		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 Informtion Technology
November 2020 | Vol. 98 No.21

Title:	RELIABILITY AND PERFORMANCE METHOD OF CORRECTING ERRORS TRANSMISSION OF LOW DENSITY PARITY CHECK CODE USING THE BIT FLIPPING ALGORITHM
Author:	LAGRINI LAKBIR, ELGHAYYATY MOHAMED, El HATI IDRISSI ANAS, HADJOUJA ADELKADER, MOULAY BRAHIM SEDRA
Abstract:	The low density parity check (LDPC) code invented by Robber Gallager in 1962, and rediscovered by Mackey in 1995, after The discovery of turbo codes in 1993 by C. Berrou, A. Glavieux, and P. Thitimajshima at the International Conference of Communication in Florida has revolutionized the means of communication. This code is one of the best performance codes in the correction of transmission errors. The purpose of this article is to study two algorithms, the first algorithm is based on the addition of another specialty to the control matrix such that the control matrix becomes at the same time an error corrector, in order to decode information without iteration compared to the bit flipping decoding algorithm based. This proposed can be applied to LDPC code regular or irregular. the result of this algorithm allows to find the position of variable noed deformed during the transmission without doing any iteration and without using any additional tool, but in this method the response exists in the control matrix, so that each syndrome found represents a column of the control matrix and each column linked by a noed variable denoted ri with i between 1 and n. The principle for the second algorithm is to write the parity equations in a table which will facilitate the detection and correction of errors without doing the iterations, and for this algorithm, I did the simulation using a hardware description language using Quartus software tools to confirm the reliability and performance of this method. The result for second algorithm, for example the LDPC code of the matrix control H (n, k), the number of syndromes which we can find is 2k-1 and for each syndrome different from zero, we can do almost four iterations for each nonzero syndrome, which give the number 4x(2k-1) iterations in totality.
Keywords:	Coding, Decoding Of LDPC Code, Control Matrix.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	MODELS AND ALGORITHMS FOR ENSURING FUNCTIONAL STABILITY AND CYBERSECURITY OF VIRTUAL CLOUD RESOURCES
Author:	ALIMSEITOVA ZH., ADRANOVA A., AKHMETOV B., LAKHNO V., ZHILKISHBAYEVA G., SMIRNOV O.A.
Abstract:	The article proposes a model that describes the effects of cyber attacks on virtual cloud resources (VCR) of various informatization objects (IO). The developed model served as the basis for an algorithm that allows to analyze threats in the IO cloud environment. The proposed algorithm in this work allows to obtain attack routes, that is achieved by synthesizing the attack graph and the graph of the correlative alert about the state of the IO virtual cloud environment (VCE). There is proposed a model for assessing the state of VCR. This model has become the basis for the algorithm for choosing countermeasures to protect the IO VCE. Ultimately, the proposed solutions allow to obtain a calculated indicator of functional stability (FS) and cybersecurity (CS) of IO virtual resources. And then to form countermeasures for increasing the FS and CS index of IO virtual cloud resources. During the research, there was developed a technique for providing FS and VCE CS based on software-configured networks. The developed technique allows to focus the attention of the protection side on increasing the FS and CS of virtual machines on the basis of the attacks detection and subsequent reconfiguration of virtual networks in VCE.
Keywords:	Attack Graph, Correlation Graph, Software-Configured Network, Virtual Cloud Environment
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	HOW TECHNOLOGY CAN MITIGATE THE IMPACT OF COVID 19 ON EDUCATION? A CASE STUDY OF SAUDI ELECTRONIC UNIVERSITY (SEU)
Author:	THAMER ALHUSSAIN
Abstract:	This paper discusses a case study research approach with the aim to find out how technology can mitigate the impact of COVID 19 on Education. It outlines how Saudi Electronic University (SEU) used information and communication technologies (ICTs) for the purpose of education before COVID-19, which help mitigate the impact of COVID 19. Data for this investigation include real information from the learning management system for six weeks before the crisis, which evaluated and compared with the following six weeks after switching to fully online given education and learning because of the pandemic. The findings indicate that the adoption of blended learning method that involves educational technology facilitate the shift to fully online and greatly mitigate the impact of COVID 19 on learning environment.
Keywords:	COVID 19; Technology; Education; Saudi Electronic University
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	RISK ANALYSIS OF HUMAN RESOURCE INFORMATION SYSTEMS USING COBIT 5
Author:	EVARISTUS DIDIK MADYATMADJA, LYDIA LILIANA, JOHANES FERNANDES ANDRY, HENDY TANNADY
Abstract:	Information technology is an important key in the company because it offers efficiency and authority to achieve goals. This can be seen from the development of technology in pharmaceutical companies in Jakarta that use Human Resource Information Systems (HRIS). HRIS provides services in the form of management information for all employees in the company. Currently, not many have conducted risk analysis on the information systems used. On the one hand, information systems have become a part that is difficult to access in almost every business process in the company. The use of technology can present threats that can affect applicable risks. Therefore, companies need to pay attention to risk management to anticipate the dangers that can occur. The study uses the COBIT 5 framework to analyze the risks that occur in the company by using the domain Monitor, Evaluate, Assessment MEA02 because it is related to the transparency process for the main stakeholders regarding the appropriateness of the internal control system so that it can ensure the achievement of company goals and objectives and provide sufficient knowledge about the system risk of human resource information. The research starts from references, determines the domains and processes used, analyzes HRIS, compiles interview lists, analyzes interview results, calculates process capability models from HRIS implementation and analyzes HRIS to risk management. The output of this study is the acquisition of risk management documents in pharmaceutical companies that contain lists of risks, level risks, impacts, risks, and the results of recommendations using the MEA02 domain from COBIT 5 and a SWOT analysis.
Keywords:	COBIT 5, Monitor-Evaluate-Assess (MEA), Human Resource Information System (HRIS).
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	MODEL FOR BUSINESS-IT ALIGNMENT: A CASE OF MALAYSIAN PUBLIC UNIVERSITIES
Author:	ESMADI ABU ABU SEMAN, TAMRIN AMBOALA, IZA AZURA AHMAD BAHAR, NOR AZIATI ABDUL HAMID, MOHAMMAD SHARF AL-QDAH
Abstract:	Business and Information Technology (IT) alignment is defined as applying IT in an appropriate and timely way, in harmony with business strategies, goals and needs. One important issue in business–IT alignment study is the absence of alignment. Findings indicate that there are many factors/variables that consistently enhance business-IT alignment. By identifying factors to achieve business-IT alignment, the problem on the absence of alignment could be addressed. Due to the complexity of business-IT alignment, there is possibility that successful alignment focuses on managing specific alignment dimension by investigating factors that encourage particular dimension. Literature on alignment discovered that there seems to be confusion in clarifying the business-IT alignment concept. Based on this gap, this research examined problem, issues on alignment, identified, analyzed, and discussed factors affecting alignment, then categorized the constructs identified into dimensions and proposed a model on factors influencing alignment in universities. The model developed is based on Resource Based View, Knowledge Based View, Uncertainty Reduction and Contingency theory and business-IT alignment models which were developed in prior studies in order to examine the influence of strategic, structural, social and cultural on business-IT alignment in public universities in Malaysia. 18 hypotheses have been developed framed on three research questions. The data for analysis was collected via a structured questionnaire survey that yielded 148 usable questionnaires from IT managers/executives and top administrators in 20 public universities who are involved in IT strategic planning. Data were analyzed using SPSS for descriptive and demographic analysis, while the model that was developed was validated using Structural Equation Modeling analysis (SEM). The result of the goodness of fit index satisfies the recommended value while 18 hypotheses were supported. The validation of results revealed that the entire model fit is appropriate and indicated the stability of the theory used in building the Business IT alignment model. The findings showed business-IT alignment is significantly affected by the four sets of factors: strategic, structural, social and cultural. Findings from this study provide insights to enable university’s top administrators to develop more comprehensive action plans for achieving greater business-IT strategic alignment, and for translating alignment into enhanced IT effects on university’s performance.
Keywords:	Alignment, Business-IT alignment, Strategic planning, Alignment model, IT strategy.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	CLASSIFICATION OF RICE IMAGE VARIETIES IN KARAWANG CITY USING SUPPORT VECTOR MACHINE ALGORITHM
Author:	JAJAM HAERUL JAMAN , AYYU NUR BAIT , ARIES SUHARSO3, GARNO , AGUNG SUSILO YUDA IRAWAN , AND INDAH PURNAMA DEWI
Abstract:	Rice is a staple food in Indonesia. Rice varieties are very diverse for example such as Inpari, Inpago, Inpara, and others. There are more varieties in this type such as Inpari which has mekongga varieties that are quite popular in Karawang city even the distribution is almost in every city in indoensia. The many rice varieties that are present, causing the problem of mixing the types of rice varieties on the market. Digital image processing can be a solution that classifies rice based on images that can be a solution to recognize types of rice varieties by applying the Support Vector Machine (SVM) algorithm. The purpose of this research is to differentiate mekongga rice varieties from other varieties. so that consumers can easily set it up. This research was conducted using a 70 image dataset. Past several stages such as pre-processing, image segmentation, feature extraction, classification with the Support Vector Machine (SVM) algorithm, then evaluation. The classification of test data from 35 images yields an accuracy of 94.28%.
Keywords:	Rice, Digital Image Processing, Support Vector Machine (SVM).
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	APPLYING NATURAL LANGUAGE PROCESSING TECHNIQUES FOR SUICIDAL CONTENT DETECTION IN SOCIAL MEDIA
Author:	SERGAZY NARYNOV, KANAT KOZHAKHMET, DANIYAR MUKHTARKHANULY, NURBEK SAPARKHOJAYEV
Abstract:	This research paper discusses computer solutions in the field of detecting and analyzing Internet texts containing suicidal and depressive content in social networks. Experience in the analysis and detection of suicidal messages, self-harming nature, accumulated by research teams in different countries, provides an opportunity to assess progress in this area and the difficulties that must be taken into account when developing solutions for the local Internet content.
Keywords:	Natural Language Processing, Suicidal Content, Suicidal Ideation Detection, Machine Learning, Social Media
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	REAL-TIME VEHICLE AND PEDESTRIAN DETECTION ON EMBEDDED PLATFORMS
Author:	HOANH NGUYEN
Abstract:	Real-time pedestrian and vehicle detection on embedded devices play crucial role in many intelligent transport systems because of the limited hardware in autonomous driving devices. This paper presents a lightweight two-stage detector for real-time pedestrian and vehicle detection. The proposed detector includes a lightweight backbone at first stage and a lightweight detection network at second stage. The proposed lightweight backbone is designed based on the ShuffleNetv2 network, which achieves the best accuracy in very limited computational budgets. The proposed lightweight detection network consists of an improved R-CNN to improve the computational cost and a separable convolution module to increase the receptive field. In addition, a lightweight region proposal network is used to improve both accuracy and inference speed of proposals generation stage. The lightweight region proposal network includes pointwise convolution to reduce the number of channels of input features and dilated convolution to enlarge the receptive field. The KITTI dataset is adopted to evaluate the effectiveness of the proposed detector. Experimental results on recent embedded devices, including Raspberry Pi 4 and NVIDIA Jetson TX2, and GPU-based computer show that the proposed method achieves a much better trade-off between accuracy and efficiency compared with recent methods and meets the requirement for real-time object detection on embedded platforms.
Keywords:	Vehicle Detection, Pedestrian Detection, Convolutional Neural Network, Embedded Platforms, Real-time Detection, Lightweight Network
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	MEASURING CITIZEN READINESS TO ADOPT ELECTRONIC CITIZEN RELATIONSHIP MANAGEMENT (E-CIRM) USING TECHNOLOGY READINESS INDEX (TRI)
Author:	VIDILA ROSALINA, TB AI MUNANDAR, A NIZAR HIDAYANTO, HARRY B SANTOSO
Abstract:	The basic principle of using ICT is to facilitate human life. Likewise, Electronic Citizen Relationship Management (e-CiRM) is used to provide the best service for citizens and to manage good relations between regional governments and their citizens. However, in several cities there are still several obstacles in the adoption of Electronic Citizen Relationship Management (e-CiRM). One of the important problems in adopting Electronic Citizen Relationship Management (e-CiRM) is the unpreparedness of human resources. Users who are not ready will reduce the efficiency of the system so that Electronic Citizen Relationship Management (e-CiRM) cannot be implemented and used optimally in its operations so that it becomes useless. The purpose of this study is to measure the level of readiness of citizens as technology users in Electronic Citizen Relationship Management (e-CiRM) in Serang Banten Indonesia using the Technology Readiness Index (TRI) method and to find solutions so that the implementation of Electronic Citizen Relationship Management (e-CiRM) can be implemented successfully with results that are well. The measurement results in this study indicate that four dimensions (optimism, innovation, discomfort and insecurity) have a significant effect on the TR variable. so that it can be seen the readiness of citizens in adopting Electronic Citizen Relationship Management (e-CiRM).
Keywords:	Citizen Readiness, CRM, e-CiRM, TRI, Serang Banten, Quantitave Explore.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	ALTERNATIVE APPROACH TO SEISMIC HAZARDS PREDICTION USING NON PARAMETRIC ADAPTIVE REGRESSION METHOD
Author:	DADANG PRIYANTO, MUHAMMAD ZARLIS, HERMAN MAWENGKANG, SYAHRIL EFENDI
Abstract:	Research with data mining processes to find certain patterns related to mathematical functions such as Correlation, Classification and regression associations, Clustering and others are grouped into two categories namely Descriptive data mining and Predicted data mining. Data mining process Prediction to find out the relationship between variables can be used Parametric and Non-Parametric methods. Many non-parametric methods used one of them is the Multivariate Adaptive Regression Spline (MARS) method. The flexible nature of MARS modeling can be applied to various fields of application including earthquake prediction research. Research on earthquakes contains many parameters that are definitely necessary to get optimal results with cone optimization models difficult to do this research was conducted to complete research on earthquake predictions with uncertain parameters. This study uses a non-parametric method with MARS and to improve its ability to use the CMARS model which is the back of the MARS algorithm. The results of this study after observing the testing of parameters with a combination of basis functions (BF), Maximum Interaction (MI) and Minimum Observation (MO) obtained the results of predictive analysis with a mathematical model that has two basis functions (BF) namely MODEL (PGA) = BF1, BF2, BF3, BF5, BF7, BF9, BF10, BF11, BF13, BF14, BF15, and BF16. The model was obtained from trial and error observations with a combination of basis functions (BF) = 16, MI = 2, and MO = 2. Based on the level of importance of the independent variables on the dependent variable is the Epicenter Distance (R-epi), Magnitude (Mw), Temperature of the incident location (SUHU), and Depth (Depth). The results of the prediction analysis can reveal six areas that have the highest level of earthquake hazard in Lombok, namely the first area of Malacca, North Lombok Regency (KLU), first Genggelang, Ganga (KLU), Tegal Maja, Tanjung, Winner (KLU), Senggigi choice, Malimbu Regency, West Lombok (Lobar), Mataram, as many as Senggigi, Malimbu (Lobar), and the sixth are Mangsit, and Senggigi (Lobar).
Keywords:	Non Parametric, Prediction Analysis, MARS, C-MARS, PGA, Data Mining
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	OBHUSPC - OPTIMAL BIG HIGH UTILITY SEQUENTIAL PATTERNS MINING WITH CUCKOO OPTIMIZATION USING HADOOP MAP REDUCE FRAMEWORK
Author:	V. MALSORU, A. R. NASEER, G. NARSIMHA
Abstract:	The unprecedented explosion of information and technology areas in recent years has resulted in the generation of massive amount of data and extracting necessary and sensitive information from these huge amount of data has become a critical and challenging task. In this direction, several data mining approaches are proposed which lay the foundation for faster and efficient knowledge discovery. Big data High Utility Sequential Pattern (HUSP) Mining has turned out to be an important and essential data mining area where several investigations are carried out for effectual information retrieval. In this work, an effectual procedure for sequential pattern mining of Big High Utility Sequential Patterns along with the Binary Cuckoo Search Optimization (OBHUSPC) is proposed. Here Big High Utility Sequential Patterns mining approach is deployed to find the High Utility Sequential Patterns from big data and the Binary Cuckoo Search Optimization (BCSO) technique is used additionally to determine efficiently the finest high utility sequences. The proposed parallel method is implemented in Hadoop disseminated atmosphere to resolve the scalability difficulty and a transformed database is implemented to diminish the scanning time. The performance of the approach used in this work is evaluated using JAVA platform based Hadoop and Map-reduce framework with various big datasets.
Keywords:	Map-Reduce Framework, Data Mining, Big High Utility Sequential Patterns, Binary Cuckoo Search Optimization, Sequential Pattern Mining
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	THE SAUDI MONARCHY @KINGSALMAN: EMOTIONAL CHOICE ON VIRTUAL SPACE
Author:	HANEEN MOHAMMAD SHOAIB
Abstract:	The purpose of this study is to explore how social media can provide leaders an emotional choice for virtual expression online. The study's case is the Saudi Monarchy, presented in the Twitter account of Saudi King Salman. It addresses the emotional aspects of communication via a Twitter account with local and international audiences while exploring the dark emotional choice of expression that the Monarchy wants to convey in different mediums. The research design builds on the dramaturgical approach and Lasswell's communication model to explore King Salman's Twitter posts, both on the frontstage (traditional media) and the backstage (Twitter). The systematic review indicates that social media, from emotional expression, lapse in the literature. The analysis considers the emotional communication of the significant events in Saudi Arabia from January 2015 to December 2015. The findings depict that the social media platform (Twitter) provides an emotional expression for lighter shades of dark emotions, while darker shades of emotions are expressed more visibly on traditional media outlets. This paper discusses a new perspective to review leadership identity via virtual communication and explores their emotional choices through Twitter posts. The paper concludes with some justifications for the leadership’s emotional choices directed by emotional intelligence.
Keywords:	King Salman, Saudi Arabia, Monarchy-Online, Virtual Space, Dramaturgical Approach, Emotional Choice
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	AN INTERACTIVE SYSTEM FOR ANALYZING MOVEMENT OF BUSES IN HAJJ
Author:	EMAD FELEMBAN, FAIZAN UR REHMAN, ASAD ALI BIABANI, ATIF NASEER, OMAR HUSSAIN, EHSAN ULLAH WARRIACH
Abstract:	Analyzing traffic behaviour performs a robust part to accomplish day-to-day activities of the users efficiently and effectively, particularly in densely populated urban areas. Activities drawing in huge numbers such as religious pilgrimage or sporting events, collisions among automotive traffic flows are likely resulting in interruptions and unsafe situations for pilgrims, often creating chaos and congestion. The issue is more ambitious as millions of pilgrim’s travels over a fixed period throughout Hajj from one location to the other. Hajj is an Islamic pilgrimage which occurs annually during the month of Dhul al- Hijjah which begins on the eighth day of the month and last for five days where millions of pilgrims from across the globe assemble in Makkah to perform the Spatio-temporal rituals. This article presents an interactive platform that utilizes large-scale GPS traces to know the motion of buses during Hajj. For a period of 60 days, GPS traces are gathered for over 20,000 plus buses for pilgrim’s mobility to conduct their rituals. To save big spatial data, we developed an interactive platform that can help in analyses and visualization. The analyses have been done for various stakeholders which includes company authorities. They can visualize the movement of buses, identify driver’s behaviour, speed violations, and area of the violations using maps-based visualization. Extracted expertise would be of benefit to stakeholders to improve the accessibility of pilgrims throughout the Hajj by creating a smart transport system like scheduling, evacuation, maximizing the number of buses or roads for each establishment.
Keywords:	GPS Data, Trajectory, Hajj, Categorization, Big Data, Clustering
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	A CRYPTOGRAPHIC KEY MANAGEMENT SYSTEM MODEL
Author:	SAULE NYSSANBAYEVA, ARMANBEK HAUMEN, ANDREY VARENNIKOV, NURSULU KAPALOVA
Abstract:	This paper describes the requirements and issues that need to be considered and taken into account when developing cryptographic key management systems. We developed the functional structure of a cryptographic key management system, as well as a cryptographic protection scheme for messages using encryption and electronic digital signature based on the OpenPGP protocol. We propose modifications of the ElGamal scheme based on non-positional polynomial notations to use as encryption and electronic digital signature algorithms. Also, an assessment of the enumeration of all possible options for the selection of working bases and secret keys is given.
Keywords:	Cryptographic, Cryptographic Keys, Key Management, Encryption Algorithm, Asymmetric Cryptosystems.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	AN OPTIMIZED CONVOLUTIONAL NEURAL NETWORK FOR HANDWRITTEN DIGITAL RECOGNITION CLASSIFICATION
Author:	WALID SALAMEH , OLA SURAKHI
Abstract:	A Convolutional Neural Network (CNN) is a deep learning algorithm that designed to demonstrate a high capability of object recognition in image data. This paper has developed a prediction model for handwritten classification problem by using CNN. A better performance has proved noticed where this performance has demonstrated over three main metrics: learning rate, number of iterations and number of hidden layers (model path). The paper suggests a best configuration based on the best reached near accuracy generated from different values for these metrics. The accuracy achieved by the suggested model shows the average of accuracy generated by each fold of 5-fold cross validation where configurations are selected randomly. The experimental results achieved a high score of accuracy with one hidden layer and ten number of epochs. A near state of the performance on MINST handwritten digit recognition task in Python using Keras deep learning library was developed and discovered.
Keywords:	Classification Problem, Convolutional Neural Networks, Deep Learning, Optimization
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	A PROPOSED TECHNIQUE FOR DETECTING VIDEO STEGANOGRAPHY
Author:	CHO DO XUAN , TISENKO VICTOR NIKOLAEVICH , LAI VAN DUONG , NGUYEN TUNG LAM
Abstract:	In this paper, we propose the method of detecting video steganography based on the blind spot. Accordingly, our method will use the calibration method to pre-process image frames and the SVM supervised learning algorithm to classify images containing information. The difference between our research and the traditional methods are in two factors: i) for the calibration method, we use the correlation technique between space and time factors to calibrate in order to seek the frames that are most similar to the original ones; ii) For the feature extraction method, we use DCT and Markov techniques to extract the features of the frames that are calibrated and the original frames. The experimental results of the method (in section 4) demonstrate that our proposed technique is more effective than traditional approaches.
Keywords:	Steganography, Video Steganography Technique, Video Steganography Detection, Feature Selection, SVM.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	TOWARDS AN ONTOLOGY-BASED FULLY INTEGRATED SYSTEM FOR STUDENT E- ASSESSMENT
Author:	SALEH ALMUAYQIL , SAMEH ABD EL-GHANY , ABDULAZIZ SHEHAB
Abstract:	Recently, many higher educational institutions have paid significant attention to distance learning. Although several learning management systems (LMSs), have been widely used in many countries, these systems still require more enhancements, especially in student assessment tasks. Consequently, this paper presents an innovative solution intended to meet the needs of the students easily, while simultaneously eliminating the burden faced by instructors. The proposed approach entails an integrated framework for fully automating the assessment process, starting from the generation of questions from a given corpus. Thereafter, the appropriate answers for each generated question are extracted from different educational resources. The experiments demonstrate the ability of the proposed framework to generate candidate questions, while measuring its difficulty score based on a hybrid technique of semantic and contextual data analyses.
Keywords:	E-assessment, Question generation, Semantic Similarity, Word2Vec.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	SCRUM METHODOLOGY AND IBM DESIGN THINKING COMBINED: AN EFFICIENT WAY FOR DEVELOP A SYSTEM (CASE STUDY)
Author:	NILO LEGOWO , ARDIAN ADITAMA
Abstract:	Choosing the correct methodology can lead system development to a better result. The traditional waterfall methodology is commonly known with its limitations with its inflexible and non-user-centric approach. Thus, to overcome waterfall limitation, other methodology can be performed in system development. Scrum methodology is said to be a new breakthrough to overcome classic waterfall methodology limitations. In order to overcome waterfall limitations, Scrum methodology can be combined with IBM Design Thinking to provide the best result as both concept build on user-centric concept. This research will be discussing how to combine and the advantages of combination of Scrum and IBM Design Thinking in order to overcome the Waterfall’s limitations. This research will cover system development with scrum methodologies that will be combined with IBM Design Thinking concept and tools in related Dashboard and Report System development. This paper will not cover the old waterfall detailed process and will only discussed it’s limitations. Scrum and IBM Design Thinking both are user-centric frameworks that can be used by system developers to help them to have a better understanding of their user. This research shows that scrum that complimented with IBM Design Thinking delivers better results than Waterfall methodologies. Both Scrum and IBM Design Thinking overcame the Waterfall’s methodology limitation which leads to better result for all team involved.
Keywords:	Development, Waterfall, Scrum, IBM Design Thinking, User-Centric, System Development
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	METHODS AND SOFTWARE FOR SIMULATION OF OPTIMAL RENEWAL OF CAPITAL ASSETS
Author:	ASKAR BORANBAYEV, SEILKHAN BORANBAYEV, YURI YATSENKO, YERSULTAN TULEBAYEV
Abstract:	This article surveys recent developments in the optimal renovation of capital assets and introduces new asset replacement algorithms under limited forecast about changing uncertain costs. The costs include operating costs of the current asset in use and the replacement cost (price of new assets). The evolution of those costs depends on external technological, economic, and environmental factors. The open innovation increases the importance and complexity of technological change. We study new modifications of the classic Economic Life replacement method for uncertain costs. The analyzed algorithms work well for arbitrary age-distribution of deterministic or stochastic operating cost. We demonstrate their superior performance in various scenarios of improving technology reflected in decreasing operating and new asset costs. Numeric experiments are provided, and managerial implications of the obtained outcomes are discussed.
Keywords:	Improving Technology, Capital Asset, Renovation, Modeling, Optimization.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text

Title:	SCALABLE PARALLEL BIG DATA SUMMARIZATION TECHNIQUE BASED ON HIERARCHICAL CLUSTERING ALGORITHM
Author:	VERONICA S. MOERTINI, MATTHEW ARIEL
Abstract:	Data reduction or summarization techniques can be applied to obtain a reduced representation of the data set that is much smaller in volume, yet closely maintains the integrity of the original data. For summarizing data, Agglomerative hierarchical clustering algorithms, has few advantages. It is quite simple, can produce summaries at specific level (in the form of cluster patterns) with simple adjustment, and can be paralyzed. Apache Spark is a data processing framework that can quickly perform processing tasks on very large data sets, and it is currently a standard tool for analyzing big data. In processing data, Spark can distribute data processing tasks across multiple machines. Spark can run on top of Hadoop with its distributed file system (HDFS) and resources management (YARN) such that it can access HDFS files and uses network resources efficiently. To achieve high performance and scalability of the data analysis technique in Spark environment, stages, narrow and wide transformation, cost of I/O and network must be considered. In this research, we develop a data summarization technique by employing Agglomerative algorithm for Spark. To avoid biased results, records in the given big data are randomly split into bags of dataset stored as Resilient Distributed Datasets (RDD) partitions in the worker machines. To reduce network and I/O cost, we employ one wide transformation that involves data shuffling across the network. In addition, the RDD partitions are then processed locally to produce cluster patterns by worker tasks. Functions with complex computations are designed as Spark parallel tasks. A series of experiments were conducted on a Spark cluster with one driver and ten worker nodes by varying data size (5 to 20 Gb), machine cores used (10 to 50) and the application variables (data split and maximum objects/dendrogram). The results show that the technique is scalable and efficient. The execution time is mostly determined by the parallel tasks run locally on the workers.
Keywords:	Big Data Summarization, Parallel Agglomerative, Apache Spark Application Design
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2020 -- Vol. 98. No. 21 -- 2020
Full Text