Table 1 Overview of existing models with its performance and disadvantages.
From: ESHA-256_GBGO: a high-performance and optimized security framework for internet of medical thing
Author name and reference | Method | Performance | Disadvantages |
|---|---|---|---|
Kanneboina et al.24 | Hybrid metaheuristic model | The network consistency was improved by 8.7% | Lack of adaptability to new threats |
Mani et al.25 | Hybrid GarraRufa Fish optimization and Nomadic People Optimizer | 29.8% reduction in delay | This approaches suffered from lower security and high resource utilization |
Veeramakali et al.26 | ODLSB | Attained sensitivity, specificity, and accuracy were 92.75%, 91.42%, and 93.68%, respectively | It could not handle centralized architectures and the lack of security issues |
Ramani et al.27 | ODMSM-FL | Performance metrics like transaction throughput of 102.75 Kbps, block processing time of 42.28 ms | It had overall limitations in performance and security regarding health systems in the IoMT framework |
Praveena Anjelin et al.28 | CNN | It achieved 17% improvement in accuracy and showed 35% less complexity | Produce the false alarms that lead to security attacks or cyber-attacks |
Ahmad et al.29 | TLADE | Latency: 0.838s | Limited adaptability to real-time encryption demands |
Alsaeed et al.30 | Group Authentication Framework for IoMT | Latency: 0.5s, Throughput: 400 TPS | High computational cost due to blockchain overhead |
Ramani et al.31 | ODMSM-FL | Transaction throughput: 102.75 Kbps, data retrieval delay: 64.02 ms, accuracy: 86.32% | Federated learning complexity may lead to higher energy consumption in IoMT devices |
