Seungchan Lee

Sparse representation-based classification scheme for motor imagery-based brain–computer interface systems

Motor imagery (MI)-based brain-computer interface systems (BCIs) normally use a powerful spatial filtering and classification method to maximize their performance. The common spatial pattern (CSP) algorithm is a widely used spatial filtering method for MI-based BCIs. In this work, we propose a new sparse representation-based classification (SRC) scheme for MI-based BCI applications. Sensorimotor rhythms are extracted from electroencephalograms and used for classification. The proposed SRC method utilizes the frequency band power and CSP algorithm to extract features for classification. We analyzed the performance of the new method using experimental datasets. The results showed that the SRC scheme provides highly accurate classification results, which were better than those obtained using the well-known linear discriminant analysis classification method. The enhancement of the proposed method in terms of the classification accuracy was verified using cross-validation and a statistical paired t-test (p < 0.001).

Noise robustness analysis of sparse representation based classification method for non-stationary EEG signal classification

Abstract In the electroencephalogram (EEG)-based brain–computer interface (BCI) systems, classification is an important signal processing step to control external devices using brain activity. However, scalp-recorded EEG signals have inherent non-stationary characteristics; thus, the classification performance is deteriorated by changing the background activity of the EEG during the BCI experiment. Recently, the sparse representation based classification (SRC) method has shown a robust classification performance in many pattern recognition fields including BCI. In this study, we aim to analyze noise robustness of the SRC method to evaluate the capability of the SRC for non-stationary EEG signal classification. For this purpose, we generate noisy test signals by adding a noise source such as random Gaussian and scalp-recorded background noise into the original motor imagery based EEG signals. Using the noisy test signals and real online-experimental dataset, we compare the classification performance of the SRC and support vector machine (SVM). Furthermore, we analyze the unique classification mechanism of the SRC. We observed that the SRC method provided better classification accuracy and noise robustness compared with the SVM method. In addition, the SRC has an inherent adaptive classification mechanism that makes it suitable for time-varying EEG signal classification for online BCI systems.

Simple adaptive sparse representation based classification schemes for EEG based brain-computer interface applications

One of the main problems related to electroencephalogram (EEG) based brain-computer interface (BCI) systems is the non-stationarity of the underlying EEG signals. This results in the deterioration of the classification performance during experimental sessions. Therefore, adaptive classification techniques are required for EEG based BCI applications. In this paper, we propose simple adaptive sparse representation based classification (SRC) schemes. Supervised and unsupervised dictionary update techniques for new test data and a dictionary modification method by using the incoherence measure of the training data are investigated. The proposed methods are very simple and additional computation for the re-training of the classifier is not needed. The proposed adaptive SRC schemes are evaluated using two BCI experimental datasets. The proposed methods are assessed by comparing classification results with the conventional SRC and other adaptive classification methods. On the basis of the results, we find that the proposed adaptive schemes show relatively improved classification accuracy as compared to conventional methods without requiring additional computation.

Motor imagery based BCI classification via sparse representation of EEG signals

Electroencephalogram (EEG) based brain-computer interface (BCI) provides a new communication and control channel for people with severe motor disabilities. Motor imagery based sensorimotor rhythm (SMR) analysis is one of the widely used methods in the BCI field. However, these motor imagery signals are very noisy and strongly depends on subjects. Therefore, it is difficult to classify them and thus more powerful classification methods are needed. In this paper, we propose a new classification method based on sparse representation of EEG signals and ell-1 minimization. Using Mu and/or Beta rhythm as EEG features, we evaluate the performance of the proposed method with four data sets. Moreover, we make performance comparison with the linear discriminant analysis (LDA), another classification method. From the results, our proposed method shows the better classification accuracy.

Performance increase by using a EEG sparse representation based classification method

Attempts are being made to make brain-computer interface system (BCIs) commercially viable for normal person. Stable performance is essential so that BCIs could widely be used for general public. We propose a new classification method based on sparse representation of EEG signals and L1 minimization. The proposed method use the common spatial filtering (CSP) and band power feature for classification. We compare the classification accuracy of proposed method to that of the conventional linear discriminant analysis (LDA) method. Our method shows improved accuracy over the LDA classification method regardless of the number of CSP filters.

Dry electrode design and performance evaluation for EEG based BCI systems

For the design of electroencephalography (EEG) based BCI systems, crucial issues are to acquire high fidelity EEG signals and to provide convenient installation to users. Electrodes are the key components which measure EEG signals from users scalp. In this paper, we introduce a design of dry electrodes for BCI systems. The proposed electrodes are equipped with six spring loaded probes. They are capable of acquiring EEG signals of good enough quality without usage of conductive gels. To verify the performance of proposed electrodes, we measure contact impedance and compare them with those of conventional wet electrodes and G.tec Sahara dry electrodes. From the results, the impedance of proposed electrodes is shown to be satisfied without conductive gels. In future research, we will improve the design of proposed electrodes by adding active circuits.

Design of active dry electrodes and its evaluation for EEG acquisition

In this paper, we aim to introduce a design of active dry electrodes for EEG based BCI systems. The proposed electrodes consist of dry probes and an active circuit for easy installation and higher quality of EEG recording. To verify the evaluation of the proposed electrodes, we tried to detect alpha rhythms as a typical EEG feature by using our own EEG acquisition boards and Matlab. Experimental results show that the power of alpha rhythm reaches over 50 percent after 10 seconds when the subject closes his eyes. We will verify the performance of the proposed electrodes through various analysis such as detection of visual evoked potential (VEP) and sensorimotor rhythm (SMR) in future research.

Dictionary update based adaptive EEG classification for real time brain-computer interface applications

Due to the non-stationarity of EEG signals, classification performance is deteriorated during experimental sessions. Therefore, adaptive classification techniques are required for real-time BCI applications. In this paper, we propose simple adaptive sparse representation based classification (SRC) methods. We study supervised and unsupervised dictionary update schemes for new test data. The proposed methods are very simple and additional computation for the re-training of the classifier is not needed. We evaluate the proposed methods using an online BCI experimental dataset. The proposed methods are assessed by comparing classification results with the conventional SRC and other adaptive classification methods. We find that the proposed adaptive schemes show improved classification accuracy as compared to conventional methods without additional computation.