MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection
In this work, a memristive spike-based computing in memory (CIM) system with adaptive neuron (MSPAN) is proposed to realize energy-efficient remote arrhythmia detection with high accuracy in edge devices by software and hardware co-design. A multi-layer deep integrative spiking neural network (DiSNN...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-12-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.761127/full |
| _version_ | 1819319266904637440 |
|---|---|
| author | Jingwen Jiang Fengshi Tian Jinhao Liang Ziyang Shen Yirui Liu Jiapei Zheng Hui Wu Zhiyuan Zhang Chaoming Fang Yifan Zhao Jiahe Shi Xiaoyong Xue Xiaoyang Zeng |
| author_facet | Jingwen Jiang Fengshi Tian Jinhao Liang Ziyang Shen Yirui Liu Jiapei Zheng Hui Wu Zhiyuan Zhang Chaoming Fang Yifan Zhao Jiahe Shi Xiaoyong Xue Xiaoyang Zeng |
| author_sort | Jingwen Jiang |
| collection | DOAJ |
| description | In this work, a memristive spike-based computing in memory (CIM) system with adaptive neuron (MSPAN) is proposed to realize energy-efficient remote arrhythmia detection with high accuracy in edge devices by software and hardware co-design. A multi-layer deep integrative spiking neural network (DiSNN) is first designed with an accuracy of 93.6% in 4-class ECG classification tasks. Then a memristor-based CIM architecture and the corresponding mapping method are proposed to deploy the DiSNN. By evaluation, the overall system achieves an accuracy of over 92.25% on the MIT-BIH dataset while the area is 3.438 mm2 and the power consumption is 0.178 μJ per heartbeat at a clock frequency of 500 MHz. These results reveal that the proposed MSPAN system is promising for arrhythmia detection in edge devices. |
| first_indexed | 2024-12-24T11:00:58Z |
| format | Article |
| id | doaj.art-560c72884a054c9f9262bd9ddafd312b |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-24T11:00:58Z |
| publishDate | 2021-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-560c72884a054c9f9262bd9ddafd312b2022-12-21T16:58:43ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-12-011510.3389/fnins.2021.761127761127MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia DetectionJingwen JiangFengshi TianJinhao LiangZiyang ShenYirui LiuJiapei ZhengHui WuZhiyuan ZhangChaoming FangYifan ZhaoJiahe ShiXiaoyong XueXiaoyang ZengIn this work, a memristive spike-based computing in memory (CIM) system with adaptive neuron (MSPAN) is proposed to realize energy-efficient remote arrhythmia detection with high accuracy in edge devices by software and hardware co-design. A multi-layer deep integrative spiking neural network (DiSNN) is first designed with an accuracy of 93.6% in 4-class ECG classification tasks. Then a memristor-based CIM architecture and the corresponding mapping method are proposed to deploy the DiSNN. By evaluation, the overall system achieves an accuracy of over 92.25% on the MIT-BIH dataset while the area is 3.438 mm2 and the power consumption is 0.178 μJ per heartbeat at a clock frequency of 500 MHz. These results reveal that the proposed MSPAN system is promising for arrhythmia detection in edge devices.https://www.frontiersin.org/articles/10.3389/fnins.2021.761127/fullspike-basedneuromorphic computingmemristivecomputation in memoryarrhythmia detection |
| spellingShingle | Jingwen Jiang Fengshi Tian Jinhao Liang Ziyang Shen Yirui Liu Jiapei Zheng Hui Wu Zhiyuan Zhang Chaoming Fang Yifan Zhao Jiahe Shi Xiaoyong Xue Xiaoyang Zeng MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection Frontiers in Neuroscience spike-based neuromorphic computing memristive computation in memory arrhythmia detection |
| title | MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection |
| title_full | MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection |
| title_fullStr | MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection |
| title_full_unstemmed | MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection |
| title_short | MSPAN: A Memristive Spike-Based Computing Engine With Adaptive Neuron for Edge Arrhythmia Detection |
| title_sort | mspan a memristive spike based computing engine with adaptive neuron for edge arrhythmia detection |
| topic | spike-based neuromorphic computing memristive computation in memory arrhythmia detection |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.761127/full |
| work_keys_str_mv | AT jingwenjiang mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT fengshitian mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT jinhaoliang mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT ziyangshen mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT yiruiliu mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT jiapeizheng mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT huiwu mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT zhiyuanzhang mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT chaomingfang mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT yifanzhao mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT jiaheshi mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT xiaoyongxue mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection AT xiaoyangzeng mspanamemristivespikebasedcomputingenginewithadaptiveneuronforedgearrhythmiadetection |