Aiming at feature selection problem of motor imagery task in brain computer interface (BCI), an algorithm based on mutual information and principal component analysis (PCA) for electroencephalogram (EEG) feature selection is presented. This algorithm introduces the category information, and uses the sum of mutual information matrices between features under different motor imagery category to replace the covariance matrix. The eigenvectors of the sum matrix represent the direction of the principal components and the eigenvalues of the sum matrix are used to determine the dimensionality of principal components. 2005 International BCI competition data set was used in our experiments, and four feature extraction methods were adopted, i. e. power spectrum estimation, continuous wavelet transform, wavelet packet decomposition and Hjorth parameters. The proposed feature selection algorithm was adopted to select and combine the most useful features for classification. The results showed that relative to the PCA algorithm, our algorithm had better performance in dimensionality reduction and in classification accuracy with the assistance of support vector machine classifier under the same dimensionality of principal components.
This paper aims to realize the decoding of single trial motor imagery electroencephalogram (EEG) signal by extracting and classifying the optimized features of EEG signal. In the classification and recognition of multi-channel EEG signals, there is often a lack of effective feature selection strategies in the selection of the data of each channel and the dimension of spatial filters. In view of this problem, a method combining sparse idea and greedy search (GS) was proposed to improve the feature extraction of common spatial pattern (CSP). The improved common spatial pattern could effectively overcome the problem of repeated selection of feature patterns in the feature vector space extracted by the traditional method, and make the extracted features have more obvious characteristic differences. Then the extracted features were classified by Fisher linear discriminant analysis (FLDA). The experimental results showed that the classification accuracy obtained by proposed method was 19% higher on average than that of traditional common spatial pattern. And high classification accuracy could be obtained by selecting feature set with small size. The research results obtained in the feature extraction of EEG signals lay the foundation for the realization of motor imagery EEG decoding.
With the advantage of providing more natural and flexible control manner, brain-computer interface systems based on motor imagery electroencephalogram (EEG) have been widely used in the field of human-machine interaction. However, due to the lower signal-noise ratio and poor spatial resolution of EEG signals, the decoding accuracy is relative low. To solve this problem, a novel convolutional neural network based on temporal-spatial feature learning (TSCNN) was proposed for motor imagery EEG decoding. Firstly, for the EEG signals preprocessed by band-pass filtering, a temporal-wise convolution layer and a spatial-wise convolution layer were respectively designed, and temporal-spatial features of motor imagery EEG were constructed. Then, 2-layer two-dimensional convolutional structures were adopted to learn abstract features from the raw temporal-spatial features. Finally, the softmax layer combined with the fully connected layer were used to perform decoding task from the extracted abstract features. The experimental results of the proposed method on the open dataset showed that the average decoding accuracy was 80.09%, which is approximately 13.75% and 10.99% higher than that of the state-of-the-art common spatial pattern (CSP) + support vector machine (SVM) and filter bank CSP (FBCSP) + SVM recognition methods, respectively. This demonstrates that the proposed method can significantly improve the reliability of motor imagery EEG decoding.
Motor imagery (MI), motion intention of the specific body without actual movements, has attracted wide attention in fields as neuroscience. Classification algorithms for motor imagery electroencephalogram (MI-EEG) signals are able to distinguish different MI tasks based on the physiological information contained by the EEG signals, especially the features extracted from them. In recent years, there have been some new advances in classification algorithms for MI-EEG signals in terms of classifiers versus machine learning strategies. In terms of classifiers, traditional machine learning classifiers have been improved by some researchers, deep learning and Riemannian geometry classifiers have been widely applied as well. In terms of machine learning strategies, ensemble learning, adaptive learning, and transfer learning strategies have been utilized to improve classification accuracies or reach other targets. This paper reviewed the progress of classification algorithms for MI-EEG signals, summarized and evaluated the existing classifiers and machine learning strategies, to provide new ideas for developing classification algorithms with higher performance.