Year: 2025
Type: article
Abstract: Resource-constrained devices, including low-power Internet of Things (IoT) nodes, microcontrollers, and edge computing platforms, have increasingly become the focal point for deploying on-device intelligence. By integrating artificial intelligence (AI) closer to data sources, these systems aim to achieve faster responses, reduce bandwidth usage, and preserve privacy. Nevertheless, implementing AI in limited hardware environments poses substantial challenges in terms of computation, energy efficiency, model complexity, and reliability. This paper provides a comprehensive review of state-of-the-art methodologies, examining how recent advances in model compression, TinyML frameworks, and federated learning paradigms are enabling AI in tightly constrained devices. We highlight both established and emergent techniques for optimizing resource usage while addressing security, privacy, and ethical concerns. We then illustrate opportunities in key application domains—such as healthcare, smart cities, agriculture, and environmental monitoring—where localized intelligence on resource-limited devices can have broad societal impact. By exploring architectural co-design strategies, algorithmic innovations, and pressing research gaps, this paper offers a roadmap for future investigations and industrial applications of AI in resource-constrained devices.
Source: Future Internet
DOI: 10.3390/fi17060257
Institution: National Polytechnic School
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,930
Funder: Escuela Politécnica Nacional
OpenAlex ID: W4411249280