire population and uses a Likert scale to measure a person's perceptions, attitudes, or opinions on a series of statements given in the questionnaire. The collected data were processed using PLS-SEM (Partial Least Squares Structural Equation Modeling). The results of this research is that consumer attitudes and corporate image greatly influence someone in making donations to the crowd funding platform. (Clearly stated what has been identified in the research in abstract and introduction sections) (DONE)
Keywords:	Consumer Attitude, Corporate Image, Decision Of Donating, Crowdfunding, Campaign.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	IN THE PROCESS OF SOFTWARE DEVELOPMENT: AVAILABLE RESOURCES AND APPLICABLE SCENARIOS
Author:	ANAS BASSAM AL-BADAREEN, ASHRAF MOUSA SALEH, HAYFA. Y. ABUADDOUS, ODAI ENAIZAN
Abstract:	For many decades, the cost, time and quality are the main concern of software engineering. The main objective of any software organization is to produce high quality software product within a shorter time and minimum cost. Software reuse is one of the main strategies concerns about using available resources to enhance the productivity of software development and the quality of software products. It aims at using existing software products and components in the development of new software systems. However, various types of software components available in different sources are used in the reuse strategy. This makes the reuse strategy confusable and its efficiency and effectiveness debatable. Selecting unsuitable component or scenario makes the reuse inefficient and ineffective. This study discusses the types of software components, their sources, characteristics and applicable scenarios for developing and reusing these components. A dataset from the literature is used to calculate and compare the cost of reuse processes. The results show that software reuse is an efficient strategy comparing with the normal development. Although, considering the reusability of software components required extra cost to the normal development, it could efficiently save the cost of the development of new software system. Moreover, using existing software components in the development of new reusable component is the most efficient strategy, which required even less than the cost of developing normal component.
Keywords:
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	ANSWER SET PROGRAM AND STANFORD DEPENDENCY PARSER TOWARD TRANSLATE TEXT TO KNOWLEDGE REPRESENTATION
Author:	FAISAL Y. ALZYOUD,NISREEN ALSHARMAN, ABDALLAH ALTAHAN ALNUAIMI
Abstract:	Knowledge representation is a promising solution that reflects intelligent behavior in artificial systems, so a proposed method is developed in this research which links the Natural Language Processing area with Knowledge Representation area by discussing one possible solution to translate text to knowledge representation. The first step in the proposed method is to get part of speech tagging (PoS) and to extract Stanford Dependency relations for a set of sentences using Stanford parser. Second, a set of linguistic rules will be generated depending on Stanford Dependency relations with PoS to generate knowledge representation for the set of input sentences. The representations reflect deep syntax and grammatical relations between words in sentences. By using theses representations, we can express the structure of the text, and distinguish between the events and their environment in the text. Answer set programming (ASP) is used to implement these linguistic rules. ASP programs consist of rules that are the same as Prolog rules which reflect computational mechanisms that used to create the fast satisfiability solvers for propositional logic, the proposed approach was tested using different metrics and compared with other works using the same dataset, and the obtained results are promising.
Keywords:	Answer Set Programming (ASP), Information Retrieval (IR), Natural Language Processing (NLP), Part of Speech Tagging (PoS), Question Answering (QA)
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	UNDERGROUND OBJECT DETECTION BASED ON RADIO PROPAGATION CHARACTERISTICS
Author:	SUHERMAN, ERWIN WIJAYANTO, ALI HANAFIAH RAMBE, NAEMAH MUBARAKAH, YULIANTA SIREGAR, MARWAN AL-AKAIDI
Abstract:	Underground object detection is useful to explore underground resources as well as to monitor underground infrastructure. Underground object detection has been employed for mineral exploration, archeological material finding and underground fault detection. Existing systems usually employ the ground penetration radar (GPR) that makes use radio signal reflection. GPR weakness is that the device relies only on a single point of signal receptions that minimize the scope of detection. This paper proposes multipoint radio receptions for underground object detection based on the received signals instead of the reflected ones. The proposed system was initially tested experimentally for bandwidth range of 97 MHz to 130 MHz which results error shifting from the employed model about 50.33% at frequency 130.762 MHz, 17.58% at 109.818 MHz and 13.38% at 97.335 MHz. Method of finding the best frequency is then developed by employing gradient comparison. Higher frequencies were chosen from 500 MHz to 1 GHz as these frequency results worse losses to ensure experiments were conducted in the worst condition. The analysis found that 537.69 MHz is the best frequency for the frequency range. In order to reconstruct the detected object, the number of multipath propagations is then determined. The object detections were then measured based on the supervised and unsupervised techniques. The supervised method exerted better precision compared to the unsupervised method by at least 30% with the detected object reducing the received signal up to 1.86 dBm or 2.68% in average.
Keywords:	Underground object detection, radio propagation losses, propagation model
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	P2P ISLAMIC INVESTMENTS USING BLOCKCHAIN, SMART CONTRACT AND E-NEGOTIATION
Author:	HASAN AL-SAKRAN, ONS AL-SHAMAILEH
Abstract:	Blockchain is receiving an increasing attention from industry and academia as a breakthrough technology that could provide enormous benefits to different sectors. Financial sector is one of those sectors that started to consider applying blockchain. However, it is still in its initial stages. The objective of this paper is to apply blockchain and smart contract technologies in managing investments that implement real Islamic investment policy (profit- loss-sharing agreement), this will result in easier, faster, secure and transparent investment transactions to both investors and entrepreneurs (or businesses). This work proposes a design of middleware infrastructure that implements the real Islamic investment policy (profit-loss-sharing rate) called Musharakah (joint venture), where investors and entrepreneurs share a pre-agreed percentage of profit or loss from the financed project. The platform acts as a trusted third party without the need for another mediator; it will help both investors and entrepreneurs negotiate their terms.
Keywords:	Peer-To-Peer Investment, E-Negotiation, Blockchain, Smart Contract, Islamic Profit-Loss-Sharing Agreement.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	APPLICATION OF ENSEMBLE ARIMA, ANFIS FOR CONSTRUCTING MODEL OF GARLIC PRICE DATA IN SEMARANG
Author:	TARNO TARNO, DI ASIH I MARUDDANI, RITA RAHMAWATI
Abstract:	This research was proposed for constructing the predictive model of commodity price data. The classical model such as Autoregressive Integrated Moving Average (ARIMA) and also machine learning model such Adaptive Neuro-Fuzzy Inference System (ANFIS) have been implemented in various field of time series analysis. This research is focused on constructing ARIMA, ANFIS and their combination or ensemble ARIMA-ANFIS. The main problem of combination is determining the weight of each vector predicted values which obtained from related models. In this research, the weight of each model were determined by variance-covariance approach and Lagrange Multiplier optimization, while in classical studies weight of each model was determined by averaging of predicted values. The main issue of this research is how to determine the weight of vector predicted values by using variance-covariance approach for constructing the ensemble ARIMA-ANFIS. The daily data of garlic price in Semarang collected from January 2019 to August 2019 were used as case studies. ARIMA, ANFIS and ensemble ARIMA-ANFIS were implemented for predicting data. ARIMA individual, ANFIS individual, ensemble model by averaging and ensemble model by weighting resulted high accuracy for predicting. The combination of ARIMA(1,0,0)-ARCH(1) and ANFIS (with lag-1, lag-2 as inputs and 2 MFs) is the best model for forecasting garlic price data in Semarang. The MAPE values of all models were less than 5% which had shown a good performance for forecasting.
Keywords:	ARIMA, ANFIS, Ensemble, Garlic Price Data
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	ON THE POSSIBILITY OF IMPLEMENTING ARTIFICIAL INTELLIGENCE SYSTEMS BASED ON ERROR-CORRECTING CODE ALGORITHMS
Author:	AKHAT S BAKIROV, IBRAGIM E SULEIMENOV
Abstract:	A new approach to the implementation of artificial intelligence systems is proposed, based on an analogy with the theory of error-correcting coding, as well as on the philosophical interpretation of intelligence as an information processing system that provides, first of all, its compression, for example, by reducing some complex digital image to a set of classification features. The approach is based on the expansion of the binary sequence into a fuzzy Fourier series, implying that the expansion approximates the original function up to a certain number of permissible deviations. This solves a problem similar to that which artificial neural networks solve, leading the recognizable image to the image from the original training set. The analogs of the images that make up the training sample are functions that form the basis for the expansion of the binary sequence into a fuzzy Fourier series and/or their combination.
Keywords:	Artificial Intelligence, Artificial Neural Networks, Error-correcting Codes, Dialectical Positivism
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	ANALYSIS OF E-COMMERCE CUSTOMER BEHAVIOR: A THEORY OF PLANNED BEHAVIOR APPROACH
Author:	EMRINALDI NUR D.P., LEDY SHAKINA GUSRAFANI
Abstract:	This research aims to examine the determinant factors of e-commerce customer behavior based on the theory of planned behavior. The research sample consists of 216 respondents who use the internet, have an interest in e-commerce or information technology, and already make transactions in e-commerce. Determinant variables of e-commerce customer behavior are safety, trust, service quality, risk perception, attitude, subjective norm, perceived behavioral control, and intention. Analysis data uses partial least square. Based on path analysis, safety and trust can make risk perception lower. Trust also can build a positive attitude for e-commerce customers. Positive attitude, higher behavioral control, and strong normative norm lead to higher intention to do e-commerce transactions. At last, the intention to do e-commerce transactions executed by the customer to buy and pay the product online. On the other hand, there is no effect of service quality on risk perception and no effect of risk perception on intention. This research has implications for e-commerce companies to improve website safety to get customer trust and lower risk.
Keywords:	Customer Behavior, E-commerce, Theory of Planned Behavior
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	AN ADVANTAGE OPTIMIZATION FOR PROFILING BUSINESS METRICS COMPETITIVE WITH ROBUST NONPARAMETRIC REGRESSION
Author:	MARISCHA ELVENY, MAHYUDDIN KM NASUTION, MUHAMMAD ZARLIS, SYAHRIL EFENDI
Abstract:	Business Intelligence can be used to support various business decisions from operational to strategic. Various new ways have been used to make progress, one of which is with electronic-based businesses, but with a large number of variations, business vulnerabilities are also increasingly difficult to anticipate. To keep up with the development of the company, it is necessary to optimize the metrics for the business. The purpose of optimization is to find the minimum or maximum value of a problem that occurs, whether the value of a company produces the desired results or vice versa. The reason for the improvement is to find a basis or estimate of the difficulty that occurs, regardless of whether the organization's estimate provides an ideal result or vice versa., where the outliers obtained are one of the parameters that can be considered in achieving profit. In this study, the Robust CMARS (Conic Multivariate Adaptive Regression Spline) was used where CMARS can manage the existing multivariate in the data and use a robust approach in handling uncertainty outliers in the data. So that the results achieved by RCMARS are in the form of a maximum value of the basis of the functions BF11, BF12, and BF13 with a maximum of 14.06% outliers.
Keywords:	Business Intelligence, Optimization, Customer Profiles, Business Metrics, Robust Nonparametric Regression, RCMARS.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	APPLICATION OF NEURAL NETWORK ALGORITHMS AND NAIVE BAYES FOR TEXT CLASSIFICATION
Author:	VADYM S. YAREMENKO, WALERY S. ROGOZA, VLADYSLAV I. SPITKOVSKYI
Abstract:	Neural network algorithms and probabilistic classifiers applied for text data set processing were analyzed. Results indicated advantages of architecture of recurrent and convolutional neural networks, deep learning neural network algorithms and Naive Bayes classifier considering accuracy of classification and processing speed of large data volumes. Classification algorithms’ and appropriate mathematical models’ development principles were generalized. Mathematical techniques are based on representing classification accuracy criteria, text processing speed in form of objective functions, and key parameters of neural network algorithms and probabilistic classifiers, as well as features of organization and volume of input data as objective function arguments. Mathematical modelling allowed identifying shortcomings of certain types of neural network and probabilistic classifiers limiting their scope. Algorithms based on the Naive Bayes classifier slowly analyzed large data sets, which limits their use. Working with neural network algorithms, features of the procedure for learning process optimization depending on type of neural network were outlined; approaches to optimization of deep and shallow neural network architecture were developed. Thereby analysis of efficiency of algorithms for machine classification of text blocks is proved to be relevant for solving fundamental problem of building artificial intelligence, and specific problems of real time processing of large volumes of text data
Keywords:	Text Data, Recurrent Neural Network, Convolutional Neural Network, Deep Neural Network
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	A NOVEL BAT ALGORITHM FOR DYNAMIC ECONOMIC POWER DISPATCH WITH PROHIBITED OPERATING ZONES
Author:	RUDI KURNIANTO, HARDIANSYAH
Abstract:	This paper proposes a new meta-heuristic search algorithm, called Novel Bat Algorithm (NBA). The proposed algorithm combines the bats’ habitat selection and their self-adaptive compensation for Doppler effects in echoes into the basic bat algorithm (BA). The selection of bat habitats is modeled as an option between quantum behavior and mechanical behavior. The effectiveness and feasibility of the proposed method are demonstrated by two real power systems and compared with other optimization algorithms reported in the literature. Many practical constraints of generators such as ramp rate limits, prohibited operating zones, and transmission losses are considered. The new algorithm is implemented for solving the dynamic economic dispatch (DED) problem so as to minimize the total generation cost when considering the linear and non-linear constraints. In order to validate the proposed algorithm, it is applied to two cases with 6-unit and 15-unit power systems for a 24-hour time interval, respectively. The results show that the proposed algorithm indeed produce a more optimal solution in both cases when compared to the results of other optimization algorithms reported in the literature.
Keywords:	Dynaic economic dispatch, novel bat algorithm, ramp rate limits, prohibited operating zones
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	A NEW ASSOCIATION CLASSIFICATION BASED METHOD FOR DETECTING PHISHING WEBSITES
Author:	FAISAL ABURUB, WAEL HADI
Abstract:	Impacting businesses across the world, phishing remains today to be a serious problem: due to anonymous access to personal details, businesses and their consumers deal with the problems materialised out of fishing attacks, huge financial loss being one of these problems. Because of this, phishing needs to be identified and dealt with efficiently using intrusion detection techniques; such mechanisms are yet to be used. It is within this paper that, with the use of a newly-arisen method (Phishing Multi-Class, founded on the grounds of Association Rule) we will study the issue of predicting phishing websites. So as to weigh up the successful use of data mining algorithms using a publicly available dataset involving 10,068 incidents of legitimate and phishing websites, two experimental studies were conducted, in which the classifier model was built. In the first of these two studies, the capability of PMCAR (Phishing Multi-Class Association Rule) compared to three associative classification algorithms (CBA, MCAR, and FACA) was examined; additionally, five benchmark algorithms (SVM, LR, DT, and ANN) were assessed in the second experiment, so as to generalise the competence of utilising data mining for resolving the phishing websites detection issue. As a result of conducting these experiments, all data mining algorithms that were evaluated predict phishing websites with decent classification rate; and so we can conclude that, when looking to tackle the issue of predicting phishing websites, these can be successful methods.
Keywords:	Phishing Websites, Associative Classification, Phishing Multi-Class
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	INTEGRATING DATA WAREHOUSE AND MACHINE LEARNING TO PREDICT ON COVID-19 PANDEMIC EMPIRICAL DATA
Author:	HASAN HASHIM, EL-SAYED ATLAM, 1MALIK ALMALIKI, RASHA EL-AGAMY, M. M. EL-SHARKASY, GUESH DAGNEW, IBRAHIM GAD, OSAMA GHONEIM
Abstract:	The world has recently been plagued by the pandemic of Corona Virus Disease 2019 (COVID-19). Since it is reported in Wuhan city of China, on the 8th of December 2019, the COVID-19 invaded every country around the world. As of October 24th, 2020, a total of 42,549,383 confirmed cases of COVID-19 were officially announced and the death toll was 1,150,163. Globally, huge volumes of datasets are generated regarding COVID-19 pandemic to open new research arena for machine learning and artificial intelligence researchers. In this work, an integration of data warehouse with deep learning approach, namely LSTM model, is introduced to predict the spread of the COVID-19 in selected countries. We present the design and development of COVID-warehouse, a data warehouse that integrates and stores the COVID-19 data made available daily by different countries. The basic idea of the framework is to use a COVID19 time-series dataset for analysis by machine learning models to make forecasting of future trend based on present values. Ultimately, the proposed prediction model can be applied to predict for other countries as the nature of the virus is the same everywhere. In terms of R2 metric, the experimental results of the decision tree model outperforms other models for recovery cases compared with confirmed and death cases. Recovery cases have a R2 of 0.996011, death cases have a R2 of 0.993124 and confirmed cases have a R2 of 0.991676. Finally, our results emphasize the importance of enforcing the public health advice of social distancing as well as applying the infection control measures to combat COVID-19 before it becomes too late.
Keywords:	COVID-19 Virus, Infection control, Artificial intelligence, Data Warehouse, Deep Learning Model, Prediction.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	MULTIMODAL PIPELINE FOR QUANTITATIVE METRICS ESTIMATION OF BRAIN TISSUE MICROSTRUCTURE USING DMRI DATA
Author:	ABDERRAZEK ZERAII , AMINE BEN SLAMA, SABRI BARBARIA, MOKHTAR MARS, CYRINE DRISSI, TAREK KRAIEM
Abstract:	White matter changes in the corticospinal tract (CST) contribute to executive dysfunction in the context of motor control of the body and limbs. The objectives of this study remained to characterize the corticospinal tract using different models for the diffusion MRI signal. We employed the DTI (diffusion tensor imaging) and Multi-Shell Multi-Tissue Constrained Spherical Deconvolution to estimate a multitissue orientation distribution function (ODF) analysis of 10 healthy Subjects. In this paper, our goal is to determine the sensitivity of fibre orientation distribution (FOD) compared to the standard Diffusion Tensor Imaging (DTI) approach and select the FOD-DEC difference existing in the two regions of interest (PLIC and PONS). For each subject, biophysical values were calculated for two Regions of Interest (the posterior limb of the internal capsule and the anterior pons) at two b-value (b=1000s/mm² and b=3000 s/mm²). Experimental results showed that the pons region more accurately predict CST integrity than the posterior limb of internal capsule using a b-value equal to 1000 s/mm². FA and ADC are a promising metric for clinical applications especially when we rely on qualitative data from the CSD model.
Keywords:	MRI, Diffusion Tensor Imaging, fibre orientation distribution, Multi-Shell Multi-Tissue, Constrained Spherical Deconvolution (MSMT-CSD).
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	A NOVEL PENDING INTEREST TABLE SHARING SCHEME USING NEURO FUZZY LOGIC FOR NAMED DATA NETWORKING COMMUNICATION
Author:	BASSAM A. Y. ALQARALLEH, MALEK Z. ALKSASBEH, AHMAD H. AL-OMARI
Abstract:	At present times, Information-Centric Networking (ICN) becomes familiar as a distinct standard for next-generation Internet and exhibits the significance of restoring the present host-centric model. The data transmission in ICN is based on the name of the contents instead of the addresses of the host. Besides, named data networking (NDN) is another hot research area, which permits the user to request data with no earlier details relevant to the hosting entity. Though earlier studies on NDN offers mobility and security over the classical Internet, it suffers from the problem of pending interest table (PIT) management. Therefore, a proficient PIT management strategy is essential for the utilization of PIT memory space. For effective management of the existing PIT memory space and improvise the cache usage, a novel PIT sharing strategy using neuro fuzzy logic called NFPIT is presented. In order to select an optimal friendly node (FN) for the requestor node (RN) which has less amount of PIT space, neuro fuzzy method will be executed. In addition, we employ a deep learning model by employing the Convolution Neural Network (CNN) for rule generation. The proposed method is simulated using NS3 simulator and the simulation outcome has been experimented under different aspects. The experimental values ensure the superiority of the NFPIT method by achieving a maximum cache hit ratio of 56.4%, content diversity of 67% with less content delivery time of 7.26ms.
Keywords:	Information-Centric Networking, Named Data Networking, Pending Interest Table Sharing, Neuro Fuzzy, Cache Hit Ratio.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	ENHANCED TEXT LINE SEGMENTATION AND SKEW ESTIMATION FOR HANDWRITTEN KANNADA DOCUMENT
Author:	SHAKUNTHALA B S, Dr. C S PILLAI
Abstract:	Abstract. When Handwritten Kannada document undergoes text line segmentation, the process is referred to as Text line segmentation and skew correction. This is quite essential for the HCRS (Human Character Recognition System). The process of text line segmentation and skew estimation tends to be quiet challenging during document analysis. The proposed system presents improvised text-line segmentation along with skew estimation for which the handwritten Kannada document forms the dataset. Following are the three methods for carrying out preprocessing, namely: (i) filtering (ii) gray scale conversion and (ii) Binarization. The ESLD (Enhanced Supervised Learning Distance) algorithm is being adopted for the assessment of distance amidst text lines and G_Clustering aids in grouping of words or the Connected Components. Also, by computing skew angle with respect to the gap, Skew estimation can be performed. It’s elucidated from the output that the proposed system exhibits higher performance.
Keywords:	Segmentation, Skew Correction, Filtering, Gray Scale, Binarization.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	FUZZY ANALYTICAL HIERARCHY PROCESS (FAHP) USING GEOMETRIC MEAN METHOD TO SELECT BEST PROCESSING FRAMEWORK ADEQUATE TO BIG DATA
Author:	SALY EID HELMY, GAMAL H.ELADL, MOHAMED EISA
Abstract:	Big data is considered a hotspot, as all organizations realize the importance of their big data to gain insights that help organizations develop and understand consumer requirements. Big data needs large storage capacity and strong processing frameworks in order to clean, process, and analyze it. Fortunately, cloud computing offers many services and processing frameworks that facilitate the storage and processing of big data. But the issue here is how to choose the best suited processing framework for big data of financial services. The best processing framework is chosen based on big data criteria and financial services requirements. We used MCDM methods to solve this decision problem and evaluated five big data processing frameworks (Spark, Hadoop, Flink, Storm, and Samza) based on twelve criteria. These criteria were collected from previous researches. Analytical hierarchy process (AHP) is a powerful and simple method of MCDM methods, but many of researchers believe that it has some weakness due to some uncertainty issues. Many researchers have preferred to combine fuzzy set theory with AHP to solve the uncertainty problem. This work introduces fuzzy AHP using geometric mean method in cloud service selection based-problem. The results show that Hadoop framework has the highest level of security, availability, scalability,and compatability, but has the heighest cost. Spark has the highest storage capacity , speed, and best processing mode at lower cost. Flink has the best usability, and processing. Storm has the best performance, sustainability, and is the cheapest. The validity of our results and the robustness of our hybird proposal were aproved by applying sensitivity analysis.
Keywords:	Big Data, Cloud Computing, MCDM, Fuzzy Set Theory, AHP, Geometric Mean Method, Hadoop, Spark, Storm, Flink, and Samza.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	A FIREWALL-ADVERSARIAL TESTING APPROACH FOR SOFTWARE DEFINED NETWORKS
Author:	RAMI MALKAWI, IZZAT ALSMADI, AHMED ALEROUD, PAVEL PETROV
Abstract:	Software Defined Networks (SDN) recently evolves to give more roles to software in network control and management. It is feared that such significant roles may risk those networks in terms of reliability and security. As a new architecture, thorough testing and evaluation should take place to ensure that those networks are robust and reliable. In this paper, we focused on testing firewall modules built on top of SDN. We modeled typical interactions between those modules and the network based on flow and firewall rules. We believe that, in future, all security controls including firewalls should be deployed as software services, created in real time, as instances and deployed without any human intervention. This paper describes also an approach that generates synthetic attacks that can target SDNs using an Adversarial approach. It can be used to create models that test SDNs to detect different attack variations. It is based on the most recent OpenFlow models/algorithms and it utilizes similarity with known attack patterns to identify attacks. Such synthesized variations of at-tack signatures are shown to attack SDNs using adversarial approaches.
Keywords:	SDN, OpenFlow, Software evaluation, Model based Testing.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text

Title:	USABILITY EVALUATION DIMENSIONS OF MOBILE HEALTH APPLICATION FOR ELDERLY: A SYSTEMATIC REVIEW
Author:	ERICK KURNIAWAN,NORASIKEN BAKAR,SAZILAH SALAM, RESTYANDITO
Abstract:	With the increase in the elderly population as a group of potential mHealth users, the need for mHealth applications increases to help overcome the limitations of elderly users. The challenges caused by aging factors in computer use are widely recognized. However, usability studies show that mHealth is still not suitably designed for elderly users. To improve mHealth design aimed at elderly users, we need usability evaluation dimensions that are in accordance with elderly characteristics to identify usability problems in mHealth applications.This study conducting Systematic Literature Review (SLR) using PRISMA to identify the challenges faced by the elderly and usability dimensions that are most widely used to evaluate mHealth applications for Elderly users, then select and propose usability dimensions that match with the elderly characteristics. Six key categories of elderly challenge influencing usability of mHealth and nineteen most-used usability dimensions on mHealth applications were identified. Nine usability dimensions are most suitable for evaluating mHealth applications for the elderly were also selected. The model, however, is incomplete without evaluation criteria and metrics. Criteria and metrics will be developed as a complete model for the next phase of this study.
Keywords:	Usability Evaluation, Usability Dimension, mHealth, mHealth for Elderly.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2021 -- Vol. 99. No. 01 -- 2021
Full Text