		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

March 2023 | Vol. 101 No.6

Title:	CONVOLUTIONAL NEURAL NETWORK BASED RASPBERRY CONTROLLER FOR THE GREENHOUSE MONITORING SYSTEM
Author:	S. SEBASTIN ANTONY JOE, S.J. JEREESHA MARY, RONALD S. CORDOVA, HAYDARSABEEH KALASH, ALI AL-BADI
Abstract:	The greenhouse monitoring system is a smart approach to monitoring and controlling the greenhouse environment with the regular monitoring of indoor carbon dioxide, humidity, soil moisture, temperature, soil ph level, and light, smoke,and air pressure. Internet of Things (IoT) based sensors are the fundamental components of green monitoring systems and can be utilized in horticulture, agriculture, and many other fields. The IoT-based sensors sense small deviations in the values and forward the signals to the controller to manage the respective switch and make corrections at right time and is a complicated task and to tackle this complication we propose a novel Raspberry pi controller based green monitoring system which includes IoT sensors for the monitoring of light, temperature, smoke, soil moisture, LCD module, 12V DC fan, LDR sensor, pump, and bulb. The smoke sensor will sense if any smoke coming from the electric connection and send an alert message by turning on the alarm, the temperature can be sensed with the temperature sensor and if it measures high then the DC fans are automatically switched on and off if it goes low. The water level in the soil can be sensed by the soil moisture sensor and automatically the pumps get on.The light gets turned on when the LDR sensor senses the absence of light and the status of the monitoring system can be forwarded each 30 sec using the GSM module sensing data from different sensors are detected and analyzed with the proposed Dilated Convolutional Neural Network (DCNN) based Fire Hawk Optimization (FHO) algorithm. Based on the classification outcomes the system takes the necessary actions that are aforementioned. The proposed system uses python programmed Raspberry pi controller and the implementation shows that the proposed system reduces the cost and complications and regularly maintains the monitoring of the greenhouse system without any hardware faults. Further, the detection of data is also superior to the methods that are compared in terms of soil moisture with time 4.11 sec, delay with 3.22, and detection accuracy of 95%.
Keywords:	Greenhouse, sensors, IoT, Dilated Convolutional Neural network, Fire hawk optimization, Raspberry pi, and indoor.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	REVIEWING OF CYBERSECURITY THREATS, ATTACKS, AND MITIGATION TECHNIQUES IN CLOUD COMPUTING ENVIRONMENT
Author:	KHOLOD SAEED ALQAHTANI, AZZAM MASHHEN ALBALAWI, MOUNIR FRIKHA
Abstract:	Cloud Computing (CC) is a great and promising technology due to its features, such as accessibility, scalability, and online storage, in that it provides a better cost reduction for organizations to run their businesses and financial activities over the cloud. confidentiality, integrity, availability, and accessibility are crucial components of the cloud infrastructure. One of the key issues in providing uninterrupted services to cloud consumers is availability. Cloud security and privacy issues exist, and they have an impact on cloud utilities. With the increase in usages of cloud computing over the past few years, security issues and threats have increased simultaneously. In this paper, we review the most common attacks and countermeasures in the cloud computing environment by conducting a systematic literature review (SLR). Additionally, we propose an Automated Cloud Security Awareness Program (ACSAP) that aims to help organizations to increase awareness of individuals before using the cloud platform to reduce the risk of data breaches since mostly is caused by human error.
Keywords:	Five Cloud Computing, Threats, Attacks, Mitigation, Cybersecurity
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	THE EFFECT OF COGNITIVE KNOWLEDGE ACQUIRED FROM INDUSTRIAL TRAINING ON COMPUTER SCIENCE DEGREE PROJECT
Author:	NNAMDI .J. EZEORA, EMMANUEL .C. UKEKWE, FOLAKE O. ADEGOKE, BASHIR .S. TENUCHE
Abstract:	Cognitive knowledge from Industrial training (IT) shapes the practical skills of graduate students. However, it is not clear how cognitive knowledge acquired in lower level courses impact the quality of degree project of students in final year.. Using the scores obtained from the IT course of 361 Computer Science students in a Nigerian University, cognitive knowledge content transfer and application are investigated. Results revealed a significant correlation of 0.23 at p = 0.05 and a slight knowledge transitional mean increase of 0.795 from their IT course to the B.Sc project. A total of 70.11% of the students who chose their degree project topic based on their IT experience performed better than their counterparts and demonstrated transitional cognitive knowledge application. An 86% accuracy was recorded in predicting the class of honours of students based on their IT courses. using K-Nearest Neighbour (KNN) machine learning algorithm.
Keywords:	Cognitive Knowledge, Industrial Training, Skill, Labour, Graduate Students, Intelligence
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	LINKED OPEN SPATIAL DATA FOR EVALUATION OF LAND SUITABILITY
Author:	CHARITAS FIBRIANI, AHMAD ASHARI, MARDHANI RIASETIAWAN
Abstract:	The agricultural land evaluation analysis is obtained from several factors, such as: Nutrients, Erosion hazard, temperature, flood hazard, and root media, in which the data are from various sources. The principle of Linked Open Data (LOD) is data can be accessed by anyone and from anywhere. The spatial data are needed for the evaluation of land suitability are connected using the longitude and latitude, information will be obtained related to soil type, andesite material, texture, relief, landform, slope, rock condition in the soil, drainage conditions, soil depth, water absorption on the soil surface and soil consistency at that point which comes from 7 different data sources. The contribution of this research is to identify the vocabulary data used for land suitability that came from several sources and connecting the Uniform Resource Name (URI) is owned by these sources using LOD in semantic web.
Keywords:	Linked Open Data, Spatial Data, Information Intelligent, Semantic Web, Land Suitability
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	CROP YIELD PREDICTION IN BIG DATA USING MARGALEF KERNEL PERCEPTRON BASED WINNOW BROWN BOOST CLASSIFIER
Author:	S. SARITHA, G. ABEL THANGARAJA
Abstract:	Crop prediction is a very difficult feature obtained by different characteristics like environment, genotype, and their associations. Policy and decision-makers depend on accurate crop yield predictions to ensure timely import and export recommendations to reinforce food security. In agriculture, boosting in machine learning (ML) is utilized to forecast crop yield. Many boosting ML approaches such as classification, prediction, and clustering predict agricultural production. Data mining techniques are a mandatory technique for achieving significant solutions for this issue. To perform the crop prediction based on different weathers in big data analytics is called as Margalef Kernel Perceptron and Winnow Brown Boosting Classification (MKP-WBBC) method. MKP-WBBC method for big data-based crop yield prediction is split into two sections, namely, feature selection and classification. First Margalef Kernel Perceptron-based feature selection is applied to the Crop Yield Prediction dataset to select computationally efficient features even in case of huge voluminous data. Second, with the unique features selected, Winnow Brown Boosting Classification is applied for accurate and precise crop yield prediction. The main contribution of the new crop yield prediction method is the potentiality to produce accurate predictions and reasonable insights in a simultaneous fashion. This was arrived at by the training and learning algorithm to choose the unique features and not only boosts the results other than enhance the cache hit rate to balance prediction accuracy for training data and generalizability to test data. A discussion of the results achieved reveals the productive performance of the MKP-WBBC method to predict crop yield accurately. Furthermore, results indicate the proposed MKP-WBBC can efficiently enhance crop yield prediction performance and analysis the existing methods in different parameters likes, feature selection accuracy, feature selection time, error rate, and air pollution prediction accuracy.
Keywords:	Machine Learning, Boosting, Margalef Kernel Perceptron, Feature Selection, Winnow Brown Boosting, Classification
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	ALGORITHM FOR SOLVING PRONOMINAL ANAPHORA IN THE KAZAKH LANGUAGE
Author:	GULZHAMAL KALMAN, YERZHAN ZHUMABAY, ELMIRA NURGALIEVA, ASSEL KUANYSHEVA, MUSATAY ESMAGANBET
Abstract:	In this article, we will present methods for solving pronominal anaphora in the Kazakh language. The goal is to identify and solve the difficulties in solving anaphoric relations in the Kazakh language. in the course of our research, we identify some issues related to anaphora annotation specific to the Kazakh language, such as the general position of the candidate antecedent, the distance between words, etc. in the study, we use an annotated text corpus and determine the types and number of pronouns in the text with the help of a morphological analyzer and a syntactic analyzer. Methods used during the research The first method uses Support Vector Machine as training and classification algorithms, the second method uses Decision Tree Inductor. we use an annotated corpus based on machine learning for these methods. We tested the anaphora solving methods with the anaphora solving system for the Kazakh language. The results are encouraging.
Keywords:	Anaphora, Support Vector, Kazakh Language, Antecedent, Kazakh Pronouns.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	EXPLORING A NOVEL PERSPECTIVE ON DESIGN PATTERN RECOVERY VIA VISUAL SIGNATURES AND CONTINUOUS-TIME SIGNALS
Author:	TARIK HOUICHIME, YOUNES EL AMRANI
Abstract:	Design Pattern Recovery is the process of detecting and retrieving pre-existing design patterns inherent in a software application, which entails a comprehensive investigation of the software and its source code, as well as its dependencies. However, this process can be both time-consuming and resource-intensive. Moreover, the automation of this process poses a significant challenge, demanding a profound understanding of the system's design goals and dependencies that are context-based. Furthermore, the absence of standardization, and the potential for ambiguity arising from the multitude of implementations of a specific design pattern further complicates the automation process. In this work, we investigate a new perspective on the problem of Design Pattern Recovery by framing it in terms of visual signatures and continuous-time signals. The resulting visual signatures and signals capture the key features of general Object-Oriented codes and well-defined design pattern micro-architectures in a language-agnostic manner, serving as an intermediary transformation prior to the recovery phase and facilitating the identification of predefined design pattern signatures in the target code. Consequently, a twofold opportunity for the retrieval of potential design information from code is provided. This is manifested in the form of a feature-rich visual signature, which encapsulates the structural, communicational, and behavioral facets of the analyzed source code. The utilization of such visual signatures may serve as a facilitator for the straightforward application of state-of-the-art pattern recognition techniques in automated design pattern identification. Additionally, the features are also expressed as a scale-invariant continuous-time signal, thereby enabling the effective deployment of signal classification techniques for design pattern mining.
Keywords:	Design Pattern Recovery, Pattern Recognition, Visual Signatures, Continuous Time-Signals, Signal Processing.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	HIERARCHICAL ATTENTION NETWORK -ATTENTION BASED BIDIRECTIONAL CNN-RNN DEEP MODEL BASED QUESTION ANSWERING SYSTEM USING ABSTRACTIVE SUMMARIZATION
Author:	T. PRIYANKA, A. MARY SOWJANYA
Abstract:	Summarization aids to minimize document size while processing the meaning amidst Natural Language Processing. Summarization models based on precise sentences are adapted as they occur in inventive text and new sentences are produced with NLP models which are classified as extractive and abstractive models respectively. The complication that lies with NLP text made the abstractive summarization a complex process. An effective model is developed for abstractive summarization with a question answering system using ensemble classifiers. Review data is considered for BERT tokenization, Aspect Term extraction (ATE)is utilized to obtain aspects from review data. The sentiment rating is predicted using ensemble classifiers and fused with the majority voting model. The abstractive summarization is done using HAN-ABCDM which involves with training and testing stages. In the training stage, HAN and ABCDM are trained with summarized text, question answer pairs and sentiment ratings obtained using the majority voting method. In testing phase, the trained HAN and ABCDM are adapted to retrieve predicted answers. Considering the question answering model, the proposed HAN-ABCDM QAS offered highest valued precision of 82.1%, recall of 95.7%, and F-measure of 93.9% compared to other existing methods.
Keywords:	Abstractive Summarization, Question Answering, HAN, ABCDM, Ensemble Classifier
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	THE IMPACT OF SDLC FRAMEWORK INVOLVEMENT TO THE CRITICAL SUCCESS FACTORS OF ROBOT PROCESSING AUTOMATION DEVELOPMENT
Author:	WILHELMUS BILLION, DR. TUGA MAURITSIUS
Abstract:	The advancement of technology, aim to eliminate human involvement especially by the upcoming of robot development and adoption that particularly exist to eliminate the iterative activities. One of robot development called Robot Processing Automation (RPA) that developed in order to take over the repetition of human’s administrative tasks. The adoption of RPA in the industries provide many advantages which on of the most essentials are efficiency of working activities. One studies conduct the research of RPA adoption towards the market potential, and the result shows it has significant impact for industries cost. On the other hand, the high market potential not running parallel with the implementation successful rate. This study will conduct a systematic review of the critical success factor of RPA Adoption. There are so many framework that able to conducted in implement the RPA. So that, to gain a specific research of the implementation, author will identify the research by analyzing the most popular implementation framework, which is SDLC.
Keywords:	Critical Success Factor, Implementation Success , RPA Adoption, SDLC Framework, Systematic Literature Review.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	A HYBRID RANDOM IMAGE GENERATION STRATEGY (HR-IGS) FOR SECURING PLAIN TEXT DATA IN NETWORKS
Author:	SUSHREE BIBHUPRADA B. PRIYADARSHINI, SMITA RATH1, SUSHREE M. PATEL, AMLAN UDGATA, APARNA MOHANTA, S. RIZWAN ALI ,SANGRAM PANIGRAHI ,PRABHAT SAHU
Abstract:	The rapid proliferation of information highways has resulted in an explosion of issues on the internet. The greater the amount of data transfers, higher is the number of cyber-attacks like man-in-the-middle, hacking, and so on. In such context, cryptography is the study of secure communication mechanisms that encrypt and decode messages using two separate keys, public and private. Our paper focuses on encrypting and decrypting text using a revolutionary hybrid technique that uses Rivest-Shamir- Adleman (RSA) and DH to ensure security in data transmission. Our suggested method uses a random picture generation process to generate largest prime numbers, which improves the security and dependability of data sent from the concerned sender to the receiver. We have used the RSA Algorithm to extract the prime numbers using XOR function from the corresponding two vectors in each row and column of the scanned picture. Moreover, with the help of DH algorithm we are generating secret keys. Then the encryption and decryption phenomenon is carried on. The main goal here is to enhance the execution time, minimize the image generation time, improving key generation time, while conjointly hiking the avalanche effect, that assert the lower the risk of being hacked in case of proposed scheme. The outcomes of the investigation support the efficacy of our proffered approach over other existing approaches.
Keywords:	Cryptography, Encryption, Decryption, RSA, Random Image generation, Public Key, Private Key, XOR-Operation, Asymmetric method.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	RISK ASSESSMENT OF CONTROL AND DECISION-MAKING IN THE AIRCRAFT CONTROL SYSTEM
Author:	TOIGANBAYEV BEGLAN, KOSHEKOV KAIRAT, ALIBEKKYZY KARLYGASH, BELGINOVA SAULE, DENISSOVA ARINA, KOSHEKOV ABAI, BAIDILDINA AIZHAN
Abstract:	The aim of the article is to develop a methodology for quantitative assessment of the risks of control and decision-making in the control system of complex objects using the example of aircraft. Manned and unmanned vehicles are considered as aircraft. The risk is presented in the work as a complex multifactorial qualitative phenomenon of a stochastic nature. For quantitative risk assessment, formal mathematical and simulation models are proposed. The process of control and decision making is studied as a complex stochastic-programmable system in the conditions of digital transformation of the internal and external environment. Under the external environment, the aviation industry is represented, and under the internal environment, the aviation enterprise. The quantitative level of control risks, conceptually and in practice, is proposed to be assessed by the digital maturity of the stages of the life cycle of control agents: design, production, and operation. The general approach and tasks of studying the processes of risk formation in the management of aircraft are presented systematically in three digital conceptual contexts. In the volume of the general context, the concept of the digital transformation of the aviation industry is explored. At the second conceptual level, the problem is considered on the example of an aviation enterprise. At the third system level, the most dynamically developing digital technologies in practice, such as "Maintenance of aviation equipment" and "Components of robotics and sensors" are explored. The unmanned aerial vehicle is presented as a robotic complex. In these structural and functional technologies of digital transformation, the most promising and significant digital components are "Staff "; "Models"; "Infrastructure and tools"; "Processes and Products"; "Data". The least secure system link in the exchange of information between an aircraft and the external environment is a radio channel, which is proposed to be replaced by VLC technology in the face of external cyber threats. The formalization of the process of quantitative assessment of the level of digital maturity of an aviation enterprise and the practiced control system in the study is based on a multi-approach methodology using sections of probability theory, mathematical statistics, simulation modeling, and the method of expert assessments.
Keywords:	Aviation Industry, Digital Transformation, Technology Model, Criterion Probability, Imitation Maturity Level.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	ECG SIGNAL CLASSIFICATION USING TUNING TECHNIQUES BASED STACK OF NEURAL NETWORKS
Author:	TATA BALAJI, N.JAYA, G.VENKATA HARI PRASAD
Abstract:	Daily cardiac health monitoring can benefit from the automatic identification of irregular heart rhythms from electrocardiogram (ECG) signal. A vibrant ECG signal is used to detect cardiac problems resembling heart attacks, and coronary ailments. From the ECG analysis doctors can adequately treat patients for a given condition. We used tuned techniques like regularization and global max-pooling and open-source databases like MIT-BIH and PTBDB. Data is pre-processed using resampling and normalization processes. The suggested method enables unique features like high accuracy with less bottleneck problems. The proposed Bi-LSTM, CNN and Attention has an F1-score of 94.7 % and an accuracy of 98.9 %. The approach improves accuracy over existing systems. On the databases PTBDB and MIT-BIH, the suggested approach was evaluated. According to experimental findings, the trained CNN-LSTM-attention was able to forecast the missing segments with greater accuracy. The quality of the projected signal ensures that the suggested method will find widespread use in medical applications and is applicable to any single channel ECG signal. A comparison of the performance with previously published research for the prediction of ECG missing data revealed improved results.
Keywords:	Tuning Techniques, Electrocardiogram Signal, Deep Learning, And Classification.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	FUZZY SYSTEM TO PREDICT PATIENT RISK IN HYPOTHYROID DISEASE USING TSH, T3, T4 HORMONES
Author:	MANOHAR ANNAPPA KOLI
Abstract:	The thyroid is an endocrine gland located in the anterior region of the neck: its main task is to produce thyroid hormones (T3 and T4), which controls our entire body. Abnormal production of thyroid hormones can lead to the production of an insufficient or excessive amount of thyroid hormone. Untreated thyroid can lead to serious complications, including heart disease and nerve damage etc. In some cases, it can be fatal. Since patient risk can’t to be predicted using discrete values, fuzzy solutions are gaining high importance in healthcare systems. The paper presents novel fuzzy solution to predict patient risk in Hypothyroid using TSH, T3, T4 hormones. The proposed method gives 97.29 percentage of accuracy. Discrete values of risk prediction can’t help much in monitoring patient health and disease progress effectively. Using Fuzzy continuous values, it is very easy to predict the progress of patient. Though continuous values based fuzzy systems should not be compared with discrete values and training based machine learning algorithms, still using cut-off values 137 proposed method is compared with existing linear regression, KNN and Bay’s algorithms and it is observed proposed method is producing excellent results. The visual results of the proposed method are also justifying the suitability of proposed fuzzy method in hypothyroid risk prediction.
Keywords:	Thyroid Treatment; Hypothyroid; Hyperthyroid; Thyroid Diseases Prediction; Fuzzy Systems; Classifiers; Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	RECONNOITERING SECURITY ALGORITHMS PERFORMANCE IN THE CLOUD: SYSTEMATIC LITERATURE REVIEW BASED ON THE PRISMA ARCHETYPE
Author:	JOHN KWAO DAWSON, DR. TWUM FRIMPONG, PROF. JAMES BENJAMIN HAYFRON ACQUAH, DR. YAW MARFO MISSAH
Abstract:	Industries and academia have embraced cloud computing for their day-to-day activities. A lot of studies have been done to unpin variants of cryptographic algorithms used to secure the cloud. This survey aims to unravel recent studies of the most employed cryptographic scheme used to secure the cloud, the type of cryptographic algorithms used, the execution time trend of the cryptographic algorithms (Linear time / Non-Linear time), the aims of these cryptographic algorithms, and identify some of the security concerns in cloud computing. The study considered published studies from 2015 to 2022 from well-known databases such as Taylor and Francis, Scopus, Research Gate, Web of Science, IEEE Xplore, Science Direct, Hindawi, Google Scholar, and ACM. A total of 72 published articles were considered to respond to the various specific objectives using the Prisma framework. The systematic literature review has revealed the usage of encryption schemes as the most employed cryptographic approach and data security and cloud security as the most researched security challenge. The security challenges that were identified are data integrity and preservation, intrusion detection, and privacy and confidentiality. It has been revealed that from 2015 to 2022, 90% of encryption algorithms depict linear time complexity. The systematic literature review has proven little usage of symmetric stream cipher algorithms to ensure the privacy and confidentiality of cloud data.
Keywords:	Data Security, Data Confidentiality, Data Integrity, Linear, Non-Linear, Intrusion Detection
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	A SYSTEMATIC LITERATURE SURVEY FOR DETECTING RUMORS BASED ON MACHINE LEARNING AND DEEP LEARNING
Author:	THANAA MOHAMED HASSAN, YEHIA MOSTAFA HELMY, DOAA S. ELZANFALY
Abstract:	Rumor detection is considered to be one of the key research areas in Social Network Analysis and it is a vital in preventing the propagation of misinformation in social networks. Several rumor detection techniques have been introduced in the recent years. These techniques presented the problem as a classification issue, for example binary ones (rumor or non-rumor). The majority of these techniques are based on machine learning (ML). The main obstacle in these techniques is mainly correlated to feature extraction from a selection of dataset. The manual extraction of features affects the efficiency of rumor detection for most of these works, due to the time and effort required. Another technique applied recently is the Deep networks which have been suggested as a means to streamline feature extraction and to offer a strong and superior capability for learning abstract representations. In general, spotting trending rumors requires the development of a robust yet flexible model that can capture long-range connections between postings and produce different representations for accurate early discovery. The aim of this paper is to present a number of carefully studied works in the area of rumor detection by focusing on machine learning and deep learning sectors. These studies are examined in the literature review section leading to answer the research questions that are addressed in this paper. This review is significant and helpful for researchers as it will enable researchers to compare their work with current works due to the accessibility of the complete description of the used evaluation matrices, dataset characteristics, and whether they applied machine learning or by applying deep learning model per each work. Furthermore, said review will also discuss the challenges that researchers in this area have faced and suggested a few potential avenues for further research.
Keywords:	Rumor Detection, Rumor Tracking, Deep Learning, Machine Learning, Social Media Analytics
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	EXOTIZATION OF OFFENSIVE LANGUAGE IN BUILDING KEANU ANGELO YOUTUBER FOLLOWERS
Author:	AHMAD MULYANA , MUHAMAD ARAS , MARDHIYYAH , SRI DESTI PURWATININGSIH
Abstract:	This research intends to uncover creative but manipulative ways in Keanu A&Q's YouTube content that uses impolite and vulgar language. This channel has twelve million followers. This indicates that netizens of the Strawberry generation love the creativity of anti-social offensive content. YouTubers manage content without empathy for the consequences of anti-social communication just because viewers or netizens like it as an entertaining product. The theory used is the Decoding-encoding Theory from Stuart Hall, namely reception analysis. This research focuses on the acceptance of the meaning of messages by audiences and uncovers ideological work in the dynamics of the social media industry. This study is designed in the critical tradition. The research method is reception analysis from Stuart Hall. Data collection techniques were carried out utilizing Focus Group Discussion (FGD). The study results show that netizens' reception is mainly in a dominant position of hegemony. The majority of netizens accepted Keanu's Q&A content. Vulgarity and anti-ethical language are considered popular entertainment. The meaning of entertainment is formed because this anti-educational content is packed with messages that are commonly used by the transgender (sissy) community, which are used to express graceful and feminine male verbal and non-verbal expressions constructed in a humorous format. Keanu cleverly plays the impression of humour that netizens need. In the context of this, YouTubers is considered successful because it managed to get 12 million subscribers. The interpretation of Negotiation's position was shown by netizens who were entertained while watching Keanu's Q&A content but were accompanied by sadness regarding the negative impact of content like this, which could make the use of communication without permissive ethics and negate educational value. These long-term interactions can negate the ethics of minors. Opposition positions are interpreted by netizens who disagree using the swearing affirmation function. This group realizes the exoticization of vulgar language and verbal violence through a transgender message approach that transfers the meaning of entertainment in the context of the cultural industry.
Keywords:	Social Media, Youtube, Followers. Exotization, Vulgar Language, Culture Industry.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	DESIGN APPLICATION SIMPLE LEARN BASED ON MOBILE WITH IMPLEMENTATION GAMIFICATION FOR LEARNING ONLINE
Author:	EURICO RANDY THEOSYMEION HARSAYA, ANGGA ADITYA PERMANA, YAMAN KHAERUZAMAN
Abstract:	The COVID-19 pandemic has affected the learning system in academic institutions, with the transition from face-to-face learning to online learning. With the advancement of mobile learning, educational systems are changing with learning process through mobile devices. According to the Quick Innovation Survey Results, out of 46 respondents, only 42% used online learning applications as learning media. This obstacle could hinder academic institutions from achieving their desired results. The smartphone ubiquity and accessibility combined with the mobile application and gamification development in teaching have encouraged the way for learning online. Therefore, it can be concluded that online learning using applications can be further developed. This study aims to increase the fun and productivity of learning in students even in the form of online learning. The proposed model of learning will be designed in game in order to attract students to learn by playing the game. Simple Learn application development for online learning with gamification implementation using games mechanics and games dynamics implementation. Application testing was carried out by conducting a survey of 36 people, the survey was made based on the Hedonic-Motivation System Adoption Model (HMSAM). The evaluation results stated that the percentage of users who will use the application again in the future is 88.48% and the percentage of users who get carried away when using the application is 88.89%, thus it can be concluded that the application has been received positively by users for online learning.
Keywords:	Applications; Game Dynamics; Game Mechanics, Gamification, HMSAM.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	MULTIRESPONSE REGRESSION SEMIPARAMETRIC TRUNCATED SPLINE (CASE STUDY: SKIN DEFECT OF FARMING COWS)
Author:	YUMNA AQILA KALTSUM, NI WAYAN SURYA WARDHANI, ADJI ACHMAD RINALDO FERNANDES, SUCI ASTUTIK, RAHMA FITRIANI
Abstract:	This study aims to model a semiparametric multiresponse regression analysis model using the Truncated Spline approach as a solution in its nonparametric component to obtain the best model in the case study to help prevent and treat skin diseases in cattle. The solution is done using Weighted Least Square (WLS) to be able to capture multiresponse modeling where there are indications between parts of the same cow's body that have correlated wounds. The novelty of this research is on a semiparametric truncated spline multiresponse model using a non-uniform order and number of knots for each predictor variables.
Keywords:	Multiresponse Analysis, Semiparametric Regression Analysis, Truncated Spline, Farming Cows, Defect Skin Disease
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	PREDICTING THE RESILIENCE OF THE TOURISM INDUSTRY AFTER THE COVID-19 HEALTH EPIDEMIC
Author:	ROUAINE ZAKARIA, TAITAI ZINEB
Abstract:	The tourism industry is a major branch of the service sector that contributes to national wealth creation. It is one of the main drivers of employment and foreign exchange drainage in the economies. However, some tragic events affect and slow down its development. The epidemiological context of the coronavirus has deeply affected the sector, implying a total halt to all tourist activities at national and international levels. In this sense, Dauphiné and Provitolo (2007) [16] state that "it is then possible to adopt another strategy based on the concept of resilience. This strategy aims, not to oppose the hazard, but to reduce its impacts as much as possible. From this reflection, we have attempted in this essay to clarify and analyze the determinants of resilience summarised in the characteristics linked to the environment, the strategies implemented, the personal traits of the manager, and the characteristics specific to tourism organizations contributing to helping these Moroccan economic units, specifically in the Rabat-Salé-Kénitra region, to overcome the setbacks caused by the covid-19 health crisis.
Keywords:	Resilience determinants, tourism sector, the coronavirus epidemic, binary logistic regression, Generalized Linear Models.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	THE IMPACT OF FACTORS THAT CAUSE ISSUES FOR NON-ICT BACKGROUND WORKERS IN ICT JOBS ON THEIR JOB SATISFACTION
Author:	DANIELLA ALEXANDRA DJULAINI, RIYANTO JAYADI
Abstract:	It is not uncommon to see non-ICT educated workers doing ICT-based roles and jobs. Through a preliminary assessment, it is discovered that workers with non-ICT background that work in ICT-based roles often face issues. The identified issues consist of four factors: the lack of information and documentation, insufficient training, insufficient mentorship, and the lack of prior IT knowledge and competencies. These issues cause effects and behaviour that indicate dissatisfaction in their work life. Working performance and person job fit were also thought to act as the bridge between these issue-causing factors and the worker’s job satisfaction. Prior studies regarding job satisfaction, working performance, and person-job fit in various fields have delved in these aspects for various fields, but not in the ICT area – especially in Indonesia. Hence, this study aims to verify if these factors contribute to job satisfaction overall, as well as its mediating variables. It is discovered that prior ICT knowledge and competencies have a significant impact towards job satisfaction through working performance and person-job fit – and greatly impacts both factors. Working performance is also impacted by the information and documentation regarding ICT technologies. However, the lack of information and documentation, training, and mentorship do not affect job satisfaction significantly. Consistent with other research in various fields, working performance and person-job fit have great impact towards job satisfaction. From this study, it is discovered that the prior ICT knowledge and competencies of the worker are key aspects that can contribute to their performance, fit, and job satisfaction overall. These findings may be used as input for various recruitment and preparation strategies for companies that seek to hire ICT workers from other educational backgrounds.
Keywords:	Knowledge Management, Background-Work Mismatch, Person-Job Fit, Job Satisfaction, Information Technology, Working Performance
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	A STUDY ON THE EFFECT OF GAMIFICATION COMPONENTS ON CUSTOMER LOYALTY TOWARD A DIGITAL BANK
Author:	RATU ANNISA GANDASARI, TUGA MAURITSIUS
Abstract:	We are in the era of digitalization. Almost all sectors have experienced changes, including banking. The banking landscape is changing with digital banks emerging and attracting the attention of users. Now, the task of digital banks is not only to attract users’ attention, but also to retain or make them loyal. Big companies in other sectors have implemented gamification to increase customer loyalty. However, there is no research yet on gamification implementation for digital banks in Indonesia. There are several digital banks in Indonesia, yet there is only one that has implemented gamification components, which is Bank Neo Commerce (BNC). This study aims to analyze the effect of gamification components on customer loyalty toward Bank Neo Commerce. In this paper, the data used were quantitative data collected using an online questionnaire that was distributed to Bank Neo Commerce users that have tried the gamification features. The data were collected from 158 BNC users in Greater Jakarta (Jakarta, Bogor, Depok, Tangerang, and Bekasi) using an online questionnaire. The data were then processed using SmartPLS 3.0 to test the validity, reliability, and hypotheses. Based on the analysis, the gamification components, namely quests, social graphs, levels (leveling system), and virtual goods, do have significant effects on hedonic and utilitarian values, which ultimately affect the users’ satisfaction and loyalty. Therefore, other digital banks can consider implementing those gamification elements for their future development to increase customer loyalty.
Keywords:	Gamification, Bank Neo Commerce, Customer Loyalty, Digital Bank, Loyalty Program, SeaBank
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	THE USAGE OF MACHINE LEARNING IN MARKETING AUTOMATION TO IMPROVE THE PERFORMANCE OF THE DIGITAL MARKETING STRATEGY
Author:	REDOUAN ABAKOUY, EL MOKHTAR EN-NAIMI, ANASS EL HADDADI, LOTFI ELAACHAK
Abstract:	The main objective of this research work is to develop Machine Learning (ML) algorithms to predict user needs based on customer data and past behavior. These predictions can be used to suggest offers based on the individual. ML can also allow marketers to use it to segment customers. The second objective of the study is to integrate the Marketing Automation process into the marketing strategy, and to study its impact on business performance focusing principally, on the effect on open rate, click rate, sales, and deliverability, as well as to identify the barriers that hinder the integration of this technology into the marketing strategy. The results reveal that marketing automation focuses on strategies that can be used to increase customer engagement and increase open rates, clicks, sales, and return on investment (ROI). Marketing automation improves the customer experience, optimizes time and resources relieving daily tasks such as message preparation and emailing, ensures consistency as the same activities will generate the same results, leads to optimization of the marketing strategy. It also allows decision-makers to reach customers with personalized content and intelligent and relevant segmentation.
Keywords:	Digital Marketing; Email Marketing; Machine learning, Marketing Automation
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	THE EFFECT OF AUDITOR EXPERIENCE, BIG DATA AND FORENSIC AUDIT AS MEDIATING VARIABLES ON FRAUD DETECTION
Author:	FRENTI NOVIKA BR SEMBIRING, RINDANG WIDURI
Abstract:	The many cases of fraud in Indonesia caused losses to the state. It has driven stakeholders, including the Government, to determine effective and efficient methods to detect fraudulent issues. Therefore, this study aimed to examine the influence of auditor experience, Big Data, and forensic auditing as mediating variables on fraud detection. It used a quantitative approach with a survey method by distributing questionnaires through a google form. Respondents comprised 128 internal, external, and government auditors. Furthermore, the data were analyzed using structural equation modeling (SEM) with the help of SmartPLS tools. The results showed that the auditor's experience, forensic audit, and Big Data positively and significantly affect fraud detection. Auditor experience and Big Data variables positively and significantly affect Forensic Audits. Additionally, a forensic audit mediates the auditor's experience with fraud detection but does not mediate Big Data against fraud detection.
Keywords:	Auditor Experience, Big Data, Forensic Audit, Fraud Detection
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	STRENUOUS GREY WOLF OPTIMIZATION-BASED FEED-FORWARD NEURAL NETWORK (SGWO-FFNN) FOR ENHANCED CROP YIELD PREDICTION
Author:	SHANMUGA PRIYA S, DR.M.SENGALIAPPAN
Abstract:	One of the most profound changes to human life brought about by technological progress has been increased food production and other essentials. Machine learning techniques have contributed to this change by making our lives easier and bringing us closer by eliminating hunger and poverty. However, these techniques can potentially cause harm if not correctly applied. Machine learning-based crop yield predictions resulted in lower yields, as predicted yields can be as low as 20% of actual yields, and it is because of the poor performance of classification algorithms. The “Strenuous Grey Wolf Optimization-based Feed-Forward Neural Network (SGWO-FFNN)” to predict crop yield prediction is a machine learning model that combines the optimization algorithm called Grey Wolf Optimization (GWO) with a feed-forward neural network (FFNN). The GWO algorithm is a population-based optimization method that is inspired by the hunting behavior of grey wolves. The goal of the SGWO-FFNN is to improve the training and performance of the FFNN by using the GWO algorithm to optimize the neural network’s weights and biases. The SGWO-FFNN has been shown to be effective in various applications, such as image classification, time series prediction, and function approximation.
Keywords:	Crop Yield, Prediction, Classification, Grey Wolf, Neural Network, Optimization
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	GENERATION OF 5X5X5 CONVEX POLYHEDRONS OVER THREE DIMENSIONAL RECTANGULAR GRID
Author:	K. PRASANNA, G. RAMESH CHANDRA, SATYA GOVINDARAJAN, E.G. RAJAN
Abstract:	Convex polyhedrons in three dimensions (3-D) are generally utilized as structuring elements for morphological processing of three dimensional digital images, as well as masks in traditional processing. Three-dimensional masks or structuring components of size 3x3x3 or 5x5x5, or generally (2n+1)x(2n+1)x(2n+1), are used to process three dimensional digital images. In a 3-D cell array of a certain size, one can build 3-D polyhedrons known as neighborhood structures in various shapes. For instance, a neighborhood structure of 3x3x3 can contain 256 convex polyhedrons. This paper presents the methodology for the generation of convex polyhedrons of 5x5x5 size in the three dimensional rectangular grid. There are 429,49,67,290 ( Approximately 429 crores) convex polyhedrons generated through an algorithm discussed in this paper.
Keywords:	Morphological Image Processing, Geometric Filters, Convex Polyhedrons.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	IDENTIFICATION OF BUSINESS AND TECHNOLOGY STRATEGIES BASED ON THE WARD PEPPARD-CASSIDY METHOD
Author:	JOHANES FERNANDES ANDRY, AZIZA CHAKIR, RONALD MARADEN PARLINDUNGAN SILALAHI, LYDIA LILIANA, MONICA CLARA
Abstract:	The role of information systems and information technology plays an essential role in an organization, especially in achieving a competitive advantage over competitors, which also applies to the electrical equipment distribution business. Taking advantage of systems and technology requires proper strategic planning to optimize business processes. Electrical appliance distributor companies have utilized technology to support organizational performance. However, problems still occur, such as an unintegrated system that makes it difficult for users to perform data maintenance and retrieve data from several divisions. In addition, the extended data processing time could be faster in monthly reporting. Companies have used technology to assist business processes, but many problems arise from implementing the system. This problem arises because of the misalignment of the application of technology with the company's business processes. Based on these problems, it is necessary to analyze the alignment of technology with organizational strategy using the Ward and Peppard method combined with the Anita Cassidy method. Ward and Peppard help with business and technology analysis from the internal and external sides of the company. Anita Cassidy's approach determines the exact direction and needs of the business. This study aims to improve business strategy and information technology alignment to produce an application development roadmap. The results of this study are roadmaps and application portfolios to be implemented in companies. Thus, the research results in application portfolios can complement existing business processes according to company needs. Then, the results of the roadmap describe the course of the application in line with the company's business strategy so that it can compete competitively in the future.
Keywords:	Strategic Planning, Ward and Peppard, Anita Cassidy, Application Portfolio
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	IMPLEMENTATION OF THE FUZZY ANALYTICAL HIERARCHY PROCESS AND DATA ENVELOPMENT ANALYSES FOR ASSESSMENT OF THE CAPABILITY OF FARMER GROUPS IN INDONESIA
Author:	ONI SOESANTO, YUSI TYRONI MURSITYO, EKO DARMANTO3, ZURAIDAH, NINIK WAHJU HIDAJATI, SAMINGUN HANDOYO
Abstract:	Farmer Groups are one of the forums for farmers to increase resources and production of agricultural products. Strong farmer groups will greatly contribute to improving the welfare of the Indonesian people. This study aims to rank farmer groups and evaluate their performance efficiency so that they are in accordance with the priority interests of each criterion unit to support the task of decision-makers in fostering farmer groups in an appropriate manner. Fuzzy Analytical Hierarchy Process (FAHP) Model - Data Envelopment Analysis (DEA) is a ranking method based on preference data in the form of fuzzy numbers. In this study, the AHP-DEA fuzzy method was modified to become AHP-DEA-CCR fuzzy (Charnes, Cooper, and Rhodes). The modification was carried out by weighting using entropy-based fuzzy AHP on the input and output models. The FAHP-DEA model developed successfully mapped 15 farmer groups into 3 groups based on 3 criteria, namely learning vehicles, cooperation vehicles, and production units. Based on performance efficiency in the 3 criteria, 2 strategies are obtained to increase their abilities. One scenario is to provide training to increase production units to farmer groups with DMU IDs 1, 2, 6, 4, and 3, provide counseling and training to increase the use of learning vehicles and provide training to increase the use of cooperation vehicles to farmer groups 10,11, 12, 14, and 15. The varying decision risk into 0.2 (pessimistic), 0.5 (moderate), and 0.8 (optimistic) do not have a significant effect on the decision maker's choice.
Keywords:	Decision Making, Efficiency Performance, Fuzzy AHP-DEA, Important Criteria, Decision Risk.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	A SOCIAL SPRAY-AND-WAIT ROUTING PROTOCOL BASED ON SOCIAL NODES IN DELAY TOLERANT NETWORKS (DTNS)
Author:	EL MASTAPHA SAMMOU
Abstract:	In this article we will discuss the problem of routing in delay tolerant networks (DTNs). The major problem in DTN networks is to find an end-to-end communication path between a source node and a destination node. This situation occurs because of several factors, namely: Disruptive and intermittent connectivity, high mobility of nodes, sparse network in several areas, highly dynamic network, etc. Among the classic routing protocols designed to overcome routing problems in the DTN network is the spray and wait routing protocol, and despite all the efforts made by researchers in recent years to improve the performance of this protocol but it still suffers from several shortcomings. Most of the researchers' proposals to improve the performance of the spray-and-wait routing protocol are based primarily on either mobile similarity and/or social similarity. Indeed, these proposals of the researchers prove ineffective in certain scenarios in which the movement of the nodes is completely random and when the nodes show non-social behaviors. To solve routing problems and effectively improve the performance of the wait phase of the Spray-And-Wait protocol, we propose a routing approach called SSW (Social Spray-and-Wait) based on mobile attributes and social attributes between nodes by exploiting the similarities (mobile and social) of the nodes as well as the probability of delivery and the probability of visit to improve the delivery rate and reduce the delivery delay as well as minimize the resources consumed in the DTNs networks. Our SSW approach proposes a strategy of selecting appropriate relay nodes to ensure successful delivery of messages in the wait phase of the spray-and-wait protocol. This strategy is based on the selection of special nodes called social nodes having higher activities and can play the role of relay nodes in the network. In other words, the social nodes are selected preferably as relay nodes to increase the delivery rate. The simulation results show that, our SSW approach significantly improves the delivery rate, and reduces the delivery time, compared to the spray and wait protocol and also shows good performance in terms of resources consumed in the network.
Keywords:	Routing, Delay Tolerant Networks, DTN, Social Spray-And- Wait, SSW, social node, Simulator
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	DETECTION OF SOIL FORMATION CHANGES USING A FUZZY INFERENCE SYSTEM-BASED OUTLIER
Author:	MOCHAMAD LUJENG PRATIKTAMA, SANI MUHAMAD ISA, HERMAN YOSEPH SUTARTO
Abstract:	Oil and gas drilling is a risky business because actual rock and soil formations may differ from the plans. The application of "artificial intelligence" (AI) is potent to detect soil-rock formation changes. "Fuzzy Inference System" (FIS) is one of many AI methods that may be used for outlier data detection from raw data sets produced by "Mud Logging Unit" (MLU) equipment from drilling activities. This research will be carried out to detect outliers using FIS. Then, detected outliers in drilling data are used to see if these outliers indicate changes in drilling parameters. While other research mainly detects outliers directly from the data set, this research will get outliers from the calculated standard statistical value that is fed to the FIS. Then the FIS results will be combined to determine whether the formation changes are indicated or not. The data sets being used are "rotation per minute" (RPM), "rate of penetration" (ROP), and "weight on bit" (WOB). From these three datasets, four (4) statistical standard values were calculated, namely DIST, N-POINT-DIST, MEM-DEG-DIST (distance from data point to center point cluster), and MEAN-DIST for each of the datasets mentioned above. The FIS method is used to detect outlier data with the input of the four (4) statistical standard values for each of the datasets above. There was outlier data detected at 6672 points for RPM, 8239 points for ROP, and 6783 points for WOB, respectively. Outlier data results are then used for further analysis to conclude whether there was a change in soil formation at a certain drilling depth. The result was obtained for 70 data points, indicating a change in soil-rock formation. Verification data was collected using the formation log report, and 0.93% of the log report was verified.
Keywords:	Drilling Operation, Fuzzy Inference System, Machine Learning, Outlier Detection, Rock-soil Formation
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	ALLEVIATING DIGITAL ANXIETY IN ONLINE TEACHING: ASSESSING THE ACADEMICS CHALLENGES IN DIGITAL TRANSFORMATION
Author:	SITI NOORSIAH JAMALUDIN, GEDE PRAMUDYA ANANTA, ABD SAMAD HASAN BASARI
Abstract:	Although online teaching has experienced an explosive growth rate, digital anxiety is still persistent in many situations; in this context, it has evolved into online teaching anxieties that are yet to be understood. This pilot study aims to investigate the digital anxiety faced among academicians in conducting online teaching. Research is scarce in this area, and studying it helps to understand its significance and impact. A mixed-method approach was used to explore the study. A sample of 65 participants was obtained to conduct the feasibility assessment. The findings showed that academicians are impacted by digital anxiety, which may positively or negatively impact their willingness to accept online teaching. The academicians seem to experience digital anxiety with online teaching due to reasons and factors. It is critical to identify and address sources of anxiety and provide an indication of self-evaluation and assessment of their online teaching experience. Therefore, digital anxiety in online teaching should take centre stage because it represents academicians’ readiness to incorporate various online tools and digital technology into their pedagogical delivery to successfully transform the field of education.
Keywords:	Digital Anxiety, Digital Transformation, Education, Online Teaching, and Technology
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	NRP-WMSN : A NOVEL ROUTING PROTOCOL FOR MULTIMEDIA TRANSMISSION IN WIRELESS MULTIMEDIA SENSOR NETWORKS
Author:	CH.JANAKAMMA, DR.NAGARATNA P. HEGDE
Abstract:	Wireless Sensor Networks(WSN)s have gained more attention in the field of research for support a wide range of applications including multimedia transmission. WSNs are widely used in real world applications. Due to rapid innovation in wireless sensor networks , more networking nodes participate in multimedia data transmission. Many multimedia applications utilize WSNs , such as video surveillance, object tracking, healthcare system, traffic monitoring, etc.. The traditional WSN have open challenges in multimedia transmission like delay in data transmission, high energy consumption and throughput performance. The proposed novel routing protocol for multimedia transmission in Wireless Multimedia Sensor Network(NRP-WMSN)addresses the limitations of traditional WSNs. The proposed routing protocol improved network performance by applying a routing algorithm in multimedia data transmission. The implementation is made using NS2 to exhibit the proposed routing concept. The experiential outcomes showed the effectiveness of the proposed routing approach. The proposed routing algorithm performance is compared with basic multimedia data transmission approach in terms of delay, throughput and packet delivery ratio
Keywords:	Wireless Sensor Network, Multimedia Application, Data Transmission, Routing Algorithm, Packet Delivery Ratio.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	OPTIMIZATION OF PHOTOMETRIC QUANTITIES FOR ROAD LIGHTING FREEWAYS IN INDONESIA
Author:	ENDAH SETYANINGSIH, HENRY CANDRA
Abstract:	Road lighting is one factor affecting driving safety on the road. Inadequate lighting has the potential to cause a traffic accident based on our previous research. Moreover, many traffic accidents occur between 18.00 - 24.00 and 00.00 - 06.00, even though the traffic volume has decreased at night. In order to investigate further the case mentioned above, this paper discussed the research for the lighting system on Cikampek and Cipularang toll roads as a sample uses case. The results revealed that the lighting system in Cikampek and Cipularang toll roads does not comply with the Indonesian national standard for lighting. In addition, a Dialux software simulation was conducted to determine the most optimum photometric illuminance, including average luminance and uniformity for the road lighting in Cikampek and Cipularang toll roads. The simulation implemented seven variables of the road-lighting design, resulting in 324 scenarios giving average illuminance between 23.88 lux to 24.40 lux with minimum uniformity of 0.53 and average luminance is 1.51 cd/m2 with a uniformity of 0.70. The simulation results show that if the Cikampek and Cipularang toll roads are redesigned according to the simulation results, they will be following SNI 7391: 2008 and able to reduce the risk of accidents.
Keywords:	Illuminance, Luminance, Road Lighting, Photometric, Uniformity
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	OCHOA-RNN: OPPOSITIONAL BASED CHIMP OPTIMIZATION ALGORITHM (OCHOA) AND RECURRENT NEURAL NETWORK (RNN) HYBRID CLASSIFIER MODEL FOR LUNG CANCER DIAGNOSIS
Author:	JENITA SUBASH, DR.KALAIVANI.S
Abstract:	One of the prominent reasons of cancer-related mortality in this world is "Lung Cancer". Therefore, precautions such as detection, prediction and diagnosis of lung cancer have become essential to be expedited and simplified the consequent clinical board. An Artificial Intelligence technique has been proposed as promising tool for classifying normal, benign and malignant nodules. The research aim is to retrospectively validate Lung Cancer Prediction through Oppositional based Chimp Optimization Algorithm (OChOA) in associates with (LSTM)Recurrent Neural Network. The investigation anticipates using various optimization techniques namely ChOA, Social Spider Optimization (SSO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA) for identifying optimal weights for RNN. The result shows that involving optimization for identifying weights forLSTM- RNN unveils 97.13% from the proposed OChOA-RNN.
Keywords:	Lung Cancer, Recurrent Neural Network, Oppositional Based Chimp Optimization Algorithm, Long Short-Term Memory, CT Images, Bengin and Malignant.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text

Title:	GOVERNMENT REVENUE PREDICTION USING FEED FORWARD NEURAL NETWORK
Author:	NADZIRA NOOR, ALIZA SARLAN, NORSHAKIRAH AZIZ
Abstract:	A countrys federal government receives revenue from several sources. Example in Malaysia the sources are direct tax, indirect tax and non-tax revenue. The federal government will then use the revenue for operations and developments in the country. There are currently limited methods to predict federal government revenue for upcoming years. Having different and better method can help to better plan the collection activities and managing the resources. For now, Malaysia federal government can only forecast or estimate the revenue. Business intelligence on the other hand is currently booming in the business world as it helps to improve and provides relevant information for decision making process. One of the branches of business intelligence is predictive analytics, where it can be used to predict future outcomes provided past data are available. Patterns can be identified to predict the upcoming trend. From the observation, predictive analytics can be applied in any financial prediction which includes federal government revenue. Numerous machine learning methods exist such as linear regression, polynomial regression, various types of neural network, decision tree, random forest, multiple linear regression and so on. Based on the literature review done, feed forward neural network is highly used and thus selected for this study. Hyperparameter tuning is conducted to determine the ideal parameters for feed forward neural network to be applied for federal government revenue prediction. From the result, it is found out that using Softsign activation function and Adam optimizer can give better accuracy. Completing the study, it contributes to provide another way to accurately predict the federal government's revenue and subsequently be advantageous to the federal government.
Keywords:	Predictive Analytics, Machine Learning, Revenue Prediction, Feed Forward Neural Network, CRISP-DM
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2023 -- Vol. 101. No. 6-- 2023
Full Text