Over the last few decades, the use of electroencephalography (EEG) signals for motor imagery based brain-computer interface (MI-BCI) has gained widespread attention. Deep learning have also gained widespread attention and used in various application such as natural language processing, computer vision and speech processing. However, deep learning has been rarely used for MI EEG signal classification. In this paper, we present a deep learning approach for classification of MI-BCI that uses adaptive method to determine the threshold. The widely used common spatial pattern (CSP) method is used to extract the variance based CSP features, which is then fed to the deep neural network for classification. Use of deep neural network (DNN) has been extensively explored for MI-BCI classification and the best framework obtained is presented. The effectiveness of the proposed framework has been evaluated using dataset IVa of the BCI Competition III. It is found that the proposed framework outperforms all other competing methods in terms of reducing the maximum error. The framework can be used for developing BCI systems using wearable devices as it is computationally less expensive and more reliable compared to the best competing methods.

/pdf/a-deep-learning-approach-for-motor-imagery-eeg-signal-2r21bpmskw.pdf

A Deep Learning Approach for Motor Imagery EEG Signal Classification

Support vector machines (SVMs) are widely used classifiers for detecting physiological patterns in human-computer interaction (HCI). Their success is due to their versatility, robustness and large availability of free dedicated toolboxes. Frequently in the literature, insufficient details about the SVM implementation and/or parameters selection are reported, making it impossible to reproduce study analysis and results. In order to perform an optimized classification and report a proper description of the results, it is necessary to have a comprehensive critical overview of the applications of SVM. The aim of this paper is to provide a review of the usage of SVM in the determination of brain and muscle patterns for HCI, by focusing on electroencephalography (EEG) and electromyography (EMG) techniques. In particular, an overview of the basic principles of SVM theory is outlined, together with a description of several relevant literature implementations. Furthermore, details concerning reviewed papers are listed in tables and statistics of SVM use in the literature are presented. Suitability of SVM for HCI is discussed and critical comparisons with other classifiers are reported.

/pdf/support-vector-machines-to-detect-physiological-patterns-for-vii2ith4c7.pdf

Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction: a review

In recent years, most of the researchers are developing brain–computer interface (BCI) applications for the physically disabled to be able to interconnect with peripheral devices based on brain activities. Electroencephalogram (EEG) is a very powerful tool for investigating patient’s health and different physiological activities of the brain. A significant challenge in this BCI application is the accurate and reliable recognition of motor imagery (MI) task. A brain–computer interface based on MI interprets the patient’s brain activities into a control signal through classifying EEG patterns of various motor imagination tasks. The appropriate features are essential to achieving higher classification accuracy of EEG motor imagery task. For EEG signal feature extraction, wavelet transform is suitable for analysis of nonlinear time series signals. Nevertheless, the dimension of the extracted feature is huge and it may reduce the performance of classification method. Dimensionality reduction and classification play an important role in BCI motor imagery research. In this study, hybridization of particle swarm optimization (PSO)-based rough set feature selection technique is proposed for achieving a minimal set of relevant features from extracted features. The selected features are applied to the proposed novel neighborhood rough set classifier (NRSC) method for classification of multiclass motor imagery. The experimental results are delivered for nine subjects of the BCI Competition 2008 Dataset IIa to show the greater performance of the proposed algorithm. The outcome of proposed algorithms produces a higher mean kappa of 0.743 compared to 0.70 from sequential updating semi-supervised spectral regression kernel discriminant analysis. Experimental results show that the strength of the proposed PSO-rough set and NRSC algorithms outperforms the champion of the BCI Competition IV Dataset IIa and other existing research using this dataset.

PSO-based feature selection and neighborhood rough set-based classification for BCI multiclass motor imagery task

Knowledge of the mental workload induced by a Web page is essential for improving users’ browsing experience. However, continuously assessing the mental workload during a browsing task is challenging. To address this issue, this paper leverages the correlation between stimuli and physiological responses, which are measured with high-frequency, non-invasive psychophysiological sensors during very short span windows. An experiment was conducted to identify levels of mental workload through the analysis of pupil dilation measured by an eye-tracking sensor. In addition, a method was developed to classify mental workload by appropriately combining different signals (electrodermal activity (EDA), electrocardiogram, photoplethysmo-graphy (PPG), electroencephalogram (EEG), temperature and pupil dilation) obtained with non-invasive psychophysiological sensors. The results show that the Web browsing task involves four levels of mental workload. Also, by combining all the sensors, the efficiency of the classification reaches 93.7%.

/pdf/using-psychophysiological-sensors-to-assess-mental-workload-3h1mw1620j.pdf

Using Psychophysiological Sensors to Assess Mental Workload During Web Browsing.

http://cone.hanyang.ac.kr/BioEST/Kor/papers/BSPC2015_ljh.pdf

Development of a hybrid mental spelling system combining SSVEP-based brain-computer interface and webcam-based eye tracking

In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates.

https://www.mdpi.com/1424-8220/14/7/12784/pdf

Yuning Yan

Papers

Classification of EEG signals using a multiple kernel learning support vector machine.