EEG artifact removal using sub-space decomposition, nonlinear dynamics, stationary wavelet transform and machine learning algorithms

Abstract

Blind source separation (BSS) methods have received a great deal of attention in electroencephalogram (EEG) artifact elimination as they are routine and standard signal processing tools to remove artifacts and reserve desired neural information. On the other hand, a classifier should follow BSS methods to automatically identify artifactual sources and remove them in the following steps. In addition, removing all detected artifactual components leads to loss of information since some desired information related to neural activity leaks to these sources. So, an approach should be employed to detect and suppress the artifacts and reserve neural activity. This study introduces a novel method based on EEG and Poincare planes in the phase space to detect artifactual components estimated by second-order blind identification (SOBI). Artifacts are detected using a mixture of well-known conventional classifiers and were removed employing stationary wavelet transform (SWT) to reserve neural information. The proposed method is a combination of signal processing techniques and machine learning algorithms, including multi-layer perceptron (MLP), K-nearest neighbor (KNN), naïve Bayes, and support vector machine (SVM) which have significant results while applying our proposed method to different scenarios. Simulated, semi-simulated, and real EEG signals are employed to evaluate the proposed method, and several evaluation criteria are calculated. We achieved acceptable results, for example, 98% average accuracy and 97% average sensitivity in artifactual EEG component detection or about 2% as mean square error in EEG reconstruction after artifact removal. Results showed that the proposed method is effective and can be used in future studies as we have considered different real-world scenarios to evaluate it.

A Review on Large-Scale Data Processing with Parallel and Distributed Randomized Extreme Learning Machine Neural Networks

“…where A ∈ R n×n is a regular matrix and B ∈ R n . Matrix-operations-based methods represent a great variety of methods that combine matrix operations to solve (10). Among the most applied and performed with distributed and parallel computing is Gaussian elimination and its variants (Gauss-Jordan, Gauss-Huard).…”

“…Among the most applied and performed with distributed and parallel computing is Gaussian elimination and its variants (Gauss-Jordan, Gauss-Huard). The methods based on Gaussian elimination used to solve (10) perform elementary operations to obtain the step form of A (diagonal or triangular). The sequence of equivalent linear systems is obtained by applying elementary operations (i.e., A k X = B k ) for k = 1, .…”

“…The particle-swarm-optimized wavelet neural network (PSOWNN) method presented was proven to be more accurate than other machine learning algorithms such as SVM, KNNs, and CNN. In this direction, a method combining signal processing techniques and machine learning algorithms (MLP, KNNs, NB, and SVM) is presented in another study [10]. The method is proposed to suppress different types of electroencephalogram artifacts.…”

Ictal EEG Source Imaging

“…It is also intuitive to clinical neurophysiologists and does not include some of the risk of removing a portion of signal of interest or introducing signal distortion possible with other unsupervised noise reduction methods to remove artifact and increase signal-to-noise ratio. 24 Caution is still required, however, for peak averaging can become an oversimplification of ictal signal because of over smoothing, what is a more complex temporally evolving source(s) of signals.…”

Research on Ocular Artifacts Removal from Single-Channel Electroencephalogram Signals in Obstructive Sleep Apnea Patients Based on Support Vector Machine, Improved Variational Mode Decomposition, and Second-Order Blind Identification

“…Subsequently, the decomposed data were further processed using the SOBI algorithm. Compared to ICA and most BSS methods, SOBI is considered a superior approach [ 12 , 32 ]. SOBI is a method based on second-order statistics (SOS), utilizing the joint approximate diagonalization of covariance matrices to achieve blind source separation of observed signals.…”