		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
August 2020 | Vol. 98 No.15

Title:	OPTIMIZING DECISION TREE CRITERIA FOR PREDICTING COVID-19 MORTALITY IN SOUTH KOREA DATASET
Author:	IVAN DIRYANA SUDIRMAN, RUDY ARYANTO, MULYANI
Abstract:	SARS CoV 2 spreads very quickly. When this research was written, there were 1,780,315 positive cases globally. Countries in the world take various actions to curb the spread of this new virus. China is taking strict lockdown steps, while other countries such as South Korea are using massive diagnoses. While it might only be acceptable for countries with not too big populations, what the South Korean Government is doing is very interesting to research so that it can be recognized by other countries. This study use data mining techniques to search for pattern or new information from the data of the Covid-19 patients in South Korea. This study studies the use of decision trees to process the data in South Korea by finding the most optimal decision tree criteria. This study contributes to the data mining related field by showing decision tree is good enough to analyze the data. There are three best criteria for using a decision tree to predict deaths from this new virus. The best decision tree metrics are the gain ratio, knowledge gain and the gini index. In this analysis the gain-ratio is use for further analysis. Another finding is the province or location of this virus is the important factor. The implication of this finding supports the strategy of reducing virus transmission. Sex and age also play an important role in the prediction model.
Keywords:	Data Mining, Decision Tree, Classification, CRISP-DM, COVID-19
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	P2P BOT DETECTION USING DEEP LEARNING WITH TRAFFIC REDUCTION SCHEMA
Author:	MOHAMMAD ALAUTHMAN
Abstract:	Nowadays, Botnet detection plays a vital role in assuring of information and internet security. This research introduces a scheme for peer-to-peer Botnet detection using a deep neural network in collaboration with the features selection approach. A classification and regression tree, ReliefF algorithm, and principal component analysis are utilized to choose the most significant features, and a deep neural network model is built based on adaptive learning methods (ADAM). The approach used in the proposed system utilizes network traffic alone, and the packet payload does not influence it, thus, avoids inherent shortcomings, such as the failure to handle encrypted payloads, as well as, preventing unknown malware from being addressed with rule-based antivirus software to be combated. This study compares the proposed model with classical machine learning methods like Gaussian NB, Logistic regression, SVM and Random Forest. The experiment results note that the proposed deep neural network model achieve the best performance with a principal component analysis as a features selection method. From the experimental results, the proposed method reached the accuracy of 98.2% along with 0.015 % false positive rate and 0.64 Root mean square error.
Keywords:	P2P Network, Botnet, Intrusion Detection, Deep Learning, Traffic Reduction
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	E-SSD: EMBEDDED DEEP CNN-BASED MODEL FOR CAR LOCALIZATION IN AUTONOMOUS VEHICLE SYSTEMS BASED ON LIGHTWEIGHT DEEP NETWORK
Author:	HOANH NGUYEN
Abstract:	Single Shot Multibox Detector (SSD) is the leading one-stage object detection method. However, the process of detecting objects at different scales with different levels of semantic information makes it difficult to fuse high-level features from deeper convolution layers with low-level features from shallower convolution layers. To mitigate the fusion process of different feature layers and create enhanced semantic information feature maps, this paper proposes a lightweight and efficient multi-feature fusion module. The proposed multi-feature fusion module includes concatenation operation to concatenate the features at different scales in a simple and efficient way, point-wise convolution layer to reduce the feature dimension, and bilinear interpolation to upsample the size of feature maps. Furthermore, ESPv2 network, a lightweight and efficient deep convolutional neural architecture, is adopted as the base network for generating base convolution layers from input image. The proposed multi-feature fusion module and base network make a significant improvement in both detection accuracy and inference speed. Experimental results on KITTI dataset show that the proposed model outperforms SSD in terms of detection accuracy while maintaining inference speed. In addition, an embedded system implemented on an NVIDIA Jetson TX2 is used for detecting cars in traffic scenes that shows the effectiveness of the proposed detector.
Keywords:	Car Detection, Convolutional Neural Network, Intelligent Transportation System, Object Detection, Embedded System
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	3D RECONSTRUCTION USING MULTI-VIEW STEREO AND DEPTH-BASED SEGMENTATION
Author:	HUTHAIFA A. AL_ISSA , OMAR E. Al-SHALABI , MOHAMMAD QAWAQZEH , OLEKSANDER MIROSHNYK
Abstract:	The current advancements in the technology of cameras especially the integration of stereo cameras into smart phones has brought ease to the process of reconstructing 3D models from different images, such broad subject could be integrated with many fields like medicine which shows the importance of studying this sub-topic of image processing. Different algorithms and techniques has been studied before for this problem where each technique has pros and cons which makes studying the previous works viable to improve or extend solutions. In this research, a general analysis of using stereo-vision will be discussed alongside with integrating the common reconstruction process with Depth-First-Search algorithm (DFS) in order to segment the object of interest from the background. The main principle of proposed method is built upon is the restriction of the angles used to photograph the object of interest, it will be limited to either 2-views denoting Front, and Back views, and 4-views consisting of Front, Back, Right, and Left views where the user has to supply these orthographic views rather than taking pictures of different angles where the program has to correlate between these images to produce a 3D model. The main goal of this paper is to show that limiting the number of input images while locking the views where shots could be taken from allows using a simple algorithm for reconstruction. To make this goal achievable, orthographic views and stereo cameras have been identified as suitable choices to simplify the reconstruction algorithm.
Keywords:	3D Reconstruction, Multi-View Stereo, Depth-Map, Elongated Image, Feature Extraction.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	A LIGHTWEIGHT AND EFFICIENT DEEP CONVOLUTIONAL NEURAL NETWORK BASED ON DEPTHWISE DILATED SEPARABLE CONVOLUTION
Author:	HOANH NGUYEN
Abstract:	Deep convolutional neural networks (CNNs) have achieved significant improvements in different vision tasks, including classification, detection and segmentation. However, the increasing model size and computation makes it difficult to implement DNNs on embedded systems with limited hardware resources. Many approaches proposed to build a lightweight network and have achieved comparable performance, such as MobileNets, ShuffleNet, and ESPNet. This paper proposes a lightweight and efficient network based on depthwise dilated separable convolution and MobileNetv2 architecture. Depthwise dilated convolution in depthwise dilated separable convolution module effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Furthermore, instead of using a convolution with 3Ã—3 kernel size for each depthwise separable convolution block in MobileNetv2, this paper uses dilated convolutions with different dilation rates to learn the representations in parallel. The proposed model is evaluated on two public datasets. The results show that the proposed model achieves better classification accuracy compared with MobileNetv2. In addition, a simple object detection framework based on the proposed model is designed and conducted on an embedded system. Experiment results show the effectiveness of the proposed model in different vision tasks.
Keywords:	Deep Convolutional Networks, MobileNetv2, Image Classification, Object Detection, Depthwise Separable Convolution
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	RESEARCH TRENDS OF NEUROMARKETING: A BIBLIOMETRIC ANALYSIS
Author:	AHMED H. ALSHARIF , NOR ZAFIR MD SALLEH, ROHAIZAT BAHARUN
Abstract:	The rising demand for exploring what is inside consumersâ€™ brains and the growth of neuroscience stimulated research efforts to explore the subtle centers in the consumerâ€™s brain that responsible for making-decisions. Therefore, understanding the essential subjects relevant to neuromarketing is important for expanding collaboration and to push the progression of research towards the desired goals perfectly. In this paper, our goals were to assess the global research trend in neuromarketing field upon on outputs of publication, co-authorships, countries, and co-occurrences. This paper has used the Scopus database to analysis related articles between 2007 and 2018, the result was 137 journal articles. In 2012, the publicationsâ€™ number has increased by about 12 articles each two-year, which led to a steady rise in the sum of the total publications. Approximately 52% of the universal publications were published in the USA, Spain, UK, Italy and Germany leading the other 32 countries/territories.
Keywords:	Neuromarketing, Bibliometric Analysis, Author Keyword Co-Occurrences, Vosviewer, Scopus Database, Web Of Science, Citation Index.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	ARABIC NAMED ENTITY RECOGNITION BASED ON TREE-BASED PIPELINE OPTIMIZATION TOOL
Author:	BRAHIM AIT BEN ALI, SOUKAINA MIHI, ISMAIL EL BAZI, NABIL LAACHFOUBI
Abstract:	Named Entity Recognition (NER) is a clue task to improve automatic text processing, which is needed in a diverse variety of applications. NER techniques vary from hand-craft rules to machine learning approaches. As a human opting for a supervised learning algorithm, it is often difficult to choose the optimal machine learning (ML) model for a classification problem. Automated ML (AutoML) aims at automatically selecting, composing, and parameterizing machine learning algorithms in order to obtain optimal performance for a given task (dataset). In this paper, we apply an approach based on Tree-based Pipeline Optimization Tool (TPOT). This method uses genetic programming based on the tree structure to find the model and its hyperparameters that more closely predicts the class of Arabic named entities in the text comes from social media. The structure and parameters are fine-tuned to achieve the optimum performance of the machine's learning pipeline. Our method outperforms strong baselines. It reaches a novel state-of-the-art in the NER task.
Keywords:	Arabic Named Entity Recognition, NLP, Social Media, Machine Learning, Automl, Genetic Programming, Tree-Based Pipeline Optimization Tool (TPOT).
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	OPTIMIZATION OF FORECASTING TIME SERIES WITH RBT (RULE BEST TIME SERIES)
Author:	RELITA BUATON, MUHAMMAD ZARLIS, HERMAN MAWENGKANG, SYAHRIL EFENDI
Abstract:	This research is motivated by the abundance of time series data stack found, often regarded as garbage and neglected due to the inability to find knowledge or interesting patterns from the data pile. Time series is one of the topics that is often associated with forecasting through a series of data that depends on time periods. The basic problem in time series data mining is how to present the knowledge contained therein, then how to find the rules of periodic data series and how to optimize the decision of the resulting time series data so that it can be used to predict in the future. Based on previous papers, there is no model to present knowledge in the form of rules in time series. In this paper the proposed model is RBT (Rule Best Time Series). The main process in RBT is to discretize periodic series to form sub-sequences, then these sub-sequences are grouped through measures of similarity with distance using euclidean, then the discovery of rules is applied to obtain hidden rules on temporal patterns and to rank with J-measures. From the results of this study time series data can be optimized, new knowledge or trends and patterns in time series databases that are uncertain and previously unknown can be generated. The decision or information can be used to display decisions, or forecasting in the future with an accuracy rate of the model mean absolute deviation (MAD) of 73%, forecasting accuracy of the mean squared deviation (MSE) of 87% and the percentage of the mean absolute percentage error of the MAPE of 4,7%.
Keywords:	Forecasting Time Series Data Mining, Rule Best Time Series
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	RSA PUBLIC KEY SOLVING TECHNIQUE BY USING GENETIC ALGORITHM
Author:	DIAN RACHMAWATI, HILDA AYU TAMARA, SAJADIN SEMBIRING, MOHAMMAD ANDRI BUDIMAN
Abstract:	The Rivest Shamir Adleman (RSA) algorithm is one of the cryptographic algorithms that have a high level of security in the message security, and this is due to the difficulty of finding the prime number factor of a huge integer (factor n being the two main factors, p, and q so that it becomes n = p ∙ q). Because it is assessed as safe in securing messages, researchers look for weaknesses in the RSA algorithm. The downside of this RSA algorithm is from the key solving technique. The algorithm for solving this key is sought and studied so that the secret key p and q can be known or cryptanalysis. The key solving technique that can be done is to use the heuristic method, which is a genetic algorithm. The process of finding factors from this public key is conducted algorithmically using a genetic algorithm. The genetic algorithm works by factoring the public key n randomly to generate the initial value of the chromosomal candidates p and q. After the initial population is formed, the chromosome will experience evaluation, selection, crossover, and mutation so that the best solution is found. The chromosomes are produced from one generation to a maximum of a predetermined generation. Furthermore, two figures of the results of the factorization must be done checking the prime number, in the study of the test method of prime numbers using the Lehmann algorithm. If the test result of the prime number is correct, then the two numbers are the secret key p and q of the RSA algorithm. The results of the research from solving the technique of public-key RSA algorithms using genetic algorithms suggest that the genetic algorithm can be used to break the public key of the RSA algorithm. The opportunity to find the secret key p and Q RSA algorithm is affected by the size of the pop size and maximum size of the generation, the larger the size of population size and maximum size of the generation, the larger the population size and maximum size of the generation then the higher the probability of the p and Q secret keys found. The size of the crossover Rate (PC) is best used to solve the problem of solving the RSA public key using the genetic algorithm is 25%-50%. While the size of the mutation rate (PM) is best used to resolve the problem of solving the RSA public key, using the genetic algorithm is 10%-20%.
Keywords:	RSA, Cryptography, Cryptanalysis, Heuristic, Genetic, Lehmann.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	IOT SYSTEM FOR LEAK DETECTION AND MONITORING OF LIQUEFIED PETROLEUM GAS
Author:	FRABOWO PRASETIA, BENFANO SOEWITO
Abstract:	LPG (Liquefied Petroleum Gas) is a common fuel used in restaurants and industries for cooking, heating, etc., but the threat of danger will always be there for every user. Initially, LPG gas does not smell, but if so it will be difficult to detect if there is a leak in the gas cylinder. The very first action is the human sense of smell so that humans can smell the gas. Then, errors also often occur on the manometer used by the regulator is still analog, so the reading of the gas pressure data is still less accurate. The purpose of this paper is to propose an LPG gas leak detection device using MQ2 sensor and LPG gas pressure measurement using MPX5700 sensor, buzzer as an alarm, led, LCD as a gas pressure information media, and serve as a tool to open the regulator valve when a leak occurs. The average results of each measurement with a good distance and time are used is to refer to the limits of excess levels ie more than 100ppm are found in an average condition of 10 seconds with a distance of 10cm, 15cm, 20cm, and 25cm. The Mean Square Error (MSE) value of the MPX5700DP sensor with the gas regulator being compared is 0.09 for the absence of gas conditions received and 0.61 for the gas conditions that have been received by the sensor, this test is to obtain a more accurate value.
Keywords:	Liquefied Petroleum Gas, Gas Leak Detection, Monitoring Gas, MQ2, MPX5700
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	A SYSTEMATIC LITERATURE REVIEW ON PREDICTION MODELS IN MICROGRIDS
Author:	ATIMAD EL KHAOUAT , LAILA BENHLIMA
Abstract:	Microgrids (MGs) constitute the new generation of electrical networks; they are more effective, reliable, scalable and allow simultaneous exchange of energy and data in the network. Prediction is one of the tools that contribute to the development and improvement of MGs because it is used for decision making since, promotes control systems, energy management and so on. In recent years researchers have produced many prediction studies in MGs using different artificial intelligence prediction methods and techniques they deem appropriate to handle with the prediction problems they are working on. We are interested in this paper to analyse those studies as a Systematic Literature Review (SLR) in order to draw the state of the art of existing prediction solutions in MGs, keep up to date with latest used techniques and evaluate if those solutions are in line with the development of Information and Communication Technologies (ICT) especially big data technology.
Keywords:	Prediction, artificial intelligence, algorithms, machine learning, MGs, SLR.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	A CLINICAL DECISION SUPPORT SYSTEM FOR THE DIAGNOSIS OF GYNECOLOGICAL DISEASES
Author:	ELHAM F. AHMAD , MOHAMMAD ALSHRAIDEH , KAMIL FRAM
Abstract:	Gynaecological diseases diagnosis is one of the important issues in the medical field globally because gynaecologists have to analyze and diagnose the disease according to various and similar symptoms. They may accidentally miss some symptoms that lead to a misdiagnosis. Hence, this paper aimed for developing a clinical decision support system (CDSS) to assist the gynaecologists in the diagnosis process for eleven types of gynaecological diseases that represent the most important diseases that are frequently diagnosed in gynaecologist's clinics which are: Polyps, Infections, Fibroids, Prolapse, Cancer, Endometrial hyperplasia, Migrants, Amenorrhea, Abortions, Dysmenorrhea and Infertility. In the proposed system, a multilayer perceptron (MLP) feed-forward neural network was used. The input layer of the proposed system included 54 input variables. An iterative process was used to determine the number of neurons and hidden layers. Furthermore, a resilient backpropagation algorithm (Rprop) was used to train the system. In particular, a 10-fold cross-validation scheme was used to access the generalization of the proposed system. We obtained 94.5% classification accuracy from the experiments made on the data that were taken from 550 patientsâ€™ medical records suffering from eleven gynaecological diseases managed at the gynaecological clinics at Jordan University Hospital (JUH).
Keywords:	Gynecological diseases, Diagnosis, Clinical Decision Support Systems (CDSSs); Multilayer Perceptron (MLP); Neural Network; Resilient Backpropagation Algorithm (Rprop);
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	ANALYSIS OF THE EFFECT OF THE IMPLEMENTATION OF WEB-BASED E-MEMBERSHIP PROGRAM TOWARDS CUSTOMER LOYALTY (CASE STUDY, PT .DKB)
Author:	NATASHA ANGELICA, TOGAR ALAM NAPITUPULU
Abstract:	PT.DKB is a company engaged in Fashion Retail sector, PT.DKB has a loyalty program which is designed to measure the loyalty of PT.DKB customers. At the beginning of 2019, the PT.DKB loyalty program changed from a physical membership card to an electronic membership card which support is provided via a website. This study is done to analyze the factors affecting the loyalty of PT.DKB customers with changes in the loyalty program to electronic membership with website-based usage. The factors analyzed in this study are Website Quality, E-Service Quality, Ease of Use, and Perceived Usefulness with the target Customer Loyalty variable. The study was conducted with a total sample of 155 respondents. The analysis is performed by testing validity using Item to Total Pearson Correlation with a correlation level ≥ 0.5, reliability testing using Cronbach's alpha with a minimum value of Cronbach's alpha ≥ 0.6, and hypothesis tests with the condition that a hypothesis is accepted if P-value ≤ 0.05. The test results performed with the SmartPLS application indicate that there are two indicators which correlation level is less than 0.5 both of those indicators are removed from the next step of the test. Reliability tests result in values above 0.6 for all variables. Hypothesis tests performed show that four of the six hypotheses were accepted in this study. The results of this study indicate that the Perceived Usefulness factor directly influences the loyalty of PT.DKB customers and indirectly that the loyalty of PT.DKB customers are influenced by Website Quality and E-Service Quality. From the results of this study, there are three factors which influenced the customers loyalty of PT.DKB. Those factors are: Website Quality, E-Service Quality, and Perceived Usefulness by increasing the function regarding these factors, PT.DKB could retain and increase their customers loyalty.
Keywords:	Customer Loyalty, Electronic Membership, SmartPLS, Website Based Membership, Affecting Factors
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	ASYNCHRONOUS MULTI-SITE METHOD DESIGN DISASTER RECOVERY CENTER ON THE BUSINESS PROCESS AUTOMOTIVE MANUFACTURING (CASE STUDY: PT XYZ)
Author:	EDY YULIANSYAH, BENFANO SOEWITO
Abstract:	In a series of business processes of a company, there are of course various obstacles that cause disasters so that business processes are disrupted even to a standstill, which ultimately results in significant financial losses, where the IT factor is one of them. These problems are found in the business process of PT XYZ which has a line stop annual recapitulation caused by IT factors for 451 minutes, with the biggest cause at the level of availability of the production process information system server. In maintaining the continuity of its business processes, PT XYZ requires a risk control measure for the main problem, namely improving the quality of the availability of the production process information system server, by building an on-premise replication method suitable for various disaster threats. This study aims to find out the specific steps in determining what replication methods are appropriate to be implemented in a manufacturing environment with the conditions of business needs such as PT XYZ, whose investment feasibility is then evaluated through a systematic approach in the form of a Cost-Benefit Analysis (CBA) method. From the overall results of the analysis process of PT XYZ's business needs, and by utilizing a combination of existing technologies, the appropriate replication method is obtained for the manufacturing environment, then integrating the needs of the Disaster Recovery Center (DRC) system with the infrastructure it has today can produce DRC designs that are more efficient and effective from a technical and cost perspective.
Keywords:	Disaster Recovery Center, Replication, Manufacturing, Risk Management, Cost-Benefit Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	HOW TO UTILIZE A CALCULATOR ON JUNIOR HIGH SCHOOL FOR SPECIAL INTELLIGENT STUDENTS IN MATH ENRICHMENT LEARNING?
Author:	CAHYA MAR A SALIHA SUMANTRI, SUGIMAN, HERI RETNAWATI
Abstract:	So far, enrichment learning has been conducted by only giving practice test without using supporting media. Therefore, students on enrichment class feel bored because they are only given working exercises and discuss the solutions. Based on the problem, this research aims to develop calculator-assisted enrichment learning tool to facilitate students, mainly the special intelligent students who take enrichment learning to obtain new knowledge and experience in using calculators. This research was Research and Development of Plomp model. Research subjects consisted of 33 students of VIII grade of Junior High Schools in Pasuruan. Validation instruments consisted of validation sheets. Practical assessment instrument consisted of an assessment sheet by teacher and students, and observation sheet of learning implementation. Effectiveness evaluation instrument was student's final test sheet. Analysis techniques of enrichment learning tools data were classified into two, qualitative and quantitative. Based on result, math enrichment learning tools meet valid criteria by successive scores of 119.5, 95, and 48.5 with good classification. Then, the tools meet practical criteria in terms of assessments by teachers and students by 119 and 76.64 with very good classification. Learning implementation achieves a percentage of 85% and student mastery achieves 95.45%. Therefore, a calculator-assisted enrichment learning tool appropriate to be used as one of the learning tools that has fulfilled the valid, practical, and effective criteria.
Keywords:	Calculator, Special Intelligent Students, Enrichment Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	SPACE SUBDIVISION FOR INDOOR NAVIGATION: A SYSTEMATIC LITERATURE REVIEW
Author:	ASEP ID HADIANA, SAFIZA SUHANA KAMAL BAHARIN, NANNA SURYANA HERMAN
Abstract:	Along with the increasing demand for indoor navigation, many attempts were made to improve indoor navigation performance. Information about the room becomes important, because one of the characteristics of indoor navigation is the dynamic indoor conditions. Space subdivision is an effort made to make indoor navigation even more accurate. The purpose of this study is to create a systematic literature review (SLR) regarding the topic of space subdivision for indoor navigation which is based on a SLR method, previously defined research question. This study examines several previous works specifically in the field of space subdivision for indoor navigation with the SLR. This research is expected to be the basis for further research to improve the quality of indoor navigation based on space subdivision.
Keywords:	Space Subdivision, Indoor Navigation, IndoorGML, Subspacing, Navigation Path
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	AN EXPERT SYSTEM FOR DIAGNOSIS COW DISEASES
Author:	SHOPAGULOV OLZHAS, TRETYAKOV IGOR, ISMAILOVA AISULU, AITIMOVA ULZADA, BEISEMBAYEV KANATZHAN, MUKHANBETKALIYEVA AIZADA
Abstract:	This article describes an automated expert system developed to diagnose cow diseases and assist veterinarians in treatment. We set before a diagnostic method based on the analysis of observed symptoms and experience of veterinarians. The system represents a web interface for maintaining a database of diseases, their symptoms and treatment methods, as well as a smartphone application for the diagnostics in offline mode. The article presents a structural diagram and describes the main parameters of the developed expert system, as well as a general scheme of the interaction of individual components. Diagnostics and ranking of possible diseases is performed by adding and sorting the results of weighting coefficients of observed symptoms and symptom complexes. Weighting values of symptoms and symptom complexes are determined by veterinary experts. Also presented in the article the information on the developed expert system, and the results of tests and testing during its use. We have simulated the real conditions of cow disease, together with students, made a comparative characteristic with and without the use of developed software product in the diagnosis. By constantly monitoring and updating the knowledge base online, the system has potential use in veterinary practice.
Keywords:	Expert System, Diagnosis Of Diseases, Weighting Coefficients, Symptoms, Application Evaluation.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	MAMMOGRAM CLASSIFICATION TECHNIQUE BY USING NEURO FUZZY SVM FOR TUMOR EXTRACTION
Author:	M PUNITHA, K PERUMAL
Abstract:	Image classification is helping radiologists to improve the accuracy of tumor detection in mammogram images for better diagnostics. The main aim of this proposed work is to build an efficient Neuro-Fuzzy support vector machine Techniques to detect and extract the tumor in the mammogram images and get an efficient result. The proffered classifiers are to achieve a very fast, simple, and efficient breast cancer diagnosis. The edge-based image segmentation and Neuro-fuzzy support vector machine are to find the Abnormality of classification such as cysts, calcification, fibro adenomas, and scar tissue. The tumor pixel values are calculated easily in a short time. Based on this experimental result, the overall performance of the proposed method is improved significantly. Furthermore, it can be inferred and ensures that the best classification accuracy of 99.85% ratio. And it has been compared in various Existing methods. There is no other research has been done for this type of research.
Keywords:	Neuro-Fuzzy support vector machine, Skeletonization, and Edge base Segmentation algorithm
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	IDENTIFYING FACTORS THAT INFLUENCE SECURITY BEHAVIORS RELATING TO PHISHING ATTACKS SUSCEPTIBILITY: A SYSTEMATIC LITERATURE REVIEW
Author:	AYMAN HASAN ASFOOR, FIZA ABDUL RAHIM, SALMAN YUSSOF
Abstract:	Over the past few years, the number of cybersecurity attacks related to phishing has been increasing, whereby usersâ€™ private information is obtained via Internet banking in an unauthorized manner. This attack places considerable risks to government agencies, businesses as well as other users with sensitive data. In this paper, the published research of factors influencing security behavior associated with phishing attack susceptibility is explored. Four major databases, including journals and conference proceedings from Scopus and a total of 1560 studies were used in our review, and a quality criterion was applied to this set of papers. A total of 68 studies were selected for further analysis, from which 18 factors were successfully identified that are influenced (directly and indirectly) to security behavior relating to phishing attacks susceptibility. This review encompassed other aspects like the focus of the study, adopted theories addressing the factors of security behavior, and the research methodology. The findings indicated that the factors that influence security behavior associated to phishing susceptibility are attitude, self-efficacy, perceived behavioral control, subjective norms, digital guardianship, online target suitability, online exposure to motivated offenders, perceived susceptibility, perceived severity, perceived effective, perceived barriers, experience, knowledge, trust, computer skills and e-mail load.
Keywords:	Phishing Victimisation, Security Behaviours, Online Banking, Conceptual Model
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	THE INFLUENCE OF TRAVELER REVIEWS ON MOBILE APPLICATIONS ON TRAVEL DECISION-MAKING TO DUBAI
Author:	ASHRAF JAHMANI, RENEH ABOKHOZA, RIMA N. ZGHYER, OMAR JAWABREH
Abstract:	Purpose: The purpose of this study is to examine the influence of traveler reviews on mobile applications on travel decision-making in Dubai. Therefore, this study is aimed to find and study the relationships between traveler reviews, intentions to visit, destination image, and destination choice. With the world in the midst of a communication revolution, it is more than obvious that mobile applications like TripAdvisor, Expedia, KAYAK, Trivago, and Tajawal, etc. are used extensively for travel and tourism. Design: This study consisted of a sample of 1000 tourists visiting Dubai and using mobile applications. A questionnaire was used to get the data of this study. The questionnaire was responded by 892 respondents who use mobile applications to plan their travel and guided by other traveler reviews. Findings: The results from the collected data indicate that traveler reviews on mobile applications have a positive influence on the choice of Dubai as a destination. Also, the results find the significant effect of traveler reviews on destination image and intentions to visit Dubai. For managerial implications, this study suggests that the Dubai government and national tourism industry board can play an active role to create mobile applications as a means of communication between them with the tourists, as well as a forum for the interaction and exchange of information among tourists themselves. Originality: The most important advantages of the use of mobile applications are online reservations, reviews and the sharing of knowledge and information among the different groups of tourists.
Keywords:	Traveler Reviews, Mobile Application, Travel Decision Making, Destination Choice, Destination Image.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text

Title:	AUTOMATED SYSTEM FOR MONITORING THE THREAT OF WATERWORKS BREAKOUT
Author:	TALGAT MAZAKOV, SHOLPAN JOMARTOVA, GULZAT ZIYATBEKOVA, MAGZHAN ALIASKAR
Abstract:	The article is devoted to the creation of an automated system for monitoring the water level in reservoirs to prevent the breakthrough of weirs and dams. The paper offers hardware and software for monitoring the reservoir occupancy with prompt notification of interested organizations (local administrations) and local emergency departments. The article developed an automated system for monitoring the water level in a reservoir, which allows to get real-time information about the relative humidity and air temperature, the distance from the dam crest to the water surface in the reservoir. Based on the information received, the system allows to estimate the forecast time of increasing the volume of water level from the current to the critical level and inform the population about the state of the reservoir.
Keywords:	Flood, Dam, Closure Channel, Waves, Water Resources, Water Level Monitoring, Microprocessor System, Temperature And Humidity Sensor, Raspberry Microcomputer, Arduino UNO Platform
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2020 -- Vol. 98. No. 15 -- 2020
Full Text