High-density channels are often used to acquire electroencephalogram (EEG) spatial information in different cortical regions of the brain in brain-computer interface (BCI) systems. However, applying excessive channels is inconvenient for signal acquisition, and it may bring artifacts. To avoid these defects, the common spatial pattern (CSP) algorithm was used for channel selection and a selection criteria based on norm-2 is proposed in this paper. The channels with the highest M scores were selected for the purpose of using fewer channels to acquire similar rate with high density channels. The DatasetⅢa from BCI competition 2005 were used for comparing the classification accuracies of three motor imagery between whole channels and the selected channels with the present proposed method. The experimental results showed that the classification accuracies of three subjects using the 20 channels selected with the present method were all higher than the classification accuracies using all 60 channels, which convinced that our method could be more effective and useful.
Common spatial pattern (CSP) is a very popular method for spatial filtering to extract the features from electroencephalogram (EEG) signals, but it may cause serious over-fitting issue. In this paper, after the extraction and recognition of feature, we present a new way in which the recognition results are fused to overcome the over-fitting and improve recognition accuracy. And then a new framework for EEG recognition is proposed by using CSP to extract features from EEG signals, using linear discriminant analysis (LDA) classifiers to identify the user's mental state from such features, and using Choquet fuzzy integral to fuse classifiers results. Brain-computer interface (BCI) competition 2005 data setsⅣa was used to validate the framework. The results demonstrated that it effectively improved recognition and to some extent overcome the over-fitting problem of CSP. It showed the effectiveness of this framework for dealing with EEG.
One of the key problems of brain-computer interfaces (BCI) is low signal-to-noise ratio (SNR) of electroencephalogram (EEG) signals. It affects recognition performance. To remove the artifact and noise, block under-determined blind source separation method based on the small number of channels is proposed in this paper. The non-stationary EEG signals are turned into block stationary signals by piecewise. The mixing matrix is estimated by the second-order under-determined blind mixing matrix identification. Then, the beamformer based on minimum mean square error separates the original sources of signals. Eventually, the reconstructed EEG for mixed signals removes the unwanted components of source signals to achieve suppressing artifact. The experiment results on the real motor imagery BCI indicated that the block under-determined blind source separation method could reconstruct signals and remove artifact effectively. The accuracy of motor imagery task of BCI has been greatly improved.
Signal classification is a key of brain-computer interface (BCI). In this paper, we present a new method for classifying the electroencephalogram (EEG) signals of which the features are heterogeneous. This method is called wrapped elastic net feature selection and classification. Firstly, we used the joint application of time-domain statistic, power spectral density (PSD), common spatial pattern (CSP) and autoregressive (AR) model to extract high-dimensional fused features of the preprocessed EEG signals. Then we used the wrapped method for feature selection. We fitted the logistic regression model penalized with elastic net on the training data, and obtained the parameter estimation by coordinate descent method. Then we selected best feature subset by using 10-fold cross-validation. Finally, we classified the test sample using the trained model. Data used in the experiment were the EEG data from international BCI Competition Ⅳ. The results showed that the method proposed was suitable for fused feature selection with high-dimension. For identifying EEG signals, it is more effective and faster, and can single out a more relevant subset to obtain a relatively simple model. The average test accuracy reached 81.78%.
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.