Seizure detection using dynamic memristor-based reservoir computing and leaky integrate-and-fire neuron for post-processing

被引：3

作者：

Yang, Zhiyu ^{[1
]}

Liu, Keqin ^{[2
]}

Yuan, Rui ^{[2
]}

Wu, Xulei ^{[2
]}

Cai, Lei ^{[2
]}

Zhang, Teng ^{[2
]}

Tao, Yaoyu ^{[2
]}

Jin, Yufeng ^{[1
]}

Yang, Yuchao ^{[1
,2
,3
,4
]}

机构：

[1] Peking Univ, Sch Elect & Comp Engn, Shenzhen 518055, Peoples R China

[2] Peking Univ, Beijing Adv Innovat Ctr Integrated Circuit, Sch Integrated Circuits, Beijing 100871, Peoples R China

[3] Peking Univ, Inst Artificial Intelligence, Ctr Brain Inspired Chips, Frontiers Sci Ctr Nanooptoelectron, Beijing 100871, Peoples R China

[4] Chinese Inst Brain Res CIBR, Ctr Brain Inspired Intelligence, Beijing 102206, Peoples R China

来源：

APL MACHINE LEARNING | 2023年 / 1卷 / 04期

基金：

中国博士后科学基金; 中国国家自然科学基金; 国家重点研发计划;

关键词：

CLASSIFICATION;

D O I：

10.1063/5.0171274

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Epilepsy is a prevalent neurological disorder, rendering the development of automated seizure detection systems imperative. While complex machine learning models are powerful, their training and hardware deployment remain challenging. The reservoir computing system offers a low-cost solution in terms of both hardware requirements and training. In this paper, we introduce a compact reservoir computing system for seizure detection, based on the alpha-In2Se3 dynamic memristors. Leaky integrate-and-fire neurons are used for post-processing the output of the system, and experimental results indicate their effectiveness in suppressing erroneous outputs, where both accuracy and specificity are enhanced by over 2.5%. The optimized compact reservoir system achieves 96.40% accuracy, 86.34% sensitivity, and 96.56% specificity in seizure detection tasks. This work demonstrates the feasibility of using reservoir computing for seizure detection and shows its potential for future application in extreme edge devices. (c) 2023 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license(http://creativecommons.org/licenses/by/4.0/).

引用

页数：9