		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
February 2025 | Vol. 102 No.3

Title:	CHALLENGES AND SOLUTIONS OF SEWERAGE NETWORKS IN KARBALA, IRAQ FOR FLOOD MONITORING USING SMART SENSORS AND GIS
Author:	IHSAN KADHIM ABED, FADI HAGE CHEHADE, ZAID FARHOOD MAKKI
Abstract:	Floods in urban areas pose major challenges to infrastructure, especially in third world countries. The sewage network in Karbala, Iraq, faces recurring difficulties and problems from floods, especially in the rainy season, taking into account the large population density in Karbala. The design of the sewage network does not meet the need for this. This study came to build a model based on one of the artificial intelligence techniques, which is machine learning through Support Vector Machines (SVM) to analyze data coming from smart sensors and Geographic Information Systems (GIS). The classification that links variable weights is used according to the data coming from the sensors to enhance the work of the classifier and obtain a classification accuracy of up to 89.7% in real time. Enhancing smart decision-making is the most important stage in improving and building sewage networks, which are the basis of urban cities and their planning. In the future, the deep learning mechanism can be combined with machine learning to reach more accurate predictions and faster data analysis.
Keywords:	Sewage network; Smart sensors; SVM; GIS; Machine Learning; Flood Monitoring.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	THE SCALABLE REVERSIBLE RANDOMIZATION ALGORITHM (SRRA) FOR BETTER PRIVACY PRESERVATION, IMPROVED FEATURE SELECTION STABILITY, AND HIGHER ACCURACY IN BIG DATA ANALYTICS
Author:	MOHANA CHELVAN P, Dr. RAJAVARMAN V N
Abstract:	In todays knowledge economy, every organization uses the enormous accumulated data for their development of business as well as for enhancing customer relationship management. However, most of the data produced is unstructured and semi-structured and comprises customers' private data. Data analysis is mostly done by a third party to get insights and hidden patterns or information. Preserving the individual’s privacy is vital for organizations before analysing it for pattern mining. Because of the proliferation of electronic gadgets and technological progressions, the dimension of the collected dataset increases into the high dimensional dataset. This will lead to feature selection, which is a vital preprocessing step for big data analytics as a dimensionality reduction technique. Previously, researchers believed that the stability of feature selection depends generally on the algorithm but recently confirmed by scientists it depends on the dataset’s statistical characteristics. Unstable feature selection results confuse researchers' minds about their research conclusions as the selection stability positively correlated with accuracy. Privacy preservation will disturb the statistical characteristics of a dataset, which will impact the stability of feature selection and accuracy. Hence, privacy conserving big data analytics techniques should protect the sensitive data of individuals with better stability of feature selection and accuracy. The research paper evaluates the methods of privacy conserving big data analytics and recommends a new reversible privacy conserving algorithm called Scalable Reversible Randomization Algorithm (SRRA).
Keywords:	Big Data, Data Analytics, Privacy Preservation, Feature Selection, Feature Selection Stability
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	IMPROVING THE QUALITY OF LEARNING FOREIGN LANGUAGES THROUGH THE USE OF MOBILE APPLICATIONS
Author:	SOLMAZ ALASGAROVA, SVITLANA MUDRA, ANASTASIIA VITCHENKO, YURIY SOBKOV, DMYTRO CHYSTIAK
Abstract:	Aim. The aim of the research is to analyse the effectiveness of specialized mobile applications in foreign language learning. Methods. The research employed the method of monitoring higher school students’ academic performance, the Vocabulary Test, the Vocabulary Confidence Scale, and the method of expert evaluations. Statistical processing of the obtained data was carried out using Student’s t-test, and correlation analysis. The reliability of the methods was tested by using the Cronbach’s alpha. Results. The experimental group (EG) participants had higher mean scores for all research methods than the control group (CG) participants. The difference between the two groups was statistically significant for language competence (t = -2.78, p < 0.01), cultural sensitivity (t = -3.12, p < 0.01), adaptability (t = -2.45, p < 0.05), and communication effectiveness (t = -2.08, p < 0.05). The mean VCS score for the EG (81.3) was higher than for the CG (75.2). The difference between the two groups was statistically significant (t = -2.34, p < 0.05). Conclusions. The obtained results testify to the positive role of the use of mobile applications in improving the quality of foreign language learning. Prospects. Further research can be focused on studying the impact of different types of mobile applications on foreign language learning in order to determine the most effective methods.
Keywords:	Educational Environment, Foreign Language Competencies, Virtualization, Digitalization of Education, Specialized Mobile Application
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	SMARTSCAN: A COMPREHENSIVE FRAMEWORK FOR EFFICIENT AND OPTIMIZED FORMAL VERIFICATION OF COMPLEX BLOCKCHAIN SMART CONTRACTS
Author:	G.SOWMYA, DR.R.SRIDEVI
Abstract:	Smart contracts are gaining popularity as blockchain technology, and its uses continue to develop rapidly. Smart contracts are necessary to enforce real-time contracts in Blockchain systems. It is essential to thoroughly verify both simple and complex smart contracts since inconsistencies could lead to issues like the inability to deliver the required services. Existing tools like SmartCheck can automatically verify the correctness of smart contracts. However, a more complete solution that ensures the accuracy of smart contracts and considers security concerns is needed. In this study, we propose SmartScan, an efficient and optimal framework for formally verifying complex blockchain smart contracts. SmartScan uses a hybrid methodology that includes formal approaches, optimized heuristics, static analysis, and an optimized verification process to find weaknesses and inconsistencies in smart contracts. SmartScan's architecture aims to be robust to complex relationships and many interconnected parts. SmartScan streamlines the verification process by lowering its temporal and computational complexity. More importantly, it can validate the smart contracts of large-scale blockchain applications due to its scalable architecture. It manages the life cycle of smart contracts and can be extended to interface with other apps. Several algorithms in SmartScan aid in realizing the underlying architecture so that its primary functions can be accomplished. In terms of computer complexity, temporal complexity, and the ability to detect flaws and irregularities in simple and sophisticated smart contracts, SmartScan outperforms many currently used approaches, per an objective analysis using the DeFiLending case study. As a result, SmartScan is more than just a tool; it is a scalable and effective solution that can be incorporated into already-existing applications that deal with the life cycle of smart contracts and blockchain application development.
Keywords:	Smart Contracts Verification, Blockchain Technology, Blockchain Applications, Formal Verification, Smart Contact Life Cycle
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	TRANSFORMING MACHINE TRANSLATION FOR ISOLATING LANGUAGES WITH MULTI-SOURCE NEURAL MODEL
Author:	NGUYEN NGOC LAN, TRINH BAO NGOC, LE PHUONG THAO, NGUYEN THANH CONG, LE MANH TOAN, , TRAN DINH DIEN, BUI PHAN TUE ANH, VUONG THI VAN, NGUYEN NHAT TRANG, NGUYEN TIEN THANH
Abstract:	Recent advancements in Artificial intelligence (AI) and Deep learning have facilitated the rapid development of machine translation technologies, among them, Neural machine translation (NMT) models have demonstrated impressive performance, especially in handling multiple language pairs. However, due to their complexity and lack of appropriate data, contemporary NMT models still have a lot of challenges when applied to isolated languages, despite their great accomplishments. This paper proposes a multi-source neural model that employs two different encoders to process both the source word sequence and the linguistic feature sequences of isolating languages. Unlike traditional NMT models, this approach improves the encoders’ input embeddings by incorporating a second encoder that integrates the linguistic elements, including part-of-speech (POS) tags and lemma. To enhance the source sentence's context representation, this article combines the encoders' conditional data with the outputs of the decoders using a serial combination technique. In this way, different metrics such as METEOR and BLEU are examined to assess the suggested model's precision of translation. Experimental results indicate that our methodology works efficiently for isolating language translation, as evidenced by the improvement of +3.9 BLEU and +3.2 METEOR scores on translation tasks conventional NMT models perform. This highlights a significant advancement in integrating linguistic features to enhance translation accuracy for isolating languages.
Keywords:	Artificial Intelligence, Neural Machine Translation, Linguistic Features, Isolated Language, BLEU, METEOR
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	FACTORS INFLUENCING RECOMMENDER SYSTEM EFFECTIVITY ON CONTINUANCE USAGE INTENTION IN INDONESIAN E-COMMERCE USER
Author:	RICHARD ADRIAN YUDHISTIRA , GUNAWAN WANG
Abstract:	As global market demand grows, e-commerce platforms face an increasingly competitive environment and an ever-rising deluge of data. To sustain their operations and improve customer experience, several of these platforms have incorporated services to assist customers in sifting through mounds of information. One of these services is Recommendation System (RS), an algorithm designed to offer personalized suggestions tailored to a consumer's preference. The study intends to explore which RS factor which has the most influence on its performance and effectivity in the Indonesian e-commerce environment, one of the biggest e-commerce economies in the region. The RS factors analyzed includes: Diversity of Suggestions, Suggestion Accuracy, Suggestion Novelty, and Recommendation Quality, alongside sociological factors such as Usage Attitude, Familiarity, Trust, and Satisfaction. This study uses a modified Technology Acceptance Model (TAM) model to study the correlations between these factors, customer usage attitude, and their subsequent Continuance Usage Intention. The data is collected through questionnaires distributed to a minimum of 106 Jakarta residents, given the region’s high concentration of e-commerce users. Results show that RS quality is driven by Accuracy, Novelty, and Diversity, with Accuracy yielding the highest influence. Higher RS quality then positively affect both the user’s Usage Attitude and Trust, while Usage Attitude boosts User Satisfaction, all of which increases the user’s continued usage intention. However, Perceived Usefulness yields a stronger impact on Usage Attitude than Recommendation Quality and Perceived Ease of Use, indicating that the system’s practical utility yields more impact on user perception than usability or technical quality. Future RS development should focus on increasing long-term use by improving customer satisfaction through increased system usability and RS accuracy, supported to a lesser extent by features that bolster user trust and familiarity. These findings offer insight on optimizing RS designs and fostering continued engagement in Indonesia’s e-commerce landscape.
Keywords:	Artificial Intelligence, Recommendation System, E-Commerce, Customer Continuance Usage Intention, Recommendation Quality.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	THE MOST EFFECTIVE METHOD FOR FINDING REGULAR EXPRESSIONS IN DOCUMENT DATABASES
Author:	KOTESWARA RAO KODEPOGU, MOLIGI SANGEETHA, RAVI UYYALA, 4CHALLAPALLI SUJANA, NARESH VURUKONDA, DR. SIVUDU MACHERLA, CHETLA CHANDRA MOHAN
Abstract:	Considering a list of n strings with a maximum length of k, where l is the longest string. The goal is to use as few regular expressions as possible to cover the strings (r1, r2, r3……………..,rm for m≥1) so that: a) Every text in the database meets at least one ri and b) Any string "X" of length at most K satisfying r1+r2+r3+And so on.The distance between a string "y" in the database and +rm is at most p, where "p" is a specified constant parameter. We presume that the database is in the form of B+ tree. We begin with leaf nodes and gather all of the database's longest strings. The goal of the paper is to create a process for detecting regular expressions in databases that is comparable to that for Boolean formulae (in DNF or CNF), where function values and don't care words are supplied.
Keywords:	CNF, DNF, Document, Databases, Effective Method.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	YOU ONLY LIVE ONCE V7 SALVAGING AND GARBAGE CATALOGUING CENTERED ASSISTANT
Author:	DR LALITHA KUMARI GADDALA, MARLA MURALI SAI VENKATA REDDY, MYNENI BHAAVAN, KAZA SIVA NAGA UDAY KIRAN, MAHESWARAM JEJI CHANDRA SEKHAR, YALAMANCHILI SUREKHA
Abstract:	The ever-growing global population has heightened resource consumption and waste generation, emphasizing the urgent need for effective waste management to safeguard the environment. Unfortunately, the recycling industry grapples with persistent challenges, primarily in the realm of accurate trash classification, a critical factor for successful recycling. Manual sorting, often prone to errors due to subjective human judgment, hampers the recycling process, contributing to inefficiencies. Furthermore, the inherent risks associated with direct contact during the sorting of hazardous materials pose serious health concerns for the workers involved. In response to these challenges, we propose a revolutionary solution: the Trash Classification and Recycling Assistant utilizing YOLO variants V5-V7. This system, rooted in image classification techniques, seeks to elevate the precision of trash sorting. Notably, YOLO variant V7 emerges as the frontrunner, showcasing remarkable accuracy improvements. By harnessing the capabilities of advanced technology, this innovative approach not only streamlines waste sorting processes but also mitigates health risks linked to manual handling of toxic materials. The integration of YOLO variants V5-V7 represents a pivotal step towards ushering in a new era of efficiency and accuracy in recycling practices, thus significantly contributing to the overarching goal of environmental sustainability.
Keywords:	Trash Classification and Recycling, YOLO Variants, Trash Sorting, Waste Sorting Processes, Toxic Materials.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	THE EFFECT OF XBRL ADOPTION, DISCLOSURE QUALITY, FIRM SIZE, AND STOCK TRADING VOLUME ON INFORMATION ASYMMETRY
Author:	SILVIA DEWIYANTI , TUBAGUS ISMAIL , LIA UZLIAWATI , HELMI YAZID
Abstract:	This study investigates the impact of XBRL adoption, disclosure quality, firm size, and stock trading volume on information asymmetry. The research employs purposive sampling on 24 companies listed in the LQ45 index on the IDX from 2017 to 2020. Using quantitative methods and multiple linear regression models, the study finds that XBRL adoption and disclosure quality significantly affect information asymmetry, while firm size and stock trading volume do not. These findings highlight the critical role of technological adoption and transparency in reducing informational disparities in capital markets
Keywords:	Information Asymmetry, XBRL, Disclosure Quality, Firm Size, Stock Trading Volume
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	EXPLAINABLE MACHINE LEARNING FOR TEXT CLASSIFICATION: A NOVEL APPROACH TO TRANSPARENCY AND INTERPRETABILITY
Author:	Dr. MOHAMMED ABDUL WAJEED , Dr. KHAJA MIZBAHUDDIN QUADRY , Dr. MOKSUD ALAM MALLIK , Dr. K. RAJESH KHANNA
Abstract:	The increasing use of machine learning (ML) models for text classification has sparked debates about their interpretability and transparency. Despite their exceptional performance in applications like sentiment analysis, spam detection, and topic categorization, the often-obscure nature of ML models presents challenges for users seeking to understand the decision-making process. Explainable Machine Learning (XML) aims to tackle these issues by offering human-comprehensible explanations of model outputs, thereby building trust and enabling improved decision-making in critical sectors such as healthcare, legal, and finance. This study offers a thorough examination of XML techniques applied to text classification models, encompassing attention mechanisms, feature importance methods, and post-hoc interpretability frameworks like LIME and SHAP. Furthermore, we assess these techniques in terms of their capacity to enhance model transparency, weighing the trade-offs between interpretability and performance. The research also delves into the future trajectory of XML in text classification, including the incorporation of user-focused explanations and regulatory requirements for AI transparency. Our results indicate that explainability not only enhances model trustworthiness but also aids in identifying model biases and enhancing overall performance.
Keywords:	Five Machine learning, Text Classification, Explainable Machine Learning. LIME, SHAP etc.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	TRUST-ENHANCED SECURE CLUSTER ROUTING IN WIRELESS SENSOR NETWORKS USING A MODIFIED MOTH FLAME OPTIMIZATION ALGORITHM
Author:	SOWMYASHREE M S ,SARITHA I G , NAVEEN I G , SHASHIBHUSHAN G
Abstract:	Wireless Sensor Networks (WSNs) are self-organizing systems composed of numerous small sensor nodes used to monitor and track various applications across extensive areas. In the context of healthcare, wireless sensor networks can play a crucial role by continuously monitoring patients' vital signs and ensuring timely data transmission to medical professionals. Despite their usefulness, WSNs face significant challenges related to energy consumption and security due to their open and limited resources. Implementing a Trust-based Modified Moth Flame Optimization (T-MMFO) algorithm in healthcare WSNs can help select secure and efficient routes for data transmission, thereby improving the overall reliability and longevity of the network. This enhanced security and energy efficiency ensure that critical health data is transmitted accurately and promptly, supporting better patient outcomes and more efficient healthcare delivery. The algorithm's performance was evaluated based on Packet Delivery Ratio (PDR), energy consumption, delay, and throughput. The results showed that T-MMFOA achieved a high PDR of 98.5% and 95.7% for networks with 200 and 400 nodes, respectively, outperforming existing methods like Fuzzy Grey Wolf Optimization (F-GWO), Quality of Service-aware Multipath Routing (QMR), Improved Duck and Traveller Optimization Multi-Hop Routing (IDTOMHR), and Quantum Behaviour and Gaussian Mutation Archimedes Optimization Algorithm (QGAOA)
Keywords:	Wireless Cluster-based Sensor Routing, Network Trust-based Modified Moth Flame Optimization, Malicious Attacks, Security.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	AN IMPROVEMENT OF METHOD FOR DIFFICULTY ADJUSTMENT BASED ON PROCEDURES IN THE GAME "LOST LABYRINTHS: ROGUE’S ODYSSEY"
Author:	HANDRIZAL, JOS TIMANTA TARIGAN, HERRIYANCE, MUHAMMAD RAIHANDI JAMAL RITONGA
Abstract:	The 2D platformer genre enjoys widespread popularity within the video game industry due to its engaging and enjoyable gameplay. However, maintaining an optimal difficulty level for players of varying skill levels presents a significant challenge for developers. This study investigates the implementation of a dynamic difficulty adjustment system within "Lost Labyrinths: Rogue's Odyssey," a 2D action platformer utilizing procedural content generation (PCG) for level design. Initial research identified key challenges, including maintaining consistent difficulty and ensuring long-term player engagement. To address these, a dynamic difficulty adjustment system was integrated alongside new game mechanics. Player feedback on an "Expert" game mode incorporating this system was collected. Results demonstrated the effectiveness of the dynamic difficulty adjustment system, with players expressing high satisfaction with the "Expert" mode. Features such as the "Fog of War" significantly enhanced the challenge and suspense, providing a more immersive and rewarding gameplay experience. This study highlights the potential of dynamic difficulty adjustment to significantly enhance the quality and player experience in 2D platformer games, offering a compelling solution for maintaining player engagement and extending game longevity.
Keywords:	Difficulty Adjustment, Fog of War, Expert Mode, Game 2D Platformer, Lost Labyrinths: Rogue’s Odessey
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	ADVANCEMENTS IN PNEUMONIA ANALYSIS AND DIAGNOSIS THROUGH MACHINE LEARNING AND DEEP LEARNING: TOWARDS EARLY DETECTION AND CLINICAL DECISION SUPPORT
Author:	SHAIK SIKINDAR , CH V RAGHAVENDRAN , G. MADHAVI
Abstract:	Pneumonia is a dangerous lung infection that can cause major morbidity and mortality globally. Numerous pathogens, such as bacteria, viruses, and fungus, are to blame. An early and precise diagnosis is necessary in order to treat and control the illness effectively. The goal of this research is to increase diagnostic accuracy and support clinical decision-making by utilizing deep learning improvements in pneumonia analysis and diagnosis to improve the performance of healthcare systems. Enhancing diagnostic precision, enabling early detection, integrating multi-modal data sources, improving model explainability, offering real-time decision support, and facilitating pre-emptive prediction and monitoring are the main goals of this project. In order to efficiently integrate data from various sources, the suggested approach consists of three comprehensive steps: data collection and pre-processing, early detection model creation, and feature fusion mechanism implementation. In order to tackle the issue of interpretability in the model, critical regions impacting the algorithm's decisions will be highlighted in heatmaps created using methods like Grad-CAM. Techniques for model acceleration and quantization will be used to lower computing needs and enable real-time applications. In order to provide prompt and accurate diagnoses, predictive models will be developed to assess the patient's information, such as their vital signs, medical background, and imaging findings. The designed systems' dependability and effectiveness will be confirmed by thorough model evaluation and validation, which will be followed by deployment and clinical validation in actual environments. This research intends to greatly improve pneumonia detection and diagnosis by utilizing these deep learning breakthroughs, ultimately leading to more effective and efficient healthcare delivery.
Keywords:	Deep Learning in Healthcare, Pneumonia Diagnosis, Medical Image Analysis, Grad-CAM, Data Science in Healthcare.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	THE IMPACT OF DIGITALIZATION AND E-GOVERNANCE ON TRANSFORMATION OF STATE MANAGEMENT MECHANISMS OF THE REGIONAL DEVELOPMENT
Author:	MYKHAILO GAZUDA, NATALIYA TYUKHTENKO, IRYNA LOMACHYNSKA, MYKOLA DUNAI, VIACHESLAV VERNYDUB, ROMAN BABICH
Abstract:	In the article, theoretical aspects of transformation of existing state management mechanisms of the regional development within digitalization and e-governance of the economy and society are researched. Priority directions to ensure effective state management mechanisms of the regional development in the conditions of the digital economy formation are substantiated. Definition of the concept of “digital transformation of state management mechanisms of the regional development” is proposed. Problems of transformation of regional management mechanisms under the digitalization impact are identified. Priority directions to carry out digital technologies by forming state management mechanisms of the regional development are considered, depending on the stages by formation of the digital society and potential of the regional digitalization. Current state of the regional digital transformation is analyzed. Formation of regional mechanisms management within digital transformations is proposed, architecture of the mechanism and results of its implementation are considered.
Keywords:	State Administration, E-Governance, Electronic Services, Mechanism, Region, Regional Administration, Digital Economy, Digital Technologies, Digitalization, Nation Security.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	THE REALITY OF MEDIA TRAINING IN JORDANIAN SATELLITE CHANNELS IN LIGHT OF THE DEVELOPMENT OF ARTIFICIAL INTELLIGENCE TECHNIQUES FROM THE POINT OF VIEW OF TECHNICAL PERSONNEL - A FIELD STUDY
Author:	SADDAM SULEIMAN SALMAN ALMASHAQBEH
Abstract:	The research aims to identify the reality of media training in Jordanian satellite channels from the point of view of technical cadres. The research population consisted of technical cadres working in governmental and private Jordanian satellite channels. The survey method was adopted by following the survey method on a simple random sample of (66) individuals from the community, using a questionnaire to collect data and information. The results showed that no one had taken a course on artificial intelligence tools. Also, it was revealed that 18% of the technical personnel working on satellite channels did not undergo any training courses during the last five years, while 7.5% underwent a high number of training courses if highlighted. The obstacles that hinder the qualification of technical personnel working in Jordanian satellite channels are that “the course topics are stereotypical and repetitive,” then the obstacles related “the lack of well-thought-out training plans in the television channels,” followed by those related to the training course times that do not suit the work conditions and pressures.” The researcher suggests involving technical cadres in identifying their training needs and establishing training centers in Jordanian satellite channels.
Keywords:	Media Training, Jordanian Satellite Channels, Technical Personnel, Artificial Intelligence, Media.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	AI- POWERED DIAGNOSIS: REVOLUTIONIZING HEALTHCARE WITH NEURAL NETWORKS
Author:	S PHANI PRAVEEN , PERURI VENKATA ANUSHA , RAMESH BABU AKARAPU , SREENATH KOCHARLA , KIRAN KUMAR REDDY PENUBAKA , VAHIDUDDIN SHARIFF , DESHINTA ARROVA DEWI
Abstract:	This paper discusses the development and evaluation of an AI-powered diagnostic system that utilizes deep learning techniques, such as neural networks, to improve the accuracy of diagnosis in healthcare. The proposed method includes several stages: data collection, preprocessing, neural network training, diagnosis generation, and result evaluation. Medical data, including imaging, patient history, and diagnostic reports, are gathered from diverse sources to ensure comprehensive input for the system. Preprocessing techniques involved normalization, transformation, and augmentation of the raw data to prepare them for training. The labeled datasets trained a neural network, in this case a Convolutional Neural Network (CNN) for images, to learn patterns regarding diseases. When the system is trained, it diagnoses new patients with decision thresholding to be applied at the output level to give high confidence on predictions. This comparison of the system with human doctors proves to be more rigorous, with higher accuracy, precision, recall, and F1-score. Moreover, it infers faster and even in the presence of noisy or missing data, exhibits robust performance. The outcomes demonstrate that AI models may have a great potential in enhancing the efficiency and accuracy of diagnostics in healthcare, which positions them as an asset in clinical decision-making.
Keywords:	Healthcare, Neural Networks, Convolutional Neural Network (CNN), Ai-Powered Diagnostic System
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	PRIVACY-PRESERVING AND EFFICIENT DATA SHARING FOR BLOCKCHAIN-BASED INTELLIGENT TRANSPORTATION SYSTEMS WITH INTERNET OF VEHICLES (IOV)
Author:	SHAIK MOHAMMAD RAFI, Dr. R. YOGESH RAJ KUMAR
Abstract:	Recent years have witnessed the development and adoption of blockchain technology in intelligent transportation systems (ITS) because of its authenticity and traceability. However, increasing ITS devices imposes grand challenges in privacy-preserving and eﬃcient data sharing. Recent research has demonstrated that integrating searchable symmetric encryption in blockchain enables privacy-preserving data sharing among ITS devices. However, existing solutions focus only on single-keyword searches over encrypted ITS data on the blockchain and suﬀer from privacy and eﬃciency issues when extended to multi-keyword scenarios. This work proposes a bloom ﬁlter-based multi-keyword search protocol for ITS data with enhanced eﬃciency and privacy preservation. We design a bloom ﬁlter to select a low-frequency keyword from the multiple keywords input by the ITS data owner. The low-frequency keyword can ﬁlter out a large portion of the ITS data from the search result, thus signiﬁcantly reducing the computational cost. Furthermore, each identiﬁer-keyword pair is attached with a pseudorandom tag that enables the completion of a search operation in only one round. To make changes in ITS data, include protocols for dynamic data updates, including addition and deletion, to the proposed system. Vehicle nodes' anonymity, data ownership, and secure communication during voting are supported by the blockchain foundation. The protocols allow for a fast, scalable, and privacy-preserving multi-keyword search for blockchain-based ITS, according to a comprehensive performance test. To ensure anonymity, traceability, and unlinkability of data sharing among vehicles. A comprehensive performance evaluation of the protocols was conducted.
Keywords:	Blockchain, Privacy-Preserving, Data Sharing, Intelligent Transportation Systems (ITS). Internet Of Vehicles (IOV).
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	HYBRIDHEARTGAN: A GAN-BASED FRAMEWORK FOR CROSS-DOMAIN WHOLE HEART SEGMENTATION FROM MRI TO CT
Author:	ANUSHA KOTTE, DR. V. KAMAKSHI PRASAD
Abstract:	Whole heart segmentation is critical to cardiology because it allows accurate diagnosis and treatment planning. Nevertheless, due to the differences in contrast, resolution, and noise between imaging modalities, existing methods can often not generalize to modalities such as MRI and CT. Although traditional architectures like U-Net perform well in a single domain, they fail to generalize due to domain shifts. Although domain adaptation models like CycleGAN improve some properties, they trade boundary accuracy and fine anatomical details. This backdrop of cross-domain segmentation presents these challenges and motivates the need for a more comprehensive framework. We present HybridHeartGAN, a proposed GAN approach composed of a Hybrid 3D U-Net generator and a CNN-based discriminator that helps to reconcile domain discrepancies and produces segmentation masks that are inferably anatomically plausible. It combines Dice loss and adversarial loss to adversarially train a segmentation network that makes both an accurate segmentation and a realistic mask. A sequential training process periodically updates the generator and discriminator, ensuring convergence and preventing overfitting for DS conditions. Validation of the framework on MRI and CT datasets revealed DSC 91.2% for MRI and 89.7% for CT, excelling in state-of-the-art methods. Its property of handling domain shifts enables multi-modal medical image segmentation via HybridHeartGAN.
Keywords:	HybridHeartGAN, Cross-Domain Segmentation, Whole Heart Segmentation, Generative Adversarial Networks (GANs), Multi-Modal Medical Imaging
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	DOES DATASET SPLITTING IMPACT ARABIC TEXT CLASSIFICATION MORE THAN PREPROCESSING? AN EMPIRICAL ANALYSIS IN BIG DATA ANALYTICS
Author:	BOUMEDYEN SHANNAQ
Abstract:	Text classification in Arabic faces numerous challenges because of the difficult structure of Arabic morphology and the absence of agreement about dataset preparation methods and splitting techniques. Research studies mostly examine feature engineering and preprocessing techniques yet fail to investigate properly the relationship between dataset splitting proportions and classification results. Research analyzes how the ratios between training and testing datasets (10%-90%, 20%-80% and 30%-70%) affect classification outcomes together with normalization, stop word filtering before stem, and tokenize operations. Numerous evaluation tests are conducted using 111,728 documents extracted from three Arabic newspapers that cover topics related to sports, politics and culture, economy, and diversity. The evaluation includes six machine-learning algorithms which are Random Forest, Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, K-Neighbors, and Decision Tree. The analysis shows that dividing the dataset impacts model performance more extensively than applying preprocessing to datasets especially when operating on large test sets. The application of genetic preprocessing resulted in minor accuracy enhancements for the Decision Tree model at +2.30% while it produced precision gains of +2.48% but SVM achieved only +0.64% sensitivity improvement through normalization techniques. Stemming and tokenization delivered the best preprocessing results because Arabic possesses numerous morphological forms. The data shows trained accuracy depends on well-managed training/testing splits, which creates an important contradiction regarding traditional preprocessing methods. This analysis adds meaningful value to Arabic text classification research by demonstrating quantitative data about the effect of dataset division techniques through practical recommendations for enhancing classification performance in big data analytics. The research results possess relevant applications in media organizations because they help optimize Arabic text processing in education systems while also enhancing business intelligence operations.
Keywords:	Arabic Text Classification, Preprocessing Techniques, Dataset Splitting, Big Data Analytics, Supervised Learning, Artificial Intelligence.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	FORWARD AND REVERSE ENGINEERING USING UML WITH RATIONAL ROSE AND OBJECT-ORIENTED PROGRAMMING LANGUAGE
Author:	DR G LAKSHMI, DR. KOLLURU SURESH BABU, DR. RATNA RAJU MUKIRI, DR L BHAGYA LAKSHMI, D VENKATA RAVI KUMAR DR SURESH BETAM, CHETLA CHANDRA MOHAN
Abstract:	Sometimes the source code itself is the only documentation available for post-delivery maintenance. When maintaining legacy systems—that is, software that is still in use but was created no more than 15 or 20 years ago—this occurs far too frequently. It might be quite challenging to maintain the code in these situations. Starting with source code and trying to reproduce the design documents or even the specs is one method of addressing this issue. We refer to this procedure as reverse engineering. This approach can be aided by CASE tools. A nice printer is one of the easiest, and it could make the code easier to see. Other technologies create diagrams, like UML diagrams or flow charts, straight from the source code; these visual aids can support the design recovery process. One of the two options available to the maintenance team after reconstructing the design is to try to reconstruct the specifications, make the necessary modifications to the reconstructed specifications, and then re-implement the product in the conventional manner. In the context of reverse engineering, forward engineering is the standard development process that moves from analysis through design to implementation. Roundtrip engineering is the process of combining forward and backward engineering. This paper describes how to use UML with Java and Rational Rose to do this.
Keywords:	Forward Engineering, Reverse Engineering, UML, JAVA, Rational Rose
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	ANALYZING CONSUMER PREFERENCE DYNAMICS IN AMAZON REVIEW DATA USING DOUBLE PROPAGATION-BASED SENTIMENT ANALYSIS
Author:	BAGUS SETYA RINTYARNA , WIWIK SUHARSO , ABADI SANOSRA , ANNISA KESY GARSIDE
Abstract:	This research proposes an innovative approach to extracting consumer preferences using Sentiment Analysis, addressing the limitations of traditional methods like Conjoint Analysis. Consumer preferences, influenced by factors such as product quality, experience, and emotions, are crucial for shaping marketing strategies and product development. While Conjoint Analysis faces issues like small sample sizes and high costs, Sentiment Analysis, particularly Aspect-Level Sentiment Analysis (ABSA), provides a more detailed and dynamic method by analyzing sentiments toward specific product attributes. Leveraging big data from e-commerce reviews, this technique offers real-time insights, is cost-effective, and does not require predefined sentiment dictionaries. The study utilizes the Double Propagation (DP) technique, which enhances sentiment accuracy through bidirectional analysis. This approach offers a more efficient, automated, and adaptive solution for understanding consumer preferences. The evaluation, conducted on Amazon Review Data, confirms the moderate effectiveness of DP in aspect extraction, with room for enhancement in dependency rules and aspect identification algorithms. The results of experiment also highlight the variability in DP's aspect-level accuracy, with consistently strong results for Price and Performance, but challenges in Port, Design, and Storage.
Keywords:	Consumer preference, Conjoint analysis, Sentiment analysis, Aspect, Opinion word
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	PRONGHORN SWIFT OPTIMIZATION FRAMEWORK (PSOF) A DYNAMIC AND SCALABLE APPROACH FOR ENHANCING WEB SERVICE PERFORMANCE
Author:	J. GNANABHARATHI , K. VADIVAZHAGAN
Abstract:	The Pronghorn Swift Optimization Framework (PSOF) is proposed to address critical challenges in web services, including high latency, inefficient resource utilization, and poor scalability. The growing demand for fast, reliable, and scalable web services has highlighted the need for frameworks capable of optimizing performance while maintaining low overhead. PSOF is designed to enhance the efficiency of data delivery, reduce response times, and improve system throughput under dynamic traffic conditions. The framework leverages adaptive mechanisms to handle fluctuating network loads, ensuring seamless performance across distributed environments. Simulation results reveal that PSOF significantly improves key metrics such as latency, throughput, and load balancing. PSOF creates a robust infrastructure for modern web applications by dynamically allocating resources and optimizing service interactions.PSOF bridges gaps in web service optimization by introducing a unified framework that enhances reliability and scalability, meeting the demands of evolving digital environments.
Keywords:	Pronghorn Swift Optimization, Web Service Optimization, Latency Reduction Scalability in Web Services, Throughput Enhancement, Load Balancing Techniques.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	AIR QUALITY PREDICTION USING IOT AND NEURAL NETWORKS-AN EMPIRICAL ANALYSIS
Author:	P. RAVI KUMAR, T. BALAJI, D. BHAVANI, R. ASHOK KUMAR T. PREM CHANDER, KIRAN KUMAR REDDY PENUBAKA, N. JAYA
Abstract:	Air pollution is one of the most critical environmental issues affecting human health, ecosystems, and climate change. The rapid urbanization and industrialization have exacerbated air quality issues, necessitating real-time monitoring and prediction systems. This paper presents a comprehensive study on using the Internet of Things (IoT) and Neural Networks for air quality prediction. By leveraging IoT for data acquisition and Neural Networks for predictive analysis, this research aims to provide a scalable and accurate solution to monitor and forecast air quality. Experimental results demonstrate the potential of this integrated approach in providing actionable insights for policymakers and the public.
Keywords:	Air Quality Prediction, IoT, Neural Networks, Environmental Monitoring, Machine Learning, Data Analytics
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	CHESTX-PNEUMONET: OPTIMIZED CNN WITH NOVEL LOSS FUNCTION FOR PNEUMONIA DETECTION
Author:	S SUGUNA MALLIKA , CH.SARADA , GAYATRI MANTRI , ARUNA KUMARI BOMMU , CH RAJYALAKSHMI
Abstract:	The automated and accurate detection of pneumonia poses a significant problem in medical analysis due to the subtlety of its indicators in X-ray or CT images. This task is of paramount importance, as pneumonia claims millions of lives annually. Leveraging sophisticated techniques such as deep learning is essential to enhancing both diagnostic precision and operational efficiency. However, adapting existing neural network frameworks for clinical imaging tasks often results in overfitting and limited transferability. To mitigate these limitations, we introduce PneumoClassifyNet, an innovative lightweight convolutional network architecture tailored specifically for Pneumonia Detection in chest X-ray analysis. This architecture is more compact yet more potent than traditional fine-tuning approaches. Additionally, we introduce a new loss function, RadCE-loss, designed to effectively extract distinguishing characteristics from incorrectly classified and fuzzy images. Furthermore, the convolutional kernels are optimized within the convolutional neural network (CNN) model to improve accuracy of classification. The paper presents PneumoClassifyNet, an optimized CNN for chest X-ray classification, and RadCE-loss, a function that enhances accuracy by handling misclassified images. Results of Experiments indicate that the lightweight PneumoClassifyNet, coupled with the RadCE-loss, achieves superior performance across key metrics, including F1-score, recall, accuracy and AUC. These findings affirm that a carefully optimized convolutional neural network (CNN) architecture can outperform fine-tuned deep learning models.
Keywords:	Pneumonia Detection, Convolutional Neural Network, Optimized Loss Function, Radce-Loss , F1 Score, Accuracy
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	BRAIN TUMOUR SEGMENTATION AND GRADE CLASSIFICATION USING MODIFIED VGG19 WITH SUPPORT VECTOR MACHINE
Author:	SYEDSAFI. S , KARTHEEBAN. K
Abstract:	A brain tumour is an abnormal cell growth that occurs either inside or outside the brain. Brain tumours are among the worst and most dangerous diseases in medicine. Convolutional neural networks produce the greatest results for tumour segmentation these days. BraTS2020 and real-time hospital images were employed in this method. Pre-processing, segmentation, and post-processing are the three phases of this methodology. During the pre-processing phase, Digital imaging & communications in medicine (DICOM) images converted to Neuroimaging informatics technology initiative (NIFTI), the images are resized, noise is removed, skulls removed process are done. During the segmentation phase, the Local binary pattern (LBP) features are identified and the modified VGG19 (M-VGG19) is employed to segment the tumour. The suggested approach obtained Dice similarity coefficient (DSC) values of 0.9415, 0.8898, 0.8862, and Hausdorff distance - 95th percentile (HD95) values of 5.65, 11.11, and 11.88 for whole tumour (WT), tumour core (TC), and enhanced tumour (ET) respectively, during the segmentation process. The usage of Graphics processing unit (GPU) reduced the training and testing computation time for segmentation and reached the speedup folds up to 3× compared with CPU. Tumour volumes are computed at the post-processing phase. Subsequently, this technique classified tumours into High-grade glioma (HGG) and Low-grade glioma (LGG) using Support vector machine (SVM). The BraTS dataset was trained using real-time hospital pictures, and this method got 85.71 classification accuracy.
Keywords:	MRI images, Image resize, Tumour segmentation, Feature extraction, VGG19, SVM, 3D volume, Classification
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	DEEP LEARNING APPROCHES FOR TUMOR DETECTION USING MRI DATA
Author:	PURNACHANDRARAO MURALA , KUNJAM NAGESWARA RAO
Abstract:	Neurological diseases are relatively severe in the field of health informatics, often associated with life-threatening symptoms and costly treatments. Among these, brain tumors stand out as a well-known concern, showing a noteworthy increase in the affected patient’s number over the past decade. MRI imaging is the primary method for tumor detection, and recent advancements in Computer-Aided Diagnosis (CAD) using deep learning have improved diagnostic accuracy. However, existing models have drawbacks, such as inadequate dataset sizes, which hinder early-stage tumor detection, and the limited number of extracted features from input images. To address the challenges, an Enhanced Convolutional Neural Network (ECNN) model has been proposed. The proposed ECNN is trained on the MRI images taken from the BR35H benchmark dataset with extensive data augmentation techniques to improve generalization. The ECNN model achieved a high accuracy of 99.3% in classifying tumor images. Once tumor-positive images were identified, further analysis was performed using a Vision Transformer (ViT) model, trained on a different subset of the BR35H dataset. The ViT model achieved an accuracy of 97% in localizing tumor regions, showing its effectiveness in precise tumor segmentation. This hybrid technique, which addresses important issues in automated brain tumor diagnosis, improves both detection accuracy and interpretability by using CNN-based classification followed by Transformer-based localization.
Keywords:	Brain Tumors, MRI Images, Computer-Aided Diagnosis (CAD), Enhanced Convolutional Neural Network (ECNN)s, Vision Transformer (VIT).
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text

Title:	A HYBRID APPROACH FOR INTRUSION DETECTION AND PREVENTION IN MOBILE AD HOC NETWORKS
Author:	S. HEMALATHA1, S. SHALINI , PULLELA SVVSR KUMAR , RACHAKONDA SRINIVAS , T.THILAGAM , DR. VIJAYA KUMBHAR
Abstract:	Mobile Ad Hoc Networks (MANETs) are highly dynamic and decentralized, making them vulnerable to various security threats, especially intrusion attacks. This paper presents a hybrid approach combining machine learning techniques and trust-based systems for efficient intrusion detection and prevention in MANETs. The proposed system leverages feature extraction, anomaly detection, and node trust evaluation to identify malicious activities while ensuring minimal impact on network performance. Experimental results demonstrate that our approach outperforms existing methods in terms of detection accuracy, false positive/negative rates, and computational overhead. Specifically, it achieves a significant improvement in energy efficiency and network reliability under varying network conditions, including node mobility and density. The findings highlight the effectiveness of integrating machine learning with trust-based systems for securing MANETs. Future work will explore scalability improvements and the integration of hybrid detection mechanisms to enhance system robustness.
Keywords:	Mobile Ad Hoc Networks (MANETs), Intrusion Detection, Prevention Mechanisms, Machine Learning, Trust-Based Systems, Hybrid Approach, Security, Data Integrity, Anomaly Detection, Energy Efficiency.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2025 -- Vol. 103. No. 3-- 2025
Full Text