Zobrazit v EDS

Ensemble learning method based on temporal, spatial features with multi-scale filter banks for motor imagery EEG classification.

Uloženo v:
Podrobná bibliografie
Název: Ensemble learning method based on temporal, spatial features with multi-scale filter banks for motor imagery EEG classification.
Autoři: Zheng, Liangsheng1,2,3 (AUTHOR) ls.zheng@siat.ac.cn, Feng, Wei1,3 (AUTHOR) wei.feng@siat.ac.cn, Ma, Yue1,3 (AUTHOR) yue.ma@siat.ac.cn, Lian, Pengchen1,2,3 (AUTHOR) pc.lian@siat.ac.cn, Xiao, Yang1,4 (AUTHOR) xiaoyang@siat.ac.cn, Yi, Zhengkun1,3 (AUTHOR) zk.yi@siat.ac.cn, Wu, Xinyu1,3 (AUTHOR) xy.wu@siat.ac.cn
Zdroj: Biomedical Signal Processing & Control. Jul2022, Vol. 76, pN.PAG-N.PAG. 1p.
Témata: Filter banks, Brain-computer interfaces, Motor imagery (Cognition), Classification algorithms, Decoding algorithms, Classification, Electroencephalography
Abstrakt: • The ensemble learning framework can build an ensemble classifier model with sample distribution diversity, time-frequency diversity and domain diversity. • A classifier weight optimization algorithm based on L2-norm is designed, which can effectively alleviate the overfitting problem in weight learning. • The proposed TSMFBEL algorithm achieves an average classification accuracy of 88.80% and 86.53% on BCI Competition IV dataset IIa and dataset IIb, respectively. Decoding motion intention from electroencephalogram (EEG) is a key part of the motor imagery-based brain-computer interface (MI-BCI). To help the disabled with neuromuscular disabilities to restore motor function through BCI, it is necessary to build an efficient and stable classification algorithm to decode the motor intention contained in the EEG signal. However, EEG signals are non-stationary and vary greatly between individuals. In this work, we propose an ensemble learning method based on temporal, spatial features and multi-scale filter banks, called TSMFBEL, which aims to design an ensemble classifier model with strong generalization capabilities for MI EEG classification. To obtain diverse ensemble classifiers, the original EEG data are divided into subsets with sample diversity by bootstrap sampling method, and then decomposed into time–frequency subsets with time–frequency distribution diversity by multi-scale filter banks method. For each time–frequency subset, features with domain diversity are extracted from temporal domain, spatial domain and temporal-spatial domain, and heterogeneous classifiers with diversity are trained based on each set of features. To obtain the optimal decision, we describe the ensemble strategy as a minimum classification error optimization problem, and propose an ensemble classifier weight optimization method based on the L2-norm, and finally integrate the decision of the ensemble classifier by weighted fusion. The proposed method was evaluated on two public datasets (BCI Competition IV Dataset IIa and BCI Competition IV Dataset IIb), and the results are compared with the classification method of the state-of-the-art methods. Experimental results show that the proposed TSMFBEL algorithm can effectively construct a diversified ensemble classifier, and the average classification accuracy on the two datasets is 88.80% and 86.53% respectively, which are the highest among the state-of-the-art methods, and the standard deviation of the results is also the lowest. Excellent classification performance shows that the proposed algorithm has great potential in the decoding of MI EEG signals. [ABSTRACT FROM AUTHOR]
Databáze: Supplemental Index
Popis
Abstrakt:• The ensemble learning framework can build an ensemble classifier model with sample distribution diversity, time-frequency diversity and domain diversity. • A classifier weight optimization algorithm based on L2-norm is designed, which can effectively alleviate the overfitting problem in weight learning. • The proposed TSMFBEL algorithm achieves an average classification accuracy of 88.80% and 86.53% on BCI Competition IV dataset IIa and dataset IIb, respectively. Decoding motion intention from electroencephalogram (EEG) is a key part of the motor imagery-based brain-computer interface (MI-BCI). To help the disabled with neuromuscular disabilities to restore motor function through BCI, it is necessary to build an efficient and stable classification algorithm to decode the motor intention contained in the EEG signal. However, EEG signals are non-stationary and vary greatly between individuals. In this work, we propose an ensemble learning method based on temporal, spatial features and multi-scale filter banks, called TSMFBEL, which aims to design an ensemble classifier model with strong generalization capabilities for MI EEG classification. To obtain diverse ensemble classifiers, the original EEG data are divided into subsets with sample diversity by bootstrap sampling method, and then decomposed into time–frequency subsets with time–frequency distribution diversity by multi-scale filter banks method. For each time–frequency subset, features with domain diversity are extracted from temporal domain, spatial domain and temporal-spatial domain, and heterogeneous classifiers with diversity are trained based on each set of features. To obtain the optimal decision, we describe the ensemble strategy as a minimum classification error optimization problem, and propose an ensemble classifier weight optimization method based on the L2-norm, and finally integrate the decision of the ensemble classifier by weighted fusion. The proposed method was evaluated on two public datasets (BCI Competition IV Dataset IIa and BCI Competition IV Dataset IIb), and the results are compared with the classification method of the state-of-the-art methods. Experimental results show that the proposed TSMFBEL algorithm can effectively construct a diversified ensemble classifier, and the average classification accuracy on the two datasets is 88.80% and 86.53% respectively, which are the highest among the state-of-the-art methods, and the standard deviation of the results is also the lowest. Excellent classification performance shows that the proposed algorithm has great potential in the decoding of MI EEG signals. [ABSTRACT FROM AUTHOR]
ISSN:17468094
DOI:10.1016/j.bspc.2022.103634