SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG

• Published in: IEEE International Symposium on Circuits and Systems proceedings pp. 2304 - 2308
• Main Authors: Zhang, Chao, Tang, Zijian, Guo, Taoming, Lei, Jiaxin, Xiao, Jiaxin, Wang, Anhe, Bai, Shuo, Zhang, Milin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.05.2022
• Subjects: Brain-machine interface (BMI); Convolution; Convolutional neural network (CNN); Electroencephalography; Field-programmable gate array (FPGA); Logic gates; Model compression; Neural networks; Power demand; Quantization (signal); Sustained attention level evaluation
• ISSN: 2158-1525
• DOI: 10.1109/ISCAS48785.2022.9937323

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.