article · IEEE Internet of Things Journal
Combining Tiny Machine Learning with human behaviour analysis allows resource-constrained devices to process behavioural data locally, efficiently, and in real time while preserving user privacy. A systematic review establishes a taxonomy of current implementations, categorising existing methods and use cases across the field. Alongside highlighting core advantages, the analysis identifies key obstacles to wider deployment, including hardware constraints, issues with data quality, and ethical considerations. It also highlights emerging trends and open issues to help steer ongoing investigation. By mapping the state of the art, this synthesis provides a structured foundation for developing and refining low-power, edge-based behavioural monitoring technologies.
Running artificial intelligence directly on small, low-power devices avoids sending sensitive personal data to the cloud. Understanding how to deploy human behaviour analysis on resource-constrained hardware helps developers create responsive, privacy-preserving tools for everyday monitoring, while also tackling the technical limitations and ethical issues associated with continuous behavioural observation.
This work informs developers and system designers seeking to build real-time, privacy-preserving behavioural monitoring into low-power devices. Because the source text is a comprehensive survey and taxonomy rather than a product validation, it represents early-stage conceptual synthesis. It enables industry teams to assess existing methodologies, identify technical constraints, and plan practical development pathways, though immediate commercial deployment is not reported.
AI-generated from the published abstract. Always read the original work before citing.
The integration of Tiny Machine Learning (TinyML) with Human Behavior Analysis (HBA) represents a significant advancement in the field of Artificial Intelligence (AI), enabling real-time, efficient, and privacy-preserving analysis on resource-constrained devices. This paper provides the first comprehensive survey exploring this integration, presenting a detailed overview of TinyML, including its definitions, key concepts and advantages. The survey proposes a systematic taxonomy of TinyML applications in HBA, categorizing state-of-the-art implementations based on their use cases and specific methodologies. Furthermore, the challenges and limitations of integrating TinyML in HBA are thoroughly discussed, including technical constraints, data quality issues, and ethical considerations. Finally, future research directions and open issues are outlined, emphasizing the potential advancements and emerging trends in this field. This survey serves as a foundational resource, guiding researchers and practitioners in harnessing the capabilities of TinyML to advance HBA.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/jiot.2025.3565688
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
