Federated Learning Framework for Self-Powered IoT Sensor Networks with Explainable AI: A Novel Approach for Sustainable and Privacy-Preserving Distributed Intelligence
Abstract
The proliferation of Internet of Things (IoT) devices has created new opportunities for distributed intelligence, yet traditional centralized machine learning approaches face significant challenges in terms of privacy preservation, energy efficiency, and scalability. This paper presents a novel federated learning framework specifically designed for self-powered IoT sensor networks that integrates triboelectric nanogenerator (TENG) technology with explainable artificial intelligence (XAI). Our approach addresses three critical challenges: sustainable power supply through TENG-based self-powered sensors, privacy-preserving distributed learning through federated learning, and decision transparency through explainable AI components. The proposed framework employs a hierarchical federated learning architecture with lightweight neural networks optimized for resource-constrained edge devices, multi-modal sensor fusion capabilities, and adaptive power management algorithms. Experimental results demonstrate significant improvements in energy efficiency (45% reduction in power consumption), privacy preservation (99.2% reduction in data exposure), and model interpretability (87% improvement in explanation consistency) compared to traditional centralized approaches. The framework achieves 92.3% classification accuracy while maintaining real-time performance with latency under 100ms. Our contributions include: (1) a novel integration of TENG sensors with federated learning, (2)…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.