Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

UR2M: Uncertainty and resource-aware event detection on microcontrollers

Jia, Hong, Kwon, Young D., Mat, Dong, Pham, Nhat, Qendro, Lorena, Vu, Tam and Mascolo, Cecilia 2024. UR2M: Uncertainty and resource-aware event detection on microcontrollers. Presented at: International Conference on Pervasive Computing and Communications, Biarritz, France, 11-15 March 2024. 2024 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 10.1109/PerCom59722.2024.10494467

[thumbnail of percom24.pdf]
Preview
PDF - Accepted Post-Print Version
Download (1MB) | Preview

Abstract

Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phases. This vulnerability can lead to severe consequences, especially in applications such as mobile healthcare. Uncertainty estimation has the potential to mitigate this issue by assessing the reliability of a model's output. However, existing uncertainty estimation techniques often require substantial computational resources and memory, making them impractical for implementation on microcontrollers (MCUs). This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection. In this paper, we present UR2M, a novel Uncertainty and Resource-aware event detection framework for MCUs. Specifically, we (i) develop an uncertainty-aware WED based on evidential theory for accurate event detection and reliable uncertainty estimation; (ii) introduce a cascade ML framework to achieve efficient model inference via early exits, by sharing shallower model layers among different event models; (iii) optimize the deployment of the model and MCU library for system efficiency. We conducted extensive experiments and compared UR2M to traditional uncertainty baselines using three wearable datasets. Our results demonstrate that UR2M achieves up to 864% faster inference speed, 857% energy-saving for uncertainty estimation, 55% memory saving on two popular MCUs, and a 22% improvement in uncertainty quantification performance. UR2M can be deployed on a wide range of MCUs, significantly expanding real-time and reliable WED applications.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: IEEE
ISBN: 979-8-3503-2603-1
Date of First Compliant Deposit: 14 June 2024
Date of Acceptance: 22 December 2023
Last Modified: 14 Jun 2024 14:45
URI: https://orca.cardiff.ac.uk/id/eprint/169181

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics