Efficient Personalized Learning for Wearable Health Applications using HyperDimensional Computing

TL;DR

This paper introduces an efficient hyperdimensional computing approach for personalized health monitoring on wearable devices, significantly reducing energy consumption while maintaining accuracy, thus enabling privacy-preserving on-device learning.

Contribution

The paper presents a novel HDC-based method tailored for resource-constrained wearables, enhancing energy efficiency and privacy in personalized health monitoring.

Findings

Energy efficiency improved by up to 45.8 times compared to DNNs

Achieved comparable accuracy with significantly lower energy consumption

Validated effectiveness across three health monitoring case studies

Abstract

Health monitoring applications increasingly rely on machine learning techniques to learn end-user physiological and behavioral patterns in everyday settings. Considering the significant role of wearable devices in monitoring human body parameters, on-device learning can be utilized to build personalized models for behavioral and physiological patterns, and provide data privacy for users at the same time. However, resource constraints on most of these wearable devices prevent the ability to perform online learning on them. To address this issue, it is required to rethink the machine learning models from the algorithmic perspective to be suitable to run on wearable devices. Hyperdimensional computing (HDC) offers a well-suited on-device learning solution for resource-constrained devices and provides support for privacy-preserving personalization. Our HDC-based method offers flexibility, high efficiency, resilience, and performance while enabling on-device personalization and privacy protection. We evaluate the efficacy of our approach using three case studies and show that our system improves the energy efficiency of training by up to $45.8\times$ compared with the state-of-the-art Deep Neural Network (DNN) algorithms while offering a comparable accuracy.