Michaelraj Kingston Roberts
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Michaelraj Kingston Roberts has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Fadl Dahan
Department of Management Information Systems, College of Business Administration - Hawtat Bani Tamim, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia
4 shared publications - Ramesh Jayabalan
PSG College of Technology
3 shared publications - Jaime Lloret
Instituto de Investigacion para la Gestion Integrada de Zonas Costeras Universitat Politècnica de València Valencia Spain
2 shared publications Jayapratha Thangavel
Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India
2 shared publications- Kuttaiyur Sridhar
Karpagam Academy of Higher Education
2 shared publications Poonkodi Ramasamy
Department of Electronics and Communication Engineering, Sri Eshwar College of Engineering, Coimbatore, India
2 shared publications
Latest Publications
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 28081-28084
Spectral-Bounded Consistency Certification for Heterogeneous Wireless Sensor Networks
Correlated faults in heterogeneous wireless sensor networks (WSNs) are troublesome because they can preserve local agreement while still corrupting the underlying field estimate. As a result, many consensus-style tests and simple outlier screens may treat coordinated drift as a legitimate environmental variation. This letter introduces spectral-bounded consistency certification (SBCC) to separate these two effects. The network is modeled as a constraint graph in which each edge compares neighboring measurements after mapping them, via fixed linear projections, into a common compatibility space. Aggregating the edge residuals yields a global inconsistency energy, and we show that the distance to the physically consistent subspace is upper-bounded by this energy scaled by the inverse spectral gap of the resulting projection-induced constraint Laplacian. The certificate can be computed in a distributed manner and supports fault localization with per-node complexity $\mathcal {O}\!\left ({{\sum _{j \in \mathcal {N}_{i}} q_{ij} d_{i}}}\right)$ . Simulations with correlated drift demonstrate a true positive rate (TPR) of 96.2% for SBCC versus 88.7% for Bayesian fusion, with performance remaining stable as the network size increases to 500 nodes.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 28081-28084
Spectral-Bounded Consistency Certification for Heterogeneous Wireless Sensor Networks
Correlated faults in heterogeneous wireless sensor networks (WSNs) are troublesome because they can preserve local agreement while still corrupting the underlying field estimate. As a result, many consensus-style tests and simple outlier screens may treat coordinated drift as a legitimate environmental variation. This letter introduces spectral-bounded consistency certification (SBCC) to separate these two effects. The network is modeled as a constraint graph in which each edge compares neighboring measurements after mapping them, via fixed linear projections, into a common compatibility space. Aggregating the edge residuals yields a global inconsistency energy, and we show that the distance to the physically consistent subspace is upper-bounded by this energy scaled by the inverse spectral gap of the resulting projection-induced constraint Laplacian. The certificate can be computed in a distributed manner and supports fault localization with per-node complexity $\mathcal {O}\!\left ({{\sum _{j \in \mathcal {N}_{i}} q_{ij} d_{i}}}\right)$ . Simulations with correlated drift demonstrate a true positive rate (TPR) of 96.2% for SBCC versus 88.7% for Bayesian fusion, with performance remaining stable as the network size increases to 500 nodes.
- Open Access
- 2 April 2026
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 77
Risk-aware resilient cloud orchestration under correlated faults using adaptive dual-regime search with self-healing control
- 2 April 2026
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 77
Open AccessRisk-aware resilient cloud orchestration under correlated faults using adaptive dual-regime search with self-healing control
- Open Access
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1)
A Depth‐Ordered Forwarding Game With Niche‐Confined Evolutionary Recovery for Energy‐Efficient Underwater Wireless Sensor Networks
Underwater wireless sensor networks operate under scarce acoustic bandwidth, long propagation delay, depth‐dependent attenuation, and a fixed energy budget that is rarely replenished. We propose the Hawk–Dove Game Optimization Algorithm with Elite Niche Clone Evolutionary Computing (HDGOA‐ENCEC), a routing protocol that couples a depth‐ordered forwarding game, inspired by Hawk–Dove interactions, with an elite niche‐confined cloning mechanism for localized recovery. A single behavioral index compresses residual energy, data priority, and congestion into one adaptive scalar; an event‐driven rule updates a node only when its standardized payoff deviates from the neighborhood mean; and recovery is restricted to depth niches, so a failed region is repaired locally rather than through network‐wide re‐optimization. We formulate the forwarding‐game payoff matrix, derive the condition under which cooperation becomes the strict best response, and obtain a Lyapunov‐drift bound for regional queue stability while the energy state remains bounded by the battery and its reserve threshold. Across NS‐3.35 simulations using the AquaSim‐NG channel and Bellhop‐derived transmission loss, under varied loads, densities, mobilities, and three failure models, the lifetime energy per delivered bit remains near 13–18 mJ/bit, which is 8%–12% lower than the strongest baseline and 22%–28% lower than RCRP in deep layers. Under depth‐correlated failure, packet delivery remains 10–16 percentage points above nonrecovery baselines. The results show that the main advantage of HDGOA‐ENCEC lies in resilience and energy‐normalized delivery rather than raw throughput.
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1)
Open AccessA Depth‐Ordered Forwarding Game With Niche‐Confined Evolutionary Recovery for Energy‐Efficient Underwater Wireless Sensor Networks
Underwater wireless sensor networks operate under scarce acoustic bandwidth, long propagation delay, depth‐dependent attenuation, and a fixed energy budget that is rarely replenished. We propose the Hawk–Dove Game Optimization Algorithm with Elite Niche Clone Evolutionary Computing (HDGOA‐ENCEC), a routing protocol that couples a depth‐ordered forwarding game, inspired by Hawk–Dove interactions, with an elite niche‐confined cloning mechanism for localized recovery. A single behavioral index compresses residual energy, data priority, and congestion into one adaptive scalar; an event‐driven rule updates a node only when its standardized payoff deviates from the neighborhood mean; and recovery is restricted to depth niches, so a failed region is repaired locally rather than through network‐wide re‐optimization. We formulate the forwarding‐game payoff matrix, derive the condition under which cooperation becomes the strict best response, and obtain a Lyapunov‐drift bound for regional queue stability while the energy state remains bounded by the battery and its reserve threshold. Across NS‐3.35 simulations using the AquaSim‐NG channel and Bellhop‐derived transmission loss, under varied loads, densities, mobilities, and three failure models, the lifetime energy per delivered bit remains near 13–18 mJ/bit, which is 8%–12% lower than the strongest baseline and 22%–28% lower than RCRP in deep layers. Under depth‐correlated failure, packet delivery remains 10–16 percentage points above nonrecovery baselines. The results show that the main advantage of HDGOA‐ENCEC lies in resilience and energy‐normalized delivery rather than raw throughput.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 19 (1)
Mobility‐Aware Lévy‐Enhanced Adaptive Squirrel Optimisation Framework With Improved Double Q‐Learning for Energy‐Efficient Dynamic Wireless Sensor Networks
Wireless sensor networks (WSNs) operating in challenging, resource‐constrained dynamic environments often struggle to address the persistent issues related to energy efficiency, node mobility, network coverage and performance. To overcome these research challenges, an innovative hybrid optimisation framework is proposed. This proposed framework effectively integrates squirrel search optimisation (SSO) with adaptive Lévy flights for enhancing the balance between the exploration‐exploitation process, and enhanced double Q‐learning for adaptive energy‐aware routing. In addition, a long short‐term memory (LSTM)‐based mobility‐aware node prediction model enables proactive cluster adaptation and a residual energy‐based cluster head (CH) selection process to improve reliability, convergence speed and energy usage. To ensure a uniform workload among sensor nodes, the proposed algorithm incorporates adaptive data aggregation and task‐aware load distribution, which minimises the possibility of redundant transmissions and enhances the operational lifespan of nodes under varying node densities. Simulation results across diverse scenarios confirm the effectiveness of our hybrid scheme in terms of performance improvements achieved across various performance evaluation metrics, including a 14.4% improvement in residual energy, a 11.7% improvement in coverage retention, a 18.71% improvement in cluster stability, a 13.42% enhancement in load balancing efficiency, a 4.5% improvement in scalability, a 11.51% enhancement in QoS reliability and a 61% reduction in complexity overhead across various node counts. Additionally, the proposed framework maintains superior network stability and outstanding packet delivery reliability under varying node densities when validated with state‐of‐the‐art algorithms. These capabilities make our hybrid framework a reliable solution for diverse WSN applications where adaptability and resource efficiency are critical priorities.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 19 (1)
Open AccessMobility‐Aware Lévy‐Enhanced Adaptive Squirrel Optimisation Framework With Improved Double Q‐Learning for Energy‐Efficient Dynamic Wireless Sensor Networks
Wireless sensor networks (WSNs) operating in challenging, resource‐constrained dynamic environments often struggle to address the persistent issues related to energy efficiency, node mobility, network coverage and performance. To overcome these research challenges, an innovative hybrid optimisation framework is proposed. This proposed framework effectively integrates squirrel search optimisation (SSO) with adaptive Lévy flights for enhancing the balance between the exploration‐exploitation process, and enhanced double Q‐learning for adaptive energy‐aware routing. In addition, a long short‐term memory (LSTM)‐based mobility‐aware node prediction model enables proactive cluster adaptation and a residual energy‐based cluster head (CH) selection process to improve reliability, convergence speed and energy usage. To ensure a uniform workload among sensor nodes, the proposed algorithm incorporates adaptive data aggregation and task‐aware load distribution, which minimises the possibility of redundant transmissions and enhances the operational lifespan of nodes under varying node densities. Simulation results across diverse scenarios confirm the effectiveness of our hybrid scheme in terms of performance improvements achieved across various performance evaluation metrics, including a 14.4% improvement in residual energy, a 11.7% improvement in coverage retention, a 18.71% improvement in cluster stability, a 13.42% enhancement in load balancing efficiency, a 4.5% improvement in scalability, a 11.51% enhancement in QoS reliability and a 61% reduction in complexity overhead across various node counts. Additionally, the proposed framework maintains superior network stability and outstanding packet delivery reliability under varying node densities when validated with state‐of‐the‐art algorithms. These capabilities make our hybrid framework a reliable solution for diverse WSN applications where adaptability and resource efficiency are critical priorities.
- Open Access
- 20 March 2024
- Published by Elsevier in Results in Engineering
- Vol. 22
An inspired chaos-based estimation-theory optimization for low-density parity-check (LDPC) code decoding
- 20 March 2024
- Published by Elsevier in Results in Engineering
- Vol. 22
Open AccessAn inspired chaos-based estimation-theory optimization for low-density parity-check (LDPC) code decoding
- 28 January 2024
- Published by Springer Nature
- p. 93-102
Reinforcement Learning Method for Identifying Health Issues for People with Chronic Diseases
- 28 January 2024
- Published by Springer Nature
- p. 93-102
Reinforcement Learning Method for Identifying Health Issues for People with Chronic Diseases