		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
August 2020 | Vol. 98 No.16

Title:	VIOLENT CRIME HOT-SPOTS PREDICTION USING SUPPORT VECTOR MACHINE ALGORITHM
Author:	FALADE ADESOLA , AMBROSE AZETA , ADERONKE ONI , A. E. AZETA,GREGORY ONWODI
Abstract:	Accurate spatio-temporal violent crime hotspot prediction is a difficult and challenging task at this present time. Large amount of violent crime dataset are usually required for predicting future occurrence of violent crime in terms of location and time. Various data mining techniques have been applied in the previous studies on violent crime prediction with accuracy and other results that needed to be improved upon. In this paper, Support Vector Machine based spatial clustering technique for violent crime prediction was used. Firstly, historical violent crime dataset between 2014 and 2019 Lagos, Nigeria were collected and pre-processed through Principal Component Analysis, and then Support Vector Machine model built using IBM Watson Studio was applied on the six different violent crime dataset collected to determine violent crime hotspot locations for next day in Lagos Nigeria. The model was evaluated using real-life dataset of six violent crime types (murder, arm robbery, kidnapping, rape, non-negligent assault and man slaughter) dataset using confusion matrix. The results obtained found to return an accuracy of 82.12 percent which is good to be relied on for violent crime prediction. Based on this result, the model could be used by the Police authority to develop new crime control strategies and plan towards mitigating crime rate in the country.
Keywords:	Confusion matric, Data Mining, Support Vector Machine, Supervised Learning, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	CYBERBULLYING DETECTION: CURRENT TRENDS AND FUTURE DIRECTIONS
Author:	KAZIM RAZA TALPUR , SITI SOPHIAYATI YUHANIZ , NILAM NUR BINTI AMIR SJARIF , BANDEH ALI , NORSHALIZA BINTI KAMARUDDIN
Abstract:	As we see the rapid growth of Web 2.0; online social networks-OSNs and online communications which provides platforms to connect each other all over the world and express the opinion and interests. Online users are generating big amount of data every day. As result, OSNs are providing opportunities for cybercrime and cyberbullying activities. Cyberbullying is online harassing, humiliating or insulting an online user through sending text messages of threatening or harassing using online tool of communication. This research paper provides the comprehensive overview of cyberbullying that occurs usually on OSNs websites and provides current approaches to tackle cyberbullying on OSNs. It also highlights the issues and challenges in cyberbullying detection system and outline the future direction for research in this area. The topic discussed in this paper start with introduction of OSNs, cyberbullying, types of cyberbullying, and data accessibility is reviewed. Lastly, issues and challenges concerning cyberbullying detection are highlighted.
Keywords:	Cyberbullying, Online Social Networks (OSNs)
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	SECURE IMAGE CRYPTOSYSTEM BASED ON HENON MAP AND ADJUSTED SINE LOGISTIC MAP
Author:	HESHAM ALHUMYANI
Abstract:	This paper presents a superior confusion-diffusion based color image cryptosystem that is based on employing both the 2D adjusted logistic sine mapping (2D ALSM) and the 2D Henon mapping (2D HM). The encryption phase of the proposed color image encryption scheme utilizes the 2D ALSM in the confusion stage to shuffle the plain color image for m-iterations. The 2D HM is employed in the diffusion stage to diffuse the resulted 2D ALSM based shuffled color image for n-iterations. The decryption phase of the proposed color image encryption scheme follows the same manner of the encryption phase but in a reverse order. The proposed 2D HM-ALSM color image encryption scheme is subjected to a series of security tests to study and investigate its security with respect to several attacks like entropy, histogram, correlation coefficient, differential, occlusion, and noise resistance attacks. The experimental outcomes for the proposed 2D HM-ALSM color image encryption scheme illustrate the superiority and efficiency of the proposed 2D HM-LSM image encryption scheme against different attacks.
Keywords:	Henon map, Adjusted Logistic-Sine map, Confusion, Diffusion, Image encryption.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	REDESIGN THE FORWARDING COMPANYÃ¢â‚¬â„¢S BUSINESS PROCESSES USING THE ZACHMAN FRAMEWORK
Author:	BERNADUS GUNAWAN SUDARSONO, JOHANES FERNANDES ANDRY, PRANCHIS RANTING, AEDAH BINTI ABD RAHMAN
Abstract:	Forwarding Company is one of the companies in Indonesia that provides delivery services using trucks. To be a company that is far superior to its competitor, the company can implement Information Systems (IS) or Information Technology (IT) that is in line with the vision and mission of its business processes (both activities in the main business processes and activities in supporting business process). Enterprise Architecture Planning or EAP helps make planning for the application of IS / IT that is more mature and better so that implementing IS/IT in the company's business processes can run away and work in accordance with the company's vision and mission. To complement the design of new business processes using EAP, this study will use the Zachman framework adapted to EAP. This framework suggests a logical structure for categorizing, organizing, and describing a detailed picture of a company. Therefore, this research is expected to be able to provide input to companies that are research objectives to execute ARE/IT in conformation with business processes and its vision and mission. Later the results of this study will form a plan about new business processes, both the main and supporting activities that are in accordance with the company based on the Zachman framework.
Keywords:	EAP, Zachman Framework, Forwarding Company, Business Process
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	DEEP LEARNING BASED ABSTRACTIVE ARABIC TEXT SUMMARIZATION USING TWO LAYERS ENCODER AND ONE LAYER DECODER
Author:	DIMA SULEIMAN, ARAFAT AWAJAN
Abstract:	In this paper, an abstractive Arabic text summarization model is proposed, which is based on sequence-to-sequence recurrent neural network encoder decoder architecture. The proposed model consists of two layers of hidden states at the encoder and one layer of hidden states at the decoder. The encoder and decoder layers use long short-term memory. The two layers of the encoder are the input text layer and the name entities layer. The inputs for the input text layer are the word embedding of the input text words, while the inputs for the name entity layer are the word embedding of the input text name entities. In all layers, the word embedding that is used is one of the AraVec pre-trained word embedding models. Furthermore, global attention mechanism is used by the decoder to generate the summary words. Special dataset is collected and used for training and evaluating the abstractive summarization model. Moreover, the proposed model is evaluated using ROUGE1 and ROUGE1-NOORDER evaluation measures. The experimental results show that, the proposed model provides good results in terms of ROUGE1 and ROUGE1-NOORDER where the values are 38.4 and 46.4 respectively. Finally, a comparison is made between the word2Vec and dependency parsing based word2Vec word embedding models. The abstractive summarization models that use dependency based word2Vec model outperformed the models that use the original word2Vec model. As a result, the quality of the word embedding highly affects the quality of the generated summary.
Keywords:	Deep Learning, Abstractive text summarization, Recurrent Neural Network, Attention Mechanism, LSTM, ROUGE.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	AUTOMATION AND ROBOTICS SYSTEM (ARS) ADOPTION IN THE TRANSFORMATIONAL COMPANIES IN THE KINGDOM OF SAUDI ARABIA: A CONCEPTUAL FRAMEWORK
Author:	MOHAMMED ALDOSSARI, ABDULLAH MOHD ZIN
Abstract:	The manufacturing sector indubitably holds great significance to the development of the global economy, whereby innovative methods have been brought forward to implement new technologies including robotics and automation in the sector. However, regardless of the robotsÃ¢â‚¬â„¢ benefits to productivity and the effectiveness of management, the circumstances under which they are used as alternatives or assistance to labor, the influence on the formation of new firms, their facilitating of effective and efficient management, and their formation of the regional economies, the topic with all the related aspects still calls for extensive investigation. Researches on factors hinders the adoption of automation and robotics are still scarce. Thus, in the present work, the factors that influence intention to adopt automation and robotics system (ARS) among the Saudi transformational companies were examined, using a conceptual framework based on the Technology Acceptance Model (TAM) and Technology, Organization, Environment (TOE) Theory. Such factors were obtained from a review of literature, theory analysis and consultation of experts via interviews. The study conducted an analysis of the qualitative findings to verify the framework, with the help of thematic approach. Based on the results, the proposed conceptual framework comprehensiveness and importance were confirmed. This paper concluded the importance of such empirical studies on factors that could influence the adoption of ARS. Furthermore, the verification of the results also showed support for the results and the experts were of the consensus in their agreement of the proposed ARS adoption frameworkÃ¢â‚¬â„¢s validity and adoption. The experts affirmed that the framework is inclusive of the significant factors that lead to effective adoption and they indicated their agreement by their involvement and by the inclusion of all the factors in the framework.
Keywords:	Robotics, Automation, Adoption, Saudi Arabia, Transformational Companies.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	SPEECH INFORMATION SECURITY ASSESSING IN CASE OF COMBINED MASKING SIGNALS
Author:	YERZHAN N. SEITKULOV, SEILKHAN N. BORANBAYEV, NURLAN N. TASHATOV
Abstract:	The paper presents the results of experimental studies directed to the speech intelligibility assessment while protecting it from leakage via acoustic channels by masking with combined acoustic signals, including Ã¢â‚¬Å“whiteÃ¢â‚¬Â noise and speech-like signals. The speech information security assessment is closely related to environmental conditions, as a rule, the most common option is a certain room with various soundproofing properties of enclosing structural elements. It is possible to take into account the influence of soundproofing properties of building envelopes only on the basis of experimental measurements of the transfer characteristic of speech signals outside the premises and the additional protection space. It necessary to note that the results of the speech information security assessment also strongly depend on the methodology for conducting experimental studies. An important phenomenon in experimental studies is the resonance of the bending vibrations of the enclosing elements of the building structures. Difficulties in the speech information security assessment are caused by uncertainties associated with difficulties in the mathematical formulation of the protection problem on the one hand and a large number of factors affecting the speech information security, on the other hand. In the paper, itÃ¢â‚¬â„¢s proposed to assess the speech information security by the determining of the speech intelligibility indicators in the limit states. For the correct assessment of the speech information security in terms of its intelligibility, a number of assumptions and limitations were adopted, which are based on practical experience and experimental studies of the speech information protection. The obtained results can be used to develop standards for the speech information protection from leakage via the acoustic channel.
Keywords:	Information Security, Speech Intelligibility; Combined Masking Signals
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	ZERO DOWN TIMEÃ¢â‚¬â€SMART DATA GUARD FOR COLLABORATIVE ENTERPRISE DATAWARE SYSTEMS
Author:	N. Z. Azeemi , O. Al-Basheer, G. Al-Utaibi
Abstract:	COVID-19 initial surge at Wuhan, China brought the pivotal role of virtual enterprise data ware houses in Supply Chain Management (SCM), eventually became a major drive momentum towards Always Available Always Online (A3O) heterogeneous data networks. Reliable and tightly coupled information deluge in the unprecedented trends toward the smart city development as well as deployment of adhoc huge Disaster Management Center (DMC), as regional Centers for Disease Control (CDC) to name a few; are prone to issues on stability, reliability and availability. Smart data storage resources are vulnerable to provide functionality due to their inherent heavy dependence on System Down Time, Redundant Systems and Software Failure or whole multiple site failures. In the absence of Production Database Management Services, duplicate deployment of similar data on disjoint but similar architecture provides a Tightly Coupled Ultimate System, which assures A3O mutually exclusive services. In this paper, we investigated active Data Guard and Data Guard role management or switchover for a real time transition performed for database at standby state to cope up both planned maintenance and accidental RS2F events. We expose our results for deep integration of active Data Guard with ODB in-terms of Fast Sync to align synchronously at an ease of zero of wait states for disk I/O and configurability to Null Data Loss. Over a large range of remote or standby databases null data lost make it certain to zero failover. The impact of Fast-Start Failover in the cloud proximity make sure guaranteed null data lost in synchronously and near null data lost protection asynchronously. Hence, avoids unusual overhead impeding disk I/O and eventually on a primary database. We observe the key performance indicator in failover does not restart the standby database for primary role resumption, but introduce cloud proximity as a new primary database and the process is performed without any intervention of manual migration. The reliability of active data guard Redo is flexible across not only standby databases but also primary sites running different operating system over diverse hardware platforms. The Redo capability enables migration with minimal downtime for any transaction in the clouds, therefore adds an inevitable functionality to big data applications.
Keywords:	Cloud Applications, Disaster Management, Enterprise Virtualization, Fault Tolerant, Smart City, Smart Data Guard, Tightly Coupled Systems
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	MULTI-LAYER COLOR QR CODE DYNAMIC DECODER FRAMEWORK WITH FUZZY COLOR RECOVERY
Author:	BAKRI BADAWI, TEH NORANIS MOHD ARIS
Abstract:	In this paper, we proposed a dynamic framework for a multi-layer color QR code decoder. The proposed decoder framework shows the general steps to decode color QR code. It contains a configuration setting standard that allows other researchers to refer in order to decode their color QR code based on the colors used in the encoder. The framework starts with color QR code detection, then search for color reference. This is followed by fuzzy sets selection based on the color QR code. Color enhancement for the QR code is implemented based on the fuzzy set decision. Next, is color de-multiplexing to get Black and White (B/W) QR code. The de-multiplexing process is based on a configuration file, for the QR code color setting. Finally, is the decoding and merging of the results for the B/W QR code to obtain the original file. We use two datasets with color reference to evaluate our framework. The first dataset used is generated by Yang et al., 2018 encoder and we obtained 83% success rate for the detection and color de-multiplexing. The second dataset is generated from our encoder and produced 90% decoding success rate. The experiment shows the framework can successfully work with different sizes of color QR code.
Keywords:	Fuzzy, Color QR Code, Decoder, Framework, Color Enhancement
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	OPTIMIZING DECISION TREE CRITERIA TO IDENTIFY THE RELEASED FACTORS OF COVID-19 PATIENTS IN SOUTH KOREA
Author:	ISTON DWIJA UTAMA , IVAN DIRYANA SUDIRMAN
Abstract:	This study aims to identify the released factors for patients infected by SARS CoV 2 virus. By taking samples from South Korea Country, then we were using the data mining process for classifying problems by optimizing the decision tree model from RapidMiner Studio educational 9.6.00 edition. Based on our study showed that the accuracy of this model is 80.46% +/- 1.68% (micro average 80.46%). The result for this study showed that location or region is a dominant factor rather than age and sex, therefore the South Korea policy to take the drive-through, walk-through, tracing, and use digital maps to let society aware is effective to prevent the spreads of diseases. The Implication of this study reconfirms that stay away from an infected area or social distancing such as staying at home is the right decision to minimize and reduce pandemic spreads, and other countries can adopt or modify the strategy that already did in South Korea.
Keywords:	SARS CoV2, South Korea, Data Mining, Decision Tree Model
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	THE ROLE OF HOFSTEDE DIMENSIONS ON THE READINESS OF IOT IMPLEMENTATION CASE STUDY: SAUDI UNIVERSITIES
Author:	OMAR SABRI , TAHIR HAKIM , BADRIAH ZAILA
Abstract:	The importance of the Internet of Things (IoT) in various institutions and organizations is crucial in the quality of services, provision, and facilitation in providing those with related services. Therefore, before deciding to implement these regulations in the institutions, it is essential to study the institutionÃ¢â‚¬â„¢s situation from various aspects to avoid loss and failure. This research study is based on the role of Hofstede Dimensions on the readiness of IoT adoption in Saudi universities. This study reviews the literature about the concept of Hofstede dimensions on the readiness of the IoT on a global scale. In-depth study and practical implications are assessed by hypothetical testing based upon predetermined variable and their possible impact of adopting IoT. A questionnaire was conducted and distributed in 6 universities in located the kingdom of Saudi Arabia. The questionnaire received 390 responses. SPSS 24.0 was used to examine the possible impact and degree of impact on the adoption of IoT in these Universities. The results demonstrated that there was a positive relationship between Hofstedefactors and the readiness of Saudi universities in applying the IoT.
Keywords:	Hofstede Factors, IoT, Saudi Universities, Culture Dimensions, IoT Applications
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	VEHICLE LOGO RECOGNITION BASED ON VEHICLE REGION AND MULTI-SCALE FEATURE FUSION
Author:	HOANH NGUYEN
Abstract:	This paper presents a deep learning-based vehicle logo recognition framework based on vehicle regions and single shot framework with multi-scale feature fusion. To exactly locate front and rear regions of a vehicle, a vehicle region detection network based on region proposal network is designed. The vehicle region detection network uses ResNet-50 as the base network to generate base convolution feature maps. Atrous convolution is used after the base network to enlarge the receptive field to incorporate larger context information without increasing the number of parameters or the amount of computation. Each of detected vehicle region is fed into a vehicle logo recognition network based on single shot framework. The vehicle logo recognition network adopts Darknet-53 as the base network to generate proposals from each vehicle region. To enhance the performance of the proposed framework on small vehicle logo recognition, this paper designs a multi-scale feature fusion subnet which generates high-level semantic feature maps from base convolution feature maps. The tasks of detection predictions and object classification are performed on the multi-scale high-level semantic feature maps. Furthermore, a collected dataset based on a large public vehicle dataset is used to evaluate the proposed method. Experimental results on the collected dataset show the effectiveness of the proposed method on vehicle logo recognition. The proposed method provided a promising solution to vehicle logo recognition applications.
Keywords:	Vehicle Logo Recognition, Deep Learning, Multi-Scale Feature Fusion, Atrous Convolution, Single Shot Framework
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	ADEQUACY AND EQUIVALENCE OF THE TEXTS TRANSLATED VIA MACHINE TRANSLATION SYSTEMS
Author:	OKSANA TARABANOVSKA, YEVHENIIA MOSHTAGH, MARIA OSINSKA, ARYNA RYZHENKO, OLENA HAVRYLOVA
Abstract:	The article is devoted to the problem of adequacy and equivalence of the texts translated via machine translation systems. The purpose of the study is to analyze existing machine translation technologies, identify the main errors in the translation of the texts of various subjects, and select the translator which does the highest quality translation of various thematic texts. Two main machine translation technologies have been in focus of the research: a rule-based translation technology (Rule-Based Machine Translation, RBMT) and a statistical translation technology (Statistical Machine Translation, SMT). It has been found out that each technology has both advantages and disadvantages. Among all the studied translation systems, namely Translate.ru (PROMT), Trident Software (Pragma), SYSTRANet, Babylon, Google Translate and Yandex.Perevod, Yandex has proved to be the most successful to complete the translation task regardless of the subject of the translation. Furthermore, it translates various lexical units quite well and confidently copes with grammatical constructions. As it has been found out, Google Translate is inferior to Yandex in the translation of lexical units, especially thematic ones, but has almost the same indicators regarding grammatical correctness. In the third place is the PROMT translator, which translates grammatical constructions well, but has problems with translating thematic vocabulary. The conclusion that can be derived from the research is that we have the most reason to advise Yandex.Perevod to use for translating the texts of different subjects. Despite of the fact that a genuine solution to the problem of machine translation has not yet been found, the development of new scientific theories, modern achievements in the field of Computer Science, Programming, and Linguistics give hope that it will be possible to satisfactory solve this task in the immediate future.
Keywords:	Computer Technologies, Translation Quality, Machine Translation, Computerized Terminological Base, Translation Process.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	EFFICIENT PREDICTION OF PHISHING WEBSITES USING MULTILAYER PERCEPTRON (MLP)
Author:	AMMAR ODEH , ABDALRAOUF ALARBI , ISMAIL KESHTA , EMAN ABDELFATTAH
Abstract:	Maximizing user protection from Phishing website is a primary objective in the design of these networks. Intelligent phishing detection management models can assist designers to achieve this objective. Our proposed model aims to reduce the computational time and increase the security against the phishing websites by applying the intelligent detection model. In this paper, we employed Multilayer Perceptron (MLP) to achieve the highest accuracy and optimal training ratio to maximize internet security. The simulation results show the selection of the most significant features minimize the computational time. The optimal training percentage is 70% as it minimizes the time complexity and it increases the model accuracy.
Keywords:	MLP, Activation function, semantic attack, Phishing
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	THE EFFECT OF IMAGE PREPROCESSING TECHNIQUES ON CONVOLUTIONAL NEURAL NETWORK-BASED HUMAN ACTION RECOGNITION
Author:	NADYA A SIMANJUNTAK , JANOE HENDARTO , WAHYONO
Abstract:	The number of the worldÃ¢â‚¬â„¢s population aged 65 or over (elderly) is projected to increase to almost 1.5 billion by 2050. Elderly is vulnerable to various risks on their daily activities, so it is necessary to recognize their actions with machine vision technology automatically. One of the methods to do action recognition is using Convolutional Neural Network (CNN). However, using CNN without preprocessing will result in poor classification accuracy. The preprocessing methods affect the performance of the resulting model. Therefore, it is necessary to research various image preprocessing methods on CNN input to get the optimal model. In this study, various preprocessing methods, namely resizing, enhancement, creation of binary and gradient images, and data augmentation, are compared. After that, the obtained models are evaluated using action recognition dataset. In the validation results, it is found that the best preprocessing method is 64Ãƒâ€”64 grayscale image preprocessing with sharpening and augmentation in the form of the horizontal flip, which achieves an accuracy of 0.852. Meanwhile, in the testing results, the preprocessing method that produces the best accuracy is the 64Ãƒâ€”64 grayscale image preprocessing with sharpening, with an accuracy of 0.660.
Keywords:	CNN, Image Preprocessing, Human Action Recognition, Machine Vision.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	A SCATTER SEARCH HYBRID APPROACH FOR TEAM ORIENTEERING PROBLEM
Author:	HAMZAH ALKHAZALEH, MASRI AYOB, AMER IBRAHIM, NAHIL ABED, MOHAMMAD HABLI, TAWFIK SAID
Abstract:	The Team Orienteering Problem (TOP) is a particular vehicle routing problem in which the aim is to search a fixed number of paths that maximize the scores associated with a set of given locations within a limited time. Scatter Search explores a search space of solutions systematically by evolving a small set of reference solutions. It has strategies for diversification (in diversification generation and subset generation methods); and intensification (in the improvement and updating method). However, all these methods are very time consuming. This paper proposes a scatter search hybrid approach (SSHA) to deal with the TOP by reduce processing time and maintaining a good set of references solutions in terms of diversity and quality. It uses some new operators, called reference set queen bee-method to initializing and updating the RefSet, and greedy select parents to selecting pairs from a reference set for the combination method to generate a new solution. Furthermore, to improve the quality of the solution, a local search is employed, called steepest descent to explore neighborhood in a fully deterministic manner and then selects the best neighbour. Experiments conducted on the standard benchmark of TOP clearly show that proposed approach outperforms the solving methods in the scientific literature. Our algorithm detects all but one of the best known solutions. A statistical test was conducted to determine the algorithm that performed better compared with the others. The results revealed that SSHA outperformed all state-of-the-art algorithms and was comparable to one algorithm.
Keywords:	Optimization, Metaheuristic, Team Orienteering Problem, Scatter Search Algorithm, Local Search.
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	ANALYSIS OF MONITORING INFORMATION SYSTEM FOR PRODUCTION FACILITIES SUPPORT AND AGRICULTURAL BUSINESS CAPITAL
Author:	YOHANNES KURNIAWAN , DEVYANO LUHUKAY , JOHAN , GANESH BHUTKAR
Abstract:	The results of the analysis of the running system shows that the problems faced by the organization today is tracking of realization and development information for the aid of production facilities and capital of agricultural business that has not been optimal. The purpose of this study is to analyse the needs of systems that support the implementation of aid monitoring. The information system of monitoring and evaluation of production facilities is considered to be the most appropriate to implement the strategy, as well as to overcome the problems occurring in the Ministry of Agriculture in relation to monitoring and evaluation of production facilities and agricultural business capital. The information system of monitoring and evaluation of production facilities and agricultural capital is an internet-based system to facilitate the Central Team (Minister of Agriculture and Technical Team of Directorate General), Provincial Agriculture Development Team, and Technical Team of Regency or Municipality Agriculture Office to access realization and development information for accurate agricultural business aid without being limited by space and time.
Keywords:	Information, System, Monitoring, Evaluation, .
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	A DEEP LEARNING FRAMEWORK FOR SMALL TRAFFIC LIGHT RECOGNITION IN TRAFFIC SCENE IMAGE
Author:	HOANH NGUYEN
Abstract:	Traffic light recognition plays a crucial role in intelligent transport systems. In traffic scene images, traffic light instances usually occupy a small region. Thus, recent state-of-the-art object detectors such as Faster R-CNN and SSD obtain low accuracy on traffic light recognition in traffic scene images. This paper presents a deep learning framework for traffic light recognition in traffic scene image. Considering that feature maps at shallow layers have higher resolution which will improve small traffic light detection, and feature maps at deep layers contain more discriminative representation which will improve traffic light classification task, this paper designs a feature fusion subnet for feature extraction to solve the problem of small traffic light detection. The feature fusion subnet fuses feature maps at different layers. Thus, the feature fusion subnet not only can preserve the information of small traffic lights but also enhance the semantic information. Furthermore, a detection subnet is designed at the detection prediction stage. The detection subnet includes multiple detection layers, and each layer performs detection predictions with a coarse-to-fine detection strategy. The coarse-to-fine detection strategy is applied to improve the classification performance of the detection network. The proposed approach is evaluated on Bosch Small Traffic Lights dataset. Experimental results show that the proposed approach obtains higher accuracy compared with recent state-of-the-art detectors such as Faster R-CNN and SSD.
Keywords:	Traffic Light Recognition, Deep Learning, Intelligent Transportation Systems, Feature Fusion, Advanced Driving Assistance System
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text

Title:	FACTORS AFFECTING INTENTION TO USE MOBILE COMMUNICATION SYSTEMS IN LIBYA SCHOOLS
Author:	NOUREDDON H. IBRAHIM BELEID , ADAM AMRIL JAHARADAK ,ABDULGADER AB SINUSI
Abstract:	Adoption of communication innovations that connect schools and families of school going children is suggested to encourage and facilitate active participation of parents in their children studies and ultimately lead to the improvement of academic performances and extra curriculum success of students. Mobile phone penetration in Libya has increased considerably. In fact, International Telecommunication Union reported that Libya currently has 121 mobile phone subscriptions per 100 inhabitants and boasts one of the cheapest broadband rate in the Middle East. Despite this growth, mobile communication systems (MCS) are not widely used to effectively resolve the issue of poor communication between schools and parents/guardians as requested by parents groups in Libya. At the moment the extant literature seems to overlook this important gap. As a result factors affecting the adoption of these technologies are misunderstood. This study aims to empirically test the influence of Relative Advantage, Compatibility, Complexity, Result Demonstrability, Perspective on Communication as well as public Trust on Internet on mobile communication systems adoption. The authors surveyed 541 parents of school going children as well as staff of twelve secondary schools in Libya. A structured equation modelling (SEM) technique was used to analyse the data. The result shows that Relative Advantage, Compatibility, Complexity, Result Demonstrability, Perspective on Communication and trust on Internet significantly influences intention to use mobile communication systems. This means that education authorities should educate both staff and parents/guardian about the benefits of using MCS, ensure them that MCS are compatible to their values, make the MCS easy to use, demonstrate the expected results of MCS and assure the users that Internet is free from any form of government manipulation. The empirical evidence provided by this study could be used by the policy makers, authoritative bodies and relevant stakeholders to formulate policies and guidelines in implementing and popularizing mobile communication systems usage among parents or guardians and the staff of Libya schools.
Keywords:	Mobile Communications Systems, Relative Advantage, Compatibility, Complexity, Result Demonstrability, Perspective on Communication, Trust on the Internet, Adoption, Libya
Source:	Journal of Theoretical and Applied Information Technology 16^th August 2020 -- Vol. 98. No. 16 -- 2020
Full Text