Classification Accuracy Of EEG Signals Research Articles

Joint multi-feature extraction and transfer learning in motor imagery brain computer interface

Motor imagery brain computer interface (BCI) systems are considered one of the most crucial paradigms and have received extensive attention from researchers worldwide. However, the non-stationary from subject-to-subject transfer is a substantial challenge for robust BCI operations. To address this issue, this paper proposes a novel approach that integrates joint multi-feature extraction, specifically combining common spatial patterns (CSP) and wavelet packet transforms (WPT), along with transfer learning (TL) in motor imagery BCI systems. This approach leverages the time-frequency characteristics of WPT and the spatial characteristics of CSP while utilizing transfer learning to facilitate EEG identification for target subjects based on knowledge acquired from non-target subjects. Using dataset IVa from BCI Competition III, our proposed approach achieves an impressive average classification accuracy of 93.4%, outperforming five kinds of state-of-the-art approaches. Furthermore, it offers the advantage of enabling the design of various auxiliary problems to learn different aspects of the target problem from unlabeled data through transfer learning, thereby facilitating the implementation of innovative ideas within our proposed approach. Simultaneously, it demonstrates that integrating CSP and WPT while transferring knowledge from other subjects is highly effective in enhancing the average classification accuracy of EEG signals and it provides a novel solution to address subject-to-subject transfer challenges in motor imagery BCI systems.

A motor imagery EEG signal optimized processing algorithm

Feature extraction and classification is a difficult area in motor imagery electroencephalogram (EEG) signal processing. In order to improve the classification accuracy of EEG signals, both a feature extraction method based on the combination of LMD-CSP and a classification algorithm based on the fusion of PSO-SVM are proposed. Firstly, the extended informax ICA algorithm is used to denoise the signal and reduce the influence of noise on the signal. Then, the pre-processed EEG signals are decomposed into multiple Product Function (PF) components by Local Mean Decomposition (LMD), and the most discriminative PF component is selected. Next, feature extraction is carried out from the selected PF components using the Common Space Pattern (CSP). Finally, the obtained features are input into a Support Vector Machine (SVM) classifier improved by Particle Swarm Optimization (PSO) for classification recognition. The experimental results show that compared with the traditional CSP-SVM method, CapsNet method, WPT-CSP+CNN method, FDCSP-SVM method, and EMD-CNN method, the classification accuracy of the proposed method is increased by 26.94 %, 14.9 %, 13.34 %, 8.34 % and 4.04 %, respectively. This further proves the superiority of the proposed method for EEG signal processing technology.

Revised Tunable Q-Factor Wavelet Transform for EEG-Based Epileptic Seizure Detection.

Electroencephalogram (EEG) signals are an essential tool for the detection of epilepsy. Because of the complex time series and frequency features of EEG signals, traditional feature extraction methods have difficulty meeting the requirements of recognition performance. The tunable Q-factor wavelet transform (TQWT), which is a constant-Q transform that is easily invertible and modestly oversampled, has been successfully used for feature extraction of EEG signals. Because the constant-Q is set in advance and cannot be optimized, further applications of the TQWT are restricted. To solve this problem, the revised tunable Q-factor wavelet transform (RTQWT) is proposed in this paper. RTQWT is based on the weighted normalized entropy and overcomes the problems of a nontunable Q-factor and the lack of an optimized tunable criterion. In contrast to the continuous wavelet transform and the raw tunable Q-factor wavelet transform, the wavelet transform corresponding to the revised Q-factor, i.e., RTQWT, is sufficiently better adapted to the nonstationary nature of EEG signals. Therefore, the precise and specific characteristic subspaces obtained can improve the classification accuracy of EEG signals. The classification of the extracted features was performed using the decision tree, linear discriminant, naive Bayes, SVM and KNN classifiers. The performance of the new approach was tested by evaluating the accuracies of five time-frequency distributions: FT, EMD, DWT, CWT and TQWT. The experiments showed that the RTQWT proposed in this paper can be used to extract detailed features more effectively and improve the classification accuracy of EEG signals.

A2FWPO: Anti-aliasing filter based on whale parameter optimization method for feature extraction and recognition of dance motor imagery EEG

The classification accuracy of EEG signals based on traditional machine learning methods is low. Therefore, this paper proposes a new model for the feature extraction and recognition of dance motor imagery EEG, which makes full use of the advantage of anti-aliasing filter based on whale parameter optimization method. The anti-aliasing filter is used for preprocessing, and the filtered signal is extracted by two-dimensional empirical wavelet transform. The extracted feature is input to the robust support matrix machine to complete pattern recognition. In pattern recognition process, an improved whale algorithm is used to dynamically adjust the optimal parameters of individual subjects. Experiments are carried out on two public data sets to verify that anti-aliasing filter-based preprocessing can improve signal feature discrimination. The improved whale algorithm can find the optimal parameters of robust support matrix machine classification for individuals. This presented method can improve the recognition rate of dance motion image. Compared with other advanced methods, the proposed method requires less samples and computing resources, and it is suitable for the practical application of brain-computer interface.

Motor imagery electroencephalogram classification based on sparse spatiotemporal decomposition and channel attention

Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.

The Application of the Gestalt Theory in Music Psychotherapy for Piano.

This paper presents an in-depth study and analysis of the application of the Gestalt theory to music psychotherapy for piano. The paper focuses on how to apply the “whole and part” and “epiphany” perspectives of the Gestalt learning theory to singing and music appreciation lessons. In addition, the Gestalt school's ideas of developing creative thinking, creating problematic situations, and transferring learning were demonstrated through the implementation of teaching cases. There are differences in the effects of different music on the distribution of body surface temperature; there are differences in the effects of yang music on the Directing Vessel compared to the effects of yin music on the Directing Vessel, and the effects are following the hierarchical model of thinking; there are individual differences in the magnitude of the effects of the same music on the body surface temperature of different people, and the identification of music needs to be combined with the three factors. The wavelet energy entropy (WEE) characteristics of EEG signals were extracted as the input of the designed and optimized deep belief network model, and the average emotional classification accuracy of EEG signals in the left and right brain regions could be obtained as 84.20% and 83.07%, respectively, under the condition of distinguishing brain regions and different music environments. Compared with the classification accuracies of DBN, restricted Boltzmann machine (RBM), and K nearest neighbor (kNN) algorithms in mixed music environments, the classification effects were improved by about 3.49%, 12.89%, and 7.24%. Relying on the ability-poor theory and Weiner attribution theory, different types of secondary school students, their psychological characteristics, and their causes were pointed out. Combined with the psychological characteristics, the case study illustrates the positive effect of music therapy on psychological support.

Analysis and application of functional connectivity in synchronic hybrid mental tasks for brain-computer interface

As a new type of human–computer interaction technology, brain-computer interface (BCI) systems can translate the electroencephalography (EEG) signals as control commands. In our previous study, the synchronous hybrid mental tasks have been proposed with higher classification accuracy. In this study, to analyze the superiority of synchronous hybrid mental tasks, the causal networks of synchronous hybrid mental tasks and single mental tasks are compared. The causal networks are based on functional connectivity, which is calculated by partial directed coherence. The networks of the synchronous hybrid mental tasks present different interaction patterns. To further improve the classification accuracy of EEG signals, a feature extraction method combining the causal network and common spatial pattern (CSP) is proposed. After combining as mixed feature vectors, they are selected by binary quantum-behaved particle swarm optimization. The optimal feature subsets are classified by extreme learning machine. This average result is 3.1% and 9.5% higher than CSP and causal flow, respectively. The superiority of hybrid experimental paradigm can be studied by the causal network, and the performance of BCIs is also improved.

Classification of EEG Signals on VEP-Based BCI Systems With Broad Learning

Brain–computer interface (BCI) systems based on electroencephalography (EEG) signals have been extensively used in medical practice. To enhance the BCI performance, improving the classification accuracy of EEG signals is the key, which has always been the focus of research and development. In this article, a novel method integrating complex network and broad learning system (BLS) is proposed for visual evoked potential (VEP)-based BCI research. First, systematic VEP-based brain experiments are conducted for obtaining EEG signals, including steady-state VEP (SSVEP) and steady-state motion VEP (SSMVEP). Then, limited penetrable visibility graph (LPVG) and its degree sequence are employed to implement the preliminary feature extraction. All these features are finally fed into a BLS to study and classify the SSVEP and SSMVEP signals, respectively. The classification results show that our LPVG-based BLS can effectively classify VEP-based EEG signals, with average classification accuracy 96.22% for SSVEP and 74.54% for SSMVEP. These results are significantly better than other comparison methods as well as traditional CCA-based methods. All these open up new venues for studying EEG-based BCI systems via the fusion of network science and BLS.

EEG Signal Processing Based on Genetic Algorithm for Extracting Mixed Features

In order to improve the classification of motor imagery EEG accuracy, this paper proposes a method based on Genetic Algorithm (GA) EEG signal classification method to extract mixed characteristics. This method uses wavelet analysis and Hilbert–Huang Transform (HHT) to analyze EEG signals and optimizes the characteristics through Common Spatial Patterns (CSP). Finally, the 14 sub features are optimized by GA, and the weights and data credibility of different sub features are obtained. The experiment was tested with 2003BCI competition data and the EEG signal collected by the laboratory. The accuracy rate of competition data was increased from about 75% before weighting to more than 80% after weighting, and the laboratory data increased from about 65% before weighting to about 75% after weighting. Experimental results show that this method can effectively improve the classification accuracy of EEG signals, and the most useful EEG signals can be extracted from large amounts of data for feature extraction and classification. Finally, the online test is carried out to further verify the feasibility of the method.

A hybrid BCI based on EEG and fNIRS signals improves the performance of decoding motor imagery of both force and speed of hand clenching

Objective. In order to increase the number of states classified by a brain–computer interface (BCI), we utilized a motor imagery task where subjects imagined both force and speed of hand clenching. Approach. The BCI utilized simultaneously recorded electroencephalographic (EEG) and functional near-infrared spectroscopy (fNIRS) signals. The time-phase-frequency feature was extracted from EEG, whereas the HbD [the difference of oxy-hemoglobin (HbO) and deoxy-hemoglobin (Hb)] feature was used to improve the classification accuracy of fNIRS. The EEG and fNIRS features were combined and optimized using the joint mutual information (JMI) feature selection criterion; then the extracted features were classified with the extreme learning machines (ELMs). Main results. In this study, the averaged classification accuracy of EEG signals achieved by the time-phase-frequency feature improved by 7%, to 18%, more than the single-type feature, and improved by 15% more than common spatial pattern (CSP) feature. The HbD feature of fNIRS signals improved the accuracy by 1%, to 4%, more than Hb, HbO, or HbT (total hemoglobin). The EEG–fNIRS feature for decoding motor imagery of both force and speed of hand clenching achieved an accuracy of 89% ± 2%, and improved the accuracy by 1% to 5% more than the sole EEG or fNIRS feature. Significance. Our novel motor imagery paradigm improves BCI performance by increasing the number of extracted commands. Both the time-phase-frequency and the HbD feature improve the classification accuracy of EEG and fNIRS signals, respectively, and the hybrid EEG–fNIRS technique achieves a higher decoding accuracy for two-class motor imagery, which may provide the framework for future multi-modal online BCI systems.

Combined Approaches of Features Selection for EEG Classification

The classification accuracy of EEG signal illustrates the degree of recognition of significant characteristics describing events revealing underlying neuronal activity. In this paper we focus on features selection, by using both t-test and entropy criteria. The feature extraction is accomplished using wavelet functions Symmlet5, Coiflet5, and DB10, and classification is achieved using Linear Discriminate Analysis and Support Vector Machines classifiers. The obtained results show an improvement in classification accuracy reaching 7% for LDA classifier, and 4% for SVM classifier.