MVRODC: Multi-Variate Regression based Outlier Detection and Classification on IoT Sensor Data — A Temporal Node Level Approach Veera Brahmam M., Gopikrishnan S. Journal of Trends in Computer Science and Smart Technology, 2026 The reliability and correctness of data detected by sensors are essential for the efficient use of Internet of Things (IoT) and Wireless Sensor Network (WSN) technologies. However, sensor readings are often affected by errors due to hardware failure or actual environmental events. This causes outliers that can affect decision-making and system efficiency. To address these problems, the present study proposes a novel outlier detection and classification technique called Multivariate Regression-based Outlier Detection and Classification (MVRODC). MVRODC uses similarity measures derived from Multiple Linear Regression (MLR) along with an adaptive buffer to model temporal relationships. This ensures that outliers are detected and classified into two different categories in real-time into two categories: errors and actual events. Inter-sensor feature correlations across multiple sensor streams (temperature, humidity, air quality, and light) are exploited along with temporal prediction consistency to enable robust real-time outlier detection and classification. The MVRODC technique ensures that relevant outliers caused by actual events are retained, allowing for the detection of environmental changes while ignoring erroneous data. This filtering technique saves energy because sending erroneous data consumes as much energy as sending legitimate data. Experimentally, MVRODC performs better than existing outlier detection techniques, achieving superior results in terms of detection rate, false alarm rate, accuracy, error detection rate, and event detection rate.
The Convergence of Deep Learning and the Metaverse: A Multidisciplinary Survey of Current Research and Future Directions Jothi Prakash Venugopal, Arul Antran Vijay Subramanian, Gopikrishnan Sundaram, Mahendhiran Ponnambalam Devadoss Computer Animation and Virtual Worlds, 2025 The convergence of deep learning and the Metaverse represents a pivotal frontier in the evolution of intelligent digital ecosystems. This paper presents a comprehensive survey of how deep learning techniques spanning convolutional, generative, transformer‐based, and reinforcement architectures collectively enable perception, creation, cognition, and governance within immersive virtual worlds. Building upon this synthesis, we propose the Deep Learning‐Empowered Metaverse Intelligence (DL‐MI) framework, which unifies sensory intelligence, generative world‐building, adaptive reasoning, and ethical‐social governance into a cohesive architecture. The study illustrates how deep learning facilitates realistic avatar synthesis, dynamic environmental rendering, emotion‐aware interaction, and predictive personalization, thereby transforming the Metaverse from reactive systems to anticipatory, self‐evolving spaces. Key challenges such as data privacy, algorithmic bias, and computational sustainability are critically examined alongside emerging paradigms, including quantum‐augmented AI and federated collaboration. By integrating technical, ethical, and societal dimensions, this survey provides a structured foundation for developing scalable, transparent, and human‐centered Metaverse intelligence.
DCAT: A Novel Transformer-Based Approach for Dynamic Context-Aware Image Captioning in the Tamil Language Jothi Prakash Venugopal, Arul Antran Vijay Subramanian, Manikandan Murugan, Gopikrishnan Sundaram, Marco Rivera, et al. Applied Sciences Switzerland, 2025 The task of image captioning in low-resource languages like Tamil is fraught with challenges due to limited linguistic resources and complex semantic structures. This paper addresses the problem of generating contextually and linguistically coherent captions in Tamil. We introduce the Dynamic Context-Aware Transformer (DCAT), a novel approach that synergizes the Vision Transformer (ViT) with the Generative Pre-trained Transformer (GPT-3), reinforced by a unique Context Embedding Layer. The DCAT model, tailored for Tamil, innovatively employs dynamic attention mechanisms during its Initialization, Training, and Inference phases to focus on pertinent visual and textual elements. Our method distinctively leverages the nuances of Tamil syntax and semantics, a novelty in the realm of low-resource language image captioning. Comparative evaluations against established models on datasets like Flickr8k, Flickr30k, and MSCOCO reveal DCAT’s superiority, with a notable 12% increase in BLEU score (0.7425) and a 15% enhancement in METEOR score (0.4391) over leading models. Despite its computational demands, DCAT sets a new benchmark for image captioning in Tamil, demonstrating potential applicability to other similar languages.
Reinforcement Q-Learning-Based Adaptive Encryption Model for Cyberthreat Mitigation in Wireless Sensor Networks Sreeja Balachandran Nair Premakumari, Gopikrishnan Sundaram, Marco Rivera, Patrick Wheeler, Ricardo E. Pérez Guzmán Sensors, 2025 The increasing prevalence of cyber threats in wireless sensor networks (WSNs) necessitates adaptive and efficient security mechanisms to ensure robust data transmission while addressing resource constraints. This paper proposes a reinforcement learning-based adaptive encryption framework that dynamically scales encryption levels based on real-time network conditions and threat classification. The proposed model leverages a deep learning-based anomaly detection system to classify network states into low, moderate, or high threat levels, which guides encryption policy selection. The framework integrates dynamic Q-learning for optimizing energy efficiency in low-threat conditions and double Q-learning for robust security adaptation in high-threat environments. A Hybrid Policy Derivation Algorithm is introduced to balance encryption complexity and computational overhead by dynamically switching between these learning models. The proposed system is formulated as a Markov Decision Process (MDP), where encryption level selection is driven by a reward function that optimizes the trade-off between energy efficiency and security robustness. The adaptive learning strategy employs an ϵ-greedy exploration-exploitation mechanism with an exponential decay rate to enhance convergence in dynamic WSN environments. The model also incorporates a dynamic hyperparameter tuning mechanism that optimally adjusts learning rates and exploration parameters based on real-time network feedback. Experimental evaluations conducted in a simulated WSN environment demonstrate the effectiveness of the proposed framework, achieving a 30.5% reduction in energy consumption, a 92.5% packet delivery ratio (PDR), and a 94% mitigation efficiency against multiple cyberattack scenarios, including DDoS, black-hole, and data injection attacks. Additionally, the framework reduces latency by 37% compared to conventional encryption techniques, ensuring minimal communication delays. These results highlight the scalability and adaptability of reinforcement learning-driven adaptive encryption in resource-constrained networks, paving the way for real-world deployment in next-generation IoT and WSN applications.
Secure and Efficient Authentication Architecture for IoT Devices in Resource-Limited Networks A Khurana, S Gopikrishnan, SR Konda, M Kokila ICCK Transactions on Information Security and Cryptography 2 (1), 16-28 , 2026 2026
RETRACTED: UIFSS: An aid for univariate data with large missing gap in IoT applications G Venkata Vidyalakshmi, S Gopikrishnan Journal of Intelligent & Fuzzy Systems 49 (1_suppl), 59-77 , 2025 2025
EFS-IDS: An enhanced feature-selective intrusion detection system for imbalanced IoT traffic data S Gopikrishnan, P Jonnalagadda, M Driss, W Boulila IEEE Open Journal of the Communications Society 6, 9673-9695 , 2025 2025 Citations: 3
Digital twins and cyber-physical systems: A new frontier in computer modeling G Vidyalakshmi, S Gopikrishnan, W Boulila, A Koubaa, G Srivastava Computer Modeling in Engineering & Sciences 143 (1), 51 , 2025 2025 Citations: 31
Enhancing IoT Security: A Review of Multi-factor Authentication Protocols and Their Effectiveness K Alluri, S Gopikrishnan International Conference on Smart Cyber Physical Systems, 619-630 , 2024 2024 Citations: 1
A Hybrid Secure Signcryption Algorithm for data security in an internet of medical things environment K Ashok, S Gopikrishnan Journal of Information Security and Applications 85, 103836 , 2024 2024 Citations: 13
Predictive health behavior modeling using multimodal feature correlations via Medical Internet-of-Things devices MD Sirapangi, S Gopikrishnan Heliyon 10 (15) , 2024 2024 Citations: 7
Energy Harvesting Integrated Sensor S Gopikrishnan, M Kokila, M Rivera, P Wheeler Advances in Distributed Computing and Machine Learning: Proceedings of … , 2024 2024
IMD-MP: Imputation of Missing Data in IoT Based on Matrix Profile and Spatio-temporal Correlations. GV Lakshmi, S Gopikrishnan Journal of Universal Computer Science (JUCS) 30 (6) , 2024 2024 Citations: 3
MAIPFE: An Efficient Multimodal Approach Integrating Pre-Emptive Analysis, Personalized Feature Selection, and Explainable AI. MD Sirapangi, S Gopikrishnan Computers, Materials & Continua 79 (2), 2229 , 2024 2024 Citations: 10
Caddisfalcon optimization algorithm for on-demand energy transfer in wireless rechargeable sensors based IoT networks KRS Kumar, S Gopikrishnan Sustainable Energy Technologies and Assessments 64, 103732 , 2024 2024 Citations: 12
CyTFS: Cyber-twin fog system for delay-efficient task offloading in 6G mobile networks S Gopikrishnan, SC Sethuraman, G Srivastava, S Theerthagiri IEEE Internet of Things Journal 11 (14), 24698-24714 , 2024 2024 Citations: 12
NODSTAC: Novel outlier detection technique based on spatial, temporal and attribute correlations on IoT bigdata MV Brahmam, S Gopikrishnan The Computer Journal 67 (3), 947-960 , 2024 2024 Citations: 8
Smart City Survey on AIoT Using Machine Learning, Deep Learning, and Its Computing Tools P Priakanth, K Jothimani, S Gopikrishnan, C Linga Reddy International Conference on Advances in Distributed Computing and Machine … , 2024 2024
Energy Harvesting Integrated Sensor Node Architecture for Sustainable IoT Networks S Gopikrishnan, M Kokila, M Rivera, P Wheeler International Conference on Advances in Distributed Computing and Machine … , 2024 2024
Efficiency in cloud computing through serverless and green computing based on microarchitecture F Fahira, RM Awangga, S Gopikrishnan Jurnal Information Technology and Cyber Security 2 (1), 51-57 , 2024 2024 Citations: 1
Correlation Composition Awareness Model with Pair Collaborative Localization for IoT Authentication and Localization K Alluri, S Gopikrishnan Computers, Materials, & Continua 79 (1), 943 , 2024 2024
Improving security performance of healthcare data in the Internet of medical things using a hybrid metaheuristic model K Ashok, S Gopikrishnan International Journal of Applied Mathematics and Computer Science 33 (4 … , 2023 2023 Citations: 12
SCHEISB: Design of a high efficiency IoMT security model based on sharded chains using bio-inspired optimizations S Gopikrishnan, P Priakanth, G Srivastava, CV Joe Computers and Electrical Engineering 111, 108925 , 2023 2023 Citations: 7
A Framework Provides Authorized Personnel with Secure Access to Their Electronic Health Records K Ashok, S Gopikrishnan International Conference on Micro-Electronics and Telecommunication … , 2023 2023
MOST CITED SCHOLAR PUBLICATIONS
Statistical analysis of remote health monitoring based IoT security models & deployments from a pragmatic perspective K Ashok, S Gopikrishnan Ieee Access 11, 2621-2651 , 2023 2023 Citations: 67
Improving sugarcane production in saline soils with Machine Learning and the Internet of Things S Gopikrishnan, G Srivastava, P Priakanth Sustainable Computing: Informatics and Systems 35, 100743 , 2022 2022 Citations: 32
Digital twins and cyber-physical systems: A new frontier in computer modeling G Vidyalakshmi, S Gopikrishnan, W Boulila, A Koubaa, G Srivastava Computer Modeling in Engineering & Sciences 143 (1), 51 , 2025 2025 Citations: 31
Network based detection of IoT attack using AIS-IDS model R Sabitha, S Gopikrishnan, BJ Bejoy, V Anusuya, V Saravanan Wireless Personal Communications 128 (3), 1543-1566 , 2023 2023 Citations: 29
EWPS: Emergency data communication in the Internet of Medical Things S Gopikrishnan, P Priakanth, G Srivastava, G Fortino IEEE Internet of Things Journal 8 (14), 11345-11356 , 2021 2021 Citations: 29
(Download: https://rdcu.be/bnCDT) HSDA: hybrid communication for secure data aggregation in wireless sensor network S Gopikrishnan, P Priakanth Wireless Networks 22 (3), 1061-1078 , 2016 2016 Citations: 20
DEDC: Sustainable data communication for cognitive radio sensors in the Internet of Things S Gopikrishnan, P Priakanth, G Srivastava Sustainable Computing: Informatics and Systems 29, 100471 , 2021 2021 Citations: 14
A Hybrid Secure Signcryption Algorithm for data security in an internet of medical things environment K Ashok, S Gopikrishnan Journal of Information Security and Applications 85, 103836 , 2024 2024 Citations: 13
An enhanced and secure trust-aware improved GSO for encrypted data sharing in the Internet of Things P Selvaraj, VK Burugari, S Gopikrishnan, A Alourani, G Srivastava, ... Applied Sciences 13 (2), 831 , 2023 2023 Citations: 13
Caddisfalcon optimization algorithm for on-demand energy transfer in wireless rechargeable sensors based IoT networks KRS Kumar, S Gopikrishnan Sustainable Energy Technologies and Assessments 64, 103732 , 2024 2024 Citations: 12
CyTFS: Cyber-twin fog system for delay-efficient task offloading in 6G mobile networks S Gopikrishnan, SC Sethuraman, G Srivastava, S Theerthagiri IEEE Internet of Things Journal 11 (14), 24698-24714 , 2024 2024 Citations: 12
Improving security performance of healthcare data in the Internet of medical things using a hybrid metaheuristic model K Ashok, S Gopikrishnan International Journal of Applied Mathematics and Computer Science 33 (4 … , 2023 2023 Citations: 12
MAIPFE: An Efficient Multimodal Approach Integrating Pre-Emptive Analysis, Personalized Feature Selection, and Explainable AI. MD Sirapangi, S Gopikrishnan Computers, Materials & Continua 79 (2), 2229 , 2024 2024 Citations: 10
IEEHR: improved energy efficient honeycomb based routing in MANET for improving network performance and longevity A Baseera, HK Kondaveeti, S Gopikrishnan, BJ Bejoy, CG Ravichandran, ... Wireless Personal Communications 129 (3), 1753-1769 , 2023 2023 Citations: 10
(PDF: https://bit.ly/322koWd ) HSIR: hybrid architecture for sensor identification and registration for IoT applications S Gopikrishnan, P Priakanth, RM Awangga The Journal of Supercomputing, 1-19 , 2019 2019 Citations: 9
Hybrid tree construction for sustainable delay aware data aggregation in wireless sensor networks S Gopikrishnan, P Priakanth Wireless Personal Communications 90 (2), 923-945 , 2016 2016 Citations: 9
NODSTAC: Novel outlier detection technique based on spatial, temporal and attribute correlations on IoT bigdata MV Brahmam, S Gopikrishnan The Computer Journal 67 (3), 947-960 , 2024 2024 Citations: 8
Predictive health behavior modeling using multimodal feature correlations via Medical Internet-of-Things devices MD Sirapangi, S Gopikrishnan Heliyon 10 (15) , 2024 2024 Citations: 7
SCHEISB: Design of a high efficiency IoMT security model based on sharded chains using bio-inspired optimizations S Gopikrishnan, P Priakanth, G Srivastava, CV Joe Computers and Electrical Engineering 111, 108925 , 2023 2023 Citations: 7
Double helical ensemble multi-dimensional 4-D structured neural network to analyze the driving pattern, driver DNA and generate license score using smartphone sensor data S Karthikeyan, S Gopikrishnan, D Batta, T Banerjee Turk. J. Comput. Math. Educ.(TURCOMAT) 12 (13), 6447-6458 , 2021 2021 Citations: 7
