Regularized CSP Research Articles

Improved empirical mode decomposition bagging RCSP combined with Fisher discriminant method for EEG feature extraction and classification

BackgroundTraditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New methodTo solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. ResultsThe improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. ConclusionsThe proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.

Brain–Computer-Interface-Based Smart-Home Interface by Leveraging Motor Imagery Signals

In this work, we propose a brain–computer-interface (BCI)-based smart-home interface which leverages motor imagery (MI) signals to operate home devices in real-time. The idea behind MI-BCI is that different types of MI activities will activate various brain regions. Therefore, after recording the user’s electroencephalogram (EEG) data, two approaches, i.e., Regularized Common Spatial Pattern (RCSP) and Linear Discriminant Analysis (LDA), analyze these data to classify users’ imagined tasks. In such a way, the user can perform the intended action. In the proposed framework, EEG signals were recorded by using the EMOTIV helmet and OpenVibe, a free and open-source platform that has been utilized for EEG signal feature extraction and classification. After being classified, such signals are then converted into control commands, and the open communication protocol for building automation KNX (“Konnex”) is proposed for the tasks’ execution, i.e., the regulation of two switching devices. The experimental results from the training and testing stages provide evidence of the effectiveness of the users’ intentions classification, which has subsequently been used to operate the proposed home automation system, allowing users to operate two light bulbs.

A logistic binary Jaya optimization-based channel selection scheme for motor-imagery classification in brain-computer interface

BCI systems use motor imagery to allow users to control external devices through their brain activity. They extract neural signals from the brain using a large number of EEG channels. However, high-dimensional data from multichannel BCI systems increases the computational burden, leading to slower processing and higher costs. In this study, we proposed a Logistic S-shaped Binary Jaya Optimization Algorithm (LS-BJOA), which combines a logistic map with the Jaya optimization algorithm to alleviate the computational burden caused by many channels. The logistic map introduces stochasticity to better simulate the chaotic behavior of brain signals and improve predictive accuracy. Our method initializes a set of three electrodes as a candidate solution and subsequently determines the most relevant channels iteratively. We used a bi-objective fitness function to evaluate the significance of the selected channels, which involves maximizing classification accuracy and minimizing the length of the channel subset. Initially, a fifth-order bandpass filter with Independent Component Analysis (ICA) was applied to filter MI signals and artifacts reduction, respectively. The Regularized Common Spatial Pattern (RCSP) was used to extract spatiotemporal features from the selected channels. Finally, the three classifiers: (1) Support Vector Machine (SVM), (2) Naïve Bayes (NB), and (3) Linear Discriminant Analysis (LDA) were used to determine maximum classification accuracy. The experiment is validated on three public EEG datasets (BCI Competition IV- 2008 – IIA, BCI Competition IV- dataset 1, BCI competition III – dataset IVa). Our method achieved superior classification accuracy (83.59%, 82.09%, and 89.02% on datasets 1, 2, and 3 respectively) with fewer channels than baseline methods. Additionally, computation time was significantly reduced without compromising accuracy. Topographical mapping revealed frontal lobe involvement in MI tasks during physical activities. Topographical mapping of the selected channels showed that the frontal lobe executes various MI tasks during physical activities.

Tensor decomposition-based channel selection for motor imagery-based brain-computer interfaces.

The number of electrode channels in a brain-computer interface (BCI) affects not only its classification performance, but also its convenience in practical applications. Despite many studies on channel selection in motor imagery (MI)-based BCI systems, they consist in matrix analysis of EEG signals, which inevitably loses the interactive information among multiple domains such as space, time and frequency. In this paper, a tensor decomposition-based channel selection (TCS) method is employed for MI BCIs. A three-way tensor is yielded by wavelet transform of a single-trial EEG signal and decomposed into three factor matrices by a regularized canonical polyadic decomposition (CPD). The channel factor matrix is used for channel selection and the important channels are selected by calculating the correlation between channels. Regularized common spatial pattern (RCSP) is employed for feature extraction and support vector machine (SVM) for classification. The proposed TCS-RCSP algorithm was evaluated on three BCI data sets and compared with the RCSP with all channels (AC-RCSP) and the RCSP with selected channels by correlation-based channel selection method (CCS-RCSP). The results indicate that TCS-RCSP achieved significantly better overall accuracy than AC-RCSP (94.4% vs. 86.3%) with 0.01 and CCS-RCSP (94.4% vs. 90.2%) with 0.05, proving the efficacy of the proposed algorithm for classifying MI tasks.

High accuracy decoding of motor imagery directions from EEG-based brain computer interface using filter bank spatially regularised common spatial pattern method

One of the important requirements of a practical Brain Computer Interface (BCI) system is the ability to establish multiple control commands corresponding to different kinematics of motor imagery. Most of the previous BCI-based motor imagery studies in literature focus on classifying left vs. right hand motor imagery from electroencephalogram (EEG) signals. Very few studies have reported decoding imagined hand movement kinematics from EEG-based BCI. The present study decodes the left vs. right directional information from the Motor Imagery (MI) of dominant hand movement using EEG-based BCI.The proposed method employs common spatial pattern (CSP) and its variants as features to decode imagined (motor imagery) bidirectional hand movements. The direction discriminability of these features are enhanced using the regularisation technique. Spatial regularisation based on electrode positions is also incorporated for comparison. The regularisation methods are applied on overlapped frequency bands and the results are compared. The classifications of extracted features are done using 5-fold cross-validation and Linear Discriminant Analysis (LDA). The study on 15 healthy subjects shows that filter bank-based spatially regularized CSP method (FBSRCSP) offers the highest average classification accuracy of 90% for decoding bidirectional motor imagery of hand movement. This is a substantial improvement in classification accuracy by 26.3% compared to the best method reported in literature on the same dataset.

Correlation-based common spatial pattern (CCSP): A novel extension of CSP for classification of motor imagery signal.

Common spatial pattern (CSP) is shown to be an effective pre-processing algorithm in order to discriminate different classes of motor-based EEG signals by obtaining suitable spatial filters. The performance of these filters can be improved by regularized CSP, in which available prior information is added in terms of regularization terms into the objective function of conventional CSP. Variety of prior information can be used in this way. In this paper, we used time correlation between different classes of EEG signal as the prior information, which is clarified similarity between different classes of signal for regularizing CSP. Furthermore, the proposed objective function can be easily extended to more than two-class problems. We used three different standard datasets to evaluate the performance of the proposed method. Correlation-based CSP (CCSP) outperformed original CSP as well as the existing regularized CSP, Principle Component Cnalysis (PCA) and Fisher Discriminate Analysis (FDA) in both two-class and multi-class scenarios. The simulation results showed that the proposed method outperformed conventional CSP by 6.9% in 2-class and 2.23% in multi-class problem in term of mean classification accuracy.

An EEG channel selection method for motor imagery based brain–computer interface and neurofeedback using Granger causality

Motor imagery (MI) brain–computer interface (BCI) and neurofeedback (NF) with electroencephalogram (EEG) signals are commonly used for motor function improvement in healthy subjects and to restore neurological functions in stroke patients. Generally, in order to decrease noisy and redundant information in unrelated EEG channels, channel selection methods are used which provide feasible BCI and NF implementations with better performances. Our assumption is that there are causal interactions between the channels of EEG signal in MI tasks that are repeated in different trials of a BCI and NF experiment. Therefore, a novel method for EEG channel selection is proposed which is based on Granger causality (GC) analysis. Additionally, the machine-learning approach is used to cluster independent component analysis (ICA) components of the EEG signal into artifact and normal EEG clusters. After channel selection, using the common spatial pattern (CSP) and regularized CSP (RCSP), features are extracted and with the k-nearest neighbor (k-NN), support vector machine (SVM) and linear discriminant analysis (LDA) classifiers, MI tasks are classified into left and right hand MI. The goal of this study is to achieve a method resulting in lower EEG channels with higher classification performance in MI-based BCI and NF by causal constraint. The proposed method based on GC, with only eight selected channels, results in 93.03% accuracy, 92.93% sensitivity, and 93.12% specificity, with RCSP feature extractor and best classifier for each subject, after being applied on Physionet MI dataset, which is increased by 3.95%, 3.73%, and 4.13%, in comparison with correlation-based channel selection method.

Wavelet Entropy-Based Inter-subject Associative Cortical Source Localization for Sensorimotor BCI.

We propose event-related cortical sources estimation from subject-independent electroencephalography (EEG) recordings for motor imagery brain computer interface (BCI). By using wavelet-based maximum entropy on the mean (wMEM), task-specific EEG channels are selected to predict right hand and right foot sensorimotor tasks, employing common spatial pattern (CSP) and regularized common spatial pattern (RCSP). EEG from five healthy individuals (Dataset IVa, BCI Competition III) were evaluated by a cross-subject paradigm. Prediction performance was evaluated via a two-layer feed-forward neural network, where the classifier was trained and tested by data from two subjects independently. On average, the overall mean prediction accuracies obtained using all 118 channels are (55.98±6.53) and (71.20±5.32) in cases of CSP and RCSP, respectively, which are slightly lower than the accuracies obtained using only the selected channels, i.e., (58.95±6.90) and (71.41±6.65), respectively. The highest mean prediction accuracy achieved for a specific subject pair by using selected EEG channels was on average (90.36±5.59) and outperformed that achieved by using all available channels (86.07 ± 10.71). Spatially projected cortical sources approximated using wMEM may be useful for capturing inter-subject associative sensorimotor brain dynamics and pave the way toward an enhanced subject-independent BCI.

Correlation-based channel selection and regularized feature optimization for MI-based BCI

Multi-channel EEG data are usually necessary for spatial pattern identification in motor imagery (MI)-based brain computer interfaces (BCIs). To some extent, signals from some channels containing redundant information and noise may degrade BCI performance. We assume that the channels related to MI should contain common information when participants are executing the MI tasks. Based on this hypothesis, a correlation-based channel selection (CCS) method is proposed to select the channels that contained more correlated information in this study. The aim is to improve the classification performance of MI-based BCIs. Furthermore, a novel regularized common spatial pattern (RCSP) method is used to extract effective features. Finally, a support vector machine (SVM) classifier with the Radial Basis Function (RBF) kernel is trained to accurately identify the MI tasks. An experimental study is implemented on three public EEG datasets (BCI competition IV dataset 1, BCI competition III dataset IVa and BCI competition III dataset IIIa) to validate the effectiveness of the proposed methods. The results show that the CCS algorithm obtained superior classification accuracy (78% versus 56.4% for dataset1, 86.6% versus 76.5% for dataset 2 and 91.3% versus 85.1% for dataset 3) compared to the algorithm using all channels (AC), when CSP is used to extract the features. Furthermore, RCSP could further improve the classification accuracy (81.6% for dataset1, 87.4% for dataset2 and 91.9% for dataset 3), when CCS is used to select the channels.

Transfer Learning Based on Regularized Common Spatial Patterns Using Cosine Similarities of Spatial Filters for Motor-Imagery BCI

In motor-imagery brain–computer interface (BCI), transfer learning based on the framework of regularized common spatial patterns (RCSP) can make full use of the training data derived from other subjects to reduce calibration time for a new subject. Covariance matrices are commonly used to estimate the difference between subjects. However, the classification performances vary greatly depending on different assumptions of the distribution of covariance matrices. Therefore, to directly observe the variations of the target subject’s features after transferring, we neglect the distribution of covariance matrices and instead compare cosine similarities of spatial filters between the target subject and the composite subject whose data comes from the target subject and a source subject. Two RCSP algorithms based on cosine measure are proposed to use the samples of all source subjects and most useful source subjects, respectively. Experiments on one public data set from BCI competition show that our proposed approaches significantly improve the classification performances compared to the conventional CSP algorithm in almost every case, based on a small training set.

Cognitive Imagery Classification of EEG Signals using CSP-based Feature Selection Method

This paper presents a novel approach of spectral feature selection using spatial filters for the classification of four cognitive imagery tasks. The input dataset consists of electroencephalogram (EEG) signals acquired through a commercial wireless headset. The spectral features included mel frequency (MF) components extracted from the low frequency bands of EEG signal. A spatial projection filter was used for the selection of the most relevant features before classification. The popular method of multiclass common spatial pattern (CSP) and regularized CSP (RCSP) are investigated for a subject dependent (intra) and subject independent (inter) generation of spatial projection filter, respectively. Based upon this, present study used two different algorithmic approaches namely MF-CSP and MF-RCSP. The developed algorithm successfully classified four imagery actions with the reported prediction accuracy of 46.23% and 64.01% and standard deviation of 11.60% and 8.67% for MF-CSP and MF-RCSP, respectively.

Reactive frequency band based movement imagery classification

This paper proposes a novel movement imagery feature extraction algorithm based on reactive frequency band (RFB) of user using electroencephalogram (EEG) signal for brain–computer interface (BCI). Based on the asymmetric nature of the human brain, the authors propose the algorithm for the feature extraction from EEG data related to the imagination of hand and leg movement. In this proposed algorithm, the RFB has been estimated by applying time–frequency series (TFS) based method over the training dataset. Further, based on this RFB, the TFS based feature extraction method has been applied to the testing dataset. An asymmetry coefficient based on Hjorth parameter as a feature extracted for each frequency bin obtained through the TFS, further subjected to support vector machine (SVM) classifier for their classification. The effectiveness of the proposed RFB estimation method of EEG signal is validated by self-generated artificial sine wave signal. The movement imagery classification method has been validated through the three open source BCI competition datasets, such as single subject, five subjects and nine subjects movement imagery dataset. The proposed method of EEG signal processing outperforms the different well established conventional methods of EEG signal processing like discriminative frequency band common spatial pattern (DFBCSP), least square support vector machine (LS-SVM), regularized common spatial pattern (R-CSP) etc. over the BCI competition II, III and IV dataset.

Filter Bank Regularized Common Spatial Pattern Ensemble for Small Sample Motor Imagery Classification.

For the last few years, many feature extraction methods have been proposed based on biological signals. Among these, the brain signals have the advantage that they can be obtained, even by people with peripheral nervous system damage. Motor imagery electroencephalograms (EEG) are inexpensive to measure, offer a high temporal resolution, and are intuitive. Therefore, these have received a significant amount of attention in various fields, including signal processing, cognitive science, and medicine. The common spatial pattern (CSP) algorithm is a useful method for feature extraction from motor imagery EEG. However, performance degradation occurs in a small-sample setting (SSS), because the CSP depends on sample-based covariance. Since the active frequency range is different for each subject, it is also inconvenient to set the frequency range to be different every time. In this paper, we propose the feature extraction method based on a filter bank to solve these problems. The proposed method consists of five steps. First, motor imagery EEG is divided by a using filter bank. Second, the regularized CSP (R-CSP) is applied to the divided EEG. Third, we select the features according to mutual information based on the individual feature algorithm. Fourth, parameter sets are selected for the ensemble. Finally, we classify using ensemble based on features. The brain-computer interface competition III data set IVa is used to evaluate the performance of the proposed method. The proposed method improves the mean classification accuracy by 12.34%, 11.57%, 9%, 4.95%, and 4.47% compared with CSP, SR-CSP, R-CSP, filter bank CSP (FBCSP), and SR-FBCSP. Compared with the filter bank R-CSP ( , ), which is a parameter selection version of the proposed method, the classification accuracy is improved by 3.49%. In particular, the proposed method shows a large improvement in performance in the SSS.

Small Sample Setting and Frequency Band Selection Problem Solving Using Subband Regularized Common Spatial Pattern

For the last few years, motor imagery electroencephalogram (EEG)-based brain-computer interface (BCI) systems have received the significant amount of attention in various areas, including medicine and engineering. The common spatial pattern (CSP) algorithm is the most commonly used method to extract features from motor imagery EEG. However, the CSP algorithm has limited applicability in small-sample setting (SSS) situations because these rely on a covariance matrix. In addition, the large differences in performance depend on the frequency bands that are being used. To address these problems, 4–40 Hz band EEG signals are divided into nine subbands, and regularized CSP (R-CSP) is applied to individual subbands. Fisher’s linear discriminant (FLD) is applied to the features of R-CSP extracted from individual subbands, and the results obtained through the foregoing are connected for all subbands to make an FLD score vector. Furthermore, principal component analysis is applied to use the FLD score vectors as the inputs of the classifier least square support vector machine. The proposed method yielded a classification accuracy of 86.61%, 98.21%, 63.78%, 87.05%, and 77.78% from five subjects (“ $aa$ ”, “ $l$ ”, “ $av$ ”, “ $aw$ ”, and “ $ay$ ”, respectively) for BCI competition III data set IVa by using 18 channels in the vicinity of the motor area of the cerebral cortex. The proposed method offers particularly excellent performance in SSS situations.

Identification of Anisomerous Motor Imagery EEG Signals Based on Complex Algorithms.

Motor imagery (MI) electroencephalograph (EEG) signals are widely applied in brain-computer interface (BCI). However, classified MI states are limited, and their classification accuracy rates are low because of the characteristics of nonlinearity and nonstationarity. This study proposes a novel MI pattern recognition system that is based on complex algorithms for classifying MI EEG signals. In electrooculogram (EOG) artifact preprocessing, band-pass filtering is performed to obtain the frequency band of MI-related signals, and then, canonical correlation analysis (CCA) combined with wavelet threshold denoising (WTD) is used for EOG artifact preprocessing. We propose a regularized common spatial pattern (R-CSP) algorithm for EEG feature extraction by incorporating the principle of generic learning. A new classifier combining the K-nearest neighbor (KNN) and support vector machine (SVM) approaches is used to classify four anisomerous states, namely, imaginary movements with the left hand, right foot, and right shoulder and the resting state. The highest classification accuracy rate is 92.5%, and the average classification accuracy rate is 87%. The proposed complex algorithm identification method can significantly improve the identification rate of the minority samples and the overall classification performance.

Regularized Common Spatial Pattern with Incomplete Generic Learning for EEG Classification in Small Sample Setting

Common spatial pattern (CSP) is based on sample covariance matrix estimation, whose estimation accuracy is severely overfit with small training sets. To address the drawback, the regularized CSP (R-CSP) was proposed that adds regularization information into the CSP learning process. In the algorithm, all samples of each generic subject were used for training sample covariance matrices. When only a part of the samples of each generic subject are allowed as generic training set, this R-CSP algorithm wouldn’t work. To solve this problem, an improved method is proposed in this paper. The new algorithm was applied to a brain-computer interface (BCI) data set containing five subjects and a mean improvement of 2.5% in classification rate was achieved.

Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting

Common spatial pattern (CSP) is a popular algorithm for classifying electroencephalogram (EEG) signals in the context of brain-computer interfaces (BCIs). This paper presents a regularization and aggregation technique for CSP in a small-sample setting (SSS). Conventional CSP is based on a sample-based covariance-matrix estimation. Hence, its performance in EEG classification deteriorates if the number of training samples is small. To address this concern, a regularized CSP (R-CSP) algorithm is proposed, where the covariance-matrix estimation is regularized by two parameters to lower the estimation variance while reducing the estimation bias. To tackle the problem of regularization parameter determination, R-CSP with aggregation (R-CSP-A) is further proposed, where a number of R-CSPs are aggregated to give an ensemble-based solution. The proposed algorithm is evaluated on data set IVa of BCI Competition III against four other competing algorithms. Experiments show that R-CSP-A significantly outperforms the other methods in average classification performance in three sets of experiments across various testing scenarios, with particular superiority in SSS.

Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms

One of the most popular feature extraction algorithms for brain-computer interfaces (BCI) is common spatial patterns (CSPs). Despite its known efficiency and widespread use, CSP is also known to be very sensitive to noise and prone to overfitting. To address this issue, it has been recently proposed to regularize CSP. In this paper, we present a simple and unifying theoretical framework to design such a regularized CSP (RCSP). We then present a review of existing RCSP algorithms and describe how to cast them in this framework. We also propose four new RCSP algorithms. Finally, we compare the performances of 11 different RCSP (including the four new ones and the original CSP), on electroencephalography data from 17 subjects, from BCI competition datasets. Results showed that the best RCSP methods can outperform CSP by nearly 10% in median classification accuracy and lead to more neurophysiologically relevant spatial filters. They also enable us to perform efficient subject-to-subject transfer. Overall, the best RCSP algorithms were CSP with Tikhonov regularization and weighted Tikhonov regularization, both proposed in this paper.