An Ultra-Low Energy Human Activity Recognition Accelerator for Wearable Health Applications

Abstract

Human activity recognition (HAR) has recently received significant attention due to its wide range of applications in health and activity monitoring. The nature of these applications requires mobile or wearable devices with limited battery capacity. User surveys show that charging requirement is one of the leading reasons for abandoning these devices. Hence, practical solutions must offer ultra-low power capabilities that enable operation on harvested energy. To address this need, we present the first fully integrated custom hardware accelerator (HAR engine) that consumes 22.4 μJ per operation using a commercial 65 nm technology. We present a complete solution that integrates all steps of HAR , i.e., reading the raw sensor data, generating features, and activity classification using a deep neural network (DNN). It achieves 95% accuracy in recognizing 8 common human activities while providing three orders of magnitude higher energy efficiency compared to existing solutions.

Document Details

Document Type
Pub Defense Publication
Publication Date
Oct 07, 2019
Source ID
10.1145/3358175

Entities

People

  • Ganapati Bhat
  • Hyung Gyu Lee
  • Sizhe An
  • Umit Y. Ogras
  • Yiğit Tuncel

Organizations

  • Arizona State University
  • Daegu University
  • Defense Advanced Research Projects Agency
  • National Research Foundation of Korea
  • National Science Foundation

Tags

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Energy Conservation and Renewable Energy Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks