|
|
|
| Transformational Spiking Neural Network and its Application in Brain-Computer Interface |
| Zhao Zechen, Yu Tianyou, Yu Zhuliang, Gu Zhenghui* |
| (School of Automation Science and Engineering, South China University of Technology, Guangzhou 510000, China) |
|
|
|
|
Abstract The monitoring of electroencephalogram (EEG) signals imposes stringent demands on the real-time performance and energy efficiency of computing systems, requiring the preservation of high temporal resolution while minimizing resource consumption. Spiking neural networks (SNNs), through their spike-based information transmission mechanism, replace the multiplication operations in traditional neural networks with addition operations. Their asynchronous communication characteristics enhance the processing efficiency of temporal data, thereby meeting real-time requirements. As a result, SNNs exhibit significant application potential in continuous EEG monitoring tasks. However, the direct design and optimization of SNNs are highly complex and challenging to deploy efficiently. To address this issue, this study proposed a quantize-clamp-quantize (QCQ) method for converting convolutional neural networks (CNNs) to SNNs and applied it to the SEED dataset for EEG emotion classification and the BCI Competition IV Dataset 2a for motor imagery. Specifically, the QCQ method introduced clamping and quantization operations in the activation and output layers of computational layers, adopted a single quantization strategy for input and pooling layer computations, and migrated batch normalization parameters to achieve efficient CNN-to-SNN conversion. The proposed QCQ method achieved accuracies of 93.79% on the SEED dataset and 78.64% on the MI dataset, yielding average performance gains of 2.77% and 4.31% over advanced existing methods, respectively. These improvements were accomplished with substantial energy efficiency enhancements of nearly 75% and 80% on the two datasets. These results validated that the QCQ method effectively inherited the classification performance of CNNs, brought SNN performance closer to CNNs on both datasets, and provided a practical implementation pathway for SNN applications.
|
|
Received: 20 September 2025
|
|
|
|
Corresponding Authors:
*E-mail: zhgu@scut.edu.cn
|
|
|
|
[1] Zhan Gege, Song Zuoting, Fang Tao, et al. Applications of spiking neural network in brain computer interface [C]//2021 9th International Winter Conference on Brain-Computer Interface (BCI). Gangwon: IEEE, 2021: 1-6.
[2] Izhikevich E M. Which model to use for cortical spiking neurons? [J]. IEEE Transactions on Neural Networks, 2004, 15(5): 1063-1070.
[3] Yan Zhanglu, Zhou Jun, Wong Weng Fai. EEG classification with spiking neural network: smaller, better, more energy efficient [J]. Smart Health, 2022, 24: 100261.
[4] Soltani Nima, Goldsmith Andrea. Directed information between connected leaky integrate-and-fire neurons [J]. IEEE Transactions on Information Theory, 2017, 63(9): 5954-5967.
[5] Alzhrani Wael, Doborjeh Maryam, Doborjeh Zohreh, et al. Emotion recognition and understanding using EEG data in a brain-inspired spiking neural network architecture [C]//2021 International Joint Conference on Neural Networks (IJCNN). Shenzhen: IEEE, 2021: 1-9.
[6] Kasabov Nikola K. NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data [J]. Neural Networks, 2014, 52: 62-76.
[7] Li Wei, Fang Cheng, Zhu Zhihao, et al. Fractal spiking neural network scheme for EEG-based emotion recognition [J]. IEEE Journal of Translational Engineering in Health and Medicine, 2024, 12: 106-118.
[8] Gong Peiliang, Wang Pengpai, Zhou Yueying, et al. A spiking neural network with adaptive graph convolution and LSTM for EEG-based brain-computer interfaces [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 1440-1450.
[9] Tan Clarence, Šarlija Marko, Kasabov Nikola. NeuroSense: Short-term emotion recognition and understanding based on spiking neural network modelling of spatio-temporal EEG patterns [J]. Neurocomputing, 2021, 434: 137-148.
[10] Virgilio G. Carlos D, Sossa A. Juan H, Antelis Javier M, et al. Spiking neural networks applied to the classification of motor tasks in EEG signals [J]. Neural Networks, 2020, 122: 130-143.
[11] Tan Ping, Xiao Han, Zou Han, et al. Spiking neural network classification method in motor imagery brain-computer interface [C]//2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). Harbin: IEEE, 2023: 1-5.
[12] Wang Hongtao, Tang Cong, Xu Tao, et al. An approach of one-vs-rest filter bank common spatial pattern and spiking neural networks for multiple motor imagery decoding [J]. IEEE Access, 2020, 8: 86850-86861.
[13] Duan Ruonan, Zhu Jiayi, Lu Baoliang. Differential entropy feature for EEG-based emotion classification [C]//2013 6th International IEEE/EMBS Conference on Neural Engineering (NER). San Diego: IEEE, 2013: 81-84.
[14] 黄泽滨. 基于深度学习的脑电信号情绪识别方法研究 [D]. 广州: 华南理工大学, 2020.
[15] Keys R. Cubic convolution interpolation for digital image processing [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1981, 29(6): 1153-1160.
[16] Lawhern Vernon J, Solon Amelia J, Waytowich Nicholas R, et al. EEGNet: A compact convolutional network for EEG-based brain-computer interfaces [J]. Journal of Neural Engineering, 2018, 15(5): 056013.
[17] Abbott LF. Lapicque's introduction of the integrate-and-fire model neuron (1907) [J]. Brain Research Bulletin, 1999, 50(5-6): 303-304.
[18] Rueckauer Bodo, Lungu Iulia Alexandra, Hu Yuhuang, et al. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification [J]. Frontiers in Neuroscience, 2017, 11: 682.
[19] Wei-Long Zheng, Bao-Liang Lu. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks [J]. IEEE Transactions on Autonomous Mental Development, 2015, 7(3): 162-175.
[20] Tangermann Michael, Müller Klaus Robert, Aertsen Ad, et al. Review of the BCI competition IV [J]. Frontiers in Neuroscience, 2012, 6: 55.
[21] Diehl Peter U, Neil Daniel, Binas Jonathan, et al. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing [C]//2015 International Joint Conference on Neural Networks (IJCNN). Killarney: IEEE, 2015: 1-8.
[22] Wang Bo, Zhou Jun, Wong Weng Fai, et al. Shenjing: A low power reconfigurable neuromorphic accelerator with partial-sum and spike networks-on-chip [C]//2020 Design, Automation & Test in Europe Conference & Exhibition (DATE). Grenoble: IEEE, 2020: 240-245.
[23] Jacob B, Kligys S, Chen Bo, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City: IEEE, 2018: 2704-2713. |
|
|
|
