隨著腦科學的研究發展，腦機介面以成為腦科學的發展重點，而具有非侵入式 優點的 EEG 腦電訊號，正是腦機介面的主要方案之一。然而腦電訊號通常被掩沒 在噪聲中，其訊號的信噪比(SNR)非常低，無法以肉眼替不同動作的腦波進行分類， 這對運動圖像分類立下了巨大的挑戰。
而近年來分析的方式也相當多元，從自動編碼器(Auto Encoder)、受限玻爾茲曼 機，到人工智慧的 CNN 和 RNN 深度學習網路，這些用於 EEG 運動圖像分類的方 式皆極大地提高了運動圖像分類的準確性。然而多分類依然為一大挑戰，不僅想像 運動的方式無法訓練出多種不同的分類，且訓練階段也將耗費相當多的時間，因此 本論文針對訓練方式提出了不同的方法，利用鏡像神經元的方式訓練想像運動，希 望藉由觀看學習的方式達到更好的效果，同時縮短訓練的時間並提高不同動作的判 斷率，與此同時在神經網路上也將採用新穎的時序性架構進行訓練。
實驗過程採用 13 通道的腦波機收集資料，於最後的辨識成果中，透過五位受 試者對五種動作各 300 次的動作觀看，三分類最高可達 56.2%，而五分類也有 40.3% 的辨識率，除此之外，以純想像運動資料放入鏡像神經元所訓練出的模型中，三分 類辨識率可達 52%，而五分類則為 33.1%。證實鏡像神經元與像想運動之間並非毫 無關聯，前者所訓練出的網路對後者依然有一定的辨識度。

With the development of EEG science research, the advanced techniques for brain wave analysis enable people to probe the profound neurocircuitry inside human brain. One promising technique is the use of brain waves to control peripheral machines through user’s intentions, which is called brain copmuter interface (BCI). But how to extract useful information from brain wave is still a big challenge.
In recent years, some deep learning solutions based on AutoEncoder, Restricted Boltzmann Machine, CNN and RNN have been proposed for EEG imagery classification which have will improved the accuracy. However, multi-task problem remains a challenge. Because of imagery movement can’t use for multi-task classification, so we try to use mirror neuron training for the better result. In this paper, we also use a new solution based on Temporal Convolutional Network(TCN) with much higher computational efficiency and accuracy.
Our experiment result have shown that the propose TCN solution has obtained state of the great performance on multi-task of mirror neuron training. A high classification accuracy as 56.2% on 3 tasks and 40.3% on 5 tasks. Besides, imagery movement data is also recognizable in the model. The three task recognition rate can reach 52% and five task recognition rate can reach 33.1%. It shows that there are some similar associations between mirror neuron training and motor imagery.

[1] B. Graimann, B. Allison and G. Pfurtscheller, Brain-Computer Interfaces: A Gentle Introduction, 2010.
[2] I. Käthner, S. C. Wriessnegger, G. R. Müller-Putz, A. Kübler, and S. Halder, “Effects of mental workload and fatigue on the P300, alpha and theta band power during operation of an ERP (P300) brain–computer interface,” Biological Psychology, pp. 118-129, October 2014.
[3] S. N. Abdulkader, A. Atia, and M.-S. M. Mostafa, “Brain computer interfacing: Applications and challenges,” Egyptian Informatics Journal, pp. 213-230, July 2015.
[4] J. J. Daly and J. R. Wolpaw, “Brain–computer interfaces in neurological rehabilitation,” The Lancet Neurology, pp. 1032-1043, November 2008.
[5] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan, “Brain–computer interfaces for communication and control,” Clinical Neurophysiology, pp. 767-791, June 2002.
[6] G. Pfurtscheller and F. H. Lopes da Silva, “Event-related EEG/MEG synchronization and desynchronization: basic principles,” Clinical Neurophysiology, pp. 1842-1857, November 1999.
[7] Aimin Jiang, Jing Shang, Xiaofeng Liu, Yibin Tang, Hon Keung Kwan, Yanping Zhu, “Efficient CSP Algorithm With Spatio-Temporal Filtering for Motor Imagery Classification,” IEEE Transactions on Neural Systems and Rehabilitation Engineering , pp. 1006-1016, April 2020.
[8] De-Shuang Huang and Jian-Xun Mi, “A New Constrained Independent Component Analysis Method,” IEEE Transactions on Neural Networks , pp. 1532-1535, September 2007.
[9] Sina Khanmohammadi, Chun-An Chou, “Adaptive Seizure Onset Detection Framework Using a Hybrid PCA–CSP Approach,” IEEE Journal of Biomedical and Health Informatics, pp. 154-160, Jan. 2018.
[10] Saugat Bhattacharyya, Anwesha Khasnobish, Somsirsa Chatterjee, Amit Konar, D.N Tibarewala, “Performance analysis of LDA, QDA and KNN algorithms in left-right limb movement classification from EEG data,” 2010 International Conference on Systems in Medicine and Biology, pp. 126-131, December 2020.
[11] R. Shantha Selva Kumari, J. Prabin Jose, “Seizure detection in EEG using time frequency analysis and SVM,” 2011 International Conference on Emerging Trends in Electrical and Computer Technology, pp. 626-630, March 2011.
[12] Bin Hu, Xiaowei Li, Shuting Sun, Martyn Ratcliffe, “Attention Recognition in EEG-Based Affective Learning Research Using CFS+KNN Algorithm,” IEEE/ACM Transactions on Computational Biology and Bioinformatics , pp. 38-45, October 2016.
[13] Johannes Hennrich, Christian Herff, Dominic Heger, Tanja Schultz, “Investigating deep learning for fNIRS based BCI,” 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2844-2847, August 2015.
[14] Na Lu, Tengfei Li, Xiaodong Ren, and Hongyu Miao, “A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines,” IEEE Transactions on Neural Systems and Rehabilitation Engineering , pp. 566-576, June 2017.
[15] Y. R. Tabar and U. Halici, “A novel deep learning approach for classification of EEG motor imagery signals,” Journal of Neural Engineering, November 2016.
[16] Guangyi Zhang, Vandad Davoodnia, Alireza Sepas-Moghaddam, Yaoxue Zhang, Ali Etema, “Classification of Hand Movements From EEG Using a Deep Attention-Based LSTM Network,” IEEE Sensors Journal , pp. 3113-3122, 15 March 2020.
[17] L. R. Fournier, G. F. Wilson, C. R. Swainc, “Electrophysiological, behavioral, and subjective indexes of workload when performing multiple tasks: manipulations of task difficulty and training,” International Journal of Psychophysiology, pp. 129-145, January 1999.
[18] T. H. Budzynski, H. Budzynski, J. Evans, and A. Abarbanel, Introduction to quantitative EEG and neurofeedback: Advanced theory and applications, Academic Press, 2009.
[19] H. J. Herbert, “The ten-twenty electrode system of the International Federation,” Electroencephalography and clinical neurophysiology, pp. 370-375, 1958.
[20] G. Pfurtscheller, G. R. Müller-Putz, R. Scherer and C. Neuper, “Rehabilitation with Brain-Computer Interface Systems,” Computer, pp. 58-65, Oct. 2008 .
[21] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural computation, pp. 1735-1780, 15 November 1997.
[22] G. Pfurtscheller and C. Neuper, “Motor imagery and direct brain-computer communication,” Proceedings of the IEEE, pp. 1123 - 1134, July 2001.
[23] R. Polikar, “The Wavelet Tutorial,” [線上]. Available: http://users.rowan.edu/~polikar/WTtutorial.html.
[24] Dalin Zhang, "Cascade amd parallel convolutional recurrent neural networks on EEG-Based", Thu, 10 Jun 2021
[25] Shaojie Bai, "An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling", Thu, 19 Apr 2018
[26] Long, Jonathan, "Fully convolutional networks for semantic segmentation", In CVPR, 2015
[27] Yu, Fisher and Koltun, "Multi-scale context aggregation by dilated convolutions", In ICLR, 2016
[28] Na Lu, " A Temporal Convolution Network Solution for EEG Motor Imagery Classification", IEEE, 26 December 2019
[29] Tian-jian Luo, " Effect of Different Movement Speed Modes on Human Action Observation: An EEG Study ", Neurosci., April 2018
[30] Jin Woo Choi, "Observing Actions Through Immersive Virtual Reality Enhances Motor Imagery Training ", IEEE, May 2020