		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
November 2019 | Vol. 97 No.22

Title:	INFORMATION TECHNOLOGY FOR NUMERICAL SIMULATION OF CONVECTIVE FLOWS OF A VISCOUS INCOMPRESSIBLE FLUID IN CURVILINEAR MULTIPLY CONNECTED DOMAINS
Author:	NURLAN TEMIRBEKOV, YERZHAN MALGAZHDAROV, SAYA TOKANOVA, FARIDA AMENOVA, DOSSAN BAIGEREYEV, AMANKELDY TURAROV
Abstract:	In this paper we describe a method for the numerical construction of curvilinear structured grids in doubly connected regions and numerical modeling of the convective flow of a non-uniformly heated liquid in a curvilinear coordinate system. The study is absolutely unique and conducted in accordance with modern scientific demands. Based on previous surveys and the latest findings in the study area, it brings the acute question of information technology for the numerical simulation of convective flows of a viscous incompressible fluid in curvilinear multiply connected domains to a significantly new level. The study is complex and attempts to analyze the theme thoroughly, taking into account all factors that may influence the final results. The paper presents a complete required set of multiple graphs, detailed equations and schemes in order to increase visualization of obtained results on a viscous incompressible fluid in curvilinear multiply connected domains and simplify the perception of the results for accurate scientific conclusions and further applied usage. In the numerical construction of curvilinear grids in doubly-connected domains, the implicit scheme and the method of fractional steps are used by the equidistribution method and Godunov-Thompson, and in the numerical realization of the equations of an incompressible fluid, an explicit scheme and a method of fractional steps are used. In the direction of the outer and inner boundaries, a cyclic run is used, and in the direction of the normal, a scalar run is used. Calculations were carried out for different cavity configurations, temperature regimes at the boundary. The graphs of numerical calculations of the temperature and current function are obtained. All this makes the current study an important contribution to the development of theoretical concepts and methodological approaches to the use of new information technologies in hydrodynamic studies that takes into account the specific features of the subject area, as well as the development, adaptation and approbation of tools in the process of modeling of natural and technogenic objects.
Keywords:	Computer Technology, Mathematical Modeling, Curvilinear Structured Grids, Doubly-Connected, Curvilinear Boundary
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	PERFORMANCE MEASUREMENT OF THE SECURITY SYSTEM IN XYZ WEBSITE USING CALCULATION OF CVSS BASE MATRIX
Author:	MOH SUKRON MUFAQIH, FORD LUMBAN GAOL
Abstract:	The Security vulnerability in website is one of the flaws in website that could be exploited by irresponsible party whose attack could jeopardise the website’s privacy, integrity and its availability. Without a vulnerability mapping in a website could harm and risk the data’s security, not to mention the effect on the SQL Injection that could led to a disturbance in information and data exchanges. This series of events will likely damage XYZ’s reputation in the eyes of the people, government and user and also financial implication to the company. To overcome this issues, XYZ will need to conduct an evaluation in its website security through website vulnerability test. The purpose of this test is to scale the maturity of the website security. The method that will be used in this test is through CVSS as the tool. This measurement is done using Access Vector, Attack Complexity dan Authentication as the gauge in the prioritising the handling and mitigation of the website vulnerability. The result of XYZ website is that it has 3 high level threats, 5 medium level and the rest are low level that will not be harmful to XYZ.Institution.
Keywords:	Website, Handling, Handling, CVSS, Security
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	DETERMINING VERTICAL SHELTER LOCATION BASED ON THE HEIGHT OF TSUNAMI
Author:	ANDREW KURNIAWAN VADREAS, DEFIARIANY, EEX KORNIADI, DWI WELLY SUKMA NIRAD, JUFRIADI NA’AM
Abstract:	This research maps buildings which are potential to be vertical shelter in Padang. According to the Regional Disaster Management Agency of Padang, there are 62 buildings which can be used as shelter. The parameters used to determine the buildings which can be used as vertical shelter are the building locations measured by the distance of the building to the shoreline, the capacity, the height of the building and the length of time required for tsunami evacuation. The system is made using the Election et Choix Traduisant La Realite (ELECTRE) method to determine buildings which are potential to be vertical shelter location. The system worked in Padang Utara Sub- district. The results show that 5 shelters from 8 public shelters can be used as a place for evacuation, with an estimated capacity of approximately 21,000 people.
Keywords:	Decision Support System; Vertical Shelter Location; ELECTRE Method; Tsunami Mitigation
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	THE ANALYSIS OF CURRENT STATE OF AGILE SOFTWARE DEVELOPMENT
Author:	SAMER ATAWNEH
Abstract:	The agile software development methods are studied in this paper. Agile software development methodology was formally represented to the community of software engineering through twelve principles and four core values. Agility is considered the cornerstone of the agile software development. This contrasts with the plan-driven technique that is explained in different conventional models (e.g. Waterfall). Currently, the agile development is an important development approach, which is derived from practical uses to encourage the cooperation between users and developers so that fast development processes could be supported, and to adapt with the modifications that are affecting the dynamic environment. Many agile methods are currently available in the literature with Scrum and Extreme Programming (XP) methods forming two most commonly used methods. This study demonstrates the value of applying the agile methods in developing software projects by analysing the current agile methods. The study results reveal that the agile development introduces significant benefits over conventional methodologies. However, these benefits are not compatible with all projects and situations. The results also show a decline in the interest in XP, while the interest in Scrum is increasing all the time.
Keywords:	Agile development, XP, Scrum, Adaptive software development, Crystal, Lean development
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	A NOVEL FINGERPRINT MINUTIAE BASED AUTHENTICATION FRAMEWORK FOR CLOUD SERVICES
Author:	RUTH RAMYA KALANGI , Dr. M.V.P. CHANDRA SEKHARA RAO
Abstract:	Biometric based Authentication plays a vital role for signature verification and user access control in the distributed cloud computing. Most of the traditional biometric based authentication models use single key for all cloud services authentication. Traditional biometric key based privacy preserving models depend on the static key generators for key extraction process. Limitations of traditional biometric based authentication models are number of keys, services and computational time. To resolve these issues, A Novel Fingerprint Minutiae based Authentication Framework for Cloud Data is proposed. This framework consists of fingerprint pattern extraction, integrity computation and authentication protocol for cloud service security. Experimental results are performed on Amazon AWS cloud services.
Keywords:	Fingerprint Minutiae Extraction, Cloud Services, Cloud Security, Biometrics, Hash, Authentication.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	A SURVEY OF KEY DISTRIBUTION IN THE CONTEXT OF INTERNET OF THINGS
Author:	ORIEB ABUALGHANAM, MOHAMMAD QATAWNEH, WESAM ALMOBAIDEEN
Abstract:	In recent years, with massive advancements in the Internet, the world is witnessing an evolution of smart environments facilitated by the deployment of the Internet of Things (IoT). IoT refers to a system of interrelated users and objects that are interconnected and have a significant impact on our lives. However, one of the most important challenges facing the ubiquitous adoption of IoT technology is security. In this regard, key distribution refers to the core process of setting up secure connection through a communication channel. This paper surveys the status of research until 2019 related to key distribution schemes in the context of IoT. Moreover, the classification of a key distribution is presented. In this study, we have conducted comparisons between different key distribution schemes in terms of memory storage, communication costs, and computation costs. Additionally, we propose a new taxonomy of symmetric key distribution while proposing a hybrid hierarchical architecture for the key distribution in the context of fog computing. Relevant observations and inferred recommendations are also given as one of the contribution of this paper. On the basis of these recommendations, a hybrid key distribution architecture is proposed to better enable new technologies of cloud and fog computing over IoT.
Keywords:	BIBD, Encryption, Hierarchical Architecture, Internet of Things, Key Distribution, Security,
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	DEEPFAKES: THREATS AND COUNTERMEASURES: SYSTEMATIC REVIEW
Author:	MARWAN ALBAHAR, JAMEEL ALMALKI
Abstract:	Deepfake, a machine learning-based software tool, has made it easy to alter or manipulate images and videos. Images are frequently used as evidence in investigations and in court. However, technological developments, and deepfake in particular, have potentially made these pieces of evidence unreliable. Altered images and videos are not only surprisingly convincing but are also difficult to identify as fake or real. Deepfakes have been used to blackmail, fake terrorism events, disseminate fake news, defame individuals, and to create political distress. To gain in-depth insight into the deepfake technology, the present research examines its origin and history while assessing how deepfake videos and photos are created. Moreover, the research also focuses on the impact deepfake has made on society in terms of how it has been applied. Different methods have been developed for detecting deepfakes including face detection, multimedia forensics, watermarking, and convolutional neural networks (CNNs). Each method uses machine learning, a technique from the field of artificial intelligence, to detect any kind of manipulation in photos and videos.
Keywords:	Authentication, Deepfake, Video Evidence, Artificial Intelligence
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	INTRODUCING A NEW CITIZEN-CENTRIC MODEL OF E-PARTICIPATION IN IRAQ
Author:	MUSTAFA A. A., FAIZAL M.A., AL-MANSOR BIN ABU SAID
Abstract:	The study objective is to validate and evaluate the proposed model of adopting an e-participation model for e-government in Iraq. The new integrated model was constructed throughout the utilization of variables from three main theories and models, namely, the Diffusion of Innovation theory (DOI), the Technology Acceptance Model (TAM) and Uses and Gratification theory (U&G), in addition to three ICT related constructs, namely, ICT Infrastructure, Security and Privacy. A survey was conducted and answers are analyzed from the respondents of 392 citizen participants in Iraq. As a result of this study, all hypothesis were accepted, additionally, the measurement and structural models showed a good fitness indexes. This study contributes to the body literature of e-government adoption and to the technology adoption literature in Iraq.
Keywords:	E-government, E-participation, Adoption, Information and Communication Technology, structural equation modeling (SEM),SPSS, AMOS and Survey.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	EXTRACTION KEYTERM IN WORK ORDER FOR DECISION SUPPORT
Author:	FARID SUKMANA, FAHRUR ROZI
Abstract:	Technician is actor from industry that has job to maintenance and repair all device or infrastructure in this area. The job of technician is execution work order (WO) from user that has description like problem, symptom, root cause and solution. So WO is collection of knowledge from technician. Researcher when look in deep structure of WO has a pattern that can help technician in engineering, information technology or maintenance section getting information more efficient by using them like a google as search engine for decision making. The one of process able to use it that is extraction keyterm. This concept of method like search engine to get key in the text as main idea but apply it in WO data. Previous research about WO for decision support already done, but the process is looking for pattern of data by relating problem, symptom, root cause and solution as variable. Main thinking in this research is not looking for pattern to get best solution, but how to retrieve information of WO by searching of keyterm to cluster data based on keyterm. This study using fuzzy association rule to get weighing number and candidate cluster. The result of this study is the best of setting number for minimum support to get best cluster for decision support.
Keywords:	Work Order, Keyterm, Fuzzy, Association Rule, Stemming
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	STATISTICAL VS. INFORMATION-THEORETIC SIGNAL PROPERTIES OVER FFT-OFDM
Author:	ALI S. ABOSINNEE , ZAHIR M. HUSSAIN
Abstract:	In this paper, properties of signals, such as speech and image are tested after transmission over OFDM system with 16-QAM under additive white Gaussian noise (AWGN). Noise could distorts the signals. The statistical and information-theoretic properties of signals that are transmitted through OFDM system are analyzed by similarity measures to determine which of properties stands better against noise. For image, statistical similarity such as Structural Similarity Index Method (SSIM) and 2D correlation were used; also used are the information-theoretic measures such as entropy and joint histogram. On other hand, Pearson Correlation Coefficient (PCC), Tanimoto coefficient and Mel-frequency cepstral coefficients (MFCC) were used for speech signals. Mean Squared Error (MSE) was also used as a similarity measure for both single- and dimensional signals. The coefficients of discrete wavelet transform (DWT) and the coefficients of the discrete cosine transform (DCT) are also tested over noisy FFT-OFDM for both image and speech signals. Results found that the MFCC-correlation measure is more stable under noise than other measures. Furthermore, DWT is more robust than DCT for both speech signal and image, where it gives higher similarity with original image under very low SNR.
Keywords:	Five Keywords are Required Separated By Commas (Capitalize Each Work Italic)
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	ENHANCING DATA SECURITY IN CLOUD COMPUTING USING PUBLIC KEY INFRASTRUCTURE
Author:	OUADIA ZIBOUH, ANOUAR DALLI, HILAL DRISSI
Abstract:	Cloud computing is an emerging computing paradigm which is perceived as the technological innovation that will transform future investments in information technology. This new technology is a growing trendy platform that is gaining an expanding interest, since it provides several benefits to its users by offering eﬃcient architectures that support the transmission, storage, and intensive computing of data. Meanwhile, the rapid growth of cloud computing increases the vulnerability of unauthorized disclosure and unauthorized modification. Cloud security is the major hurdle in wide adoption of cloud computing. Hence, there is a need of an appropriate security and privacy solution that provides all security services. This paper proposes and implements the public key infrastructure cryptography scheme combined with IPSec VPN to strengthen security and privacy in the cloud environment. The proposed architecture based on certificate authority that provides the service of binding X509 certificate with user’s identity, and which ensures the protection of critical data stored in cloud.
Keywords:	Cloud Computing, Cloud Security, Hash value, IPSec VPN, Public Key Infrastructure, X.509
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	AN ENHANCED GROUP MOBILITY MANAGEMENT METHOD IN WIRELESS BODY AREA NETWORKS
Author:	RADHWAN MOHAMED ABDULLAH , ALI A. ALWAN2, KAMIL G. SALIH , ZURIATI AHMAD ZUKARNAIN
Abstract:	Mobility management of wireless body area networks (WBANs) is an emerging key element in the healthcare system. The remote sensor nodes of WBAN are usually deployed on subjects’ body. Certain proxy mobile IPv6 (PMIP) methods have been recommended, however, PMIP is relatively impractical in group mobility management pertaining to WBAN. It is likely to cause enormous registration and handover interruptions. This paper presents an approach aims at overcome these limitations using improved group mobility management method. The method emphasizes on incorporation of authentication, authorization, and accounting (AAA) service into the local mobility anchor (LMA) as an alternative to independent practice. Furthermore, proxy binding update (PBU) and AAA inquiry messages are merged. Additionally, AAA response and proxy binding acknowledge (PBA) message are combined. The experiment results demonstrate that the proposed method outperforms the existing PMIP methods in terms of delay time for registration, the handover interruptions and the average signaling cost.
Keywords:	Handover Operation, Wireless Sensor Network, Mobility Management, Pmipv6, Low-Power Wireless Personal Area Networks
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	COMPARATIVE ANALYSIS OF SUPERVISED AND UNSUPERVISED LEARNING ALGORITHMS FOR ONLINE USER CONTENT SUICIDAL IDEATION DETECTION
Author:	SERGAZY NARYNOV, DANIYAR MUKHTARKHANULY, ILMURAT KERIMOV, BATYRKHAN OMAROV
Abstract:	Suicide is one of the leading causes of death in most countries around the world; it is one of the three most common causes of death in a group of young people (15-24 years old), but so far no methods have been developed for diagnosing suicidal tendencies. In this connection, the problem of developing methods for identifying people prone to suicidal behavior is becoming especially topical. One of the directions of such research is the search for typological features of the speech related to suicide using the methods of mathematical linguistics, automatic text processing and machine learning. In foreign science, the texts of people that were motivated by suicide (mainly suicide notes) are studied using methods of automatic text processing (natural language processing), machine learning methods, and models that are constructed to allow to classify whether the text is related to suicide or not. It seems obvious that in order to develop methods for identifying people who are prone to suicide, it is necessary to analyze not only suicide notes (which are usually texts of small volume), but also other texts created by people who have committed suicide. The purpose of this work is to build a model of machine learning, apply teaching methods with and without a teacher, then select the most efficient algorithm for the task to classify whether the text is connected to suicide using comparative analysis. Our research contributes to detection of depressive content that can cause suicide, and to help such people reach confident help from psychologists of national suicide preventing center in Kazakhstan. Obtaining highest result for 95% of f1-score for Random Forest (Supervised) with tf-idf vectorization model, in conclusion we may say that K-means (Unsupervised) using tf-idf shows impressive results, which is only 4% lower in f1-score and precision.
Keywords:	Random Forest, Sentiment Analysis, K-means, Machine Learning, Suicidal Ideation Detection.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	A HYBRID COMPUTATIONAL METHOD OF TRIANGULAR FUZZY NUMBER ARITHMETIC APPROACH AND TOPSIS FOR FOOD CROPS SELECTION ON DRY LAND
Author:	WIWIEN HADIKURNIAWATI, EDY WINARNO, DWI BUDI SANTOSO, PURWATININGTYAS
Abstract:	Humans often have difficulty making decisions in complex, subjective situations with many realistic choices.So it takes a systematic and organized mathematical way to evaluate choices and find the best solution to the problem. This study uses the hybrid computational method of fuzzy triangular number (TFN) and TOPSIS approaches to solve the problem. Linguistic values which are triangular fuzzy numbers are used to determine decision-makers' preferences. Implementation of the hybrid triangular fuzzy number arithmetic approach and TOPSIS method in real-life problems helps the farmer to take a correct decision of food crops from the available alternatives. The application of the proposed model can help the user in determining the most suitable food crops to be planted in certain fields with eleven land characteristics parameters.
Keywords:	Multi Attribute Decision Making, Arithmetic Approach, Triangular Fuzzy Number, Food Crops
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	CURRENT TRENDS AND RESEARCH DIRECTIONS IN THE DICTIONARY-BASED APPROACH FOR SENTIMENT LEXICON GENERATION: A SURVEY
Author:	MOHAMMAD DARWICH, SHAHRUL AZMAN MOHD NOAH, NAZLIA OMAR, NURUL AIDA OSMAN, IBRAHIM SAID AHMAD
Abstract:	Modern sentiment analysis models rely on a sentiment lexicon, which is the most essential feature that drives their performance. This resource is indispensable for, and greatly contributes to, sentiment analysis tasks. This is evident in the emergence of a large volume of research devoted to the development of automated sentiment lexicon generation models. The task of tagging sentiment-bearing words with a positive or negative connotation, and sometimes with a strength, comprises of two core approaches: the dictionary-based approach and the corpus-based approach. The former involves making use of a digital dictionary to tag words, while the latter relies on co-occurrence statistics or syntactic patterns embedded in text corpora. The end result is a linguistic resource comprising a priori information about words, across the semantic dimension of sentiment. This paper contributes to the existing literature by providing a survey on the most prominent research works that have employed lexical resources, dictionaries and thesauri for sentiment lexicon generation. We also conduct a comparative analysis on the performance of state-of-the-art models proposed for this task, and shed light on the current progress and challenges in this area.
Keywords:	Sentiment Lexicon, Opinion Lexicon, Sentiment Lexicon Generation, Sentiment Analysis, Opinion Mining
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	SPOKEN ARABIC LETTERS RECOGNITION THROUH MFCC WITH COMPARISON WITH SHORT TIME ENERGY PER FRAME
Author:	ZAHRAA M. I. ALY , 1EHAB R. MOHAMED, IBRAHIM ZEDAN
Abstract:	This article introduces a comparison between two different techniques for the selection of speech features. These features can be used for speaker recognition or speech recognition. Feature selection is very effective for recognition accuracy. A comparison between short time energy per frame and the mel frequency cepstral coefficient (MFCC) to extract the speech features is given. Neural network and Hidden Markov model are used as classifier tools. The objective of the article is to enhance the recognition rate of phonetic Arabic letters through selecting the proper speech feature. Dynamic Time Warping (DTW) technique is used to align the analogous frames from different samples of the same signal. An effective and robust method is proposed to evaluate the feature of spoken Arabic letters. This work introduces applying the Mel Frequency Cepdstral coefficient(MFCC) to extract the speech feature.The objective of the proposed system is to enhance the performance by introducing three systems which are proposed to recognize the spoken Arabic letters. The first is based on neural networks. The second is based on hidden Markov model. Third system is based on combination between neural networks and hidden Markov models. The accuracy of neural network is found to be 42% with MFCC for 84 spoken letters while with short time energy it is found to be 84.3% for 28 spoken letters. By grouping the letters into similar letters, the accuracy of feature based on short time energy reached to 98.9%.For MFCC, the hidden Markov model performance is found to be 98.5%. But for combination system based on neural network and hidden Markov models with MFCC, the accuracy of 99.25% is obtained.
Keywords:	Speech Recognition, Feature Extraction, Hidden Markov Model, Neural Networks, Dynamic Time Warping.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	RANSOMWARE DETECTION USING CLASSIFICATION METHOD AGAINST REGISTRY DATA
Author:	ASHMIN AZMAN, WARUSIA YASSIN, OTHMAN MOHD, MOHD FAIZAL ABDOLLAH, RAIHANA SYAHIRAH ABDULLAH
Abstract:	An intrusion detection system (IDS) is used to detect numerous kinds of malware attacks, and many classification methods have been introduced by the researcher to detect malware behavior. However, even though various classification method has been proposed, the detection of malware behavior remains a challenging task as the detection method focusing more on traffic data classification. Consequently, there is a lack of classification approach employed to classify Windows Registry data for malware detection. Such a situation could cause more damages if the ransomware activity intended to affect registry besides traffic. Henceforward, the objective of this paper is to study the malware behavior which targeted registry and analyzing a series of machine learning algorithm as well as identify the most accurate algorithm in the detection of malware. Thus, this paper proposes a framework for ransomware detection by using registry data as features through a number of a machine learning algorithm. Based on conducted literature, Support Vector Machine, Decision Tree, Random Forest, Jrip, and Naïve widely applied as a classification method for malware detection. The experiments have been carried out via the algorithm mentioned above against registry data that been affected by ransomware. The algorithm is capable of classifying registry data to detect ransomware activity precisely. The main contribution of this research illustrates that registry data could be examined via the proposed framework ‘Malware Registry Detection Framework (MRDF)’ specifically for malware detection. The findings of this experiment is the capability of the proposed method to identify ransomware activity and classify which machine learning algorithm come with the highest detection rate.
Keywords:	Ransomware, Malware Detection, Machine Learning, Registry, Classification
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	CONTEXT-FREE GRAMMAR FOR ASPECT-ORIENTED UML DESIGN MODELING DIAGRAMS
Author:	AWS A. MAGABLEH
Abstract:	It is well known that aspect orientation (AO) has the potential to support the continued smooth running of software programs. In AO, before developing a program that may need to be updated all the aspects (crosscutting concerns) contained therein must be meticulously assessed to ensure that a change to one or more of those aspects will not have an adverse effect on other parts of the program. To address this issue, in this paper, three main objectives are targeted. First, a formal representation for aspect-oriented unified modeling language (UML) design modeling diagrams is proposed in which context-free grammar (CFG) is used for the aspects. An aspect model encompasses pointcuts, advice, inter-model declarations and aspect precedence, as well as references the behaviors of other classes and aspects. To ensure that there is consistency in a system, the aspect-oriented UML design model of the system is converted into a CFG that consists of set of rules for all the strings that could be present in the formal language being assessed. Second, the extended Backus–Naur form (EBNF) is applied to represent the CFG rules for the aspect-oriented model. Third, the potential use of the proposed EBNF transformation for all aspect-oriented UML diagrams is investigated. This study is inspired by the results of existing research on object-oriented UML transformation using EBNF. As AO is an extension of object orientation, it seemed natural to extend the idea of using EBNF to AO and assess whether it would be beneficial in transforming aspect-oriented UML modeling diagrams.
Keywords:	Context-Free Grammar, CFG, Aspect Orientation, AO, Extended Backus–Naur Form, EBNF, Model Transformation.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	EFFICIENT DEEP LEARNING-BASED NETWORK FOR CRACK DETECTION IN PIPELINE SYSTEMS
Author:	HOANH NGUYEN, THANH QUYEN NGO
Abstract:	Crack detection is a crucial problem in many tasks such as inspection conditions of concrete pipes or tunnels, diagnosing structural damages, ensuring road safety and so on. Thus, vision-based crack detection had attracted researchers recently, and many approaches for crack detection had been proposed. However, it remains a great challenging task due to the intensity inhomogeneity of cracks and complexity of the background. Inspire by the fast development of deep convolutional neural network (CNN) in image processing recently, we propose a multi-scale deep convolutional network based on encoder-decoder architecture. More specific, our network is based on SegNet network, which is a deep convolutional encoder-decoder architecture designed for pixel-wise semantic segmentation. We first discard the softmax layer in the SegNet network, and then build enhanced modules based on the convolution feature maps from encoder and decoder network. Furthermore, we adopt the focal loss function instead of cross-entropy loss in the original SegNet network to focus on learning the hard examples and down-weighting the numerous easy negatives. Experimental results on public datasets show that our network achieves better results compared to other state-of-the-art methods on crack detection.
Keywords:	Crack Detection, Deep Learning, Convolutional Neural Network, Object Detection, Encoder-Decoder Architecture
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text

Title:	A CONCEPTUAL FRAMEWORK FOR NETWORK TRAFFIC CONTROL AND MONITORING USING ARTIFICIAL NEURAL NETWORKS
Author:	UZOMA RITA ALO , SYLVESTER I. ELE , HENRY FRIDAY NWEKE
Abstract:	Over the years, efforts have been made by various researchers to optimize Wireless area network enterprise to improve network performance with reduced cost. With necessary and appropriate network control and monitoring methods, reliable QoS of network traffic can be achieved which in turn would improve connections especially with high reliance of today businesses and commercial enterprises on fast internet. Moreover, the need for efficient network monitoring to improve quality of services have driven many companies to employ Multiprotocol Label Switching circuit for connectivity to see how to have control over traffic flow to and from branch offices in order to achieve QoS with optimize WAN enterprise. In this paper, machine learning algorithms with various backpropagation algorithms are analysed for effective network traffic control and monitoring. Specifically, the paper analyze the impact of neural network approach with various network parameters to improved network quality of service (QoS). In this case, ten different Back-propagation training algorithms were used to carryout ten different training attempts in order to determine the algorithms with the best performance. The result showed that there is a perfect correlation between the predicted values of the neural network model and the target output which implies that the model was successful in the prediction of the network traffic flow. The result also confirmed that the training algorithm of Back-Propagation was sufficient for predicting network traffic flow using the BR algorithms.
Keywords:	Network Traffic Control, Neural Network, Multilayer Perceptron, Multiprotocol Label Switching, Quality of Service
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2019 -- Vol. 97. No. 22 -- 2019
Full Text