An Energy-efficient and Programmable RISC-V CNN Coprocessor for Real-time Epilepsy Detection and Identification on Wearable Devices

Yi Wen Hung, Yao Tse Chang, Shuenn Yuh Lee, Chou Ching Lin, Gia Shing Shieh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper has proposed an energy-efficient epilepsy detection framework for embedded systems. The epilepsy detection framework is implemented in 11 layers Convolution Neural Network (CNN) with a 2-stage RISC-V core and a coprocessor to accelerate CNN inferences. The CNN algorithm provides 97.8% and 93.5% accuracy on floating-point and fixedpoint operations respectively. The proposed CNN coprocessor is designed to offload CNN inference from RISC-V core to hardware with 51 nJ data transfer energy and 0.9 μJ inference energy for each 500 points input data frame. The coprocessor reduces the runtime of CNN inferences over 106x to perform only 0.012 s latency for each classification. According to the energy-efficient coprocessor, an AI-based solution is practical for real-time epilepsy detection on wearable devices for consumer electronics.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665433280
DOIs
Publication statusPublished - 2021
Event8th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021 - Penghu, Taiwan
Duration: 2021 Sep 152021 Sep 17

Publication series

Name2021 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021

Conference

Conference8th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2021
Country/TerritoryTaiwan
CityPenghu
Period21-09-1521-09-17

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Instrumentation

Fingerprint

Dive into the research topics of 'An Energy-efficient and Programmable RISC-V CNN Coprocessor for Real-time Epilepsy Detection and Identification on Wearable Devices'. Together they form a unique fingerprint.

Cite this