Trustworthy Adaptive AI for Real-Time Intrusion Detection in Industrial IoT Security Mohammad Al Rawajbeh, Amala Jayanthi Maria Soosai, Lakshmana Kumar Ramasamy, Firoz Khan Iot, 2025 Traditional security methods fail to match the speed of evolving threats because Industrial Internet of Things (IIoT) technologies have become more widely adopted. A lightweight adaptive AI-based intrusion detection system (IDS) for IIoT environments is presented in this paper. The proposed system detects cyber threats in real time through an ensemble of online learning models that also adapt to changing network behavior. The system implements SHAP (SHapley Additive exPlanations) for model prediction explanations to allow human operators to verify and understand alert causes while addressing the essential need for trust and transparency. The system validation was performed using the ToN_IoT and Bot-IoT benchmark datasets. The proposed system detects threats with 96.4% accuracy while producing 2.1% false positives and requiring 35 ms on average for detection on edge devices with limited resources. Security analysts can understand model decisions through SHAP analysis because packet size and protocol type and device activity patterns strongly affect model predictions. The system underwent testing on a Raspberry Pi 5-based IIoT testbed to evaluate its deployability in real-world scenarios through emulation of practical edge environments with constrained computational resources. The research unites real-time adaptability with explainability and low-latency performance in an IDS framework specifically designed for industrial IoT security. The solution provides a scalable method to boost cyber resilience in manufacturing, together with energy and critical infrastructure sectors. By enabling fast, interpretable, and low-latency intrusion detection directly on edge devices, this solution enhances cyber resilience in critical sectors such as manufacturing, energy, and infrastructure, where timely and trustworthy threat responses are essential to maintaining operational continuity and safety.
Hybrid convolutional neural network optimized with an artificial algae algorithm for glaucoma screening using fundus images M. Shanmuga Eswari, S. Balamurali, Lakshmana Kumar Ramasamy Journal of International Medical Research, 2024 Objective We developed an optimized decision support system for retinal fundus image-based glaucoma screening. Methods We combined computer vision algorithms with a convolutional network for fundus images and applied a faster region-based convolutional neural network (FRCNN) and artificial algae algorithm with support vector machine (AAASVM) classifiers. Optic boundary detection, optic cup, and optic disc segmentations were conducted using TernausNet. Glaucoma screening was performed using the optimized FRCNN. The Softmax layer was replaced with an SVM classifier layer and optimized with an AAA to attain enhanced accuracy. Results Using three retinal fundus image datasets (G1020, digital retinal images vessel extraction, and high-resolution fundus), we obtained accuracy of 95.11%, 92.87%, and 93.7%, respectively. Framework accuracy was amplified with an adaptive gradient algorithm optimizer FRCNN (AFRCNN), which achieved average accuracy 94.06%, sensitivity 93.353%, and specificity 94.706%. AAASVM obtained average accuracy of 96.52%, which was 3% ahead of the FRCNN classifier. These classifiers had areas under the curve of 0.9, 0.85, and 0.87, respectively. Conclusion Based on statistical Friedman evaluation, AAASVM was the best glaucoma screening model. Segmented and classified images can be directed to the health care system to assess patients’ progress. This computer-aided decision support system will be useful for optometrists.
Deep learning model construction for a semi-supervised classification with feature learning Sridhar Mandapati, Seifedine Kadry, R. Lakshmana Kumar, Krongkarn Sutham, Orawit Thinnukool Complex and Intelligent Systems, 2023 Several deep models were proposed in image processing, data interpretation, speech recognition, and video analysis. Most of these architectures need a massive proportion of training samples and use arbitrary configuration. This paper constructs a deep learning architecture with feature learning. Graph convolution networks (GCNs), semi-supervised learning and graph data representation, have become increasingly popular as cost-effective and efficient methods. Most existing merging node descriptions for node distribution on the graph use stabilised neighbourhood knowledge, typically requiring a significant amount of variables and a high degree of computational complexity. To address these concerns, this research presents DLM-SSC, a unique method semi-supervised node classification tasks that can combine knowledge from multiple neighbourhoods at the same time by integrating high-order convolution and feature learning. This paper employs two function learning techniques for reducing the number of parameters and hidden layers: modified marginal fisher analysis (MMFA) and kernel principal component analysis (KPCA). The MMFA and KPCA weight matrices are modified layer by layer when implementing the DLM, a supervised pretraining technique that doesn't require a lot of information. Free measuring on citation datasets (Citeseer, Pubmed, and Cora) and other data sets demonstrate that the suggested approaches outperform similar algorithms.
Cyber physical systems: A smart city perspective Firoz Khan, R. Lakshmana Kumar, Seifedine Kadry, Yunyoung Nam, Maytham N. Meqdad International Journal of Electrical and Computer Engineering, 2021
Evaluation of functional maturity for a network information service - Design and case analysis International Journal of Ad Hoc and Ubiquitous Computing, 2021
Research contemplate on educational data mining M Amala Jayanthi, R Lakshmana Kumar, Abhijith Surendran, K Prathap 2016 IEEE International Conference on Advances in Computer Applications Icaca 2016, 2017
Improvising the web search results using enhanced lingo algorithm in big data analysis for health care Journal of Advanced Research in Dynamical and Control Systems, 2017
Evaluation of quality of service through genetic approach in telecommunication based semantic web services composition International Journal of Control Theory and Applications, 2016
An Anonymous and Secure IoT Session Sharing for Industrial Automation Using Ring Signature Scheme F Khan, AJM Soosai, LK Ramasamy, E Abd Al Rahman 2026 IEEE International Conference on Consumer Electronics (ICCE), 1-6 , 2026 2026
Explainable artificial intelligence in a diagnostic support system S Kapoor, A Singh, P Garg, LK Ramasamy Explainable AI in Clinical Practice, 131-145 , 2026 2026
Sustainability Reporting and Emission Tracking in Smart Hospitals Using LLMs F Khan, LK Ramasamy 2025 10th International Conference on Information Technology Trends (ITT … , 2025 2025
Trustworthy adaptive AI for real-time intrusion detection in industrial IoT security M Al Rawajbeh, AJ Maria Soosai, LK Ramasamy, F Khan IoT 6 (3), 53 , 2025 2025 Citations: 24
AI as a Research Partner: Advocating for Co-Authorship in Academic Publications J Dempere, LK Ramasamy, J Harris The Artificial Intelligence Business Review 1 (2) , 2025 2025 Citations: 4
Inaugural Editorial for the Journal of Blockchain Technology (JBT) LK Ramasamy Journal of Blockchain Technology 1 (1), 1-3 , 2025 2025
Integrating Artificial Intelligence and Cybersecurity in Healthcare for the Advancements of Industry 5.0 F Khan, LK Ramasamy, EA Al Rahman, A Jayanthi International Conference on Wearables in Healthcare, 198-209 , 2024 2024 Citations: 2
Hybrid convolutional neural network optimized with an artificial algae algorithm for glaucoma screening using fundus images MS Eswari, S Balamurali, LK Ramasamy Journal of International Medical Research 52 (9), 03000605241271766 , 2024 2024 Citations: 9
Blockchain for Global Education LK Ramasamy, F Khan Springer , 2024 2024 Citations: 6
A Deep Dive into Mango Variety Classification Using Convolutional Neural Network and Random Forest Model LK Ramasamy, F Khan, S Joghee, J Dempere, P Garg 2024 International Conference on Automation and Computation (AUTOCOM), 80-84 , 2024 2024 Citations: 1
Forecast of students’ mental health combining an artificial intelligence technique and fuzzy inference system LK Ramasamy, F Khan, S Joghee, J Dempere, P Garg 2024 International Conference on Automation and Computation (AUTOCOM), 85-90 , 2024 2024 Citations: 32
Blockchain-Based E-Learning Platform: Transforming Education Through Decentralization LK Ramasamy, F Khan Blockchain for Global Education, 103-123 , 2024 2024 Citations: 6
Blockchain-based certification system: Ensuring trust in educational credentials LK Ramasamy, F Khan Blockchain for global education, 125-145 , 2024 2024 Citations: 11
Blockchain-Based Online Learning: Empowering Education Through Decentralization LK Ramasamy, F Khan Blockchain for Global Education, 165-185 , 2024 2024
Utilizing blockchain for a decentralized database of educational credentials LK Ramasamy, F Khan Blockchain for Global Education, 19-35 , 2024 2024 Citations: 7
Cross-Border Credit Transfer: Unlocking Educational Opportunities with Blockchain LK Ramasamy, F Khan Blockchain for Global Education, 83-102 , 2024 2024
Introduction to Blockchain Technology in Education LK Ramasamy, F Khan Blockchain for Global Education, 1-17 , 2024 2024 Citations: 1
Future of Blockchain in Education: Envisioning Transformation and Innovation LK Ramasamy, F Khan Blockchain for Global Education, 187-210 , 2024 2024 Citations: 1
Secure and transparent educational data record-keeping with blockchain LK Ramasamy, F Khan Blockchain for global education, 147-164 , 2024 2024 Citations: 11
Digital Identity System for Students LK Ramasamy, F Khan Blockchain for Global Education, 63-81 , 2024 2024 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
The impact of ChatGPT on higher education J Dempere, K Modugu, A Hesham, LK Ramasamy Frontiers in education 8, 1206936 , 2023 2023 Citations: 801
Secure smart wearable computing through artificial intelligence-enabled internet of things and cyber-physical systems for health monitoring LK Ramasamy, F Khan, M Shah, BVVS Prasad, C Iwendi, C Biamba Sensors 22 (3), 1076 , 2022 2022 Citations: 185
Blockchain-based secure healthcare application for diabetic-cardio disease prediction in fog computing PG Shynu, VG Menon, RL Kumar, S Kadry, Y Nam IEEE Access 9, 45706-45720 , 2021 2021 Citations: 169
A survey on blockchain for industrial internet of things RL Kumar, F Khan, S Kadry, S Rho Alexandria Engineering Journal 61 (8), 6001-6022 , 2022 2022 Citations: 159
A digital DNA sequencing engine for ransomware detection using machine learning F Khan, C Ncube, LK Ramasamy, S Kadry, Y Nam IEEE Access 8, 119710-119719 , 2020 2020 Citations: 158
Ensemble-based cryptography for soldiers’ health monitoring using mobile ad hoc networks BVV Siva Prasad, S Mandapati, L Kumar Ramasamy, R Boddu, P Reddy, ... Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 111
BSF-EHR: Blockchain Security Framework for Electronic Health Records of Patients I Abunadi, RL Kumar Sensors 8 (21), 2865 , 2021 2021 Citations: 106
Blockchain-based wireless sensor networks for malicious node detection: A survey LK Ramasamy, FK KP, AL Imoize, JO Ogbebor, S Kadry, S Rho IEEE Access 9, 128765-128785 , 2021 2021 Citations: 95
Recurrent neural network and reinforcement learning model for COVID-19 prediction RL Kumar, F Khan, S Din, SS Band, A Mosavi, E Ibeke Frontiers in public health 9, 744100 , 2021 2021 Citations: 94
Hybrid method for mining rules based on Enhanced Apriori Algorithm with Sequential Minimal Optimization in Healthcare industry SK Lakshmana Kumar Ramasamy, Ching-Hsien Hsu Neural Computing and Applications , 2020 2020 Citations: 86
Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier RD Lakshmana Kumar Ramasamy, Shynu Gopalan Padinjappurathu, Seifedine Kadry PeerJ Computer Science , 2021 2021 Citations: 84
IoT-based humanoid software for identification and diagnosis of COVID-19 suspects S Karmore, R Bodhe, F Al-Turjman, RL Kumar, SK Pillai IEEE sensors journal 22 (18), 17490-17496 , 2020 2020 Citations: 80
Performance analysis of sentiments in Twitter dataset using SVM models LK Ramasamy, S Kadry, Y Nam, MN Meqdad International Journal of Electrical and Computer Engineering (IJECE) 11 (3 … , 2021 2021 Citations: 73
Detecting malicious URLs using binary classification through ada boost algorithm. F Khan, J Ahamed, S Kadry, LK Ramasamy International Journal of Electrical & Computer Engineering (2088-8708) 10 (1) , 2020 2020 Citations: 71
An efficient apriori algorithm for frequent pattern mining using mapreduce in healthcare data M Sornalakshmi, S Balamurali, M Venkatesulu, MN Krishnan, ... Bulletin of Electrical Engineering and Informatics 10 (1), 390-403 , 2021 2021 Citations: 65
Diagnosis of diabetic retinopathy using multi level set segmentation algorithm with feature extraction using svm with selective features JP Kandhasamy, S Balamurali, S Kadry, LK Ramasamy Multimedia Tools and Applications 79 (15), 10581-10596 , 2020 2020 Citations: 61
Autonomous vehicles: A study of implementation and security. F Khan, RL Kumar, S Kadry, MN Meqdad International Journal of Electrical & Computer Engineering (2088-8708) 11 (4 … , 2021 2021 Citations: 59
Cyber physical systems: A smart city perspective F Khan, RL Kumar, S Kadry, Y Nam, MN Meqdad International Journal of Electrical and Computer Engineering 11 (4), 3609 , 2021 2021 Citations: 52
An efficient and privacy-preserving scheme for disease prediction in modern healthcare systems S Padinjappurathu Gopalan, CL Chowdhary, C Iwendi, MA Farid, ... Sensors 22 (15), 5574 , 2022 2022 Citations: 51