Feature Extraction Of EEG Signals Research Articles

Using Deep Learning for Human Computer Interface via Electroencephalography

<table class="Heading1Char" width="593" border="0" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="387"><p>In this paper, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised and unsupervised machine learning models, for the EEG motor imagery classification are identified. Brain Computer Interfaces are becoming the next generation controllers not only in the medical devices for disabled individuals but also in the gaming and entertainment industries. In order to build an effective Brain Computer Interface, it is important to have robust signal processing and machine learning modules which operate on the EEG signals and estimate the current thought or intent of the user. Motor Imagery (imaginary hand and leg movements) signals are acquired using the Emotiv EEG headset. The signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques are applied and validated. The performances of various ML techniques are compared and some important observations are reported. Further, Deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is presented and analyzed by performing classification by using the ML techniques. It is shown that hand engineered ‘ad-hoc’ feature extraction techniques are less reliable than the automated (‘Deep Learning’) feature learning techniques. All the findings in this research, can be used by the BCI research community for building motor imagery based BCI applications such as Gaming, Robot control and autonomous vehicles.</p></td></tr></tbody></table>

Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

In spite of recent advances, the interest in extracting knowledge hidden in the electroencephalogram (EEG) signals is rapidly growing, as well as their application in the computational neuroengineering field, such as mobile robot control, wheelchair control, and person identification using brainwaves. The large number of methods for the EEG feature extraction demands a good feature for every task. Digging up the most unique feature would be worthy for the identification of individual using EEG signal. This research presents a novel approach for feature extraction of EEG signal using the empirical mode decomposition (EMD) and information-theoretic method. The EMD technique is applied to decompose an EEG signal into a set of intrinsic mode function. These decomposed signals are of the same length and in the same time domain as the original signal. Hence, the EMD method preserves varying frequencies in time. To measure the performance of the features, we have used hybrid learning for classification where we have selected learning vector quantization neural network with fuzzy algorithm. In order to test the performance of proposed classifier based on fuzzy theory, we have tested classification accuracy of each cognitive task over all participated subjects. The results are compared with the past methods in the literature for feature extraction and classification methods. Results confirm that the proposed features present a satisfactory performance.

Epileptic seizure detection by exploiting temporal correlation of electroencephalogram signals

Electroencephalogram (EEG) has a great potential for diagnosis and treatment of brain disorders like epileptic seizure. Feature extraction and classification of EEG signals is the crucial task to detect the stages of ictal and interictal signals for treatment and precaution of epileptic patients. However, existing seizure and non-seizure feature extraction techniques are not good enough for the classification of ictal and interictal EEG signals considering the non-abruptness phenomena and inconsistency in different brain locations. In this study, the authors present a new approach for feature extraction and classification by exploiting temporal correlation within EEG signals for better seizure detection as any abruptness in the temporal correlation within a signal represents the transition of a phenomenon. In the proposed methods, they divide an EEG signal into a number of epochs and arrange them into two-dimensional matrix and then apply different transformation/decomposition to extract a number of statistical features. These features are then used as an input into LS-SVM to classify them. Experimental results show that the proposed methods outperform the existing state-of-the-art method for better classification in terms of sensitivity, specificity and accuracy of ictal and interictal period of epilepsy for benchmark datasets and different brain locations.

Multi-channel EEG signal feature extraction and pattern recognition on horizontal mental imagination task of 1-D cursor movement for brain computer interface.

Brain computer interfaces (BCIs), based on multi-channel electroencephalogram (EEG) signal processing convert brain signal activities to machine control commands. It provides new communication way with a computer by extracting electroencephalographic activity. This paper, deals with feature extraction and classification of horizontal mental task pattern on 1-D cursor movement from EEG signals. The hemispherical power changes are computed and compared on alpha & beta frequencies and horizontal cursor control extracted with only mental imagination of cursor movements. In the first stage, features are extracted with the well-known average signal power or power difference (alpha and beta) method. Principal component analysis is used for reducing feature dimensions. All features are classified and the mental task patterns are recognized by three neural network classifiers which learning vector quantization, multilayer neural network and probabilistic neural network due to obtaining acceptable good results and using successfully in pattern recognition via k-fold cross validation technique.

Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques.

This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task--Raven's advance progressive metric test and (2) the EEG signals recorded in rest condition--eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98 % by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53-3.06 and 3.06-6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate.

Simultaneous channel and feature selection of fused EEG features based on Sparse Group Lasso.

Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs). Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

Cognitive State Estimation by Effective Feature Extraction and Proper Channel Selection of EEG Signal

This paper presents a cognitive state estimation system focused on some effective feature extraction based on temporal and spectral analysis of electroencephalogram (EEG) signal and the proper channel selection of the BIOPAC automated EEG analysis system. In the proposed approach, different frequency components (i) real value; (ii) imaginary value; (iii) magnitude; (iv) phase angle and (v) power spectral density of the EEG data samples during different mental task performed to assess seven types of human cognitive states — relax, mental task, memory related task, motor action, pleasant, fear and enjoying music on the three channels of BIOPAC EEG data acquisition system — EEG, Alpha and Alpha RMS signal. Also the time and time-frequency-based features were extracted to compare the performance of the system. After feature extraction, the channel efficacy is evaluated by support vector machine (SVM) based on the classification rate in different cognitive states. From the experimental results and classification accuracy, it is determined that the overall accuracy for alpha channel shows much improved result for power spectral density than the other frequency based features and other channels. The classification rate is 69.17% for alpha channel whereas for EEG and alpha RMS channel it is found 47.22% and 32.21%, respectively. For statistical analysis standard deviation shows better result for alpha channel and it is found 65.4%. The time-frequency analysis shows much improved result for alpha channel also. For the mean value of DWT coefficients the accuracy is highest and it is 81.3%. Besides the classification accuracy, SVM shows better performance in compare with kNN classifier.

An Improved EEG Signal Classification Using Neural Network with the Consequence of ICA and STFT

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

EEG Feature Extraction Based on Wavelet Decomposition

Wavelet decomposition is a commonly used tool, signal analysis using the wavelet decomposition, can put the source according to their demand is decomposed into different frequency signals, so as to provide convenience for the feature extraction and identification in this paper, the EEG signals, using the theory of wavelet decomposition is calculated, look from the calculation results, the wavelet decomposition can be used for feature extraction of EEG signals as well.

Feature Extraction and Classification for EEG Signals of Motor Imagery in Brain-Computer Interface

Feature Extraction and Classification for EEG Signals of Motor Imagery in Brain-Computer Interface

Research on Heuristic Feature Extraction and Classification of EEG Signal Based on BCI Data Set

In this study, an EEG signal classification framework was proposed. The framework contained three feature extraction methods refer to optimization strategy. Firstly, we selected optimal electrodes based on the single electrode classification performance and combined all the optimal electrodes’ data as the feature. Then, we discussed the contribution of each time span of EEG signals for each electrode and joined all the optimal time spans’ data together to be used for classifying. In addition, we further selected useful information from original data based on genetic algorithm. Finally, the performances were evaluated by Bayes and SVM classifiers on BCI 2003 Competition data set Ia. And the accuracy of genetic algorithm has reached 91.81%. The experimental results show that our methods offer the better performance for reliable classification of the EEG signal.

Improved Feature Extraction of Hand Movement EEG Signals based on Independent Component Analysis and Spatial Filter

In brain computer interface (BCI) system, the most important part is classification of human thoughts in order to translate into commands. The more accuracy result in classification the system gets, the more effective BCI system is. To increase the quality of BCI system, we proposed to reduce noise and artifact from the recording data to analyzing data. We used auditory stimuli instead of visual ones to eliminate the eye movement, unwanted visual activation, gaze control. We applied independent component analysis (ICA) algorithm to purify the sources which constructed the raw signals. One of the most famous spatial filter in BCI context is common spatial patterns (CSP), which maximize one class while minimize the other by using covariance matrix. ICA and CSP also do the filter job, as a raw filter and refinement, which increase the classification result of linear discriminant analysis (LDA).

Detection and classification of subject-generated artifacts in EEG signals using autoregressive models

We examine the problem of accurate detection and classification of artifacts in continuous EEG recordings. Manual identification of artifacts, by means of an expert or panel of experts, can be tedious, time-consuming and infeasible for large datasets. We use autoregressive (AR) models for feature extraction and characterization of EEG signals containing several kinds of subject-generated artifacts. AR model parameters are scale-invariant features that can be used to develop models of artifacts across a population. We use a support vector machine (SVM) classifier to discriminate among artifact conditions using the AR model parameters as features. Results indicate reliable classification among several different artifact conditions across subjects (approximately 94%). These results suggest that AR modeling can be a useful tool for discriminating among artifact signals both within and across individuals.

The feature extraction of epileptic EEG signals based on nonlinear prediction

Based on the nonlinear time series prediction，a feature extraction method for epileptic EEG signals using nonlinear prediction is proposed to automatically detect the epileptic EEG from EEG recordings. To reconstruct the phase space，the approach of determining the embedding dimension based on nonlinear predictability is used to determine the embedding dimension of the EEG signals. The experimental results show that the feature extracted with the method based on nonlinear prediction could clearly distinguish the epileptic EEG from the normal EEG，and the proposed nonlinear feature extraction method is fit for the small set time series and is stable to noise.

Comparison of feature selection and classification methods for a brain–computer interface driven by non-motor imagery

The aim of this study was to compare methods for feature extraction and classification of EEG signals for a brain-computer interface (BCI) driven by auditory and spatial navigation imagery. Features were extracted using autoregressive modeling and optimized discrete wavelet transform. The features were selected with exhaustive search, from the combination of features of two and three channels, and with a discriminative measure (r (2)). Moreover, Bayesian classifier and support vector machine (SVM) with Gaussian kernel were compared. The results showed that the two classifiers provided similar classification accuracy. Conversely, the exhaustive search of the optimal combination of features from two and three channels significantly improved performance with respect to using r(2) for channel selection. With features optimally extracted from three channels with optimized scaling filter in the discrete wavelet transform, the classification accuracy was on average 72.2%. Thus, the choice of features had greater impact on performance than the choice of the classifier for discrimination between the two non-motor imagery tasks investigated. The results are relevant for the choice of the translation algorithm for an on-line BCI system based on non-motor imagery.

Validity of Dimensional Complexity Measures of EEG Signals

The measure of dimensional complexity has the potential for feature extraction, modeling and prediction of EEG signals. However, the nonlinear dynamics of neuronal processes is under criticism that EEG signals may have a simpler stochastic description and chaotic dynamical measures of EEG may be spurious or unnecessary. Surrogate-data testing has been propounded to detect nonlinearity and chaos in experimental time series and to differentiate it from linear stochastic processes or colored noises. The surrogate data tests of brain signals (EEG) have produced equivocal results. Therefore, we examine the surrogate testing procedure using numerical data of classical chaotic systems, mixed sine waves, white Gaussian and colored Gaussian noises and typical EEGs. White Gaussian noise and classical chaotic time series are easily discerned by the surrogate-data test. However, a colored Gaussian noise data of low correlation dimensions (D2) or mixed sine waves containing less number of sinusoids show behaviors similar to the low dimensional deterministic chaotic systems. There are significant differences in D2 values between the original and surrogate data sets. The colored Gaussian noise appears linear and stochastic only when there is an increased randomness in its pattern and the signal is high dimensional. Our results clearly indicate that the "surrogate testing" alone may not be a sufficient test for distinguishing colored noises from low dimensional chaos. The EEG time series produce finite correlation dimensions. The surrogate testing of 8 independent realizations of different forms of EEG activities produce significantly different D2 values than the original data sets. Apparently many natural phenomena follow deterministic chaos and as the dimensional complexity of the system increases (D2 > 5) it may approximate a stochastic process. Thus EEG appears unlikely to have originated from a linear system driven by white noise.