TY - GEN
T1 - Motor imagery EEG signal classification based on deep transfer learning
AU - Wei, Mingnan
AU - Yang, Rui
AU - Huang, Mengjie
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - Deep transfer learning (DTL) has developed rapidly in the field of motor imagery (MI) on brain-computer interface (BCI) in recent years. DTL utilizes deep neural networks with strong generalization capabilities as the pre-training framework and automatically extracts richer and more expressive features during the training process. The goal of this paper is utilizing the DTL to classify MI electroencephalogram (EEG) signals on the premise of a small data set. The publicly available dataset III of the second BCI competition is applied in both the training part and testing part to evaluate the effectiveness of the proposed method. Firstly in the process, finite impulse response (FIR) filter and wavelet transform threshold denoising method are used to remove redundant signals and artifacts in EEG signals. Then, the continuous wavelet transform (CWT) is utilized to convert the one-dimensional EEG signal into a two-dimensional time-frequency amplitude representation as the input of the pre-trained convolutional neural network (CNN) for classifying two types of MI signals. Employing the input data of 140 trials for training, the final classification accuracy rate reaches 96.43%. Compared with the results of some superior machine learning models using the same data set, the accuracy and Kappa value of this DTL model are better. Therefore, the proposed scheme of MI EEG signal classification based on the DTL method offers preferably empirical performance.
AB - Deep transfer learning (DTL) has developed rapidly in the field of motor imagery (MI) on brain-computer interface (BCI) in recent years. DTL utilizes deep neural networks with strong generalization capabilities as the pre-training framework and automatically extracts richer and more expressive features during the training process. The goal of this paper is utilizing the DTL to classify MI electroencephalogram (EEG) signals on the premise of a small data set. The publicly available dataset III of the second BCI competition is applied in both the training part and testing part to evaluate the effectiveness of the proposed method. Firstly in the process, finite impulse response (FIR) filter and wavelet transform threshold denoising method are used to remove redundant signals and artifacts in EEG signals. Then, the continuous wavelet transform (CWT) is utilized to convert the one-dimensional EEG signal into a two-dimensional time-frequency amplitude representation as the input of the pre-trained convolutional neural network (CNN) for classifying two types of MI signals. Employing the input data of 140 trials for training, the final classification accuracy rate reaches 96.43%. Compared with the results of some superior machine learning models using the same data set, the accuracy and Kappa value of this DTL model are better. Therefore, the proposed scheme of MI EEG signal classification based on the DTL method offers preferably empirical performance.
KW - Brain-Computer Interface
KW - Convolutional Neural Network
KW - Deep Transfer Learning
KW - Motor Imagery
UR - http://www.scopus.com/inward/record.url?scp=85110928092&partnerID=8YFLogxK
U2 - 10.1109/CBMS52027.2021.00083
DO - 10.1109/CBMS52027.2021.00083
M3 - Conference Proceeding
AN - SCOPUS:85110928092
T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems
SP - 85
EP - 90
BT - Proceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021
A2 - Almeida, Joao Rafael
A2 - Gonzalez, Alejandro Rodriguez
A2 - Shen, Linlin
A2 - Kane, Bridget
A2 - Traina, Agma
A2 - Soda, Paolo
A2 - Oliveira, Jose Luis
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021
Y2 - 7 June 2021 through 9 June 2021
ER -