Optimising TinyML with quantization and distillation of transformer and mamba models for indoor localisation on edge devices
Top Cited Papers
Open Access
- 24 March 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Abstract
This paper proposes small and efficient machine learning models (TinyML) for resource-constrained edge devices, specifically for on-device indoor localisation. Typical approaches for indoor localisation rely on centralised remote processing of data transmitted from lower powered devices such as wearables. However, there are several benefits for moving this to the edge device itself, including increased battery life, enhanced privacy, reduced latency and lowered operational costs, all of which are key for common applications such as health monitoring. The work focuses on model compression techniques, including quantization and knowledge distillation, to significantly reduce the model size while maintaining high predictive performance. We base our work on a large state-of-the-art transformer-based model and seek to deploy it within low-power MCUs. We also propose a state-space-based architecture using Mamba as a more compact alternative to the transformer. Our results show that the quantized transformer model performs well within a 64 KB RAM constraint, achieving an effective balance between model size and localisation precision. Additionally, the compact Mamba model has strong performance under even tighter constraints, such as a 32 KB of RAM, without the need for model compression, making it a viable option for more resource-limited environments. We demonstrate that, through our framework, it is feasible to deploy advanced indoor localisation models onto low-power MCUs with restricted memory limitations. The application of these TinyML models in healthcare has the potential to revolutionize patient monitoring by providing accurate, real-time location data while minimising power consumption, increasing data privacy, improving latency and reducing infrastructure costs.Keywords
All Related Versions
Funding Information
- Ministry of Higher Education, Science, Research and Innovation, Royal Government of Thailand.
This publication has 36 references indexed in Scilit:
- TimeMachine: A Time Series is Worth 4 Mambas for Long-Term Forecasting2024
- TinyML applications and use cases for healthcare2024
- TinyML using neural networks for resource-constrained devices2024
- Machine learning techniques for indoor localization on edge devices2024
- Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement LearningJACS Au, 2024
- Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation2023
- A TinyML Deep Learning Approach for Indoor Tracking of AssetsSensors, 2023
- Design Space Exploration of a Multi-Model AI-Based Indoor Localization SystemSensors, 2022
- A survey of transformersAI Open, 2022
- Residential wearable RSSI and accelerometer measurements with detailed location annotationsScientific Data, 2018