Jul 2026· International Conference on Ubiquitous and Future Networks· pp. 453-458· 0 citations· 21 references
Abstract
AI-driven Internet of Medical Things (IoMT) services increasingly rely on federated learning (FL) for privacy-preserving remote patient monitoring; however, existing frameworks often neglect the longitudinal battery sustainability required for persistent clinical care. This paper presents BattFL, an energy-sustainable federated AI framework that reframes distributed healthcare intelligence as a battery-budgeted service. By integrating explicit per-client battery evolution modeling with computation-communication-security energy decomposition, BattFL supports role-heterogeneous participation (attack-only, health-only, and hybrid) via masked multi-task learning. Furthermore, we incorporate risk-driven adaptive sensing to regulate workload intensity based on predicted clinical risk. Experimental results reveal a pronounced sustainability asymmetry: high-workload attack clients experience up to 41.2% battery depletion within five FL rounds, while health-only clients remain near initial capacity. Across extended horizons $(R=5-60)$, we identify diminishing energy-accuracy returns and participation decay, motivating the need for energy-aware stopping and orchestration mechanisms. By explicitly coupling battery dynamics, security overhead, and federated optimization, BattFL provides a systems-level foundation for secure, resilient, and long-lived AI-driven healthcare services in next-generation ubiquitous IoMT networks.
Results indicate that a federated TinyML architecture with lightweight patient-state tracking, validation-based ensemble filtering, differential privacy, and post-quantum-secure communication can support privacy-aware and attack-resilient ICU monitoring experiments in resource-constrained IoMT settings.
Umar Hayat Khan, Rahim Khan, Tahani Alsaedi et al.· Scientific Reports· 0 citations
Internet of Medical Things (IoMT) applications require collaborative learning across healthcare institutions while ensuring patient data privacy. Traditional centralized learning approaches require sharing sensitive medical records, increasing privacy and security risks. Federated Learning (FL) enables distributed model training by exchanging model parameters instead of raw data, but its performance is affected by client dropouts and communication failures. This paper proposes a Resilience-Enhanced Federated Learning Framework for IoMT applications that improves the reliability of collaborative learning under unstable network conditions. The framework incorporates Federated Averaging (FedAvg), resilient aggregation using historical model updates with staleness decay, and quantized model updates to reduce communication overhead. The proposed model was evaluated using a heart disease dataset distributed across multiple healthcare clients. Experimental results demonstrate that the framework achieves 95.72% accuracy while maintaining stable model convergence during client failures. The proposed approach provides a secure, privacypreserving, and fault-tolerant solution for distributed healthcare applications.
Potharam Shiva Kumar, O. Ramanaiah· International Journal of Inn...· 0 citations
Introduction The deployment of Federated Learning (FL) across the Internet of Medical Things (IoMT) is severely hindered by computational asymmetry and statistical heterogeneity. Traditional synchronous aggregation protocols suffer from severe straggler effects when deployed across devices with varying computational capacities, such as hospital servers vs. ambulatory wearables. Methods In this study, we propose the Asynchronous Proximal Federated Aggregation (APFA) framework to address these dual bottlenecks. APFA integrates a local proximal regularizer with a server-side staleness dampening penalty, permitting continuous, uncoordinated model updates from edge devices. Results Evaluated on highly skewed partitions of the CheXpert and MIMIC-IV datasets, APFA reached an 80% diagnostic viability threshold in just 4.1 simulated hours, representing a 71% reduction in total wait time compared to standard synchronous baselines like FedProx. Discussion Our mathematical integration effectively mitigates weight divergence, indicating the robustness of asynchronous machine learning for scalable, privacy-preserving clinical diagnostics.
M.H. Sreelakshmi, R. Delhibabu· Frontiers in Digital Health· 0 citations
The rapid evolution of the Internet of Things (IoT) technology makes smart healthcare monitoring systems, in which patient health data is constantly collected with the help of wearable sensors and medical equipment. Nevertheless, transmitting large volumes of high latency medical information directly to remote cloud-computers can often lead to energy usage and communication latency. These problems are addressed by fog computing through decreasing the network congestion, improving system performance, and moving the processing of the data near the IoT devices. This paper presents an AI-based adaptive offloading of tasks infrastructure with a reinforcementbased scheduling system in the healthcare monitoring field. The proposed approach involves a Q-learning algorithm to dynamically decide whether cloud servers or fog nodes should process healthcare tasks. The decision-making is made considering realtime system components such as network latency, node energy availability, CPU requirements, and job deadlines. Experimental testing based on a healthcare IoMT dataset containing 1000 task instances reveals better performance with approximately $\mathbf{1 5}-\mathbf{2 0}$ percent lower latency and 10-15 percent energy consumption.
Priyanshu Sekhar Bhuyan, Rishav Kumar Shrivastava, Vridhi Patnala et al.· International Conference on...· 0 citations
Federated learning (FL) reduces raw-data sharing in Internet of Things (IoT) intrusion detection systems (IDSs), but standard FL can still overuse battery-powered clients by assigning local training without considering device health. This paper presents ResFed-IDS, a resource-aware FL framework that combines server-side healthy-client selection with client-side self-preservation. Clients are eligible only when battery is at least 30% and central processing unit (CPU) load is at most 0.85; the server then selects up to ⌈0.6K⌉ healthy clients per round and aggregates successful updates through sample-weighted federated averaging (FedAvg). On a balanced CICIoT2023 subset, ResFed-IDS reached 82.11% best accuracy in a 15-round, 5-client simulation with zero device depletion, whereas standard FedAvg reached 81.56% and produced 27 client-unavailability events with four ultimately depleted clients. The same policy transferred to CICIIoT2025 and CIC-ToN-IoT, yielding 78.87% and 69.35% best accuracy while preserving all devices. Relative to the centralized SimpleMLP baseline, the remaining gap is only 0.73 percentage points, indicating that most loss is architectural rather than caused by the resource-aware FL procedure.
Seidy Kante, Kerem Küçük, S. A. Khan· 2026 6th International Confe...· 0 citations
This paper explains the integration of advanced AI-driven techniques within the smart healthcare monitoring systems to significantly enhance the patient care for early diagnosis and real-time health management. In Existing methodologies, we propose a comprehensive AI-based framework that synergizes IoT sensor data analytics, machine learning models, and cloud-edge hybrid computing to enable continuous, personalized, and efficient health monitoring. Our approach explains the critical challenges such as data heterogeneity, latency, privacy, and interoperability by as a part of dynamic task allocation and secure data transmission protocols. The experimental results demonstrate the superior accuracy, responsiveness, and resource optimization which compared to conventional cloud-only or edge-only systems. This paper improves a scalable, secure, and patient-centric solution, for future clinical adoption and integration with electronic health records and federated learning models.
Ramakant Katiyar, N. Thirugnanasambandan, Frenisha Digaswala et al.· 2026 6th International Confe...· 0 citations