A Hybrid Expert System Using Symbolic Reasoning and Neural Networks for Predictive Maintenance in Mechatronic Systems Venkatesh S, Chandravadhana S, Rajesh R, Sagar Imambi S, Arivazhagan D, Vedaraj M Journal of Machine and Computing, 2025 Predictive maintenance (PdM) in mechatronic systems demands high-precision failure prediction and interpretability for real-time operational decisions. This study presents a hybrid expert system integrating symbolic reasoning and Deep Neural Networks (DNNs) to enhance predictive accuracy and semantic traceability. The symbolic layer consists of 42 fuzzy inference rules, enabling domain expert interpretability, while the neural network layer comprises a 4-layer feedforward architecture with 128-64-32-1 units using ReLU and sigmoid activations. Experiments were conducted on a real-world dataset, and the hybrid model achieved an accuracy of 96.8%, a precision of 94.22%, and a recall of 97.31%, outperforming conventional Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) models, and rule-based systems by margins of 3.2–7.8%. The proposed method reduced false positives by 21.4% and improved time-to-failure prediction by 18.7% compared to standalone models. Maintenance scheduling optimized using the proposed model yielded a 14.5% reduction in unplanned downtime. The hybrid inference strategy not only improved prediction granularity but also supported rule-based diagnostics. This framework significantly advances predictive intelligence in safety-critical mechatronic domains.
Novel data-driven approach for optimizing workforce alignment in smart manufacturing systems D. Arivazhagan, Aruna Singh, T. Dhanabalan, Sasanka Choudhury, Usha Chauhan, Manish Nagpal Multidisciplinary Science Journal, 2025 Workforce alignment is the process of assuring employees' skills, roles, and responsibilities in manufacturing companies to assess individual performance to meet the vision and mission of the organization effectively. This technique is useful to improve the engagement of employees in the corresponding organization. It has some limitations like an increasing resignation rate and reduction in satisfaction with job, which leads to a fall in productivity in more industries. It also creates more pressure on the managers who maintain the respective organizations. This research aims to improve operational effectiveness and production by creating a new data-driven strategy for workforce alignment optimization in smart manufacturing systems. This research focused on determining the most efficient use of worker resources by examining data at each worker's level. To guarantee proper workforce characterization, data collecting entails obtaining confidential data about employees, such as their talents, experience, and performance indicators. On-Line Analytical Processing (OLAP) methods are used for data pretreatment to enable multiple-dimensional analysis and effective data aggregation, which allows for a deeper knowledge of labor dynamics. The hybrid Red Deer Optimizer driven Efficient K-Nearest Neighbors (RDO-EKNN) model utilizes optimization approaches to increase the efficiency of the classification of KNN, guaranteeing effective labor synchronization in the manufacturing setting. According to the results, the RDO-EKNN approach improves workforce synchronization and optimization of resources in intelligent production systems exhibits a 90.5% F1 score and a 95.6% recall, the suggested model performs better than conventional techniques, which helps to improve labor management.
Adaptive and Quantum-Resilient Intrusion Detection for Wireless Sensor Networks and IoT Environments Mathan Kumar Mounagurusamy, A. Anil Kumar Reddy, C. M. Velu, Gera Vijaya Nirmala, D. Arivazhagan, Myasar Mundher Adnan, Rahmaan Κ., T. Prabhakaran Engineering Technology and Applied Science Research, 2025 Integrating Wireless Sensor Networks (WSNs) with the Internet of Things (IoT) has transformative potential for data acquisition, processing, and decision-making across dynamic connected environments. Ensuring the security and integrity of these systems is paramount, especially in the face of increasingly sophisticated cyber threats. This study introduces a novel security framework that combines Quantum Key Distribution (QKD) with an adaptive Deep Reinforcement Learning (DRL)-based Intrusion Detection System (IDS), specifically designed to address the unique challenges of the WSN-IoT ecosystem. The key innovation lies in integrating QKD not only for encryption but also as a dynamic quantum-secure layer that continuously adapts to security requirements based on real-time threats and communication patterns. Unlike previous approaches that focus primarily on routing and resource allocation, the proposed framework employs DRL with Proximal Policy Optimization (PPO) to refine intrusion detection by adapting its policies based on evolving attack signatures and threat types. This dual-layer QKD-DRL approach enhances intrusion detection accuracy and establishes a self-optimizing, quantum-secure communication protocol. Tested using the CICIDS2017 dataset, the proposed model achieved a 99.75% detection rate, outperforming traditional Random Forest (97.12%) and Deep Neural Network (96.88%) models. This improvement underscores the efficacy of combining quantum cryptographic techniques with DRL-based adaptive learning, providing a robust, real-time defense mechanism for IoT-driven environments in applications such as smart cities, healthcare, and industrial IoT systems. Thus, the proposed QKD-DRL framework sets a new standard for scalable, secure communication and threat mitigation in the IoT ecosystem.
Cyber Neutrosophic Model for Secure and Uncertainty Aware Evaluation in Indoor Design Projects Manju A, Rukmani Devi S, Mohammed Alaa H Altemimi, Jwalant Baria, Arivazhagan D, Lakshmi Prasanna P Journal of Machine and Computing, 2025 To perform a secure evaluation of Indoor Design data, the research introduces a Cyber-Neutrosophic Model, which utilizes AES-256 encryption, Role-Based Access Control, and real-time anomaly detection. It measures the percentage of unpredictability, insecurity, and variance present within model features. Also, it provides reliable data security. Similar features have been identified between the final results of the study, corresponding to the Cyber-Neutrosophic Model analysis, and the cybersecurity layer helped mitigate attacks. It is worth noting that Anomaly Detection successfully achieved response times of less than 2.5 seconds, demonstrating that the model can maintain its integrity while providing privacy. Using neutrosophic similarity scores that ranged from 0.85 to 0.98, the Cyber-Neutrosophic Model proved to have higher analysis accuracy. Additionally, it provided robust data security by utilizing Advance Encryption Standards (AES)-256 with Role-Based Access Control.
Cybersecurity in Telemedicine: A Multi-Layered Framework with Quantum Encryption and AI-Based Intrusion Detection Mohammad Bdair, Salman Mohammad Abdullah, Attarde Viren Bhaskar, D. Arivazhagan, Valisher Sapayev Odilbek Uglu, Maheswari. S 2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025 Telemedicine has changed the face of healthcare delivery by allowing consultations to be conducted remotely and monitoring of patients to be done around the clock. Nevertheless, this online revolution makes confidential medical information susceptible to advanced hacking attacks. As a measure against these risks, a multi-layered security model is suggested that incorporates the use of quantum encryption to enable secure communication, the use of CNN-LSTM to detect intrusions, a context-sensitive access control system based on dynamic trust scores, and a layered homomorphic encrypted cloud storage. The telehealth network was simulated to test the framework. The results indicate a threat detection rate of 98.6%, data integrity of 99.3% and a reduction of more than 92% in unauthorized entries with low system latency of less than 8 milliseconds. The intrusion detection system incorporates AI, achieving an F1-score of 94.8% across a range of attack types, including DDoS, brute force, and SQL injection. The practice provides effective safeguarding against current and upcoming cyberattacks, with a flexible and smart method of securing telemedicine setups.
Optimising the User Experience in E-Commerce Platforms Using Ergonomic Interface Design and Motion Analysis Sundari Dadhabai, Firas Tayseer Ayasrah, Kancharla K Chaitanya, Arivazhagan D, Jagadeesan P, Rahmaan K Journal of Machine and Computing, 2025 This study investigates how Motion Analysis (MA) and Ergonomic Interface Design (EID) can enhance the User Experience (UX) in e-commerce (E-comm) platforms. MA, including Eye-Tracking (ET) and Gesture Recognition (GR), was used to examine User Interfaces (UI) patterns, while EID principles were applied to optimize UI elements such as button size, layout spacing, and navigation. A total of 45 participants, considered by device preference and shopping habits, were observed across PC, mobile, and tablet platforms. Key findings indicate that mobile users engage in more frequent hand and wrist movements and UX higher discomfort levels due to smaller screens and touch-based UI, while PC users reported the highest comfort levels. Scroll depth analysis revealed that mobile users scrolled the deepest, especially during product discovery, while PC users engaged less with deeper content. GA showed heavy UI with more complex gestures, such as pinch-to-zoom and drag-and-drop, while light users relied on more straightforward gestures like tapping and scrolling. EID improvements significantly reduced movement frequency and increased comfort, particularly for mobile and tablet users. The study concludes that optimizing E-comm platforms through MA and EID leads to enhanced usability, reduced physical strain, and greater user satisfaction across devices.
An Adaptive Deep Learning Framework for Human Activity Recognition using Video Data Chejarla Raja S, D. Arivazhagan, S Lavanya, Rajeswari C, Banu S, Rahmaan K Esic 2025 5th International Conference on Emerging Systems and Intelligent Computing Proceedings, 2025 This research presents a dual-pathway SlowFast network in order to provide a novel approach for the recognition of human actions. The method has the ability to capture low-intensity as well as high-intensity activities efficiently. The model is trained on two different datasets: one on the routine activities, such as sitting and walking, and the other on complex sports and leisure activities. The SlowFast network increases the accuracy in a wide variety of scenarios by incorporating high-level spatial context along with fast motion characteristics using a dual-path architecture. The proposed model outperforms the conventional HAR methods on different grounds such as adaptability and accuracy, and thus aptly useful for applications such as security surveillance, healthcare, and sports analysis. This approach brings forth a robust system able to identify a range of human actions in static as well as dynamic environments by removing some of the limitations from existing HAR models.
An Enhanced Deep Learning Model for Intrusion Detection System: A Robust Gradient-Based Defence Mechanism Mukesh Kumar, Rahmaan. K, Abrar Ahmed Katiyan, Narendran M, P. Suwathi, D. Arivazhagan 2025 2nd International Conference on Circuits Power and Intelligent Systems Ccpis 2025, 2025 Intrusion Detection Systems (IDS) are pivotal in protecting network infrastructure from cyber-attacks. Conventional Machine Learning (ML)based IDS cannot deal with co-evolving attack types, adversarial manipulations, and high dimensional data complexities. In order to overcome these limitations, this paper presents Gradient Based Defense Mechanism with a Fuzzy Min-Max Neural Network (GDM-FMM-NN), an advanced IDS that combines gradient-based optimization with the Fuzzy Min Max-Neural Network (FMM-NN). GDM-FMM- NN introduces a class of traffic patterns based on dynamic adjustments of sets of hyperboxes to accommodate a subset of the feature space or to make local or global improvements as patterns evolve. Specifically, FMM-NN faces high numbers of False Positives (FP)and misclassification errors due to overlapping hyperboxes, changes to rigid boundaries, and adversarial perturbations. GDM-FMM-NN uses adaptive learning rates and gradient constraints to refine hyperbox updates, thus preservingexpansion accuracy, overlap detection, and contraction robustness. Experimental evaluation on the NSL-KDD dataset shows that GDM-FMM-NN is 98.7% accurate, outperforming the existing IDS methods such as Random Forest (RF) (94.6%) and Support Vector Machine (SVM) (92.8%) as well as traditional FMM-NN (95.3%). It is a robust solution for real-time IDS applications, as GDM-FMM-NN speeds up classification and is more resilient against adversarial attacks. The results show that GDM-FMM-NN is Effective in achieving higher intrusion detection accuracy at the same time or a reduced computational cost.
An Edge Assisted Internet of Things Model for Renewable Energy and Cost-Effective Greenhouse Crop Management Nabeel S Alsharafa, Sudhakar Sengan, Santhi Sri T, Arivazhagan D, Saravanan V, Rahmaan K Journal of Machine and Computing, 2025 Improved greenhouse Crop Yields (CY) are now within reach due to the rise of "Smart Farming (SF)" based on the Internet of Things (IoT). The IoT presents a massive opportunity for precision farming, which has the potential to increase CY, optimize resource use, and decrease the environmental impact of agriculture. Kenya's climate challenges greenhouse CY, but this paper lays out an integrated model that works well for growing Capsicum there. A multi-layered system equipped with sensors allows for the real-time monitoring of critical Environmental Factors (EF) in the model. For faster responses and less dependence on distant cloud services, these sensors send data to a processing layer that acts as an intermediary and uses Edge Computing (EC) for data management and immediate action. The analytics layer successfully reads sensor data, predicts possible scenarios, and makes decisions using Random Forest (RF) algorithms to improve crop productivity and yield. Also, the framework's user-friendly interface integrates data display and control, enabling efficient human communication. Kenya's climate impedes the cultivation of horticultural crops. The current study demonstrates that a hybrid model using IoT + EC + RF substantially improves Capsicum growth. The research establishes a standard for SF operations by combining advanced data analytics with the IoT to demonstrate how to develop a sustainable and adaptive SF system. This research set the standard for SF production by proving how a dynamic SF environment can be developed by applying advanced analytics with IoT.
A Novel Digital Mark CP-ABE Access Control Scheme for Public Secure Efficient Cloud Storage Technique International Journal of Intelligent Systems and Applications in Engineering, 2023
A birds view on success aspects and failure elements in network of small & medium enterprises and entrepreneurial firms in India International Journal of Scientific and Technology Research, 2020
The role of technology in supply chain management International Journal of Scientific and Technology Research, 2020
Logistics network in india: Challenges and scope International Journal of Scientific and Technology Research, 2020
Cognition and emotions during teachinglearning process International Journal of Scientific and Technology Research, 2020
Best organizational practices: Role of corporate information security International Journal of Scientific and Technology Research, 2020
Develop cloud security in cryptography techniques using DES-3l algorithm method in cloud computing International Journal of Scientific and Technology Research, 2020
An analysis of smart car parking management system International Journal of Scientific and Technology Research, 2020
An investigation of IOT based smart agriculture International Journal of Scientific and Technology Research, 2020
Experimental analysis of rpl routing protocol in iot International Journal of Scientific and Technology Research, 2019
Generating a digital signature based on new cryptographic scheme for user authentication and security Indian Journal of Science and Technology, 2014
Optimal scheduling based On instance niche for channel assignment in ad-hoc network International Journal of Engineering and Technology, 2014
Power saving mechanism for ad-hoc network using 3G fast dormancy technology Indian Journal of Science and Technology, 2014
Prevention of co-operative black hole attack in manet on DSR protocol using cryptographic algorithm International Journal of Engineering and Technology, 2014
A recurrent Elman neural network - based approach to detect the presence of epileptic attack in Electroencephalogram (EEG) signals International Journal of Engineering and Technology, 2014
Ontology based semantic web technologies in E-learning environment using Protégé Indian Journal of Science and Technology, 2014
A survey on query processing in mobile database Indian Journal of Science and Technology, 2014
RECENT SCHOLAR PUBLICATIONS
An Enhanced Deep Learning Model for Intrusion Detection System: A Robust Gradient-Based Defence Mechanism M Kumar, AA Katiyan, P Suwathi, D Arivazhagan 2025 2nd International Conference on Circuits, Power and Intelligent Systems … , 2025 2025
Cybersecurity in Telemedicine: A Multi-Layered Framework with Quantum Encryption and AI-Based Intrusion Detection M Bdair, SM Abdullah, AV Bhaskar, D Arivazhagan, VSO Uglu 2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-6 , 2025 2025
Adaptive and quantum-resilient intrusion detection for wireless sensor networks and IoT environments MK Mounagurusamy, AAK Reddy, CM Velu, GV Nirmala, D Arivazhagan, ... Engineering, Technology & Applied Science Research 15 (4), 24723-24728 , 2025 2025 Citations: 5
Technologies for Additive Manufacturing of Metals and Their Classification M Bhuvanesh Kumar, CT Justus Panicker, D Arivazhagan Metal Additive Manufacturing: Principles, Techniques and Applications, 1-26 , 2025 2025 Citations: 2
An Adaptive Deep Learning Framework for Human Activity Recognition using Video Data D Arivazhagan, S Lavanya 2025 International Conference on Emerging Systems and Intelligent Computing … , 2025 2025
An edge assisted internet of things model for renewable energy and cost-effective greenhouse crop management NS Alsharafa, S Sengan, T Santhi Sri, D Arivazhagan, V Saravanan, ... Journal of Machine and Computing 5 (1), 576-588 , 2025 2025 Citations: 20
A Hybrid Expert System Using Symbolic Reasoning and Neural Networks for Predictive Maintenance in Mechatronic Systems S Venkatesh, S Chandravadhana, R Rajesh, SS Imambi, D Arivazhagan, ... 2025
Recommendation systems and content personalization: algorithms, applications, and adaptive learning JA Venice, D Arivazhagan, N Suman, HJ Shanthi, R Swadhi AI for Large Scale Communication Networks, 323-348 , 2025 2025 Citations: 69
Sustainable Practices of Teachers in Private Educational Institutions: Exploration of Organizational Behavior AH Vidhyalakshmi, D Arivazhagan 3rd International Conference on Reinventing Business Practices, Start-ups … , 2024 2024
Exploring the Interplay of Emotional Intelligence, Stress, and Their Impact on Personal Life AH Vidhyalakshmi, D Arivazhagan Journal for ReAttach Therapy and Developmental Diversities 6 (10s), 993-1000 , 2023 2023
Medical Inflation-Issues and Impact S Poongavanam, R Srinivasan, D Arivazhagan, NV Suresh Chettinad Health City Medical Journal (E-2278-2044 & P-2277-8845) 12 (2 … , 2023 2023 Citations: 46
An assessment of challenges of digitalization of agrarian sector D Arivazhagan, K Patil, C Dubey, A Uppal, SK Gupta, P Mishra, ... International Conference on Business and Technology, 48-57 , 2022 2022 Citations: 57
A bird’s view on Deduplication and encryption technology – A secured data transaction in Cloud computing Network GV D. Arivazhagan1 R. Kirubakaramoorthi2 International Journal of Mechanical Engineering 7 (2), 337-342 , 2022 2022
Fall of Automobile Industry H S. Poongavanam, D. Arivazhagan TEST Engineering & Management 83 (March 2020), 9336 - 9338 , 2020 2020
Rupee - Dollar Fluctuation H S. Poongavanam, D. Arivazhagan TEST Engineering & Management 83 (March 2020), 8912 - 8915 , 2020 2020
Imprints made by Technology in Work Life of Fishermen for Advancement in Fishing Methods along the East Coast of Chennai RV D. Arivazhagan , J. Rengamani , S. Poongavanam TEST Engineering & Management 83 (March 2020), 8773-8777 , 2020 2020
A Birds View On Success Aspects And Failure Elements In Network Of Small & Medium Enterprises And Entrepreneurial Firms In India DRV D.Arivazhagan, Dr.S.Poongavanam, Dr. C. Manoharan, R. Divyaranjani INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH 9 (4), 1535-1537 , 2020 2020
The Core Aptitudes Of Freight Forwarders Network In Handling Consignments In Chennai Segment D Arivazhagan, A Kaushick, J Rengmani Solid State Technology 63 (4), 1798-1804 , 2020 2020
Enhancing Security in cloud Computing Using Idea Algorithm RK Dr. D. Arivazhagan International Journal of Research and Analytical Reviews (IJRAR) 7 (1), 764-768 , 2020 2020
The core Aptitudes of Freight Forwarders Network im handling Consignment in Chennai Segment RJ Arivazhagan D, Kaushick A Solid Sate Technology 63 (4), 1798-1804 , 2020 2020
MOST CITED SCHOLAR PUBLICATIONS
Applications, advantages and challenges of ad hoc networks D Helen, D Arivazhagan Journal of Academia and Industrial Research (JAIR) 2 (8), 453-457 , 2014 2014 Citations: 100
Recommendation systems and content personalization: algorithms, applications, and adaptive learning JA Venice, D Arivazhagan, N Suman, HJ Shanthi, R Swadhi AI for Large Scale Communication Networks, 323-348 , 2025 2025 Citations: 69
An assessment of challenges of digitalization of agrarian sector D Arivazhagan, K Patil, C Dubey, A Uppal, SK Gupta, P Mishra, ... International Conference on Business and Technology, 48-57 , 2022 2022 Citations: 57
Cognition And Emotions During TeachingLearning Process Dr. D. Arivazhagan INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH 9 (2), 267-269 , 2020 2020 Citations: 51
Medical Inflation-Issues and Impact S Poongavanam, R Srinivasan, D Arivazhagan, NV Suresh Chettinad Health City Medical Journal (E-2278-2044 & P-2277-8845) 12 (2 … , 2023 2023 Citations: 46
Survey on encryption techniques used to secure cloud storage system R Kirubakaramoorthi, D Arivazhagan, D Helen Indian J. Sci. Technol 8 (36), 1-7 , 2015 2015 Citations: 29
Generating a digital signature based on new cryptographic scheme for user authentication and security K Ganeshkumar, D Arivazhagan Indian Journal of Science and Technology 7 (S6), 1-5 , 2014 2014 Citations: 29
Analysis of cloud computing technology R Kirubakaramoorthi, D Arivazhagan, D Helen Indian Journal of Science and Technology 8 (21), 1-3 , 2015 2015 Citations: 26
Prevention of Co-operative Black Hole attack in Manet on DSR protocol using Cryptographic Algorithm G Vennila, D Arivazhagan, N Manickasankari Int. J. Eng. Technol.(IJET) 6 (5), 2401 , 2014 2014 Citations: 24
An edge assisted internet of things model for renewable energy and cost-effective greenhouse crop management NS Alsharafa, S Sengan, T Santhi Sri, D Arivazhagan, V Saravanan, ... Journal of Machine and Computing 5 (1), 576-588 , 2025 2025 Citations: 20
New cryptography algorithm with fuzzy logic for effective data communication K GaneshKumar, D Arivazhagan Indian journal of Science and Technology 9 (48), 1-6 , 2016 2016 Citations: 19
Ontology based Semantic Web technologies in E-learning environment using protege N Manickasankari, D Arivazhagan, G Vennila Indian Journal of Science and Technology 7, 64 , 2014 2014 Citations: 19
AN EFFICIENT PATIENT INFLOW PREDICTION MODEL FOR HOSPITAL RESOURCE MANAGEMENT. K Srikanth, D Arivazhagan ICTACT Journal on Soft Computing 7 (4) , 2017 2017 Citations: 14
Application of design thinking techniques in marketing of fashion apparel e-commerce S Misra, D Arivazhagan Indian Journal of Marketing, 18-30 , 2017 2017 Citations: 8
A survey on query processing in mobile database N Manickasankari, D Arivazhagan, G Vennila Indian Journal of Science and Technology 7, 32 , 2014 2014 Citations: 8
Strategies of cybercrime: Viruses and security sphere K Ganeshkumar, D Arivazhagan, S Sundaram Journal of Academia and Industrial Research (JAIR) 2 (7), 397-401 , 2013 2013 Citations: 8
Develop Cloud Security in Cryptography Techniques using DES-3L Algorithm method in Cloud Computing RK Dr. D. Arivazhagan INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH 9 (1), 252-255 , 2020 2020 Citations: 7
An Investigation of IOT Based Smart Agriculture DRJ G. Vennila, Dr. D. Arivazhagan INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH 9 (1), 2054-2056 , 2020 2020 Citations: 6
Hash based technique to identify the selfish node in Mobile Ad-hoc Network G Vennila, D Arivazhagan Indian Journal of Science and Technology 8 (14), 1 , 2015 2015 Citations: 6
Power saving mechanism for Ad-Hoc Network using 3G fast dormancy technology D Helen, D Arivazhagan Indian Journal of Science and Technology 7 (S6), 74-77 , 2014 2014 Citations: 6
