		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
April 2021 | Vol. 99 No.08

Title:	SHORT-TERM LOAD FORECASTING USING SUPPORT VECTOR REGRESSION WITH AFRICAN-BUFFALO OPTIMIZATION ALGORITHM
Author:	INUSA SANI MAIJAMA A , YUHANIS YUSOF , MOHAMAD FARHAN MOHSIN
Abstract:	Short-term electric load forecasting is a critical issue due to idiosyncrasies associated with production and consumption of electricity as it cannot be stored in large quantity for future use. Electricity load forecasting remains a challenging task due to non-linearity and uncertainty of associated forecasting variables. This paper presents a hybrid technique based on Support Vector Regression (SVR) optimized using African Buffalo Optimization (ABO) algorithm to predict fourteen (14) days ahead of electricity consumption. Comparison of forecasting performance against PSO and GA as optimizing algorithms for SVR hyper-parameters based on Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Mean Absolute Deviation (MAD) has been carried out. Experiment results has shown that ABO algorithm was able to determine optimal parameters of SVR better than state-of-the-art swarm-based optimization algorithms.
Keywords:	African Buffalo Optimization (ABO), Energy Forecasting, Machine Learning, Support Vector Regression (SVR), Swarm Intelligence
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	FIXED PARTITIONING USING AN HEURISTIC APPROACH FOR LOOP CLOSURE DETECTION
Author:	AZIZI ABDULLAH, IZWAN AZMI, MOHAMMAD FAIDZUL NASRUDIN, MOHAMMED SALAMEH
Abstract:	Loop closure detection using visual information needs proper representation to interpret objects in a scene effectively. The scene may contain several objects corresponding to known and new landmarks. The most widely used methods to detect and describe the regions is to use a keypoint detector to localize objects such as in speeded-up robust features (SURF). Most keypoint-based schemes compute salient points on the object based on the curvature principles of geometrical object surfaces. However, not all the object surfaces can distinctively be described using these rules, such as in scenery images that contain high repeating texture features. In the keypoint detector scheme does not consider the flat texture regions resulting in a few detected points which hinder the holistic visual description of images. Thus, we propose to use a fixed-partitioning scheme that divides the image into several blocks for grouping spatial semantic of significance image features. One possible problem in the proposed approach is to identify the number of partitions and partition size for image description. Thus, an heuristic approach is used to identify these parameters for loop closure detection. A famous computational expensive Real-Time Appearance Based Mapping (RTAB-Map) simultaneous localization and mapping (SLAM) is used to validate the proposed scheme. The results show that the proposed approach outperforms the standard keypoint detector on two datasets, namely Lib6 Indoor and New College
Keywords:	Vision-based SLAM, Loop-closure detection, localization, Fixed Partitioning
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	POLLUTANT TRANSPORT MODELING USING GAUSSIAN APPROXIMATION FOR THE SOLUTION OF THE SEMI-EMPIRICAL EQUATION
Author:	RAKHMETULAYEVA S.B. , DUISEBEKOVA K.S. , KOZHAMZHAROVA D.K. , AITIMOV M. ZH
Abstract:	The paper presents the process of modeling air pollution processes and constructing concentration fields at small and medium distances from the emission source (which most accurately reflects the physical picture of atmospheric pollution with constant emissions) based on two approaches –on scattering according to Gaussian formulas, which includes an estimate of the concentration distribution pollutants along the coordinate axes and on the theory of mass transfer (the so-called "gradient" models or K-models based on solving the equations of turbulent diffusion. According to this method, the process of transport of harmful substances is described by the equations of turbulent diffusion in the atmosphere. Applying then averaging techniques pass from the diffusion equation for instantaneous concentrations to the equation of turbulent diffusion for average values of concentrations.
Keywords:	Monitoring, Intelligent system, Big data, Dynamic data, Sensors
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	AN EMPIRICAL STUDY OF MOBILE TICKETING SERVICE ADOPTION IN RAPID TRANSIT: EVIDENCE FROM JAKARTA
Author:	TASKIA FIRA INDRIASARI , RIYANTO JAYADI
Abstract:	This research aims to know whether the implementation of the QR Code as fare media in MRT Jakarta has provided the expected benefits by identifying factors that encourage people to use it. Therefore, this research was conducted using an integration of Technology Acceptance Model (TAM) Theory and Diffusion of Innovation Technology Theory (DIT). This research conducted a survey method and resulted in 401 respondents indicated that Actual Usage was influenced by various reasons related to Behavioral Intention to Use, Attitude, Perceived Cost, Perceived Ease of Use, Perceived Usefulness, Timesaving, Compatibility, and Trust. among others. This study's outcomes enhance the current knowledge about QR Code System as fare media in MRT Jakarta. It can also be used by MRT Jakarta to devise appropriate strategies to improve the quality of QR Code system in MRT Jakarta in order to increase the number of passengers using QR Code.
Keywords:	Technology Adoption, User Behavior, Mobile Payment, Technology Acceptance Model, Structural Equation Modeling
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	MONITORING THE BREATHING RATE IN THE HUMAN THERMAL IMAGE BASED ON DETECTING THE REGION OF INTEREST
Author:	FARAH Q. AL-KHALIDI , SHAIMAA H. AL-KANANEE , SAMIRA A. A HUSSAIN
Abstract:	Methodology to monitor the breathing rate based on the thermal image processing techniques has been investigated. This approach is based on detecting the skin temperature change of the region. A methodology to monitor the breathing rate based on the thermal image processing techniques has been investigated. This approach is based on detecting skin temperature change of the area of importance (ROI) which represented the range between the tip of the nose and the superior lip of the mouth due to the breathing operation. The major steps to compute breathing rate included enhancement the thermal imaging to improve the contrast quality and to reduce the noise, Segmenting the region of interest (ROI) from the rest of the image, Applying feature extraction to extract the respiration signal, and then determine respiration rate from the respiration signal. In this study, the manual segmented method to detect the ROI with the alignment technique was investigated. It was demonstrated that the methods could successfully track the ROI for both regular and random head movement types and could determine respiration rate in a non-contact manner. The correlation technique was used to measure the accuracy between the reference and the alignment images. Also, three methods were suggested to segment the ROI automatically from the subject's head. The ROI signifies the facial exaggerated part most influenced by inhaled air temperature variations. Further work is in progress to enhance the algorithms so that they can cope with very large head movements.
Keywords:	Thermal Imaging, Region Of Interest, Skin Temperature Change, And Respiration Rate
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	A METAHEURISTIC APPROACH FOR SOLVING FEATURE SELECTION IN SENTIMENT ANALYSIS PROBLEM
Author:	MOCHAMAD WAHYUDI , MUHAMMAD ZARLIS , HERMAN MAWENGKANG , SYAHRIL EFENDI
Abstract:	Huge business data could make data analysis becomes problematic such that the decision-making procedure would be improbable. In the topics of consumer buying behavior, an interesting technique known as sentiment analysis can support in obtaining information about the latest trends and is capable to raise market value of product through upgrading its quality. One peculiar method in solving the sentiment analysis is feature selection technique. Yet, this method includes a combinatorial behavior and the analysis of the huge data can experience difficulty in solving the combinatorial feature selection problem. In order for tackling the combinatorial problem, this paper proposes a new metaheuristic approach based on the movement of non basic variables,in such a way could force the basic non-integer variables to take integer values. The combinatorial structure of the feature selection approach for sentiment analysis can be implemented in various marketing applications.
Keywords:	Combinatorial Optimization, Sentiment Analysis, Feature Selection Approach, Buying Behavior Analysis.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	HYBRID APPROACH CRITIC-TOPSIS FOR CLOUD SERVICE SELECTION
Author:	SALY EID HELMY, GAMAL H.ELADL, MOHAMED EISA
Abstract:	Recently, Cloud computing is an ideal solution to complete business processes of most enterprises. The number of cloud services providers has increased, and consequently the number of cloud services and offerings has increased. The said issue is how choosing the best suitable cloud service adequate to business requirements. The aim of this paper is to provide a novel MCDM approach that gives accurate and reliable results for cloud service selection based problem. This paper proposes a hybrid MCDM (CRITIC-TOPSIS) approach to select best cloud service. CRITIC method used for determining weights of criteria objectively, furthermore, TOPSIS method used for ranking six virtual dedicated servers (VDS silver, VDS Gold, Cloud4You, SMART8, SMART16, QUAD SMART) based on 4 criteria (Dedicated CPU cores, Dedicated RAM , Storage HDD , Price/month). To approve the validity and robustness of the proposed hybrid approach, sensitivity analysis was conducted through sum experiments as different scenarios. Proposal’s result was compared to another hybrid approach result, which used Entropy weighting method to determine the weights of criteria and TOPSIS to rank alternatives. More MCDM methods were applied (Classical TOPSIS, PROMETHEE-\|\|, weighted sum product, weighted sum model), then this experimental results compared with the two hybrids and approved validity of CRITIC-TOPSIS approach.
Keywords:	MCDM, Cloud Computing, CRITIC, TOPSIS, Entropy, PROMETHEE-\|\|, Weighted Sum Product, Weighted Sum Model
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	A SELF-ATTENTION LAYER MECHANISM BASED MODIFIED BI-DIRECTIONAL LONG SHORT TERM MEMORY FOR TWITTER SENTIMENT CLASSIFICATION
Author:	D. RAMANA KUMAR, S. KRISHNA MOHAN RAO
Abstract:	The rapid growth of social networking services has resulted in the creation of a large amount of explicit information in the form of electronic text. Studies on the emotional analysis of texts have therefore received great interest. Semantic analysis (SA) on social media like Twitter has become a very important and challenging task. Characteristics of such data include the length of the tweet, misspellings, abbreviations, and special characters, where analysing emotions requires an unconventional approach. Additionally, tweets often contain sounds in the form of abbreviations, incorrect grammar, freestyle and grammatical errors. SA aims to estimate real emotions based on the raw human-expressed text in the area of natural language processing (NLP). The main goal of this work is to identify the polarity of the tweets by using raw input data. In this research study, a Modified Bi-directional Long Short Term Memory (MBLSTM) is developed for predicting the sentiments. Initially, raw data is given as input to pre-processing techniques and extracted the important features using two feature extraction techniques. Text blogs are used to identify the polarity of tweets and learning rate of MBLSTM is improved by Self-Attention mechanism. The experiments are conducted on Twitter dataset in terms of accuracy, precision, recall and f-score. The validated results proved that the proposed MBLSTM achieved 93.66% of accuracy and 93% of precision, where traditional BLSTM achieved 90.05% of accuracy and 88.12% of precision.
Keywords:	Bi-directional Long Short Term Memory; Emotions; Polarity; Self-Attention; Sentiment Analysis; Twitter data
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	SYNERGY, SYSTEM IT, RISK MANAGEMENT AND THE INFLUENCE ON CYBER TERRORISM AND HOAX NEWS ACTION
Author:	TIGOR SITORUS, HENDY TANNADY
Abstract:	This study aims to investigate the factors hoax and cyber terrorism also variables that influence the acts of cyber terrorism in the jurisdiction of the Republic of Indonesia National Police. The research approach uses mixed methods with triangulation analysis and multiple regression analysis while surveys, interviews and focus group discussions were conducted on 1078 personnel and the stakeholders in Jakarta, West Java, East Java, Bali and North Sumatra. The Normality Test shows the data is normally distributed and the hypothesis test using multiple linear regression analysis shows; 1) The Influence of Synergy on the Acts of Cyber Terrorism and Hoax with indicators of propaganda, agitation, doctrine, jihadists is negative and significantly with the perception of respondents who show that the implementation of synergy is good, 2). The Influence of IT Systems on the Acts of Cyber Terrorism and Hoax is negative and significantly, with the perception of respondents showing that the implementation of synergy is good. 3). Influence of Risk Management on the Acts of Cyber terrorism and Hoax is negative and significantly, with the perception of respondents who show that the implementation of risk management is good. 4). Simultaneously the influence of Synergi, IT System, Risk Management toward Cyber Terrorism and Hoax Actions with propaganda, agitation, doctrine, jihadist indicators is negative and significantly, meaning that if Synergi, IT System, Police Risk Management are good, then cyber terrorism acts in the form of Jihadists decreased significantly. 5). The synergy of prevention, Police Information Technology System, Risk Management, Simultaneously have a negative and significantly effect on cyber terrorism and hoax, so As a major finding that hoax typology is very varied and public perceptions about synergy, IT systems and risk management implemented by the Indonesian Police are good enough and significantly influence toward Cyber Terrorism and the spread of hoax news.
Keywords:	Synergi, IT System, Risk Management, Terrorism, Hoax
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	MACHINE LEARNING APPLICATIONS TO MOBILE NETWORK PERFORMANCE MODELING
Author:	BRANDON LITWIN, KHALED ELLEITHY, LAIALI ALMAZAYDEH
Abstract:	Network optimization is a highly relevant solution to the growing demands of mobile communications. Increasing the efficiency of the existing spectrum and infrastructure drives down costs and improves provider networks' usability. This paper focuses on applying data mining to the evaluation of network performance as a viable tool for resource allocation. Network performance parameters are evaluated and passed through an artificial neural network to determine the categorization of high vs. low performance of the network environment and will detail parameters such as algorithm run time, accuracy and system requirements using a variety of different machine learning techniques.
Keywords:	Machine Learning, Mobile Network, Performance Modeling, Resource Allocation, Data Mining, Artificial Neural Network.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	IOT DEVICES INTEGRATION AND PROTECTION IN AVAILABLE INFRASTRUCTURE OF A UNIVERSITY COMPUTER NETWORK
Author:	BLOZVA A., KYDYRALINA L.M., MATUS Y.V., OSYPOVA T.Y., SAUANOVA K., BRZHANOV R.T., SHALABAYEVA M.
Abstract:	With every passing year computer network security requires new approaches to its structure. Taking into consideration the development of IoT devices and their active integration in such networks this makes another challenge to the cybersecurity network engineer. This article is an attempt to disclose practical approaches to the design and implementation of a computer network of an educational institution (using the example of a university network), which recently have increasingly begun to suffer from outside interference. The possibility of using a web application firewall in such networks and corresponding software for security and incident response at the L5-L7 OSI level is considered. The results have been summed up and further directions of research have been determined.
Keywords:	Cybersecurity, Computer Network, Iot Device, Security Systems Integration
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	INTELLIGENT MONITORING METHOD FOR OCCUPANTS BEHAVIOR AND INDOOR ENVIRONMENT USING INTERNET OF THINGS TECHNOLOGY
Author:	CUI LI , GUOWEN LI , YUMIN LIANG ， WEIRAN ZHU
Abstract:	The effects of the indoor environment on people’s comfort and health have been increased in public awareness. However, although occupants are often dissatisfied with an indoor environment, they will passively accept their situation. The development of Internet of Things technology can provide users with convenient, comfortable and creative indoor environments in the most effective way and can quickly respond to the user's various requirements to ensure good indoor environment quality in a sustainable environment. However, the intelligent monitoring systems of buildings have mainly been focused on building equipment and energy consumption and are not standardized construction in building environmental monitoring. In this research, take an office building as an example, an intelligent monitoring framework that considers occupants’ demands is designed, and the problems of environmental intelligent monitoring methods are analyzed and compared with existing standards in China, based on occupants’ evaluation of the indoor environment investigating.
Keywords:	Intelligent Monitoring; Building Environment; Evaluation; Office Building
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	AN ENHANCED ACCESS CONTROL MODEL TO ENCRYPTED DATA BASED ON AN XACML FRAMEWORK IN CLOUD ENVIRONMENT
Author:	AMJAD ALRUWAILI , A. A. EL-AZIZ , HEDI HAMDI
Abstract:	Cloud computing is a cutting-edge innovation for improving and developing plans of action in associations. It tends to be utilized for giving programming and framework administrations sent in data focuses. Encryption of data by its owner and saving them on the cloud causes many efficiency and secrecy issues. In Cloud computing, a client who has approved certifications ought to be able to get to classified data, such as data owners or cloud providers. In conventional techniques for making data secure, data are encrypted and are kept in trusted hosts and their access is constrained by an access control policy. If the cloud server is penetrated from unapproved clients, the secrecy of touchy data will be uncovered. This paper proposes an enhanced cloud access control approach over encrypted data utilizing an XACML framework system and proof of ownership (POW) procedures. The proposed model controls the access over encrypted data by identifying that the user, who sends requests for accessing the encrypted data, is authorized or not dependent on his/her attributes stored in the XACML policy. By applying the proposed XACML framework, the cloud administrations will play out its concurred capacities with forestalling data spillage, data misfortune, and maltreatment of cloud administrations.
Keywords:	XACML, Cloud Computing, Proof of Ownership, Fingerprint
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	PREDICTIVE DATA MINING RULE-BASED CLASSIFIERS MODEL FOR NOVEL CORONAVIRUS (COVID-19) INFECTED PATIENTS’ RECOVERY IN THE KINGDOM OF SAUDI ARABIA
Author:	HUSSAIN MOHAMMAD. ABU-DALBOUH , SULAIMAN ABDULLAH. ALATEYAH
Abstract:	The coronavirus disease (COVID-19) pandemic, which appeared in Wuhan, China, in December 2019, is quickly spreading worldwide, with over 56 million cases as of mid-November 2020. There is no scientifically validated vaccine or drug for COVID-19; however, patients have recovered with the help of antibiotic drugs, anti-viral drugs, chloroquine, and supplements such as vitamin C. It is now evident that the world needs a quicker and better way to contain and handle the further spread of COVID-19 worldwide with the assistance of non-clinical methods including data mining approaches, augmented intelligence, and other artificial intelligence techniques in order to alleviate the enormous burden on the healthcare system, and also provide the most promising means for the patients' diagnoses. The first objective of this research was to consider a real dataset of coronavirus patients, which included regular statistical reports and also clinical data on patients, which could bring about crucial collaborations within the global research community and the discovery of new insights into tackling the outbreak. Then, using the epidemiological dataset of COVID-19 Kingdom of Saudi Arabia patients, data mining models were constructed for predicting the recovery of COVID-19 infected patients. The Cross-Industry Standard Process for Data Mining was used as the framework for the data mining classification of patients’ health care data. The process for generating the classification rules was based on the decision tree algorithm and the created rules were evaluated for use by health care administration for predicting the maximum and minimum number of days for the recovery of COVID-19 patients, the age group of patients at high risk of not recovering from the COVID-19 disease, those expected to recover from the COVID-19 disease, and those likely to quickly recover from the COVID-19 disease. Three different classification methods were tested, i.e., Bayes Net-D, naive Bayes, and J48. As a percentage of the correctly identified cases using the three separate algorithms, the overall accuracies of the evaluation results were 74.7748%, 81.0811%, and 93.6937%, respectively.
Keywords:	Artificial Intelligance, Machine Learning, Classification; Clinical Data; Algorithm, Disease, Healthcare; Coronavirus Dataset
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	THE METHOD OF STOCHASTIC APPROACH ALGORITHM FOR PROBLEM SOLVING OF FEATURE SELECTION TECHNIQUE
Author:	MOCHAMAD WAHYUDI, MUHAMMAD ZARLIS , HERMAN MAWENGKANG, SYAHRIL EFENDI
Abstract:	The opinion from people can be adopted as important piece of information for most of the management during the decision-making process. The Internet and social media provide a major source of information about people’s opinions. Due to the rapidly-growing number of online documents, it becomes both time-consuming and hard to obtain and analyze the desired opinionated information. The exploding growth in the Internet users is one of the main reasons that a method called sentiment analysis can help in extracting information about the opinion of people to classifies whether the opinion is positive or negative. One of the approaches in solving the sentiment analysis is feature selection method. However this technique contains a combinatorial behaviour and the analysis of the huge data can experience uncertainty parameter. This paper proposes a stochastic programming approach for solving the feature selection technique in order to obtain a decision from sentiment analysis
Keywords:	Sentiment Analysis, Feature Selection, Machine Learning, Stochastic Programming
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	FAKE NEWS DETECTION BASED ON WORD AND DOCUMENT EMBEDDING USING MACHINE LEARNING CLASSIFIERS
Author:	IBRAHIM EL DESOUKY FATTOH, FARID ALI MOUSA
Abstract:	Fake news is a problem that has a major effect on our life. Detection of fake news considered an interesting research area that has some limitation of the available resources. In this research, we propose a classification model that is capable of detecting fake news based on both Doc2vec and Word2vec embedding as feature extraction methods. Firstly, we compare between the two approaches using different classification algorithms. According to the applied experiments, the classification based on Doc2vec model provided promising results with more than one classifier. The Support vector machine resulted the best accuracy with 95.5% followed by Logistic Regression 94.7% and the Long Short Term Memory produced the lowest accuracy. On the other hand, the classification based Word2vec embedding model results high accuracy only with Long Short Term Memory classifier with 94.3%. Secondly, the classification models based on proposed Doc2vec have shown to outperform a corresponding model that based on TF-IDF on the same dataset using Support Vector Machine and Logistic Regression classifiers.
Keywords:	Fake News Detection; Word2Vec; Doc2Vec; Machine Learning; Deep Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	AN EVALUATION THE IMPLEMENTATION OF E-PROCUREMENT APPLICATION AT CONTRACTOR COMPANY
Author:	RACHMAWAN ADWITIA ATMAJA, SFENRIANTO
Abstract:	To prove that the company has implemented the principles of Good Corporate Governance (GCG), companies can digitize the procurement process by developing an E-Procurement application. One of the contractor companies that utilize E-Procurement is PT. XYZ. This research was conducted at PT. XYZ to evaluate the successful implementation of the E-Procurement application using DeLone & McLean. Success is represented as a Net Benefits variable measured through the Use and User Satisfaction variables and is connected to the Quality System, Information Quality, Service Quality. The questionnaire data was distributed to application users and collected as many as 304 respondents. The questionnaire data were collected and then processed using SmartPLS 3.0 and the results were that 5 out of 10 hypotheses were rejected, 3 of which were not significant and the other 2 were significant. Then for the other 5 hypotheses are accepted and are entirely significant. So it is evident that Net Benefits are greatly influenced by Use and User Satisfaction through System Quality, Information Quality and Service Quality.
Keywords:	E-Procurement; IT Evaluation; Delone and Mclean; User Satisfaction; Net Benefits
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text

Title:	NEW METRIC THAT USES A MEASURE OF RESEMBLANCE BETWEEN TERMS TO TAKE INTO ACCOUNT THE NOTION OF SEMANTIC PROXIMITY
Author:	DARKHAN O. ZHAXYBAYEV, MURAT N. BAKIYEV
Abstract:	In this article, we extended the vector model by adapting the parameter by combining it with the formula for index word extraction and evaluation in order to describe the relevant principles that describe a text. Indeed, by combining the calculation with an approach, we have proposed a new metric that uses a measure of resemblance between terms to take into account the notion of semantic proximity. This indexation approach is supported by a contextual and semantic appraisal. In order to have a comprehensive descriptor index, we used not only a semantic graph to illustrate the semantic relationships between words, but also an auxiliary dictionary to strengthen the cohesion of the established graph and thus the semantic weight of indexation phrases. In the presented article, two semantic similarity approaches were explored in Kazakh-Russian, namely, the direct path-based and distributional model, and their cross-lingual counterparts were synthesized in the light of English. The suggested approaches were evaluated on a specific dataset of 1000 Russian and Kazakh word pairs, formatted by analysis. The correlation scores obtained between the four tests and the human evaluation scores suggest a major shift that brings the cross-lingual approach to the semantic similarity estimation process in the Kazakh and Russian languages.
Keywords:	Semantic-Lexical Groups, Verbal Word Identification And Indexation, Similarity, Automized Search Engine, Algorithm-Based Search
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2021 -- Vol. 99. No. 08 -- 2021
Full Text