		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 2022 | Vol. 100 No.08

Title:	NETWORK PERFORMANCE OPTIMISATION USING ODD AND EVEN DUAL INTERLEAVING ROUTING ALGORITHM FOR OIL AND GAS PIPELINE NETWORKE
Author:	MOHAMAD YUSRY LEE, AMIERUL SYAZRUL AZMAN, SIVA KUMAR SUBRAMANIAM, FARAH SHAHNAZ FEROZ, R SUJATHA
Abstract:	Wireless Sensor Network (WSN) provide promising and resilient solutions in a broad range of industrial applications, especially in the pipeline of oil and gas midstream pipeline. Such application requires a wide communication coverage area because the pipelines are usually stretched over a long distance. To fit the requirement, the sensor nodes have to be arranged in a linear formation. Performance evaluation has been carried out using reactive (AODV) and proactive (DSDV) routing protocols during the initial phases of the research. The factors causing the overall network performance to degrade as the network density increases are identified. It is mainly due to the load's increment, which will inhabit the packet queue and clog the network. These will result in packet loss, throughput unfairness, higher power consumption, and passive nodes in the network. The AODVEO reactive routing protocol is proposed to reduce the routing instabilities by splitting the traffic into (1) even-path and (2) odd with the consideration of the x-axis. The proposed routing algorithm was then compared to AODV and DSDV routing algorithms in terms of network performance with node deployment of 20,40,60,80,100,120,140,160,180 and 200. The proposed routing algorithm has shown substantial improvements in the delivery ratio (19.07% more), throughput (9 kbps more), fairness index (0.06 more), passive node's presence (30% less), and energy consumption (0.038J less) when compared to AODV on 200 nodes deployment.
Keywords:	Wireless Sensor Network, Linear, Static, WSN, Routing Algorithm, Oil and Gas Pipeline
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	EFFECTIVENESS OF ENHANCED TAKAGI SUGENO KANG’S FUZZY INFERENCE MODEL
Author:	SUGIYARTO SURONO, GOH KHANG WEN, CHOO WOU ONN, YOSZA BIN DASRIL, ASIH YULI ASTUTI, NITHYA PERIASAMY
Abstract:	Fuzzy logic is one of the components from soft computing and it is useful as a method to map the problem from input into the desired output. The main feature of fuzzy logic is membership function. Takagi Sugeno Kang fuzzy system appears to be more preferred and easier to use, thanks to its simple structure and high proximity. The use of learning rate is extremely important in Mini-Batch Gradient Descent to improve the quality and the rate of training convergence. However, choosing the right learning rate is one of the shortcomings of the MBGD method, so AdaBound is used to optimize the selection of learning rates. AdaBound is an adaptive method that applies dynamic boundaries on learning rate. The said dynamic boundaries has the definition of learning rate limitation, both from up and down, to make sure the learning rate is neither too big nor too small. Aside from that, the boundaries become tighter as iteration goes and forcing the learning rate close to constant value. The optimization of AdaBound is intended not only to improve the convergence rate, but also to optimize the convergence into global minimum value in the end of training period. The method used in this study is Takagi Sugeno Kang (TSK) method. The rule of Takagi Sugeno Kang fuzzy system will be optimized using Mini-Batch Gradient Descent that has been modified by AdaBound. The goal of this study is to observe the accuracy of classification done by TSK with MBGD-A. The data used in this study is obesity data obtained from Kaggel dataset, while the variables are composed of three independent variables and one dependent variable. There are 32 rules in the TSK inference model based on data, however only 24 of them can be applied. To obtain firm numbers, the defuzzification value is derived using the weighted average approach from the 24 rules obtained. MAD was utilized as the evaluation model, and the error value was 14,549, indicating that the approach was effective and efficient.
Keywords:	Fuzzy TSK, Optimization, MBGD, AdaBound
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	SPECTRAL UNMIXING OF HYPERSPECTRAL IMAGES USING MULTI-OBJECTIVE LION-RIDER OPTIMIZATION TECHNIQUE
Author:	RAJA NATARAJAN, VADIVEL RAMASAMY
Abstract:	In hyperspectral image processing, spectral unmixing is a key computation for extracting endmembers and determining their fractional abundances from mixed pixels. Despite the fact that the sparse unmixing model has recently attracted a lot of attention, the acquired hyperspectral images are influenced by noise, indicating that the sparse unmixing model needs to be improved in order to extract the best collection of endmembers. The Lion-Rider algorithm is proposed in conjunction with a linear sparse spectral unmixing to address this complexity. The proposed optimization algorithm determines the fractional abundances of the endmembers bydefining a multi-objective function. The objective function includes Euclidean and Frobenius norms and optimization variables that are associated with the abundance and mixing matrices. The proposed lion-rider optimization approach is the modified rider optimization algorithm whichuses lion optimization algorithm as anintegral component of computation.To define the objective function in estimating fractional abundances, the optimization variables namely Reconstruction Error, Sparsity, Spatial Neighbor, and Spatial Neighbor Correlation are used simultaneously. Urban and Cuprite hyperspectral image datasets are used to evaluate the proposed method. Based on the performance analysis, the proposed lion-rider optimization approach outperformed its competitors namely,Bilinear and Trilinear Multi-Objective Spectral Unmixing, Robust Collaborative Nonnegative Matrix Factorization, Pareto-Multi-Objective Spectral Unmixing, and Rider Optimization, in estimating the endmembers and their correspoinding fractional abundances with a minimal reconstruction error and root mean square error of 22.4027 and 0. 0297, respectively.
Keywords:	Hyperspectral Image; Spectral Unmixing; Endmembers; Fractional Abundance; Multi-Objective Function.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	OPTIMAL ALLOCATION AND SIZING OF CAPACITORS EMPLOYING PATTERN SEARCH OPTIMIZATION
Author:	ERITA ASTRID, KRISMADINATA, DONI TRI PUTRA YANTO, CITRA DEWI
Abstract:	Utilizing capacitors has long been recognized to improve the voltage profile and reduce the losses in power system. Many strategies have been successfully developed to determine the best allocation of capacitors in order to achieve the greatest results. In this paper, a method to find the optimal placement and sizing of capacitors in distribution system is presented. The objective function is composed of the line loss and the voltage profile of each bus. A power loss sensitivity factor is employed to identify the appropriate buses for optimal location and sizing of capacitors which is formulated and determined by using Pattern Search Optimization. This technique is used in power distribution system to select candidate locations for compensating reactive power which will enhance the system voltage and lower the power loss. To validate the proposed method, the IEEE 34 radial distribution system is used to observe the method’s performance, effectiveness, and efficiency in finding solutions.
Keywords:	Capacitor Allocation, Capacitor Sizing, Loss Sensitivity Factor, Pattern Search Optimization
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	IMPROVING OPTICAL CHARACTER RECOGNITION ACCURACY FOR INDONESIA IDENTIFICATION CARD USING GENERATIVE ADVERSARIAL NETWORK
Author:	EMILDA ZHANG, VINCENT ARDYAN PUTRA, GEDE PUTRA KUSUMA
Abstract:	e-KTP (Kartu Tanda Penduduk Elektronik) is a national identity card for Indonesian has been widely used not only as an identification but also used in various aspects of life such as for administration, finance-related matters, etc. Detecting information from the ID card field can be done using previous methods with segmentation and text extraction. However, these methods need a proper high-quality captured image. In fact, most of the ID card images are taken using mobile phones' cameras, which do not really produce good quality images all the time. Image enhancement using GAN (Generative Adversarial Network) was also proposed as a method of increasing the accuracy of OCR (Optical Character Recognition). But in previous studies, this method was only limited to document text images with a white background. To overcome these problems, we propose a new pre-processing approach consists of DeblurGAN (Generative Adversarial Network for deblurring image), shadow removal, and binarization to pre-process the image for Tesseract-OCR. We also propose a simple post-processing method for Tesseract-OCR output to extract key-value pairs for each field in e-KTP. By using our approach, we have achieved an average Character Error Rate of 18.82% which is better compared to without pre-processing which is 38.13%.
Keywords:	Optical Character Recognition, Tesseract Model, Generative Adversarial Network, Pre-processing, Character Error Rate
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	EXPLORING POSITIVE EMOTIONS AND GAMES TECHNOLOGY AMONG OLDER ADULTS WITH MILD COGNITIVE IMPAIRMENT
Author:	NITA ROSA DAMAYANTI, NAZLENA MOHAMAD ALI, HYOWON LEE
Abstract:	Mild cognitive impairment (MCI) is one of the cognitive challenges confronting older adults. MCI interferes with the memory state and is closely related to feeling. MCI affects the emotional state of older adults. Identifying the exercises or brain training activities that contribute to positive feelings among older adults with MCI is therefore vital. The study investigates the use of games technology and its contribution to positive emotion on cognitive to older adults with MCI. Twelve older adult respondents aged 50 and above were chosen from two nursing homes to take part in this study. The Mini-Mental State Examination set of questionnaires was used to screen respondents to differentiate those with cognitive impairment. We conducted in-depth interviews to explore activities that contribute to positive effects in older adults with MCI. Results show that activities such as listening to old music, playing games, and social activities with family and recreation incrementally improve their positive feelings. Games technology has the potential to help older adults to train their cognitive and contributes to positive emotions. An innovative game design could be proposed with memory reminiscence therapy that may be advantageous to older adults in overcoming their cognitive and improving positive feelings.
Keywords:	Mild Cognitive Impairment, Older Adults, Technology, Positive Emotion
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	FUTURE HOST LOAD STATE DETECTION WITH HIDDEN MARKOV PREDICTION MODEL
Author:	M. AMARENDHAR REDDY , K. RAVINDRANATH
Abstract:	In virtual machine(VM) live migration process, the VM selection and host detection which are overloaded or underload is place crucial role. host load is dynamic nature, so detection of overload or under load is very challenging take, the live migration process is done with current host loads state, we proposed method, it use future host state, the future loads detection by using Hidden markov model, by this it avoids intermediate live migration of VM. Our suggested techniques are tested using CloudSim simulations on a variety of PlanetLab actual and random workloads. The experimental results reveal that our suggested algorithms outperform the other competitive algorithms in terms of service-level agreement violations, number of VM migrations, and other metrics.
Keywords:	VM Live Migrations. Host Selection Placement And Host Detection
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	RESEARCH ON THE DEPLOYMENT OF RFID TECHNOLOGY TO ENHANCE SUPPLY CHAIN INVENTORY PERFORMANCE
Author:	MOUAD BEN-FARESS, ABDELMAJID ELOUADI
Abstract:	We give in this research the significance of innovation advancement and its effect on the improvement of store network the executives execution, for example, distribution center administration frameworks, mechanical technology, RFID innovation which is our principle center in this paper by introducing Using a Newsvendor model, specialists looked different strategies to utilize RFID to forestall stock misfortune. We analyze the effect of request satisfaction rate, RFID improvement rate, and label cost in an examination of two situations reliant upon whether or not to embrace RFID. The findings reveal that the choice to install RFID is influenced by the order fulfillment rate; when the order fulfillment rate falls below a certain point, the store profits more from RFID deployment. We also present an analytical critical tag cost, which reduces the cost of RFID adoption.
Keywords:	RFID Technology, Inventory Accuracy, Newsvendor Model
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	PENALIZED REGRESSION METHOD IN HIGH DIMENSIONAL DATA
Author:	ZUHARAH JAAFAR, NORAZLINA ISMAIL
Abstract:	In huge multivariate data set with a number of variables greater than the number of samples, the standard linear model (or ordinary least squares method) performs badly. In such situations, a better option is penalized regression, which allows you to design a linear regression model that is penalized for having too many variables by adding a constraint to the equation Shrinkage or regularization procedures are other names for this. The penalty has the effect of reducing (i.e. shrinking) the coefficient values towards zero. This permits the coefficients of the less important variables to be near to or equal to zero. By decreasing the number of coefficients and maintaining those with coefficients greater than zero, penalized regression models improve prediction in new data when compared to traditional methods. We demonstrate that the proposed regularizer is capable of achieving competitive results as well as exceedingly compact networks. Extensive tests are carried out on a number of benchmark datasets to demonstrate the effectiveness of the method.
Keywords:	Lasso, Ridge, Adaptive Lasso, Elastic-Net, Vgg-19, MNIST, CIFAR-10, ImageNet
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	A DATA COLLISION AVOIDANCE AND DELAY-ENERGY EFFICIENT MAC PROTOCOL FOR WIRELESS BODY AREA NETWORK
Author:	ALOKE KUMAR SAHA, SHAH MURTAZA RASHID AL MASUD, MD. RAJIBUL ISLAM, MD. AKHTARUZZAMAN ADNAN
Abstract:	Traffic collision is one of the main reasons for the excessive delay and higher energy consumption in Wireless Body Area Networks (WBANs). WBAN is an emergent healthcare technology that has been designed for urgently monitoring patients. To transmit patients’ physiological data to the healthcare center, it is very important to design a delay tolerant and energy efficient Medium Access Control (MAC) protocol. Medical data are time-bounded; hence any delay in transmission may impede patients’ life. Hence, in this research, we propose a data collision avoidance and delay-energy efficient MAC protocol which is designed considering the Contention Access Phase (CAP) of IEEE 802.15.4 based MAC superframe structure and also Exclusive Access Phase (EAP) of IEEE 802.1.5.6 based MAC superframe structure. We experiment with the proposed scheme using the Castalia simulator and compare the results using different scenarios. First of all, we compare the delay and energy efficiency considering different numbers of nodes ranging from 1 to 12 nodes. Secondly, the results are compared with data of various sizes ranging from 16 to 255 bytes. In both cases, results are verified for both IEEE 802.15.4 and IEEE 802.1.5.6 standards and it is found that delay and power consumption is much lower in EAP enabled IEEE 802.15.6 based MAC protocol. In addition, in the third scenario, we consider five different types of data with different priority levels and the experiment result shows that data with the higher priority level consumes lower energy and minimum delay than that of data with lower priority levels in IEEE 802.15.6 based collision avoidance MAC protocol. Finally, we compared the proposed EAP enabled IEEE 802.15.6 based MAC protocol with conventional IEEE 802.15.6 and state-of-the-art i-MAC protocol. The performance comparison is done for both delay and energy consumption. The results show that our proposed MAC model performs better than that of the existing protocol and standard.
Keywords:	WBAN, MAC, Delay, Energy, Traffic Collision
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	A REVIEW ON IOT ENABLED TECHNOLOIES FOR DESIGN AND DEVELOPMENT OF SMART AGRICULTURE SYSTEMS
Author:	J.ARUMAIRUBAN, Dr.S.SANTHOSHKUMAR,
Abstract:	Indian economy majorly depends on the agriculture as its contribution is high in economy as well a grater population is depending on farming as they earn livelihood through the practice. An integrative way farming can be practiced to developed for smart agriculture, this practice increase the convenience of the farmers basing on climatic conditions and it also develops the flexibility of farmers to farming. The capability of smart farming can be extended by using IoT (Internet of Things) technology as it is a fundamental in industry 4.0. IoT implements an Automatic irrigation. In this paper, the discussion is done on the conventional practices and the new techniques through research works for development and growth of cultivation is performed in order to benefit the farmers. These works used different technologies and methods to build a smart farming based on IOT. Each work is described and their result analyses are analyzed. Then acomparative analysis is performed on all the works and the best method that can best in developing smart farming is chosen.
Keywords:	IoT (Internet of Things), Automatic irrigation, Smart Agriculture.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	BIG DATA CHALLENGES: PRESERVING TECHNIQUES FOR PRIVACY VIOLATIONS
Author:	TAMER ABDEL LATIF ALI, MOHAMED HELMY KHAFAGY, MOHAMED HASSAN FARRAG
Abstract:	The endless and quick development of data has brought the consideration of analysts to utilize it within the most conspicuous way for decision-making in different rising applications. These huge data are greatly valuable and profitable for logical investigation, increment efficiency in trade, and make strides for humanity. It makes a difference from the open division to commerce exercises, healthcare to way better route, smart cities to national security. Despite the fact that there are more opportunities to work, the obstacles of handling these data have also grown. In this study, various aspects of big data, as well as their applications and limitations, are discussed. This paper focuses on privacy challenges, privacy violations, and privacy-preserving techniques in big data, smart cities, and IoT. This paper introduces a comparative study among the different privacy-preserving techniques showing their advantages and their drawbacks to propose a powerful and applicable privacy protection technique that securely guarantees data integrity when dealing with big datasets and sensitive information in important fields.
Keywords:	Big Data, Big Data Challenges, Security, Privacy, Privacy Violations, Privacy-Preserving Techniques, Data Integrity.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	AN OPTIMIZING REBROADCAST MECHANISM FOR MINIMIZING THE CONTROL OVERHEAD IN MOBILE AD-HOC NETWORKS
Author:	BAIDAA HAMZA KHUDAYER, LIAL RAJA ALZABIN, MOHAMMED ANBAR, RAGAD M TAWAFAK, TAIEF ALAA ALAMIEDY, SOHAIL IQBAL MALIK, GHALIYA MUSLEM ALFARSI
Abstract:	Mobile Ad-hoc Network (MANET) is assumed an encouraging technology that constructs interim network connectivity without the aid of any prior architecture which is required during abnormal circumstances or in provisional events such as in emergencies, crisis conditions, and military conflicts. Source routing in MANET is challenged by arbitrary and random node mobility that triggers a lot of route discoveries due to frequent link breakages. This generates a massive number of Route Request (RREQ) packets resulting from the flooding procedure. The flooding procedure is used in the route discovery process and produces a storm of the broadcast, leading to an increase in packet loss and control overhead. Thus, the aim of this research is to enhance the source routing protocols by presenting an optimized route discovery strategy to minimize the RREQs flooding in the network that contributes to diminishing the overhead. The performance of the proposed routing mechanism was evaluated using NS3 and compared to DSR in terms of Normalized Routing Load (NRL) and Packet Delivery Ratio (PDR). The evaluation results showed that the proposed routing mechanism outperforms the well-known mechanisms such as Dynamic Source Routing (DSR) protocol.
Keywords:	MANET, Source Routing, RREQ, DSR, NRL
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	APPLYING AUGMENTED AND VIRTUAL REALITY IN ONLINE AND OFFLINE EDUCAION
Author:	NIYAZOVA GULZHAN ZHOLAUSHIEVNA, RUSTAM ABDRAKHMANOV, ELVIRA ADYLBEKOVA, KOSHANOVA GULNAZIRA DANEBEKKYZY
Abstract:	The technologies of augmented and virtual reality are studied by the example of their use in education. The subject of the study is the study of well-known and previously developed teaching methods using AR and VR, advantages and disadvantages in terms of their use in educational purposes. The purpose of the work is to conduct an analytical literature review and analysis of known methods of using augmented and virtual reality, to present the most promising solutions in various tasks of science. The paper proves the capabilities of augmented reality technology and how they might be used in educational and project-based activities. The goal of this research is to prepare instructors to employ augmented reality technology in their classrooms in online and offline types of education. Moreover, the possibility of using AR technology to develop cognitive interest among students in the process of studying specialized disciplines is substantiated. In this report, it is suggested that components of AR technology be included in 10th grade physics classes, particularly while studying optics.
Keywords:	Virtual Reality, Augmented Reality, Education, Online Education, Offline Education.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	OPTIMIZING REGRESSION ALGORITHM PERFORMANCE FOR WEAK RAINFALL DATASET PREDICTION VIA ENSEMBLE MACHINE LEARNING MODELS
Author:	PRABOWO WAHYU SUDARNO, AHMAD ASHARI, MARDHANI RIASETIAWAN
Abstract:	A flood is a natural disaster that cannot be stopped, but preventive measures can be taken to deal with it. The factors that cause flooding can be predicted using machine learning, one of which is by predicting rainfall. But in reality, rainfall data has many shortcomings, such as missing values and the appearance of outliers that can affect model performance. Therefore, we propose an ensemble stacking method to deal with this problem. The performance value of the Multilayer Perceptron algorithm without Stacking is 10.128 for MSE and1.5696 for MAE. The performance value of the XGBoost algorithm without stacking is 9.2548 for MSE and 1.4427 for MAE. While the performance value of combining the Multilayer Perceptron and XGBoost algorithm with Stacking resulted in an MSE value of 9.2377 and an MAE value of 1.4396. The results show that the ensemble method with stacking can be a solution to improve algorithm performance on weak datasets to predict rainfall value. The novelty of this paper is as follows: machine learning ensembles can handle the weak rainfall dataset to give a better result.
Keywords:	Ensemble Machine Learning, Stacking, MLP, XGB, Rainfall
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	PREDICTING SARCASM AND POLARITY IN ARABIC TEXT AUTOMATICALLY: SUPERVISED MACHINE LEARNING APPROACH
Author:	MOHAMED ABDELRAZEK ABDELAAL, MOHAMED ABDEL FATTAH, MONA MOHAMED ARAFA
Abstract:	Arabic text is one of the main challenges for machine learning and sentiment analysis to this day. In this paper, we introduce an Arabic text classifier that predicts both polarity and sarcasm. Six different supervised machine learning classification algorithms were used and gauged on our Arabic classifiers: Logistic Regression (LR), Multinomial Naïve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF) and K-Nearest Neighbor (KNN) along with different N-gram for tokenizing and TF-IDF for feature selection. SVM shows the best accuracy results (F1-score of 58.5%) when predicting polarity, while DT achieves the best accuracy results (F1-score of 64.4%) when predicting sarcasm. Previous sarcasm classification research achieved (F1-score of 46%) accuracy using BiLSTM on Arabic corpus.
Keywords:	Text Classification, Supervised Machine Learning, N-Gram, Sarcasm Detection
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	DIGITAL MARKETING STRATEGY OF INDONESIAN STARTUPS TO ACHIEVE UNICORN STATUS
Author:	CHRISTINA TJANDRAWIRA, MAULANA IBRAHIM, STEFAN MARTIN, LA MANI, Z. HIDAYAT
Abstract:	The development of the digital startup ecosystem in Indonesia is inextricably linked to digital marketing, as sales of startups occur digitally through websites or mobile applications (apps). The purpose of this study is to analyze the application of digital marketing strategies in Indonesian startups, along with the benefits and challenges of using digital marketing compared to traditional marketing in its efforts to become a “unicorn” startup. The research was conducted on digital startups at the developing level (cockroach) and high level (unicorn), thoroughly examining four startups in Indonesia from various industries. Data collection is carried out through in-depth interviews with key informants in the startup industry, representing various startup categories. This study indicates that the startups named Bukalapak, Sribu.com, Terampil.com, and Koolio.id use various digital marketing channels linked to workforce and marketing budgets, focusing on maximizing the most important media for each startup's category. Content marketing is found to be the primary strategy used by digital marketing practitioners in digital startups. In growing and becoming a unicorn, a combination of digital and traditional marketing is recommended to get the best possible outcomes.
Keywords:	Business Strategy, Digital Marketing Communication, Startups, Marketing Strategy, Inbound Marketing, Online Marketing
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	BORUTA FEATURE SELECTION AND PARTICLE SWARM OPTIMIZATION FOR FRAUD DETECTION ON PAWN TRANSACTION
Author:	MASDRA WAHYU KUNCORO, SUHARJITO
Abstract:	The pawn company is one of the largest financial service companies in Indonesia, pawning is become an alternative for Indonesia people to obtain credit other than Bank. The number of pawn transaction raises the potential for fraud action. The use of PSO has shown promising result for improving classification accuracy. This will be a problem if the dataset used has many attributes. Previous research on fraud detection is usually carried out on credit card transaction, there has not been any research on fraud detection in pawn transaction. This research proposes based on data mining model to combining Boruta Feature selection and Particle Swarm Optimization (PSO). For classification using Gradient Boosted Tree (GBT) and C5.0 to measure the level of accuracy. The research is comparing several classifications and to know the highest accuracy of some classification. Pawn transaction data has been taken from pawn company in Indonesia. There are 216 transactions in 2019 until 2020. Among them, 26 transactions detected as fraud and 191 are no fraud. The attributes used is 24, among other is name of the customer, address, type of work, age, address, loan destination, identity number, collateral category, estimated value of collateral, loan money, credit time, type of product, type of transaction, class of collateral, maximum loan money, weight of collateral, and others. The results indicate that the combination of C5.0 optimizing by PSO and Boruta feature selection gives the highest classification accuracy of 96.82% and the GBT optimizing by PSO and Boruta feature selection reaching accuracy 93.57%.
Keywords:	Fraud Detection, Boruta, Particle Swarm Optimization, Gradient Boosted Tree, C5.0
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	DECISION SUPPORT SYSTEM FOR ELECTRICAL OSH INSPECTION AND TESTING BASED ON FUZZY LOGIC
Author:	NASHRUDDIN ANWAR, ARIEF MARWANTO, MUHAMAD HADDIN
Abstract:	Conventional Electrical OSH inspection and testing usually only refers to one standard (SNI, IEC, IEEE or ANSI-NETA), this has an impact on analysis and a longer time besides the objectivity and subjectivity of the results is also a problem in itself. To overcome this, it is necessary to create an information system and validation of analysis based on Fuzzy Logic. The model is set as an Electrical OSH inspection and testing on the electricity distribution and utilization system. Parameters set include: assessment of administrative documents, assessment, measurement, calculation and testing. The results of the examination and testing are analyzed using the Fuzzy Logic method to improve its accuracy. The results of the development of this model produce a faster and more efficient analysis time and accurate results compared to conventional systems, this is evidenced by application testing on the factory X electricity distribution system which results in the conclusion that it meets the OSH requirements with an output value of 80,8 %. Meanwhile, the factory Y electricity utilization system concluded that it did not meet the OSH requirements with an output value of 40 %.
Keywords:	Inspection and Testing, Electrical OSH, Fuzzy Logic, Distribution System, Utilization System
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	IMPLEMENTING DECISION TREES THROUGH AUGMENTING TREE DATA STRUCTURE FOR CLASSIFICATION PURPOSES
Author:	MAJED ABUSAFIYA
Abstract:	The main goal of this paper is to define a data structure to implement decision trees for classification purposes. A classification problem is defined by a set of items with defined attributes and a set of classifiers, its output is a set of classes of items. The method we followed in this paper is the known problem solving technique called augmenting data structures. The basic tree data structure is chosen. The required information to augment is defined. Also the basic operations to build, update and query this data structure are defined as algorithms. One important issue that was considered in defining this data structure is deal with ill-formed classification. Ill-formed classification may result in having an item ending in zero, one or more final classification classes. One main advantage of this data structure is that it can be used as base for software tools that facilitate the automated and interactive design, update and querying of decision trees for classification purposes.
Keywords:	Algorithms, Decision trees; Augmenting data structures; Classification; Ill-formedness
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	SUCCESS FACTORS OF ERP SYSTEM AT ADHESIVE MANUFACTURING INDUSTRY IN INDONESIA
Author:	DESI LIARTO, ASTARI RETNOWARDHANI
Abstract:	The rapid growth of technology in the digital era requires companies to implement Information Technology System, such as Enterprise Resources Planning (ERP). ERP is an integrated and systematic information system of various business functions to improve cross-functional and enterprise collaboration. In the use of ERP based on SAP Business One, there are several findings related to the ERP system’s internal control that impact the integrity of the ERP system and ease of use. The purpose of this research is to analyze the factors that influence the success of ERP Information System based on SAP Business One with the aim of identifying success factors that can become an alternative solution to improve ERP system. The success factors also need to be considered to ensure successful ERP System in the industry. A new model is proposed to figure out these success factors, which is a combination of Technology Acceptance Model (TAM) and D&M Information Systems Success Model. This research uses data from one of the adhesive manufacturing companies in Indonesia. For determining the factors that affect Perceived Ease of Use, Perceived Usefulness, User Satisfaction and Net Benefits, data was collected with 50 respondents. Data analysis was performed using the PLS-SEM method using software SmartPLS version 3.0. The results show User Satisfaction affects Net Benefits, Perceived Usefulness and Service Quality affect User Satisfaction, Perceived Ease of Use and Management Support affect Perceived Usefulness, and System Quality affects Perceived Ease of Use. In addition, from the answer to open questions in terms of other factors that affect the success of ERP information systems, users answer that human factors, availability of infrastructure, and User Interface affect success of ERP in this digital era.
Keywords:	ERP System, Success Factors, Technology Acceptance Model, Information Systems Success Model, Net Benefits
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	USER SATISFACTION APPROACH TO IMPROVE BUSINESS INTELLIGENCE SYSTEM FOR BANKING INDUSTRY
Author:	LIM GABRIELA, ASTARI RETNOWARDHANI
Abstract:	An information system success is also depending to user satisfaction. This study taken a sample in a Korean Bank to see the relationship between business intelligence and user satisfaction. Business intelligence in a Korean Bank was receiving complaint such as inquiry from BI website is very time consuming, the system has difficulty in processing large data, not user friendly, information is not accurate, information not updated and lack of availability especially every early month. The main aim of this research is to assess user satisfaction towards current BI system using EUCS model and give recommendation to the company for their system development in the future. Data was collected using questionnaire that distributed to BI users in the company. There are 207 responses collected. However, 203 responses are valid in the condition of the user access BI website in 2020. The result of regression analysis is content, accuracy, format, ease of use, timeliness on user satisfaction of BI has significant positive correlation simultaneously and partially. Business intelligence user satisfaction on content, format, ease of use and timeliness is fair. Meanwhile, accuracy on user satisfaction is poor. From user satisfaction scoring indicate that accuracy need to be prioritize when development because it is still poor.
Keywords:	User Satisfaction, Business Intelligence, Bank, EUCS, Analytical Tools
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	MENTAL HEALTH TREATMENT PREDICTION FOR TECH EMPLOYEE WITH THE IMPLEMENTATION OF ENSEMBLE METHODS
Author:	MICHAEL HENRY, SANI MUHAMAD ISA
Abstract:	Individual has two awareness, one of them is mental health. It is the ability of a person to recognize the pressure in work and interaction within social life. Statistics shown an enormous amount of 2.570 billion people in the world experienced mental health disorders including depression, anxiety, alcohol abuse, etc. By considering this fact, mental health is one of the most important life essentials which needs to be taken care of. This study proposes an implementation of ensemble methods such as Bagging, Light Gradient Boosting Machine (GBM) and Stacking with Binary Particle Swarm Optimization (BPSO) as a feature selection and Open Sourcing Mental Illness (OSMI) as the dataset for the purpose of predicting whether IT employees need a mental health treatment or not. This study shows that ensemble methods do not always give better prediction with Naïve Bayes and BPSO which has 88.44% accuracy and Stacking with Naïve Bayes as the meta classifier has 87.86% accuracy, a 0.58% accuracy difference. Based on the performance, this study also shows the best features for predicting mental health treatment needs where IT Employees who have the problems or the best features, need to consult a treatment.
Keywords:	Ensemble Method, Machine Learning, Particle Swarm Optimization, Mental Health, Feature Importance
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	A SCALABLE AND ROBUST CLUSTERING FRAMEWORK FOR HANDLING LARGE DATASETS
Author:	Mrs. RAMANA LAKSHMI ADUSUMILLI, Prof. M. SHASHI
Abstract:	Clustering large datasets often suffer from scalability issues as they involve pair-wise distance computations among all the instances of the dataset. Grid based algorithms achieve scalability as they circumvent the distance estimation step but are vulnerable to quality and coverage issues. In this paper, the authors proposed a new framework for cluster formation with high scalability while maintaining the coverage and quality. The Scalable and Robust Clustering (SRC) framework has three modules. The first module involves PCA to convert the multi-dimensional dataset into a low dimensional grid space and based on the joinable boundaries, the dense grid cells are merged to form macro-clusters representing dense regions. The second module involves density based clustering applied separately within the dense regions to form micro-clusters. Finally the third module involves statistical technique to find appropriate clusters for data objects located in non-dense grid cells. The first two modules of the framework handles scalability issues while the third module focuses on improving coverage without affecting the quality of clusters. The experimental results obtained on bench mark datasets show that the framework could achieve scalability, coverage and quality while handling large multi-dimensional datasets.
Keywords:	Hybrid Clustering, Grid Based Approach, Density Based Clustering, Post Processing.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	FACTUAL MODEL OF INFORMATION TECHNOLOGY ASSISTED ECE CURRICULUM MANAGEMENT
Author:	EDI WALUYO, EKO SUPRAPTONO, AGUS HERMANTO, FAKHRUDDIN
Abstract:	Curriculum management is a very important part of educational management. Curriculum management creates systematic work steps starting from planning, organizing, implementing, and evaluating curriculum. Through information technology-assisted ECE curriculum management, it is easier for principals and teachers to develop a curriculum that facilitates children's learning needs. The objective of this research was to examine and analyze the factual model of information technology-assisted ECE curriculum management that has been practiced so far has contributed to the development of a curriculum that is in accordance with the needs. The qualitative research method was used to obtain in-depth data and carried out interactively as needed. The subjects of this study were the principals and teachers at Taman Kanak-kanak Negeri Pembina and PAUD Lab School UNNES, Semarang. Data collection was carried out by questionnaires, interviews, and Focus Group Discussions (FGD). The results of this research on the factual model of information technology-assisted ECE curriculum management obtained fairly results, and it is necessary to adapt the use of information technology in curriculum management. The implication is that an in-depth study is needed in the field of curriculum management by utilizing information technology in order to provide more effective and innovative curriculum development services according to the needs of children, institutions and society.
Keywords:	Factual Model, Curriculum Management, ECE, Information Technology
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	ENHANCEMENT OF VOLTAGE REGULATION AND LOAD SHARING IN DC MICROGRID USING PSO AND FUZZY LOGIC
Author:	B. MOHAN, C.D. VARAPRASAD, T. NARASIMHA PRASAD
Abstract:	In DC Microgrid stand-alone applications, the main problem is to maintain DC bus voltage regulation and load sharing among distributed generating sources are affected by unequal line impedances. The control strategy is designed in such a way that the sources are assumed to feed current to DC bus via virtual resistance called droop resistance and line impedances. Load sharing between distributed generations (DG) sources is improved done by optimizing droop resistance values, voltage reference values using PSO (Particle Swarm Optimization). A fuzzy logic based distributed control strategy is implemented considering the optimized droop resistance values obtained from PSO, for droop control in order to achieve voltage regulation and load sharing effectively among DG units. The performance of fuzzy based droop controller with optimal droop parameter of DC distributed control scheme is shown better compared with existing PI controller-based approach and results are verified through simulation in MATLAB/SIMULINK.
Keywords:	DC Microgrid, PSO, Fuzzy Logic, Droop Control, Secondary Control, Load Sharing
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	DO MARKET CAPABILITIES AND STRATEGIC ALLIANCES IMPACT IT BUSINESS PERFORMANCE?
Author:	ANDERES GUI, MUHAMAD FAIRUZ AHMAD JASMI, FAIZAH SHAHUDIN, SURYANTO4, KEVIN JONATHAN
Abstract:	The business performance of the corporation was ismpacted by a number of elements, whether internal or external. Because technological advancement continues to advance, businesses should optimise their usage of information technology to improve their business performance in order to obtain an advantage over their competitors in the industry. This article aims to research variables impacting the business performance of a firm, evaluate how information technology governance impacts business performance, and examine how information technology usage impacts business performance, among other things. A questionnaire-based survey was used to gather information from 94 Indonesian business owners, managers, supervisors, and employees. The findings indicate that technological, organisational, and environmental variables all have a substantial impact on IT adoption and the role of the manager in the decision-making process for IT adoption and IT usage in the workplace. The findings provide useful insights that may be used to educate small and medium-sized enterprises (SMEs) about the potential benefits they can reap from utilising the cost-effective capabilities of the Internet to grow their operations. The research model for this study is based on the TOE theoretical development. Also provided by this study is a better understanding for managers or owners of developing companies of the importance of information technology usage, adoption, and governance to make business processes more effective and efficient and improve business performance to achieve a better position in the industry.
Keywords:	IT Adoption, Business Performance, IT Usage, IT Governance, TOE Framework.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	SYNTHESIS OF STUDENT ENGAGEMENT ON ELEARNING: A SYSTEMATIC REVIEW OF THE LITERATURE
Author:	HEND OSAMA, AHMED BAHGAT , SOHA SAFWAT
Abstract:	Restrictions on physical gathering due to COVID-19 has prompted higher education institutions to swiftly adopt e-learning technologies to enhance teaching and learning. While technically, the use of e-learning technologies offers an alternative, importance should be given to such methods’ educational suitability, especially how students engage and learn in the spaces provided by these technologies. In this perspective, we evaluated the extent to which e-learning technologies have aided to instructional and learning practices during the recent years. The study conducted a systematic review employing a recently founded tripartite methodology for performing and displaying literature review studies. The paradigm tackles the literature review process systematically and includes three phases for the critical study of literature: description, synthesis, and critique. This review paper focused on student engagement across e-learning platforms. Needed information were gathered from the Scopus and Web of Science databases. We believe that using numerous datasets and diverse methodological techniques can provide deeper insights into student engagement with e-learning technologies.
Keywords:	Student Engagement, E-learning, Online Learning, Student Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	CRITICAL EVALUATION ON SPAM CONTENT DETECTION IN SOCIAL MEDIA
Author:	ANTONIUS RACHMAT CHRISMANTO, ANNY KARTIKA SARI, YOHANES SUYANTO
Abstract:	The spam content detection problem is still challenging due to its complexity, feature extraction process, language, context-aware detection capabilities, performance, and evaluation method. Spam content detection is different from spammers' detection and thus requires a different approach. This paper aimed to conduct a comprehensive literature review for "spam content detection" to identify the various approaches taken and generate up to date issues, especially in the social media case study. Literature data are collected from 2015 to 2021 based on seven journal repository databases and filtered into 69 main articles. This research compared the latest approaches and methods to see the gaps between these studies. Discussions on the approach, research media, dataset, feature extraction & selection, the language, context-based or not, the algorithm, performance, future research direction, and challenges were carried out. Additionally, this paper also discussed spam content on Indonesian social media and provided comprehensive suggestions for possible implementation, further research direction, and a possible new approach. This article can be used to develop new approaches, methods, and models in detecting spam content on social media.
Keywords:	Spam Content Detection; Social Media; Literature Survey; Systematic Review; Future Research And Challenge
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	IMPROVEMENT OF PARALLEL AVERAGE PARTITIONING AND SORTING ALGORITHM WITH DECREASING SINGLE POINT OF FAILURE AND BOTTLENECK
Author:	AHMED HAMMAD HELAL, MASOUD E SHAHEEN
Abstract:	Sorting algorithms are algorithms which put elements of a list in a certain order. The first sorting algorithms were sequential and there are many contributions to make these algorithms parallel, these contributions have been attracted many researchers may be due to the complexity of solving it efficiently. Parallel sorting algorithms have conquered many problems like decreasing processing time and resource utilization. This paper presents some enhancements on a parallel partitioning and sorting algorithm to overcome single point of failure and bottleneck problems.
Keywords:	Bottleneck, Single Point of Failure, Resource Utilization, Distributed Shared Memory System, Many to Many Communication.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	PV FED MODIFIED MULTILEVEL INVERTER WITH REDUCED NUMBER OF SWITCH COUNT
Author:	HEMALATHA JAVVAJI, BASAVARAJA BANAKARA
Abstract:	Inverter plays very important role in many areas of Renewable Sources of Energy (RSE). One of the major developments in using RSE is solar power. This article introduces the power converter topology and consists of a power interface and various levels of MIT (Multilevel Inverter Topology). A modified version of the Cascade H-Bridge Multilevel Inverter (CH-MLI) has been introduced to improve power quality, power loss and topology complexity and cost. The input voltage is set to the rated voltage by the power converter and transferred to the DC bus. The MIT converts the DC bus voltage to AC and is supplied to an AC load. For such inverters, the ideal number of levels and switching frequency are explored, and five-level architecture is chosen based on the trade-offs. To suppress harmonics, this inverter uses a level shifted in phase disposition pulse width modulation technique, which was chosen after extensive testing of other advanced disposition pulse width modulation techniques. To lower the harmonics even more, the use of filters was studied, and an LC filter has been used, which yielded satisfactory results. The entire system is simulated with MATLAB / SIMULINK. The proposed inverter is compared to CH-MLI in terms of DC sources, number of switches, diodes, driver circuit and dv/dt stress.
Keywords:	Multilevel Inverter Topology (MIT), Modulation Techniques, Duty Cycle, Total Harmonic Distortion(THD), Maximum Power Point Tracking (MPPT).
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text

Title:	ASYMPTOTIC OF SOLVING A DYNAMIC PROBLEM OF ELASTICITY THEORY FOR AN INCOMPRESSIBLE MEDIUM
Author:	D.K. KOIKELOVA, M.M. BUKENOV, A.M. KANKENOVA, R. MURATKHAN, A.B. SERIKBAYEVA
Abstract:	In this paper, the behavior of the solution of the dynamic problem and the theory of elasticity as λ → ∞ for the second boundary value problem is studied. An unimprovable estimate of the rate of convergence of the solution for a compressible medium to an incompressible parameter 1/ λ is obtained. In [1], the following question was considered, approximations of the solution of the problem for an incompressible medium by the solution of the problem for compressible media as λ → ∞, as well as the possibility justification for using the difference schemes proposed in [2] to obtain a solution to the problem under study. In [3,4], the dynamic problem of contact of compressible and incompressible media was considered, theorems on the existence and uniqueness of a generalized solution were proved, and estimates were obtained for the proximity of the solution of a contact problem to solutions of problems for compressible and incompressible media. In this paper, we have studied the stability of the difference scheme proposed by A.N. Kanavalov for solving the dynamic problem of elasticity theory. The approximation analysis allows to select the optimal grid steps associated with the parameter λ.
Keywords:	Incompressible Medium, Deformations, Displacements, E Task Of The Stokes, Theory Of Elasticity.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2022 -- Vol. 100. No. 08 -- 2022
Full Text