Machine learning-enhanced embedded systems for autonomous IoT devices in industrial applications
Year: 2025
Type: article
Abstract: The review explores the integration of machine learning (ML) with embedded systems in the context of autonomous IoT devices for industrial applications. It provides a comprehensive overview of the current state, challenges, and opportunities within this domain. Key methodologies, successful case studies from various industries, and a novel adaptive resource-aware ML framework (ARM-ML) are discussed. The review highlights the significance of ML in enhancing operational efficiency, predictive maintenance, and real-time decision-making in industrial settings. Future research directions are outlined, focusing on enhancing on-device learning, reducing power consumption, improving security, and integrating new computing paradigms like quantum computing. The article concludes by emphasizing the transformative potential of ML in shaping the future of industrial IoT.
Author: Tharan, Nikin
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7078719188
FWCI:
Cites:
Cited by:
Related to: