SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG
文献类型：会议论文
| 作者 | Zhang, Chao1,2; Tang, Zijian1,2; Guo, Taoming2; Lei, Jiaxin1,2; Xiao, Jiaxin2; Wang, Anhe3; Bai, Shuo3; Zhang, Milin1,2 |
| 出版日期 | 1905-07-14 |
| 会议日期 | May 27, 2022 - June 1, 2022 |
| 关键词 | Brain computer interface - Classification (of information) - Convolution - Convolutional neural networks - Energy efficiency - Field programmable gate arrays (FPGA) - Low power electronics |
| 卷号 | 2022-May |
| DOI | 10.1109/ISCAS48785.2022.9937323 |
| 页码 | 2304-2308 |
| 英文摘要 | This paper proposes SaleNet-an end-to-end convolutional neural network (CNN) for sustained attention level evaluation using prefrontal electroencephalogram (EEG). A bias-driven pruning method is proposed together with group convolution, global average pooling (GAP), near-zero pruning, weight clustering and quantization for the model compression, achieving a total compression ratio of 183. 11x. The compressed SaleNet obtains a state-of-the-art subject-independent sustained attention level classification accuracy of 84.2% on the recorded 6-subject EEG database in this work. The SaleNet is implemented on a Artix-7 FPGA with a competitive power consumption of 0.11 W and an energy-efficiency of 8.19 GOps/w. 漏 2022 IEEE. |
| 项目编号 | This work is supported in part by the National Key Research and Development Program of China (No.2018YFB220200*), in part by the Natural Science Foundation of China through grant 92164202. in part by the Beijing Innovation Center for Future Chip, in part by the Beijing National Research Center for Information Science and Technology. |
| 会议录 | Proceedings - IEEE International Symposium on Circuits and Systems
 ; 2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
|
| 会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
| 学科主题 | Electroencephalography |
| 源URL | [http://ir.ipe.ac.cn/handle/122111/59616]  |
| 作者单位 | 1.Institute for Precision Medicine, Tsinghua University, China 2.Tsinghua University, Department of Electronic Engineering, China 3.State Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chinese Academy of Sciences, China |
| 推荐引用方式 GB/T 7714 | Zhang, Chao,Tang, Zijian,Guo, Taoming,et al. SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG[C]. 见:. May 27, 2022 - June 1, 2022. |
入库方式： OAI收割
来源：过程工程研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。