Classification of EEG Using Adaptive SVM Classifier with CSP and Online Recursive Independent Component Analysis.

Motor imagery (MI) is the most used paradigm in Brain-Computer Interface (BCI). As in other BCI paradigms, it is divided into feature extraction and classification. In this study, we implemented two feature extraction methods, one based on the well-known Common Spatial Pattern (CSP) algorithm and the other based on a not so well-known electroencephalogram (EEG) source localization technique called Low-Resolution Brain Electromagnetic Tomography (LORETA). We evaluated 30 right-handed subjects from an EEG data set made publicly available through Giga Science, where participants performed MI of left- and right-hand movements. After feature extraction with CSP and LORETA, MI tasks classification were carried out using the Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), Naïve Bayes (NB) and Multi-Layer Perceptron (MLP) algorithms. Finally, we evaluated classification performance with all possible combination of classifiers and feature extraction methods. For all classifiers, the CSP feature extraction method performed better than LORETA. The best classification accuracy for the LORETA method was 71.2% and for the CSP method was 94.2%, both achieved with SVM.

Brain computer interface (BCI) is known as a good way to communicate between brain and computer or other device. There are many kinds of physiological signal can operate BCI systems. Motor imagery (MI) has been demonstrated to be a good way to operate a BCI system. In some recent studies about MI based BCI systems, low accuracy rate and time consuming are common problems. In this thesis, a novel motor imagery algorithm is proposed to improve the accuracy rate and computational efficiency at the same time. The architecture of many BCI system is quite complex and they involve time consuming processing. The electroencephalography (EEG) signal is the most commonly used inputs for BCI applications but EEG is often contaminated with noise. To overcome such drawbacks, in this paper we use the common spatial pattern (CSP) for feature extraction from EEG and the linear discriminant analysis (LDA) for motor imagery classification. In this study, CSP and LDA have been used to reduce the artifact and classify Mi-based EEG signal. We have used two-level cross validation scheme to determine the subject specific best time window and number of CSP features. We have compared the performance of our system with BCI competition results. This novel algorithm with high accuracy rate and efficiency can be applied to real time BCI system in real-life applications.

Recognition of motor imagery tasks for BCI using CSP and chaotic PSO twin SVM

A brain-computer interface (BCI) allows the user to control a device or software with brain activity. Many BCIs rely on dynamics of brain oscillations related to semantic and motor imaginary tasks in the electroencephalogram (EEG) and magnetoencephalography (MEG). Decoding brain activity of corresponding high-level tasks may lead to an independent and intuitively controlled BCI. Most of today’s BCI research focuses on analyzing EEG and MEG which provide only limited signal-to-noise ratio. Derived electrocorticographic (ECoG) signals allow the investigation of spatially highly focused task-related activation within the high-gamma frequency band, making the discrimination of individual finger movements or complex grasping tasks possible. Common spatial patterns (CSPs) are commonly used for BCI systems and provide a powerful tool for feature optimization and dimensionality reduction. This work focused on the discrimination of (i) three complex hand movements as well as (ii) hand movement and idle state. Two subjects S1 and S2 performed single “open,” “peace,” and “fist” hand poses in multiple trials and (iii) one subject S3 controlled a humanoid in the remote place. Signals in the high-gamma frequency range between 100 and 500 Hz were spatially filtered based on a CSP algorithm for (i), (ii), and (iii). Additionally, a manual feature selection approach was tested for (i). A multi-class linear discriminant analysis (LDA) showed for (i) an error rate of 13.89 %/7.22 % and 18.42 %/1.17 % for S1 and S2 using manually/CSP selected features, where for (ii) a two-class LDA leads to a classification error of 13.39 % and 2.33 % for S1 and S2, respectively. For motor imaginary to remotely control the humanoid, (iii) S3 was able to perform such control over four sessions: three of those were performed consecutively over 1 day and the last one was performed 2 days afterward. After each session, the performance of the classifier improved, reaching about 90 % in the end. This experiment showed that ECoG-based motor imagery performed well despite a short training period, providing future possibility for MEG-based BCI with higher sensitivity than present MEG sensors.

Current Brain Computer Interface (BCI) systems are still not commercialized due to their insufficient accuracies. Although Common Spatial Pattern (CSP) is an effective method for BCI applications, it does not consider the channels' co-activation information. This study is aimed at modifying CSP method by incorporating synchronization of channels in the CSP formula and then passes the values through a nonlinear kernel function to enhance the discrimination rate between the left and right imagery movements. Inserting the synchronization of every two channels into the kernel CSP formula is performed in two different ways. Experimental results on a set of EEG signals belonged to three subjects for discrimination of left and right hand imagery movements reveal that the proposed kernel synchronous CSP method outperformed the standard CSP, synchronous CSP and kernel CSP methods for all subjects.

Brain-computer interfaces (BCIs) were initially created to help individuals with disabilities control devices and communicate without muscle movement. Today, BCIs are used for prosthetic control, cognitive enhancement, and neurological rehabilitation. The BCI system depends on analyzing electroencephalogram (EEG) signals captured from the brain. Decoding these EEG signals is a complex process that combines multiple algorithms to extract meaningful information from these intricate and noisy signals. One of the most popular techniques is the Common Spatial Patterns (CSP), which helps preserve useful and sensitive information. This paper presents an optimized extension of the CSP model for extracting EEG data features in a multiclass setting using Riemannian geometry-based weighting. The use of weighting based on Riemannian geometry enhances the robustness of covariance matrix computation, thereby decreasing the influence of noise that can significantly distort the mean of covariance matrices in the traditional CSP method. The proposed approach is also extended by the integration of a multi-band filter bank, providing a more detailed examination of EEG signals. Three classifiers, Linear Discriminant Analysis (LDA), Random Forest Classifier (RFC), and Multi-Layer Perceptron (MLP), are employed to differentiate features across four motor imagery tasks. LDA achieves an accuracy of 80.40%, while MLP and RFC reach 80.02% and 80.90%, respectively. The results obtained using a majority vote combining the decisions of the three classifiers are 81.83% for accuracy and Recall, 82.74% for precision, and 81.87% for F1-score. The proposed architecture is evaluated using the BCI Competition IV set 2a dataset, proving its effectiveness in EEG signal classification for BCI applications.

BackgroundOne of the most promising applications for electroencephalogram (EEG)-based brain computer interface is for stroke rehabilitation. Implemented as a standalone motor imagery (MI) training system or as part of a rehabilitation robotic system, many studies have shown benefits of using them to restore motor control in stroke patients. Hand movements have widely been chosen as MI tasks. Although potentially more challenging to analyze, wrist and forearm movement such as wrist flexion/extension and forearm pronation/supination should also be considered for MI tasks, because these movements are part of the main exercises given to patients in conventional stroke rehabilitation. This paper will evaluate the effectiveness of such movements for MI tasks.MethodsThree hand and wrist movement tasks which were hand opening/closing, wrist flexion/extension and forearm pronation/supination were chosen as motor imagery tasks for both hands. Eleven subjects participated in the experiment. All of them completed hand opening/closing task session. Ten subjects completed two MI task sessions which were hand opening/closing and wrist flexion/extension. Five subjects completed all three MI tasks sessions. Each MI task comprised 8 sessions spanning a 4 weeks period. For classification, feature extraction based on common spatial pattern (CSP) algorithm was used. Two types were implemented, one with conventional CSP (termed WB) and one with an increase number of features achieved by filtering EEG data into five bands (termed FB). Classification was done by linear discriminant analysis (LDA) and support vector machine (SVM).ResultsEight-fold cross validation was applied on EEG data. LDA and SVM gave comparable classification accuracy. FB achieved significantly higher classification accuracy compared to WB. The accuracy of classifying wrist flexion/extension task were higher than that of classifying hand opening/closing task in all subjects. Classifying forearm pronation/supination task achieved higher accuracy than classifying hand opening/closing task in most subjects but achieved lower accuracy than classifying wrist flexion/extension task in all subjects. Significant improvements of classification accuracy were found in nine subjects when considering individual sessions of experiments of all MI tasks. The results of classifying hand opening/closing task and wrist flexion/extension task were comparable to the results of classifying hand opening/closing task and forearm pronation/supination task. Classification accuracy of wrist flexion/extension task and forearm pronation/supination task was lower than those of hand movement tasks and wrist movement tasks.ConclusionHigh classification accuracy of the three MI tasks support the possibility of using EEG-based stroke rehabilitation system with these movements. Either LDA or SVM can equally be chosen as a classifier since the difference of their accuracies is not statistically significant. Significantly higher classification accuracy made FB more suitable for classifying MI task compared to WB. More training sessions could potentially lead to better accuracy as evident in most subjects in this experiment.

Over the past decade, many laboratories have begun to explore brain-computer interface (BCI) technology as a radically new communication option. BCI can help users send messages and commands to the external world without using their brain's normal output channels or muscles. The central element in each BCI system is to find a reliable method to detect the specific feature patterns extracted from the raw brain signals, and then translate it into usable control signals. In this paper, we introduce our approach to detect N170 component of the event-related brain potential (ERP) based on its spatiotemporal patterns in single-trial EEG signals. Common spatial pattern (CSP) method and machine-learning technique support vector machine (SVM) are adopted for N170 feature extraction and translation, i.e. they convert electrophysiological input from the user into on-off signal to control external devices. Our results indicate that the CSP can effectively extract discriminatory information, and SVM has an efficient performance for N170 classification. Comparing to several other methods, high performances of our framework show that the temporal and spatial features of N170 are very stable and it is promising for new type BCI applications.

In this paper, an ECG signal classification method is presented to classify multi-lead ECG signals into normal and abnormal classes using Common Spatial Pattern (CSP) as the feature extraction algorithm. The method consists of two main stages: CSP-based feature extraction and classification. After segmenting the signal into non-overlapping segments, each segment is projected onto a CSP projection matrix to extract the training and testing feature vectors. These vectors are used in the classification stage. In this study, three classifiers — linear discriminant analysis (LDA), naive Bayes (NB), and support vector machine (SVM)—were used. The proposed approach was evaluated using 104 subjects' recordings (52 normal and 52 abnormal) from the Physikalisch-Technische Bundesanstalt (PTB) dataset. The three classifiers achieved accuracy rates of 80.65%, 84%, and 100%, respectively.

Traditional common spatial pattern (CSP) algorithms for upper limb neural rehabilitation face inherent challenges of overlapping cortical representations and frequency sensitivity, which hinder the decoding performance of motor imagery (MI) electroencephalogram (EEG) signals. To address these issues, this study adopts an improved discriminative filter bank CSP (DFBCSP) framework and applies it to the decoding of upper limb MI-EEG signals, achieving remarkable classification performance. EEG data were acquired from sixteen participants performing two-class (left upper limb flexion-extension vs. relaxing) and three-class (left upper limb flexion vs. right upper limb extension vs. relaxing) MI tasks. The acquired EEG data were then decomposed into nine distinct sub-bands, followed by the adoption of a mutual information-based feature selection strategy to optimize the feature sets. These optimized feature sets were subsequently input into three classification models, namely multilayer perceptron (MLP), support vector machine (SVM), and linear discriminant analysis (LDA), for MI task classification. Experimental results demonstrate that the DFBCSP + MLP method significantly outperforms the traditional CSP approach. Specifically, it achieves an accuracy of 94.83% (Kappa coefficient: 0.890) in two-class MI tasks and 86.20% (Kappa coefficient: 0.775) in three-class MI tasks. The DFBCSP + MLP framework exhibits high robustness and provides a potential technical framework and theoretical basis for future research on the rehabilitation of patients with upper limb motor dysfunction.

Here, we present a state-of-the-art review of the research performed on the brain-computer interface (BCI) technologies with a focus on signal processing approaches. BCI can be divided into three main components: signal acquisition, signal processing, and effector device. The signal acquisition component is generally divided into two categories: noninvasive and invasive. For noninvasive, this review focuses on electroencephalogram. For the invasive, the review includes electrocorticography, local field potentials, multiple-unit activity, and single-unit action potentials. Signal processing techniques reviewed are divided into time-frequency methods such as Fourier transform, autoregressive models, wavelets, and Kalman filter and spatiotemporal techniques such as Laplacian filter and common spatial patterns. Additionally, various signal feature classification algorithms are discussed such as linear discriminant analysis, support vector machines, artificial neural networks, and Bayesian classifiers. The article ends with a discussion of challenges facing BCI and concluding remarks on the future of the technology.

Effective common spatial pattern (CSP) feature extraction for motor-imagery (MI) EEG recordings usually depends on the filter band selection to a large extent. However, the most proper filter band can hardly be determined manually due to its subject-specific property. This study introduces a sparse support vector machine (SSVM) approach to implement simultaneous CSP feature selection and classification for MI-based brain–computer interface (BCI). In SSVM, CSP features are first extracted on multiple signals that are filtered from raw EEG data at a set of overlapping subbands. SVM with l 1-norm regularization is then proposed to classify MI tasks with automatic selection of filter bands giving the significant CSP features. The effectiveness of SSVM for MI classification is demonstrated on the BCI Competition III dataset IVa, in comparison with several other competing methods. Experimental results indicate that the proposed SSVM method is promising for development of an improved MI-based BCI.

The common spatial pattern (CSP) is a popular method in feature extraction for motor imagery (MI) electroencephalogram (EEG) classification in brain-computer interface (BCI) systems. However, combining temporal and spectral information in the CSP-based spatial features is still a challenging issue, which greatly affects the performance of MI-based BCI systems. Here, we propose a novel circulant singular spectrum analysis embedded CSP (CiSSA-CSP) method for learning the optimal time-frequency-spatial features to improve the MI classification accuracy. Specifically, raw EEG data are first segmented into multiple time segments and spectrum-specific sub-bands are further derived by CiSSA from each time segment in a set of non-overlapping filter bands. CSP features extracted from all time-frequency segments contain more sufficient time-frequency-spatial information. An experimental study was implemented on the publicly available EEG dataset (BCI Competition III dataset IVa) and a self-collected experimental EEG dataset to validate the effectiveness of the CiSSA-CSP method. Experimental results demonstrate that discriminative and robust features are extracted effectively. Compared with several state-of-the-art methods, the proposed method exhibited optimal accuracies of 96.6% and 95.2% on the public and experimental datasets, respectively, which confirms that it is a promising method for improving the performance of MI-based BCIs.

Research on brain machine interface (BMI) has been developed very fast in recent years. Numerous feature extraction methods have successfully been applied to electroencephalogram (EEG) classification in various experiments. However, little effort has been spent on EEG based BMI systems regarding familiarity of human faces cognition. In this work, we have implemented and compared the classification performances of four common feature extraction methods, namely, common spatial pattern, principal component analysis, wavelet transform and interval features. High resolution EEG signals were collected from fifteen healthy subjects stimulated by equal number of familiar and novel faces. Principal component analysis outperforms other methods with average classification accuracy reaching 94.2% leading to possible real life applications. Our findings thereby may contribute to the BMI systems for face recognition.

Depression or Major Depressive Disorder (MDD) is a psychiatric disorder. It is the major contributor to overall global burden of disease. Any deterioration in brain functioning is reflected in Electroencephalogram (EEG) signals. EEG signals are highly complex, nonstationary and nonlinear. So, it is very difficult to analyze visually and identify changes in the waveform in order to classify MDD and normal subjects. Thus, computerized quantitative EEG is used for the analysis of signals. Support Vector Machine (SVM) using band power feature reported an accuracy of 98.33% and using Kernel Eigen-Filter-Bank Common Spatial Patterns (KEFB-CSP) gave an accuracy of 91.67% [1, 2]. Logistic Regression (LR) using band power feature reported an accuracy of 98.33%, using 4 nonlinear features combination provided an accuracy of 90%, using wavelet transform provided an accuracy of 87.5% and using only alpha power gave an accuracy of 73.3% [1, 3, 4]. Naive Bayesian (NB) using band power feature provided an accuracy of 96.8% [1]. Artificial Neural Network using Relative Wavelet Energy (RWE) reported an accuracy of 98.11%, using power spectrum feature gave accuracy of 84% and using Lep–Ziv complexity accuracy of 60–80% was reported [5, 6, 7]. Linear Discriminant Analysis (LDA) reported an accuracy of 91.2% using SASI (Spectral Asymmetry Index) and DFA (Detrended Fluctuation Analysis) [8]. Decision Tree provided an accuracy of 80% using EEG band power as feature [9]. The study reveals that, in general, high classification accuracy is achieved by SVM, LR and ANN and highest classification accuracy of 98.33% is achieved by SVM. Highest accuracy is achieved by SVM because it is more robust and computationally more efficient due to maximal margin gap between separating hyper planes and kernel trick. The study gives some ideas which could be helpful for guiding and improving future researches. Since linear and nonlinear method for feature extraction are both equally efficient. So any of the linear/nonlinear feature can be used. For feature selection and reduction, Genetic Algorithm (GA), Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) can be used. Since SVM, LR and ANN give high classification accuracy and any of them can be used or any hybrid technique like GA-SVM, GA-ANN can be used. This chapter compares various EEG signal analysis techniques, compares their accuracy and methodology used and finally recommends the most suitable technique based on the accuracy for detection of depression. The chapter also summarizes some of the key finding related to EEG features based on present state of art. These results could be helpful for guiding and improving the future research in this area.