Classification of focal and non-focal EEG signals using optimal geometrical features derived from a second-order difference plot of FBSE-EWT rhythms

BACKGROUND/INTRODUCTION

Manual detection and localization of the brain's epileptogenic areas using electroencephalogram (EEG) signals is time-intensive and error-prone. An automated detection system is, thus, highly desirable for support in clinical diagnosis. A set of relevant and significant non-linear features plays a major role in developing a reliable, automated focal detection system.

METHODS

A new feature extraction method is designed to classify focal EEG signals using eleven non-linear geometrical attributes derived from the Fourier-Bessel series expansion-based empirical wavelet transform (FBSE-EWT) segmented rhythm's second-order difference plot (SODP). A total of 132 features (2 channels × 6 rhythms × 11 geometrical attributes) were computed. However, some of the obtained features might be non-significant and redundant features. Hence, to acquire an optimal set of relevant non-linear features, a new hybridization of 'Kruskal-Wallis statistical test (KWS)' with 'VlseKriterijuska Optimizacija I Komoromisno Resenje' termed as the KWS-VIKOR approach was adopted. The KWS-VIKOR has a two-fold operational feature. First, the significant features are selected using the KWS test with a p-value lesser than 0.05. Next, the multi-attribute decision-making (MADM) based VIKOR method ranks the selected features. Several classification methods further validate the efficacy of the features of the selected top n%.

RESULTS

The proposed framework has been evaluated using the Bern-Barcelona dataset. The highest classification accuracy of 98.7% was achieved using the top 35% ranked features in classifying the focal and non-focal EEG signals with the least-squares support vector machine (LS-SVM) classifier.

CONCLUSIONS

The achieved results exceeded those reported through other methods. Hence, the proposed framework will more effectively assist the clinician in localizing the epileptogenic areas.

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

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.

The Masking Impact of Intra-artifacts in EEG on Deep Learning-based Sleep Staging Systems: A Comparative Study

Elimination of intra-artifacts in EEG has been overlooked in most of the existing sleep staging systems, especially in deep learning-based approaches. Whether intra-artifacts, originated from the eye movement, chin muscle firing, or heart beating, etc., in EEG signals would lead to a positive or a negative masking effect on deep learning-based sleep staging systems was investigated in this paper. We systematically analyzed several traditional pre-processing methods involving fast Independent Component Analysis (FastICA), Information Maximization (Infomax), and Second-order Blind Source Separation (SOBI). On top of these methods, a SOBI-WT method based on the joint use of the SOBI and Wavelet Transform (WT) is proposed. It offered an effective solution for suppressing artifact components while retaining residual informative data. To provide a comprehensive comparative analysis, these pre-processing methods were applied to eliminate the intra-artifacts and the processed signals were fed to two ready-to-use deep learning models, namely two-step hierarchical neural network (THNN) and SimpleSleepNet for automatic sleep staging. The evaluation was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDF Expanded, and a clinical dataset that was collected in Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed SOBI-WT method increased the accuracy from 79.0% to 81.3% on MASS, 83.3% to 85.7% on Sleep-EDF Expanded, and 75.5% to 77.1% on HSFU compared with the raw EEG signal, respectively. Experimental results demonstrate that the intra-artifacts bring out a masking negative impact on the deep learning-based sleep staging systems and the proposed SOBI-WT method has the best performance in diminishing this negative impact compared with other artifact elimination methods.

A Novel Method Based on Combination of Independent Component Analysis and Ensemble Empirical Mode Decomposition for Removing Electrooculogram Artifacts From Multichannel Electroencephalogram Signals

Electrooculogram (EOG) is one of common artifacts in recorded electroencephalogram (EEG) signals. Many existing methods including independent component analysis (ICA) and wavelet transform were applied to eliminate EOG artifacts but ignored the possible impact of the nature of EEG signal. Therefore, the removal of EOG artifacts still faces a major challenge in EEG research. In this paper, the ensemble empirical mode decomposition (EEMD) and ICA algorithms were combined to propose a novel EEMD-based ICA method (EICA) for removing EOG artifacts from multichannel EEG signals. First, the ICA method was used to decompose original EEG signals into multiple independent components (ICs), and the EOG-related ICs were automatically identified through the kurtosis method. Then, by performing the EEMD algorithm on EOG-related ICs, the intrinsic mode functions (IMFs) linked to EOG were discriminated and eliminated. Finally, artifact-free IMFs were projected to obtain the ICs without EOG artifacts, and the clean EEG signals were ultimately reconstructed by the inversion of ICA. Both EOGs correction from simulated EEG signals and real EEG data were studied, which verified that the proposed method could achieve an improved performance in EOG artifacts rejection. By comparing with other existing approaches, the EICA obtained the optimal performance with the highest increase in signal-to-noise ratio and decrease in root mean square error and correlation coefficient after EOG artifacts removal, which demonstrated that the proposed method could more effectively eliminate blink artifacts from multichannel EEG signals with less error influence. This study provided a novel promising method to eliminate EOG artifacts with high performance, which is of great importance for EEG signals processing and analysis.

Recognizing humanity: dehumanization predicts neural mirroring and empathic accuracy in face-to-face interactions

Dehumanization is the failure to recognize the cognitive and emotional complexities of the people around us. While its presence has been well documented in horrific acts of violence, it is also theorized to play a role in everyday life. We measured its presence and effects in face-to-face dyadic interactions between strangers and found that not only was there variance in the extent to which they perceived one another as human, but this variance predicted neural processing and behavior. Specifically, participants showed stronger neural mirroring, indexed by electroencephalography (EEG) mu-suppression, in response to partners they evaluated as more human, suggesting their brains neurally simulated those targets' actions more. Participants were also marginally more empathically accurate about the emotions of partners deemed more human and performed better with them on a cooperative task. These results suggest that there are indeed differences in our recognition of the humanity of people we meet-demonstrated for the first time in a real, face-to-face interaction-and that this mundane variation affects our ability to neurally simulate, cooperate and empathize.

METROID: an automated method for robust quantification of subcellular fluorescence events at low SNR

Background

In cell biology, increasing focus has been directed to fast events at subcellular space with the advent of fluorescent probes. As an example, voltage sensitive dyes (VSD) have been used to measure membrane potentials. Yet, even the most recently developed genetically encoded voltage sensors have demanded exhausting signal averaging through repeated experiments to quantify action potentials (AP). This analysis may be further hampered in subcellular signals defined by small regions of interest (ROI), where signal-to-noise ratio (SNR) may fall substantially. Signal processing techniques like blind source separation (BSS) are designed to separate a multichannel mixture of signals into uncorrelated or independent sources, whose potential to separate ROI signal from noise has been poorly explored. Our aims are to develop a method capable of retrieving subcellular events with minimal a priori information from noisy cell fluorescence images and to provide it as a computational tool to be readily employed by the scientific community.

Results

In this paper, we have developed METROID (Morphological Extraction of Transmembrane potential from Regions Of Interest Device), a new computational tool to filter fluorescence signals from multiple ROIs, whose code and graphical interface are freely available. In this tool, we developed a new ROI definition procedure to automatically generate similar-area ROIs that follow cell shape. In addition, simulations and real data analysis were performed to recover AP and electroporation signals contaminated by noise by means of four types of BSS: Principal Component Analysis (PCA), Independent Component Analysis (ICA), and two versions with discrete wavelet transform (DWT). All these strategies allowed for signal extraction at low SNR (− 10 dB) without apparent signal distortion.

Conclusions

We demonstrate the great capability of our method to filter subcellular signals from noisy fluorescence images in a single trial, avoiding repeated experiments. We provide this novel biomedical application with a graphical user interface at 10.6084/m9.figshare.11344046.v1, and its code and datasets are available in GitHub at https://github.com/zoccoler/metroid.

Low-Element Image Restoration Based on an Out-of-Order Elimination Algorithm

To reduce the consumption of receiving devices, a number of devices at the receiving end undergo low-element treatment (the number of devices at the receiving end is less than that at the transmitting ends). The underdetermined blind-source separation system is a classic low-element model at the receiving end. Blind signal extraction in an underdetermined system remains an ill-posed problem, as it is difficult to extract all the source signals. To realize fewer devices at the receiving end without information loss, this paper proposes an image restoration method for underdetermined blind-source separation based on an out-of-order elimination algorithm. Firstly, a chaotic system is used to perform hidden transmission of source signals, where the source signals can hardly be observed and confidentiality is guaranteed. Secondly, empirical mode decomposition is used to decompose and complement the missing observed signals, and the fast independent component analysis (FastICA) algorithm is used to obtain part of the source signals. Finally, all the source signals are successfully separated using the out-of-order elimination algorithm and the FastICA algorithm. The results show that the performance of the underdetermined blind separation algorithm is related to the configuration of the transceiver antenna. When the signal is 3 × 4 antenna configuration, the algorithm in this paper is superior to the comparison algorithm in signal recovery, and its separation performance is better for a lower degree of missing array elements. The end result is that the algorithms discussed in this paper can effectively and completely extract all the source signals.

Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records

This paper addresses the overlearning problem in the independent component analysis (ICA) used for the removal of muscular artifacts from electroencephalographic (EEG) records. We note that for short EEG records with high number of channels the ICA fails to separate artifact-free EEG and muscular artifacts, which has been previously attributed to the phenomenon called overlearning. We address this problem by projecting an EEG record into several subspaces with a lower dimension, and perform the ICA on each subspace separately. Due to a reduced dimension of the subspaces, the overlearning is suppressed, and muscular artifacts are better separated. Once the muscular artifacts are removed, the signals in the individual subspaces are combined to provide an artifact free EEG record. We show that for short signals and high number of EEG channels our approach outperforms the currently available ICA based algorithms for muscular artifact removal. The proposed technique can efficiently suppress ICA overlearning for short signal segments of high density EEG signals.

Simultaneous ocular and muscle artifact removal from EEG data by exploiting diverse statistics

Electroencephalography (EEG) recordings are frequently contaminated by both ocular and muscle artifacts. These are normally dealt with separately, by employing blind source separation (BSS) techniques relying on either second-order or higher-order statistics (SOS & HOS respectively). When HOS-based methods are used, it is usually in the setting of assuming artifacts are statistically independent to the EEG. When SOS-based methods are used, it is assumed that artifacts have autocorrelation characteristics distinct from the EEG. In reality, ocular and muscle artifacts do not completely follow the assumptions of strict temporal independence to the EEG nor completely unique autocorrelation characteristics, suggesting that exploiting HOS or SOS alone may be insufficient to remove these artifacts. Here we employ a novel BSS technique, independent vector analysis (IVA), to jointly employ HOS and SOS simultaneously to remove ocular and muscle artifacts. Numerical simulations and application to real EEG recordings were used to explore the utility of the IVA approach. IVA was superior in isolating both ocular and muscle artifacts, especially for raw EEG data with low signal-to-noise ratio, and also integrated usually separate SOS and HOS steps into a single unified step.

Methods for artifact detection and removal from scalp EEG: A review

Electroencephalography (EEG) is the most popular brain activity recording technique used in wide range of applications. One of the commonly faced problems in EEG recordings is the presence of artifacts that come from sources other than brain and contaminate the acquired signals significantly. Therefore, much research over the past 15 years has focused on identifying ways for handling such artifacts in the preprocessing stage. However, this is still an active area of research as no single existing artifact detection/removal method is complete or universal. This article presents an extensive review of the existing state-of-the-art artifact detection and removal methods from scalp EEG for all potential EEG-based applications and analyses the pros and cons of each method. First, a general overview of the different artifact types that are found in scalp EEG and their effect on particular applications are presented. In addition, the methods are compared based on their ability to remove certain types of artifacts and their suitability in relevant applications (only functional comparison is provided not performance evaluation of methods). Finally, the future direction and expected challenges of current research is discussed. Therefore, this review is expected to be helpful for interested researchers who will develop and/or apply artifact handling algorithm/technique in future for their applications as well as for those willing to improve the existing algorithms or propose a new solution in this particular area of research.

An automatic ocular artifacts removal method based on wavelet-enhanced canonical correlation analysis

In this paper, a new method for automatic ocular artifacts (OA) removal in EEG recordings is proposed based on wavelet-enhanced canonical correlation analysis (wCCA). Compared to three popular ocular artifacts removal methods, wCCA owns two advantages. First, there is no need to identify the artifact components by subjective visual inspection, because the first canonical components found by CCA for each dataset, also the most common component between the left and right hemisphere, are definitely related to artifacts. Second, quantitative evaluation of the corrected EEG signals demonstrates that wCCA removed the most ocular artifacts with minimal cerebral information loss.

Segmentation and Classification of Vowel Phonemes of Assamese Speech Using a Hybrid Neural Framework

In spoken word recognition, one of the crucial points is to identify the vowel phonemes. This paper describes an Artificial Neural Network (ANN) based algorithm developed for the segmentation and recognition of the vowel phonemes of Assamese language from some words containing those vowels. Self-Organizing Map (SOM) trained with a various number of iterations is used to segment the word into its constituent phonemes. Later, Probabilistic Neural Network (PNN) trained with clean vowel phonemes is used to recognize the vowel segment from the six different SOM segmented phonemes. One of the important aspects of the proposed algorithm is that it proves the validation of the recognized vowel by checking its first formant frequency. The first formant frequency of all the Assamese vowels is predetermined by estimating pole or formant location from the linear prediction (LP) model of the vocal tract. The proposed algorithm shows a high recognition performance in comparison to the conventional Discrete Wavelet Transform (DWT) based segmentation.

EEG mu component responses to viewing emotional faces

Simulation theories for the perceptual processing of emotional faces assert that observers recruit the neural circuitry involved in creating their own emotional facial expressions in order to recognize the emotions and infer the feelings of others. The EEG mu rhythm is a sensorimotor oscillation hypothesized to index simulation of some actions during perceptual processing of these actions. The purpose of this research was to extend the study of mu rhythm simulation responses during perceptual tasks to the domain of emotional face perception. Subjects viewed happy and disgusted face photos with empathy and non-empathy task instructions while EEG responses were measured. EEG components were isolated and analyzed using a blind source separation (BSS) method. Mu components were found to respond to the perception of happy and disgusted faces during both empathy and non-empathy tasks with an event-related desynchronization (ERD), activation that is consistent with face simulation. Significant differences were found between responses to happy and to disgusted faces across the right hemisphere mu components beginning about 500ms after stimulus presentation. These findings support a simulation account of perceptual face processing based on a sensorimotor mirroring mechanism, and are the first report of distinct EEG mu responses to observation of positively and negatively valenced emotional faces.