		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
June 2025 | Vol. 103 No.11

Title:	SGB-IDS: A SWARM GRADIENT BOOSTING INTRUSION DETECTION SYSTEM USING HYBRID FEATURE SELECTION FOR ENHANCED NETWORK SECURITY
Author:	VAHIDUDDIN SHARIFF, NVS PAVAN KUMAR, N ASHOKKUMAR, SURESH KUMAR MANDALA, MOHAN AJMEERA, N S KOTI MANI KUMAR TIRUMANADHAM, P CHIRANJEEVI
Abstract:	This paper proposes an integrated approach to build up IDS with proper effectiveness toward the rising need for strong network security. Network traffic anomaly detection and classification are one of the major aims and enhance the security layer against various types of cyber threats. This study is a methodical approach in which a diverse set of data is first extracted from Kaggle. The collected dataset is a comprehensive one that includes various kinds of network traffic data. The first step includes preprocessing the data, i.e., handling missing values, removing erroneous entries, and dealing with outliers using the Z-score method. To counter class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is utilized in generating synthetic samples in underrepresented classes for the generalization of models. The feature selection is done by using the Variance Mutual Forest (VMF) algorithm relies on the Variance Thresholding, Mutual Information, and Random Forest Selection methods. This method unites Variance Thresholding, to select statistically significant features with Mutual Information, and Random Forest for feature dimension reduction with the goal of overfitting minimization. For building models, a hybrid of Particle Swarm Optimization (PSO) and Light Gradient Boosting Machine (LightGBM), which is termed Swarm Gradient Boosting (SGB), is used. By using soft voting to aggregate the outputs of PSO and LightGBM, the proposed SGB model improves the prediction accuracy, the degree of robustness, and adaptability. The presented methodology has achieved high classification accuracy of 97.28%, precision of 93.49%, recall of 91.88%, F1 score of 94.23%, and low RMSE of 0.2592. These metrics demonstrate that the model is reliable and of practical use for intrusion detection in dynamic, high-dimensional environments of networks, providing a proper solution to modern security network challenges.
Keywords:	Intrusion Detection System, Network Security, SGB Model, PSO, LightGBM, Variance Mutual Forest (VMF), SMOTE, Z-score Method, Data Preprocessing.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	A CONSTRUCT FOR RECOMMENDING STRATEGIC MOBILE NETWORK PROMOS FOR IMPROVED SERVICE DELIVERY BASED ON PREVALENT REGIONAL NETWORK SERVICE REQUEST
Author:	EMMANUEL C. UKEKWE, CAROLINE N. ASOGWA, JUDE RAIYETUMBI, AKPA JOHNSON, DANIEL A. MUSA, GREGORY. E. ANICHEBE, NNAMDI J. EZEORA, ADAORA, A. OBAYI, RICHARD AKOMODI, BASHIR TENUCHE, FOLAKEMI O. ADEGOKE
Abstract:	Mobile network providers make use of promos to attract more clients or consolidate on existing ones. Network service request of voice and Internet differ across locations and pre-knowledge of prevalent network service request for a given location will determine the promo type and subsequently impact positively on the network providers. This paper proposes a construct for identifying the prevalent network service of different regions of coverage. To test the construct, three quarters of telecommunication data obtained from the Nigerian Bureau of Statistics for the four major mobile network providers (Mtn, Globacom, Airtel and 9-Mobile) in 2021 were used. Clustering models such as K-Means, Agglomerative and Affinity propagation were compared to determine the most suitable. The affinity propagation model gave the best results in terms of Silhouette score, Davies-Bouldin Index and Calinski-Harabasz Index metric tests Subsequently, the Affinity propagation model was used to cluster and determine the prevalent network service of voice and Internet for the states and for each network provider. A mean-based linguistic classification identified Airtel and Glo mobile network providers as having equal subscription of voice and Internet across the states while Mtn and 9-Mobile had variable subscriptions. Suitable voice and Internet subscription promos and tariff bundles were thus recommended based on the classification.
Keywords:	Mobile Network, Clustering, Machine-Learning, Subscription Rate, Promos, Tariff Bundles
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ENHANCING WATER QUALITY CLASSIFICATION IN LAKE TOBA WITH DEEP LEARNING APPROACH
Author:	SARAH PURNAMAWATI, ROMI FADILLAH RAHMAT, MUHAMMAD ISA DADI HASIBUAN, IQBAL FAKHRIZA, FARHAD NADI, SHARFINA FAZA, RAHMAT BUDIARTO
Abstract:	Lake Toba serves as a crucial water resource that is extensively utilized for various purposes. However, different water types have distinct uses, necessitating proper classification. Government Regulation No. 82 of 2001 establishes water quality standards to classify water into several categories, each indicating its appropriate use. This study proposes the use of a deep neural network (DNN) to classify the water quality of Lake Toba. The research explores different activation functions—Softmax, ReLU, and Sigmoid—along with the SGD, RMSProp, and Adam optimizers. To determine the most effective model architecture, each activation function was tested in combination with different optimizers. The findings indicate that deep neural networks (DNNs) can be effectively utilized for water quality classification, with accuracy and error rates influenced by the activation function, optimizer, number of neurons, and number of hidden layers. The dataset used in this study includes measurements of water temperature, pH level, dissolved oxygen concentration, oxidation-reduction potential, air temperature, and humidity, which are essential for monitoring the water quality of Lake Toba. The testing process consists of two approaches: (1) classification using three parameters, based on Government Regulation No. 82 of 2001, and (2) classification using six parameters. Each test is conducted using the same model architecture. The highest recorded accuracy in the experiments was 99% (0.998402), with the lowest recorded loss at 0.014616. These results were obtained from studies utilizing three parameters.
Keywords:	Lake Toba; Water quality Classification; Deep Neural Network (DNN); Machine Learning; Government Regulation No. 82 of 2001
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	IMPROVING SECURITY IN WIRELESS MOBILE COMMUNICATION THROUGH MACHINE LEARNING: INSIGHTS FROM GSM AND TDMA APPROACHES
Author:	RAKESH KUMAR, ANANT KUMAR SINHA, RAKESH KUMAR YADAV, SANTOSH KUMAR SHUKLA
Abstract:	Wireless communication allows for the exchange of information between numerous locations without the use of physical means like cables or optical fibers. Wireless security, a critical component of Wi-Fi networks, protects against unauthorized access and data breaches. Wireless solutions, unlike conventional communication, do not require infrastructure or cable maintenance. The research seeks to improve the user experience in wireless mobile communication by utilizing machine learning technologies for security considerations. It looks at how machine learning, together with Global System for Mobile Communication (GSM) and Time Division Multiple Access (TDMA) technologies, can be used to improve wireless security. The study predicts that as technology advances, there will be a greater reliance on wireless communication around the world. Furthermore, it underscores the importance of providing future-proof security solutions for wireless users, particularly in contexts where wiring individual devices is impractical due to the scale of digital networks.
Keywords:	Machine, Machine Learning (ML), Network, Security, Technology
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	A SYSTEMATIC REVIEW ON ENHANCING IOT SECURITY WITH DEEP LEARNING AND BIG DATA ANALYTICS
Author:	ANKUR GUPTA , DR. DINESH CHANDRA MISRA
Abstract:	The exponential expansion of the Internet of Things (IoT) has altered connection and automation in many industries. The vast amount of data produced and the restricted processing power of various IoT devices have caused major security issues, however, as the Internet of Things (IoT) has grown quickly. This paper offers a thorough examination and analysis of current studies combining deep learning (DL) and big data analytics to improve IoT security. Among the many notable contributions examined were blockchain-integrated security systems, hybrid DL models combining CNNs and RNNs with big data analytics, and anomaly detection in industrial IoT using autoencoders and LSTM. The evaluation also takes into account federated learning strategies meant to provide privacy-preserving security in highly dispersed IoT networks. Though the accuracy—often over 90% in threat detection—is remarkable, other research points out drawbacks include the focused attention on certain frameworks, lack of generalizability across IoT sectors, and difficulties in using hybrid or federated models. This paper underlines the changing function of integrating deep learning with big data analytics by means of insights from 15 major research and discusses the future promise of these technologies in creating safe, scalable, and smart IoT systems. Authors have utilized a hybrid deep learning approach combining Convolutional Neural Networks (CNNs) and autoencoders for anomaly detection within general IoT environments, achieving a high detection accuracy of 92.3%. Some of the author focused specifically on Industrial IoT (IIoT), employing a combination of Long Short-Term Memory (LSTM) networks and autoencoders. This approach yielded an even higher detection accuracy of 94.1%. Meanwhile, many researchers proposed a privacy-preserving model using federated learning, achieving an estimated detection accuracy of around 90%.
Keywords:	Big Data, CNN, Deep Learning, IoT, LSTM, Security.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	A MULTILAYERED SECURITY SCHEME FOR DATA ENCRYPTION AND DECRYPTION FOR STRONGER SECURITY TOWARDS POST-QUANTUM CRYPTOGRAPHY IN CLOUD COMPUTING
Author:	DASARI VEERA REDDY, DR.PADMAJA MADUGULA
Abstract:	Post-quantum cryptography (PQC) is poised to revolutionize data, network, and information system security as quantum computing gains traction. Shor and Grover's methods show how the potential of quantum computing might make cryptographic primitives like RSA and AES susceptible. This suggests that developments in quantum computing are replacing the most advanced conventional encryption methods. Future quantum computers might be far quicker than current ones because of techniques like superposition and entanglement in quantum computing. As such, initiatives are underway to create security solutions that are compliant with PQC. It's important to note that more work will need to be done to construct security primitives compatible with PQC, as the research of these schemes is still in its early phases. The Multilayered Data Encryption Standard (MDES) is one multilayered security technique that addresses this. Because this approach uses many data transformations, data in transit and at rest is exceptionally safe. Encrypting the first layer's data uses the enhanced AES encryption standard. Data availability and integrity are enhanced by slicing and modifying the ciphertext at the second layer using the Optimal Information Dispersal Algorithm (OIDA). The data is converted into an alternate format once slices are created, before the hash value is computed. The data is stored in cloud computing or any other storage system after conversion. Java is the programming language used to construct the specified security solution. An empirical investigation reveals that the proposed technique is highly secure and supports data availability and integrity through a verifiable data loss recovery mechanism. Security research shows the recommended strategy is safer than the most recent methods.
Keywords:	Security, Cryptography, Post Quantum Cryptography, Multi-layered Security Scheme, Data Integrity, Data Availability
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	NEXT-GENERATION RANSOMWARE DEFENSE: DEEP LEARNING-BASED TRAFFIC CLASSIFICATION AT THE NETWORK LAYER
Author:	ZAID ALI HUSSEIN , OMER ABDULHALEEM NASER , ZAID ALI HAMID
Abstract:	They were more advanced than ever in ransomware, fileless execution, polymorphic encryption, and encrypted C2 communications. The problem, however, widens, with Ransomware as a Service (RaaS) now having joined the party. To fight against these trends, we introduce a next-generation ransomware defense framework that is a deep learning-based real-time detection system capable of detecting ransomware in real encrypted network traffic without any payload inspection. In particular, the system classifies traffic using statistical flow metrics, protocol-specific patterns, and behavioral anomalies by means of transformer-based models. The trained model is tested on a 35 million flow dataset consisting of real ransomware samples, benign enterprise traffic, and adversarial flow samples with around 98.9%, 99.2%, and 98.5% in accuracy, precision, and recall, respectively. In addition, it is robust and scalable for adversarial training and federated learning. The system is deployed into the enterprise environment and has the capability to provide real-time response (0.5s detection) and hence is viable for current enterprise, IoT, and cloud networks.
Keywords:	Ransomware Detection, Encrypted Network Traffic, Deep Learning, Transformer Models, Federated Learning, Adversarial Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	OPTIMIZING DEMENTIA PREDICTION: A COMPARATIVE PERFORMANCE STUDY OF ML AND DL
Author:	DHULIPALLA NAGAJYOTHI , CHIRRA VENKATA RAMI REDDY
Abstract:	Dementia, a progressive neurological disease that impairs cognitive ability, is one of the most important worldwide health issues. With the projected number of affected people to exceed 130 million by 2050, an early and accurate diagnosis is essential to improve patient outcomes. However, conventional diagnostic methods including cognitive evaluations, neuroimaging, and clinical evaluations are time consuming, expensive, and often subjective, stalling timely intervention and increasing the strain on healthcare systems. In order to overcome these obstacles, this work predicts dementia using a novel fusion of deep learning (DL) and machine learning (ML). We investigated a variety of models, such as autoencoders, support vector machines (SVMs), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and other machine learning-based classifiers. To enhance predictive robustness, we propose a hybrid ensemble stacking classifier that integrates multiple base classifiers with a metaclassifier. This ensemble approach effectively harnesses the strengths of different models, significantly improving diagnostic accuracy and reliability. This work can facilitate early detection, enable personalized treatment strategies, and ultimately improve the quality of care for people at risk for dementia. To evaluate our model, a dataset of patients with dementia was used. The hybrid ensemble stacking classifier reached 100% compared to the remaining models which were in the range of 62.33% to 97.67%.
Keywords:	CNN, SVM, SGD, Ensemble Learning, RNN
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	AN ENHANCED INNOVATION RESISTANCE THEORY TO MEASURE THE BARRIERS OF AI-BASED CHATBOTS USAGE AMONG TEACHER TRAINEES
Author:	LIU YONGGANG, HAPINI AWANG ,NUR SUHAILI MANSOR
Abstract:	In recent years, Information and Communication Technology (ICT) has experienced tremendous progress (especially the advancement of AI-based Chatbots), profoundly affecting the global economic structure, social transformation, business innovation, education models, soft skills acquisition, human lifestyles, and so on. The main objective of this study is to develop and validate an enhanced Innovation Resistance Theory (IRT) model to measure the barriers of AI-based Chatbots usage among teacher trainees. This study mainly uses the quantitative research method and PLS-SEM for data analysis. This study finds that Value Barrier (VB), Risk Barrier (RB), Image Barrier (IB), Information Quality Barrier (IQB), and Job Relevance Barrier (JRB) have a significant and direct influence on teacher trainees’ resistance to AI-based Chatbots (RTAC). However, the effects of Usage Barrier (UB) and Tradition Barrier (TB) on teacher trainees’ RTAC are less significant. VB plays a mediating role in the relationship between Technology Anxiety (TA) and RTAC. RB mediates the relationship between the Electronic Word-of-Mouth Barrier (E-WOMB) and RTAC. JRB can also play a mediating role. This study not only proposes a new theoretical model, which is based on the traditional IRT model and combines new constructs (e.g., IQB and E-WOMB) and new paths (e.g., the mediating role of JRB), but also contributes to the cultivation of future technological talents and the spread and development of AI-based Chatbots in the future.
Keywords:	AI, AI-based Chatbots, Information and Communication Technology (ICT), Barrier, Education.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	COLLABORATIVE SQL AND JSON INJECTION DETECTION SYSTEM USING MACHINE LEARNING
Author:	ALAA S. ALNEMARI , SAMAH H. ALAJMANI
Abstract:	SQL and JSON injection attacks are still a significant security vulnerability in contemporary web applications, particularly in API-based systems. This paper introduces a new collaborative machine learning system designed to detect and mitigate SQL and JSON injection attacks in real time. The system adopts a stratified defensive approach, integrating database query analysis, behavioural scrutiny of API requests, and instantaneous anomaly detection to establish a resilient protective framework. Utilizing advanced machine learning techniques—including Support Vector Machines (SVM), Naive Bayes (NB), Decision Trees (DT), and Random Forest (RF)—it achieves high-fidelity discrimination between benign and malicious queries. Also, the system maintains dynamic response to new attack methods through real-time threat monitoring, input sanitization mechanisms, and adaptive learning strategies. The model is trained on a mixed dataset of labelled SQL and JSON injection attempts along with actual queries, which enhances its accuracy in detection. Empirical evaluations demonstrate 94% accuracy with zero false positives compared to conventional syntax-based detection mechanisms. Future improvements may involve the application of transformer-based architectures (e.g., BERT, GPT-activated detection), graph neural networks (GNNs), and reinforcement learning to enhance accuracy and responsiveness. This research highlights the need for multi-pronged security that is AI-driven to safeguard modern database systems and API infrastructures against advanced SQL-JSON injection attacks.
Keywords:	SQL Injection, JSON Injection, Machine Learning-based Detection, API Security, Real-time Anomaly Detection,
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	DEPLOYING LIGHTWEIGHT MOBILENET MODELS ON EDGE DEVICES FOR ENERGY EFFICIENT REAL TIME AI IN IOT NETWORKS
Author:	BETHALA RAMYA, JAGADEESWARA RAO ANNAM, V SITAMAHALAKSHMI, V.V. RAMA KRISHNA, K. TRINADHA RAVI KUMAR, REDNAM S S JYOTHI, KRISHNA SURESH B V N V, ANIL KUMAR PALLIKONDA
Abstract:	This paper proposes a framework for deploying energy-efficient AI models on devices in real-time time applications. This approach minimizes latency, power consumption, and dependence on cloud-based systems by utilizing edge computing's proximity to the IoT devices. The paper evaluates the accuracy, latency, and energy consumption of the MobileNet model, a lightweight convolutional neural network (CNN), for use in IoT environments. We can see models get 92% training and 90% test accuracy. Based on latency comparison, an edge device processes an image in 20ms while compared to 10ms processing on a cloud server. The edge and cloud energy consumption per image was measured to be 0.5mJ and 1.2mJ, respectively. These results illustrate the potential of deploying scalable, energy-efficient AI models on resource-constrained edge devices to achieve real-time IoT applications.
Keywords:	Edge Computing, Artificial Intelligence, Internet of Things (IoT), MobileNet, Energy Efficiency, Real-Time Processing, Scalability, Latency, Cloud Computing, Lightweight Neural Networks
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	COMPUTATIONAL EPISTEMIC UNCERTAINTY MODELING OF SINGLE EDGE CRACKED PLATES USING THE FUZZY FINITE ELEMENT METHOD (FUZZYFEM)
Author:	A.Y.N. YUSMYE, A.K. ARIFFIN, C.B.M. RASHIDI, B. NAKARMI
Abstract:	This study investigates the analysis of a two-dimensional (2D) single-edge crack plate using the Fuzzy Finite Element Method (FuzzyFEM), incorporating uncertainties inherent in engineering systems. Addressing critical engineering challenges, such as damage progression or loading effects from real-world conditions, requires consideration of uncertainty as an unavoidable factor. These uncertainties arise from incomplete data, conflicting information, and subjective interpretations, necessitating systematic approaches to mitigate material failure in engineering applications. The primary objective of this research is to evaluate the application of FuzzyFEM while accounting for epistemic uncertainties associated with single-edge crack plates. Accurately modeling these uncertainties is crucial for improving the reliability of structural assessments. To achieve this, a fuzzy system is proposed as an effective approach. Unlike conventional statistical methods, fuzzy system theory is a non-probabilistic technique well-suited for handling uncertainty when data is limited. The methodology begins with fuzzification, where crisp inputs are transformed into fuzzy values, followed by a core mapping process. At the mapping stage, a hybrid approach integrating fuzzy systems with the finite element method is employed. The extension principle method is used to numerically process fuzzy inputs, allowing for systematic uncertainty quantification. The results of this study, presented in figures and tables, demonstrate the efficiency and reliability of the proposed FuzzyFEM approach. By incorporating fuzzy logic into finite element analysis, this method provides a more comprehensive framework for addressing uncertainties in structural integrity assessments, offering valuable insights for engineering applications.
Keywords:	Epistemic Uncertainty, Stress Intensity Factor, Linear Elastic Fracture Mechanics, Fuzzy Finite Element Method (FuzzyFEM).
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	MACHINE LEARNING FOR THE MARITIME INDUSTRY
Author:	SAIRAGHUNANDAN PULIBANDLA, MOHAMED EL-DOSUKY, SHERIF KAMEL
Abstract:	This article handles two problems in maritime industry. The first is how to track ships and vessels. The second is the fact that numerous maritime trade routes are utilized by ships depending on the nation, topographical elements, and ship characteristics. This article proposes a system for tracking ships and developing maritime traffic routes using statistical density analysis. It uses information from an automatic identification system (AIS) to create quantifiable traffic routes. The approach includes preprocessing, deconstruction, and database management. DBSCAN detects boat waypoints, and kernel density estimation analysis (KDE) assesses the breadth of sea routes. The waypoints along the primary route are assessed while taking into account statistical data on all maritime traffic. The findings can be used to plan paths for autonomous surface ships, ensuring safe routes for ships in designated ocean regions.
Keywords:	Maritime, Ship Trajectory, Ship Maneuvering Instructions, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	A SYSTEMATIC AGILE FRAMEWORK FOR TEST-DRIVEN ONTOLOGY VALIDATION IN ACADEMIC PERFORMANCE ANALYTICS AND DECISION-MAKING
Author:	MOHD HAFIZAN MUSA, SAZILAH SALAM,MOHD ADILI NORASIKIN, MUHAMMAD SYAHMIE SHABARUDIN, UNING LESTARI
Abstract:	The rapid growth of educational data from diverse e-learning platforms such as Learning Management Systems (LMS) and Student Information Systems (SIS) presents challenges for universities in integrating and analyzing this data to monitor student performance, assess course effectiveness, and optimize faculty resource allocation. Ontologies provide a robust framework for enabling semantic interoperability and facilitating the integration of heterogeneous data sources for Learning Analytics (LA) and decision-making purposes. This study introduces the SPC_Academic_Performance ontology, a domain-specific ontology developed to consolidate and analyze academic performance data. To ensure the reliability and accuracy of the SPC_Academic_Performance ontology, we adopt the Test-Driven Development Ontology (TDDOnto2) methodology. TDDOnto2 systematically integrates validation techniques into the ontology development process, focusing on consistency checking and property testing. By applying TDDOnto2, this study aims to address common challenges such as logical inconsistencies and incomplete property definitions, ensuring the ontology’s robustness for data integration and retrieval. The findings contribute to developing a systematic ontology validation framework that supports reliable ontology-driven analytics and informed decision-making in higher education. This approach ensures that the proposed ontology can effectively map and retrieve data from heterogeneous sources, ultimately enhancing the accuracy and utility of Learning Analytics in academic performance monitoring and resource management.
Keywords:	Learning Analytics, University Ontologies, Data Retrieval Model, Ontologies Evaluation, Ontologies Validation, Web Semantic Ontology
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ENHANCING SKIN DISEASE DETECTION WITH OPTIMIZED VGG-19 AND EXPLAINABLE GRAD-CAM VISUALIZATION
Author:	M RAMAKRISHNA MURTY, Dr. SIREESHA VIKKURTY, SHAIK JOHNY BASHA, DR. GOTTUMUKKALA SANTHI, T.N.V.S. PRAVEEN, Dr. S. SELVAKANMANI, Dr. SIVA KUMAR PATHURI
Abstract:	Skin infections are a major concern for human health, as they can cause significant skin damage, leading to loss of confidence and emotional distress in patients. Advancements in deep learning offer promising solutions for diagnosing and treating such conditions effectively. AI-driven approaches enable automated skin disease detection without requiring expert intervention, making diagnosis more accessible. Enhancing the user interface of these systems can further improve user experience. Early identification of skin disorders is crucial in preventing misdiagnosis as minor allergies, which can otherwise lead to severe complications. This research explores the application of deep learning for improved skin infection detection and treatment. Leveraging the power of AI, the study introduces a novel classifier combining the VGG-19 convolutional neural network with Grad-CAM (Gradient-weighted Class Activation Mapping). This approach aims to enhance diagnostic accuracy and reduce the risk of misdiagnosis, ultimately minimizing patient complications. The model was trained and evaluated using a dataset sourced from Kaggle, a popular platform for machine learning datasets. Performance was compared against baseline machine learning models, including decision trees and Support Vector Machines (SVMs). Results indicate that the proposed dual-input model, incorporating VGG-19 and Grad-CAM, achieved a remarkable accuracy of approximately 96%. This significantly outperforms the baseline models, demonstrating the potential of deep learning techniques for accurate and efficient skin condition diagnosis. The improved performance suggests that this approach could be a valuable tool for dermatologists and other medical professionals in the future.
Keywords:	Deep Learning, SVM, Skin Disease , Decision Tree, VGG-19, Grad-Cam.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	A NOVEL EVALUATION METHODOLOGY FOR DETERMINING I-LEVEL TEST CYCLE-TIME IN MISSILE MAINTENANCE
Author:	CHENG-WEN LEE, YUAN-CHAO CHI, ROMI ILHAM
Abstract:	The periodic testing cycle of missiles is a critical factor influencing operational readiness, reliability, and associated logistics costs, including maintenance, transportation, and testing. Despite the importance of optimizing these cycles, a clear understanding of the optimal testing intervals for different missile types remains underexplored. This study investigates the impact of various I-Level periodic testing cycles for K-type missiles, utilizing the "Important Factor Weighted Exponential Distribution Function (IFWEDF)" method to estimate and compare reliability across different intervals. A cost-benefit analysis is then conducted to evaluate the implications of extending the testing cycle. The results indicate that a three-year testing cycle optimizes reliability while minimizing costs. This paper offers a novel approach to missile maintenance strategy formulation and contributes to the existing literature by providing evidence-based recommendations for determining optimal testing cycles in missile systems. The findings of this research can inform future strategies for military maintenance planning and contribute to cost-effective operational readiness management.
Keywords:	I-Level Periodic Testing Cycle, Important Factor Weighted Exponential Distribution Function (IFWEDF)
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	INTEGRATING COMPUTER VISION AND MACHINE LEARNING MODELS FOR HANDWRITING ANALYSIS
Author:	NAGAVALI SAKA, ABHINAV KUMAR, KOLLURU SURESH BABU, KONALA PADMAVATHI, JAGADEESWARA RAO PALISETTI, PADMAVATHI PANGULURI, G LAKSHMI
Abstract:	Handwriting has emerged as an essential characteristic in many applications, including forensic science, signature verification, and document authentication. Even though optimal character recognition (OCR) and machine learning (ML) have evolved more, the different handwriting styles combined with real-time processing issues have prevented current systems. For this reason, this study introduces a system that combines Computer Vision (CV) for preprocessing handwritten images with deep learning models CNN and LSTM for handwriting analysis. We believe integrating all these advanced techniques would improve handwriting analysis systems' accuracy and scalability. Moreover, our approach includes behavior capturing, which provides psychological insight based on the learned psychological cognition state of the writers, by using dynamic pen features such as pressure, writing speed, and stroke order. Compared to current state-of-the-art solutions, the proposed hybrid model has improved accuracy, real-time performance, and adaptability to different handwriting styles. This improves the accuracy of handwriting recognition and establishes a new avenue for behavioral profiling, potentially impacting fields like forensic investigation, psychological evaluation, and signature verification. Finally, the study concludes with prospects related to adding more behavioral traits and optimizing real-time processing capabilities.
Keywords:	Handwriting analysis, Computer Vision, Convolutional Neural Networks, Recurrent Neural Networks, Signature verification, Document forensics, Deep learning
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	EXPLORING THE TRANSFORMATIVE ROLE OF ARTIFICIAL INTELLIGENCE IN HEALTHCARE
Author:	HABIBULLA MOHAMMAD, K RAMANJANEYULU, M CHAITANYA KUMARI, GADI LAVA RAJU, VAHIDUDDIN SHARIFF, M JEEVANA SUJITHA
Abstract:	The objective of this study is to monitor ongoing scientific advancements, assess the accessibility of technology, recognize the vast potential of artificial intelligence (AI) in biomedicine, and encourage researchers in related fields. With continuous innovations, AI is significantly transforming healthcare by improving diagnostics, treatment planning, patient management, and drug discovery. The rapid evolution of AI-driven technologies, such as machine learning, deep learning, and natural language processing, has expanded the scope of their applications in medical imaging, personalized medicine, robotic surgery, and predictive analytics. These advancements are expected to grow exponentially, revolutionizing patient care and healthcare systems. This paper provides an overview of recent AI developments in healthcare, highlighting their impact on disease detection, early diagnosis, and treatment outcomes. AI-driven tools enhance precision in medical decision-making, reduce human errors, and optimize healthcare delivery. However, integrating AI into healthcare comes with ethical challenges, including data privacy, bias in algorithms, regulatory concerns, and the need for transparent AI models. Addressing these ethical concerns is crucial for ensuring the responsible use of AI in medicine. By summarizing key advancements and ethical considerations, this study aims to contribute to the understanding of AI's transformative role in healthcare and inspire further research in this rapidly evolving field.
Keywords:	Artificial Intelligence, Healthcare, Biomedicine, Machine Learning, Deep Learning, Medical Imaging.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	DECISION MAKING IMPROVEMENT USING FUZZY NEURAL NETWORK FOR ELECTRIC VEHICLE CONTROLLERS
Author:	RIDZKY KRAMANANDITA, ULIL HAMIDA, SAFRIL SAFRIL, DENNY RIANDHITA ARIEF PERMANA
Abstract:	The upcoming need for electric car development is essential in Indonesia. This is because the amount of energy from oil fuel is increasingly limited. To anticipate an energy crisis from oil fuel, especially in motorized vehicles, namely cars, electricity becomes more flexible energy for cars. One of the important parts of an electric car is the control system. This research focuses on the speed control used by electric vehicles so that the speed of the car can change gradually, thereby increasing the comfort and safety of electric vehicles. This makes electric car control system becomes more responsive. The method used in speed control is to combine fuzzy logic and artificial neural networks. The combination of the two methods gives satisfactory results for the artificial neural network model with an MSE value of 0.02566, but it is still not satisfactory for the fuzzy logic model which has an error of 1.732. Improvements to the membership function in the fuzzy logic model need to be done by using more data. In the future, the implementation of the model in the control system needs to be done to get real-time data
Keywords:	Electric Car, Control System, Speed Control, Fuzzy Logic, Artificial Neural Network
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	AN INTEGRATED APPROACH TO TEXTURE CLASSIFICATION USING RULE-BASED MOTIFS AND MAGNITUDE TEXTONS
Author:	UJWALA BHOGA, VIJAYA KUMAR V
Abstract:	Texture classification plays a significant role in computer vision that affects many fields, including medical image analysis, content-based image retrieval, face recognition, industrial inspection, etc. The effectiveness of texture classification relies on the extensiveness of the features extracted from the image data. Despite advancements in texture classification, many existing methods still struggle with ambiguous pattern representation and insufficient integration of local and global texture features, leading to decreased classification performance on complex datasets. To address these challenges, in this paper, we proposed a novel framework for texture classification by integrating rule-based motifs with magnitude textons. The method begins by transforming the input image into a complete magnitude-based texton-indexed (CMTi) image by examining the local pixel intensity relationships on a 2x2 grid, which precisely encapsulates structural features. Further, it applies an average filter to the 2x2 grids of the CMTi image, then calculates the absolute difference between each pixel of the CMTi image and the average of the 2x2 grid. Later, on the image derived average rule-based motif (ARMiCMT) indexed image through predefined rules, ensuring consistent and unique motif indexing even in cases of ambiguous intensity values, it is named as the average rule-based motif on complete magnitude texton (ARMiCMT) indexed image. Subsequently, the Gray Level Co-occurrence Matrix (GLCM) is computed on the ARMiCMT indexed image at various angles. This operation yields six spatial features: energy, contrast, entropy, angular second moment, correlation, and homogeneity. The feature vector integrates local descriptors with global spatial relationships, resulting in a holistic representation of texture. This strong feature extraction method enhances accuracy and robustness in texture classification, making it highly effective for diverse applications.
Keywords:	Magnitude Textons, Complete Magnitude-based Texton Indexed (CMTi) Image, Rule-based Motifs, Average Rule-based Motif on Complete Magnitude Texton (ARMiCMT) Indexed Image, Average Rule-based Motif on Complete Magnitude-based Texton Co-occurrence Matrix (ARMiCMT-CM)
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ADAPTING THE VIRTUAL NOMINAL GROUP TECHNIQUE FOR ENHANCED RISK ASSESSMENT IN CLOUD COMPUTING A MACHINE LEARNING APPROACH FRAMEWORK USING DATA ANALYSIS AND PREDICTIVE MODELLING
Author:	N. SUJATA KUMARI, SWARNA KUCHIBHOTLA
Abstract:	Given the ongoing evolution of cloud computing platforms and the increasing complexity of cyberattacks, risk assessment is a critical topic. By utilizing algorithmic modeling to forecast risks and altering the traditional Virtual Nominal Group Technique (VNGT), the current study offers an improved method for risk evaluations. The suggested method uses data analysis tools to categorize worry levels, assess possible risks, and offer useful information for proactive risk minimization. The approach enhances cloud security decisions by combining measurable predictive machine learning models with expert-driven subjective assessments. A variety of machine learning algorithms, including supervised and unsupervised methods, are also examined in order to improve the accuracy of risk prediction. Validated on real-world cloud security datasets, the methodology's application shows how well it enhances recognizing risks and remediation tactics.
Keywords:	Cloud Computing, Risk Assessment, Virtual Nominal Group Technique (VNGT), Predictive Modelling, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	FRAMEWORK-DRIVEN GUIDELINE GENERATION FOR AI ADOPTION: A RISK-BASED PERSPECTIVE
Author:	DAVID LAU KEAT JIN, GANTHAN NARAYANA SAMY, FIZA ABDUL RAHIM, MAHISWARAN SELVANANTHAN, NURAZEAN MAAROP, MUGILRAJ RADHA KRISHNAN, SUNDRESAN PERUMAL
Abstract:	The adoption of artificial intelligence (AI) presents unique risks that existing frameworks inadequately address, including issues of accountability, accuracy, fairness, safety, and privacy. According to AI Incident Database, there is an increase of 156% of published AI incidents from the year 2020 to 2024. This study bridges the gap between reported AI incidents and actionable countermeasures by analyzing an AI incident repository and contextualizing risks with mitigative strategies drawn from the literature. A knowledge graph was developed to integrate contextual data, risks, and countermeasures, enabling the generation of customizable, risk-based guidelines tailored to specific applications and stakeholders. Key findings include the identification of countermeasures for diverse AI risks, emphasizing the need for systematic risk assessment throughout the AI life cycle. The developed prototype serves as both a risk assessment tool and risk reference database in an enhanced enterprise risk management framework which facilitates responsible AI adoption, guiding developers, risk managers, and policymakers in advancing ethical and sustainable AI practices. This work lays the groundwork for automated tools that enhance scalability and usability in addressing AI risks in various organizational contexts.
Keywords:	Responsible AI; Risk; Countermeasure; Framework; Guideline
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ENHANCED SENTIMENT ANALYSIS AND DATA MINING OF POLITICAL LEADERS' POPULARITY ON SOCIAL MEDIA PLATFORMS USING AN OPTIMIZED APACHE HADOOP FRAMEWORK FOR ACCURATE ELECTION OUTCOME PREDICTION
Author:	CHANDRA SHEKHAR , RAKESH KUMAR YADAV
Abstract:	The paper presents an enhanced approach to sentiment analysis and data mining for evaluating the Popularity of political leaders on social media using the Apache Hadoop framework. Social media platforms have become influential in shaping public opinion, making it critical for political campaigns to understand the sentiment behind public discourse. In this study, social media data (e.g., tweets and posts) were collected and processed using Hadoop’s MapReduce framework to efficient handling large-scale data. Sentiment analysis was performed using a logistic regression model to classify public sentiment as positive, negative, or neutral. The model achieved an accuracy of 85%, with a precision of 0.86 for predicting a win and 0.84 for predicting a loss. Positive sentiment drivers such as "Viksit Bharat" and "stronger nation" had a strong positive impact on the likelihood of winning, while terms like "vote" and "voice" were associated with negative sentiment and a higher probability of losing. The study demonstrates that data-driven sentiment analysis can provide valuable insights for political strategists, enabling informed decision-making and improving campaign effectiveness.
Keywords:	Sentiment Analysis, Data Mining, Political Leaders' Popularity, Social Media Analytics Apache Hadoop Framework
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	OPTIMIZED TASK SCHEDULING IN FOG-CLOUD ENVIRONMENTS USING A COST-AWARE GENETIC ALGORITHM
Author:	YOUSSEF OUKISSOU, HAMZA ELHAOU, DRISS AIT OMAR, HICHAM ZOUGAGH, SAMIR ELOUAHAM
Abstract:	Cloud technology offers flexible computing and storage solutions over the internet. However, for latency-sensitive applications such as smart healthcare and smart cities, the reliance on centralized cloud data centers leads to significant performance issues, particularly in terms of delay. Fog and edge computing paradigms aim to address these issues by bringing resources closer to end-users, thus reducing latency and enhancing energy efficiency. In this paper, we propose a cost-aware, genetic-based (CAG) task scheduling algorithm tailored for fog-cloud environments, which seeks to improve cost efficiency for real-time applications with strict deadlines. Our approach is implemented and evaluated using the PureEdgeSim simulator, focusing on key performance metrics such as latency, network congestion, and cost. The results demonstrate that the proposed algorithm surpasses existing techniques like Round-Robin and Trade-off algorithms, achieving superior performance in terms of cost and throughput efficiency. These results demonstrate that the CAG algorithm is an effective solution for task scheduling in fog-cloud environments, offering better cost and deadline management compared to existing methods. This research has significant implications for latency-sensitive IoT applications, such as smart healthcare and smart cities, where efficient resource allocation and cost optimization are critical.
Keywords:	Fog Computing, IoT Scheduling, Edge Computing, Resource Allocation, Task Management
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	BRAIN TUMOR DETECTION USING DEEP LEARNING: A COMPREHENSIVE APPROACH TO AUTOMATED DIAGNOSIS
Author:	K SUNEETHA, M BABU RAO
Abstract:	Brain tumors are the most critical and life-threatening medical conditions, necessitating early and accurate detection for effective treatment planning. The main aim of the project is to investigate the application of transfer learning using state-of-the-art deep learning architectures, including VGG 16, VGG-19, ResNet-50, Inception-V3, and DenseNet-201, for accurate and efficient brain tumor detection from MRI images. These approaches are able to address the challenges such as data scarcity and computational constraints in medical imaging. The conventional manual analysis of brain image data, such as MRI scans is time-consuming and prone to subjective biases, so making automated methods highly desirable. The aforementioned methodologies leverage pre-trained models, fine-tuned to classify brain tumor images effectively. Each model was evaluated on a benchmark dataset, with preprocessing steps including normalization, augmentation, and segmentation to enhance feature extraction. Performance metrics such as accuracy, precision, recall and F1-score were employed to rigorously assess and compare the models. The results indicate that ResNet-50 demonstrate superior performance due to their deeper architectures and efficient feature extraction capabilities followed by VGG-19 and Inception-V3. DenseNet-201 exhibits notable results in terms of computational efficiency and accuracy trade-offs, while VGG-16, despite their simplicity, performs reliably in identifying tumor characteristics. This research highlights the potential of transfer learning in addressing challenges such as data scarcity and computational constraints in medical imaging tasks. By identifying the strengths and limitations of these models, the study provides a comprehensive foundation for deploying deep learning solutions in clinical settings, paving the way for improved diagnostic accuracy and efficiency in brain tumor detection.
Keywords:	Brain Tumor; Transfer Learning; CNN; Accuracy; F1 Score
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	AN INVESTIGATION OF DYNAMIC TOPIC MODELING FOR REAL-TIME AND EVOLVING TEXTUAL DATA USING DTM, BERTOPIC, RECURRENT NEURAL NETWORKS AND PROPOSED HYBRID DTM WITH RNN ALGORITHMS
Author:	C.B.PAVITHRA, DR.J.SAVITHA
Abstract:	Given the dynamic nature of textual data, Dynamic Topic Modeling has become an effective real-time analysis tool for streams of textual data. The objective of this study is to present a thorough review of different dynamic topic modeling strategies, such as advanced neural network-based methods like Recurrent Neural Networks (RNN), recent methodology like BERTopic, and traditional approaches like DTM. It also looks at the possible advantages and difficulties of combining RNN and DTM in a hybrid framework. We explore the effectiveness of these techniques in capturing temporal dynamics, identifying changing subjects, and offering insights into the underlying structures of the data through empirical evaluations on real-world textual datasets. Using the "Advanced Topic Modeling for Research Articles 2.0" dataset, this study assesses the methods according to a number of criteria, including accuracy, recall, precision, coherence, perplexity, and F-score. This research also assesses the subject modeling performance, scalability, and flexibility of our hybrid DTM and RNN strategy in relation to real-time and dynamic textual data, in comparison with other methods. The outcomes of our trials highlight the benefits of this hybrid strategy and offer insightful information to practitioners and researchers who want to use dynamic topic modeling for textual data analysis that is dynamic and real-time.
Keywords:	Dynamic Topic Modeling, Real-Time Data Analysis, Textual Data Streams, DTM, BERTopic, Recurrent Neural Networks, RNN, Hybrid Models, Natural Language Processing and Text Mining.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	FORECASTING FUTURE TRENDS: A GENERATIVE AI APPROACH TO DYNAMIC TREND PREDICTION
Author:	VINODKUMAR REDDY SURASANI , SARVANI ANANDARAO , NAGARAJU DEVARAKONDA
Abstract:	In the rapidly evolving digital landscape, trend forecasting has become a critical task for decision-makers across industries. Traditional methods struggle with adaptability, scalability, and real-time trend identification. This paper presents a novel framework that integrates Generative AI with the Proposed Guided Remora Optimization Algorithm (PGROA) to enhance trend prediction accuracy while maintaining robustness across dynamic and multimodal datasets. The framework leverages transformer-based architectures for feature extraction, adaptive learning mechanisms for real-time updates, and cross-domain generalization techniques to ensure scalability. Additionally, interpretability methods such as SHAP values and attention mechanisms provide transparency in model predictions. The proposed system is evaluated on diverse datasets, demonstrating superior performance with an accuracy of 94.8%, an F1-score of 93.8%, and a significantly reduced RMSE of 0.072, outperforming existing deep learning and hybrid models. This research establishes a scalable and interpretable AI-driven approach to trend prediction, equipping decision-makers with actionable insights for dynamic environments.
Keywords:	Generative AI, Trend Prediction, Adaptive Learning, Remora Optimization, Cross-Domain Generalization.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ENABLING INFORMATION TECHNOLOGY IN DESIGNING THE TVET MODEL FOR TVET EDUCATION PROGRAM
Author:	ROSZIATI IBRAHIM, KHADIJAH MD ARIFFIN, SANI INUSA MILALA, MAZIDAH MAT REJAB, SAPIEE JAMEL, ABDUL RASID ABDUL RAZZAQ
Abstract:	Technical and Vocational Education and Training (TVET) is essential for equipping students with industry-relevant skills and bridging the gap between vocational training and higher education. In Malaysia, the TVET matriculation program serves as a pathway for students transitioning into degree program. However, concerns persist regarding its effectiveness in preparing students for the academic and technical demands of higher degrees while meeting industry expectations. This study reviews previous research on TVET models, then the features of TVET models are extracted from different countries. The ideal TVET model is then proposed. The implementation plan of TVET model is executed to enhance the employability of students in TVET education program. Enabling the information technology in designing the TVET model, this paper discusses the effectiveness of executing the TVET model. Four main domains are discussed for effectiveness of TVET model. They are curriculum, implementation, feedback and review. This TVET model provides a structured framework for continuous curriculum improvement, ensuring better student preparedness and workforce alignment.
Keywords:	IT and Education, TVET Model, Workforce Alignment, Career Awareness, Industry Skills
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	DEVELOPING A DEEP LEARNING MODEL WITH TRANSFER LEARNING FOR BREAST CANCER DETECTION AND CLASSIFICATION USING MAMMOGRAPHY IMAGES
Author:	DR. S. SWAPNA RANI, ARUNA RAO S L, JAYASHREE S PATIL, VADLAMANI VEERABHADRAM
Abstract:	Breast cancer affects people all around the world and is a major cause of death for women. For the disease to be prevented and managed, early discovery is essential. Although there are other ways to identify breast cancer, mammography has shown to be a very successful strategy. The need to develop deep learning architectures and use transfer learning to increase detection performance has been brought to light by current research on the use of artificial intelligence (AI) and deep learning in breast cancer diagnosis. In this research, we offer a deep learning architecture that uses mammography imagery to autonomously diagnose breast cancer. Our framework utilizes a modified DenseNet-121 model and transfer learning, resulting in the Intelligent Learning Based Breast Cancer Detection (ILB-BCD) algorithm. An empirical study with a benchmark dataset, known as CBIS-DDSM, demonstrates that our proposed model surpasses numerous existing deep learning models with an impressive 99.16% accuracy. The success of our deep learning framework suggests its potential integration into existing healthcare systems to create an automated clinical decision support system (CDSS) for the detection of breast cancer.
Keywords:	Breast Cancer Screening, Artificial Intelligence, Deep Learning, Mammography Imaging, Cancer Detection
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	VANET SMART SECURITY SYSTEM FOR INTRUSIONS UTILISING ARTIFICIAL INTELLIGENCE AND DEEP LEARNING
Author:	Dr. RAMESH BABU P, CHINNEM RAMA MOHAN, SRIDHARA MURTHY BEJUGAMA, DR. K. SUGUNA, P UMA MAHESHWARA RAO, D SATYA PRASAD, DR. R. SENTHAMIL SELVAN
Abstract:	In a Vehicular Ad hoc Network (VANET) strategy, assault detection plays a major role in enhancing the security and reliability of ideas amongst all vehicles. Two deep learning techniques that are accepted in this field as indiscriminate Intelligent Intrusion Detection Systems (IDS) are the Adaptive Neuro Fuzzy Inference Systems (ANFIS) and Convolutional Neural Networks (CNN). The current approaches in VANET atmospheres are created to recognise certain types of dangers. The Intelligent IDS plan establishes a smooth estimating law, removing this restraint. Known Intrusion Detection Systems (KIDS) and Unknown Intrusion Detection Systems (UIDS) are the parts of the submitted approach that can label two famous and mysterious types of assaults. A deep knowledge method is cast in a piece of UIDS to label mysterious attacks in VANET, while the KIDS whole engages the ANFIS categorisation component to recognise popular injurious assaults. To discover obscure attack types, this paper proposes a reduced Leenet (MLNET) design. This study uses this composite knowledge approach to label Dos attacks, PortScan attacks, Botnet attacks, and Brute Force attacks. The submitted arrangement demands 1.76 s to discover the Dos attack on the i-VANET dataset and achieves 96.8% Pr, 98.8% Sp, 98.4% Se, and 98.7% Acc. The submitted arrangement detects the Botnet assault in 0.96 seconds while getting 98.2% Pr, 98.2% Sp, 98.8% Se, and 98.2% Acc. The submitted arrangement labelled the PortScan attack in 1.39 seconds, accompanying a Pr of 98.8%, Se of 99.2%, Sp of 98.8%, and an accuracy of 99.3%. The suggested Brute Force attack detection system takes 1.28 s and yields 99.2 Pr, 97.9% Se, 98.8% Sp, and 98.6% Acc. The approach is evaluated on the actual time CIC-IDS 2018 dataset and associated with other state-of-the-art methodologies.
Keywords:	Convolutional Neural Networks, Deep Learning Techniques, VANET, Intelligent IDS system, Known Intrusion Detection Systems.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	EVALUATING COMPUTER FORENSICS FOR CYBERCRIME INVESTIGATIONS IN CRITICAL INFRASTRUCTURE SECTORS
Author:	VALERII BOZHYK, MYROSLAV POPOVYCH, OLHA KHAKHUTSIAK, MYKOLA DENYSENKO, OLEKSADR HERASYMENKO
Abstract:	The increased digitization of critical infrastructure has compounded the threat of cybercrime in entrepreneurial enterprises handling high-value assets and sensitive information. Despite the abundance of literature on digital forensics, the unique application and value of these methods in critical infrastructure investigations remain largely unexplored. This study bridges this gap by evaluating the real-world efficacy of computer forensic techniques to detect and investigate crime in large industries, including finance, retail, and technology. A mixed-methods approach combined digital forensic analysis, statistical modeling, and expert interviews with 50 real-world cases. The findings reveal high rates of success in the use of forensic tools in uncovering evidence within complex business crimes, with data recovery and statistical analysis being most effective. Different from past studies, this research integrates empirical evidence and expert insights in assessing the real challenges and contributions of digital forensics in practice. This study contributes to the literature by developing a sectoral forensic framework, ascertaining legal and procedural limitations, and proposing paths for the uptake of AI-driven tools within forensic activities. These findings have practical implications in improving investigative accuracy, resource allocation, and interagency collaboration in cybercrime law enforcement.
Keywords:	Computer Forensics, Critical Infrastructure Security, Digital Evidence Analysis, Cybercrime In Entrepreneurship, Forensic Investigation Methods, AI In Digital Forensics, Statistical Forensic Evaluation.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	ENHANCING QUANTUM CRYPTOGRAPHY WITH MACHINE AND DEEP LEARNING A HYBRID APPROACH FOR SECURE AND SCALABLE POST-QUANTUM SECURITY
Author:	RAVI KUMAR INAKOTI, MEKA JAMES STEPHEN, P.V.G.D.PRASAD REDDY
Abstract:	Generation of secure communication was getting known as a promising technology called as a quantum cryptography. Unfortunately, it still faces several challenges, most notably in terms of high computational demands, scalability limitations, quantum decoherence, and vulnerability to side channel attacks, such that deployment of it in real world remains impossible yet. This study shows how Machine Learning (ML) and Deep Learning (DL) can be applied to tune the mentioned obstacles so that quantum cryptographic frameworks become more secure, more efficient and more scalable. In particular, we introduce a hybrid AI enabled model where RL can be utilized for tuning the performance of the post quantum cryptographic algorithm implementations, GANs can be adopted for measuring the robustness of the system, and FL can be used to make the quantum key distribution scalable. Besides, this thesis uses Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to incorporate the quantum authentication and key exchange methods. Additionally, our methodology employs techniques based on Graph Neural Networks (GNNs) to achieve the best performance in the networks and Adversarial Machine Learning (AML) to counter and detect, and then reduce cyber threats in the run time. For preferable cryptographic computations, we introduce Quantum Neural Networks (QNNs) to reduce its dependency on expensive quantum hardware. Experimental results also show that ML/DL based quantum security frameworks provide lowering of compute burden, improvement in real time security of data, and improve resistance to cyber threats. The result of this roadmap based on AI driven strategy is a comprehensive view, with a high level of direction describing the main steps to lead to post quantum security and take benefit of quantum cryptography and apply it in a multitude of significant utilization including secure communication, cryptographic financial systems or national infrastructure protection.
Keywords:	Quantum Cryptography, Post-Quantum Security, Machine Learning in Cryptography, Deep Learning for Quantum Systems, Quantum Key Distribution (QKD), Adversarial Machine Learning, Federated Learning in Security and Graph Neural Networks for Cryptography
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	RECOMMENDATION SYSTEM FOR E-LEARNING STUDENT ORIENTATION BASED ON MACHINE LEARNING ALGORITHMS AND QCM
Author:	MOULAY AMZIL , AHMED ELGHAZI , MOHAMED ERRITALI
Abstract:	This article is part of a student guidance project. It involves a recommendation and classification system (E_orientation) based on a real MCQ test. This test is administered to the student and provides random answers that are then used by our recommendation system. We use binary modelling of the answers, which produces a vector of data for each student at the end of the test. For modelling and classification, we use several machine-learning algorithms to optimize the accuracy of the recommendations. The results of the experiment show that Random Forest is the best model (85.93% accuracy), ahead of SVM (80.43%). KNN achieves 76.10%, and the Decision Tree, Logistic Regression and Naive Bayes algorithms have the lowest performance (Accuracy ≤ 67.03%). We can therefore improve the students’ method of orientation by basing it on simple technical questions. This will also improve their contribution to the labor market.
Keywords:	Recommendation System, School Guidance, Machine Learning, E-Learning Platform, MCQ Test
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text

Title:	TRITAG RECOMMENDER: A HYBRID APPROACH TO STACK OVERFLOW TAG PREDICTION USING TRANSFORMERS AND KEYWORD EXTRACTION
Author:	MORARJEE KOLLA, SRINIVASA RAO BURAGA, SUBHASH BHAGAVAN KOMMINA, J KAVITHA4, NITYA RAMIREDDY, SREEMUKHI SAVALGE
Abstract:	Community question-answering (CQA) platforms offer new opportunities for users to share knowledge online. Tags are added to data on these platforms to define, classify, and discover the information. Accurate tags help find users to answer the question. However, tags may be inaccurate or improper since users tag questions based on their understanding of the question's content and other tags that are on the site. Existing methods often fail to fully capture the semantic context of questions, especially those containing code snippets, leading to suboptimal tag suggestions. This highlights a gap in the literature for models that can effectively handle both natural language and programming content. To address this issue, we propose a novel deep learning approach combining advanced transformer-based architectures with keyword extraction techniques to understand the context in text and code snippets and produce relevant tags. Our proposed method will be able to suggest relevant and appropriate tags and demonstrate superior performance compared to state-of-the-art techniques, thus contributing new insights into context-aware tag recommendations for CQA systems.
Keywords:	Tag Recommendation, Community Question-Answering, Transformer, Keyword Extraction, Tritag Recommender
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2025 -- Vol. 103. No. 11-- 2025
Full Text