Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis

Circulant Singular Spectrum Analysis and Discrete Wavelet Transform for Automated Removal of EOG Artifacts from EEG Signals

Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals.

Estimating the Depth of Anesthesia from EEG Signals Based on a Deep Residual Shrinkage Network

The reliable monitoring of the depth of anesthesia (DoA) is essential to control the anesthesia procedure. Electroencephalography (EEG) has been widely used to estimate DoA since EEG could reflect the effect of anesthetic drugs on the central nervous system (CNS). In this study, we propose that a deep learning model consisting mainly of a deep residual shrinkage network (DRSN) and a 1 × 1 convolution network could estimate DoA in terms of patient state index (PSI) values. First, we preprocessed the four raw channels of EEG signals to remove electrical noise and other physiological signals. The proposed model then takes the preprocessed EEG signals as inputs to predict PSI values. Then we extracted 14 features from the preprocessed EEG signals and implemented three conventional feature-based models as comparisons. A dataset of 18 patients was used to evaluate the models' performances. The results of the five-fold cross-validation show that there is a relatively high similarity between the ground-truth PSI values and the predicted PSI values of our proposed model, which outperforms the conventional models, and further, that the Spearman's rank correlation coefficient is 0.9344. In addition, an ablation experiment was conducted to demonstrate the effectiveness of the soft-thresholding module for EEG-signal processing, and a cross-subject validation was implemented to illustrate the robustness of the proposed method. In summary, the procedure is not merely feasible for estimating DoA by mimicking PSI values but also inspired us to develop a precise DoA-estimation system with more convincing assessments of anesthetization levels.

Fear memory in humans is consolidated over time independently of sleep

Fear memories can be altered after acquisition by processes, such as fear memory consolidation or fear extinction, even without further exposure to the fear-eliciting stimuli, but factors contributing to these processes are not well understood. Sleep is known to consolidate, strengthen, and change newly acquired declarative and procedural memories. However, evidence on the role of time and sleep in the consolidation of fear memories is inconclusive. We used highly sensitive electrophysiological measures to examine the development of fear-conditioned responses over time and sleep in humans. We assessed event-related brain potentials (ERP) in 18 healthy, young individuals during fear conditioning before and after a 2-hour afternoon nap or a corresponding wake interval in a counterbalanced within-subject design. The procedure involved pairing a neutral tone (CS+) with a highly unpleasant sound. As a control, another neutral tone (CS-) was paired with a neutral sound. Fear responses were examined before the interval during a habituation phase and an acquisition phase as well as after the interval during an extinction phase and a reacquisition phase. Differential fear conditioning during acquisition was evidenced by a more negative slow ERP component (stimulus-preceding negativity) developing before the unconditioned stimulus (loud noise). This differential fear response was even stronger after the interval during reacquisition compared with initial acquisition, but this effect was similarly pronounced after sleep and wakefulness. These findings suggest that fear memories are consolidated over time, with this effect being independent of intervening sleep.

Extended Detrended Fluctuation Analysis of Coarse-Grained Time Series

A coarse-graining procedure, which involves averaging time series in non-overlapping windows followed by processing of the obtained multiple data sets, is the initial step in the multiscale entropy computation method. In this paper, we discuss how this procedure can be applied with other methods of time series analysis. Based on extended detrended fluctuation analysis (EDFA), we compare signal processing results for data sets with and without coarse-graining. Using the simulated data provided by the interacting nephrons model, we show how this procedure increases, up to 48%, the distinctions between local scaling exponents quantifying synchronous and asynchronous chaotic oscillations. Based on the experimental data of electrocorticograms (ECoG) of mice, an improvement in differences in local scaling exponents up to 41% and Student's t-values up to 34% was revealed.

Removing ocular artifacts from magnetoencephalographic data on naturalistic reading of continuous texts

Naturalistic reading paradigms and stimuli consisting of long continuous texts are essential for characterizing the cortical basis of reading. Due to the highly dynamic nature of the reading process, electrophysiological brain imaging methods with high spatial and temporal resolution, such as magnetoencephalography (MEG), are ideal for tracking them. However, as electrophysiological recordings are sensitive to electromagnetic artifacts, data recorded during naturalistic reading is confounded by ocular artifacts. In this study, we evaluate two different pipelines for removing ocular artifacts from MEG data collected during continuous, naturalistic reading, with the focus on saccades and blinks. Both pipeline alternatives are based on blind source separation methods but differ fundamentally in their approach. The first alternative is a multi-part process, in which saccades are first extracted by applying Second-Order Blind Identification (SOBI) and, subsequently, FastICA is used to extract blinks. The other alternative uses a single powerful method, Adaptive Mixture ICA (AMICA), to remove all artifact types at once. The pipelines were tested, and their effects compared on MEG data recorded from 13 subjects in a naturalistic reading task where the subjects read texts with the length of multiple pages. Both pipelines performed well, extracting the artifacts in a single component per artifact type in most subjects. Signal power was reduced across the whole cortex in all studied frequency bands from 1 to 90 Hz, but especially in the frontal cortex and temporal pole. The results were largely similar for the two pipelines, with the exception that SOBI-FastICA reduced signal in the right frontal cortex in all studied frequency bands more than AMICA. However, there was considerable interindividual variation in the effects of the pipelines. As a holistic conclusion, we choose to recommend AMICA for removing artifacts from MEG data on naturalistic reading but note that the SOBI-FastICA pipeline has also various favorable characteristics.

RNeuMark: A Riemannian EEG Analysis Framework for Neuromarketing

Neuromarketing exploits neuroimaging techniques so as to reinforce the predictive power of conventional marketing tools, like questionnaires and focus groups. Electroencephalography (EEG) is the most commonly encountered neuroimaging technique due to its non-invasiveness, low-cost, and its very recent embedding in wearable devices. The transcription of brainwave patterns to consumer attitude is supported by various signal descriptors, while the quest for profitable novel ways is still an open research question. Here, we suggest the use of sample covariance matrices as alternative descriptors, that encapsulate the coordinated neural activity from distinct brain areas, and the adoption of Riemannian geometry for their handling. We first establish the suitability of Riemannian approach for neuromarketing-related problems and then suggest a relevant decoding scheme for predicting consumers' choices (e.g., willing to buy or not a specific product). Since the decision-making process involves the concurrent interaction of various cognitive processes and consequently of distinct brain rhythms, the proposed decoder takes the form of an ensemble classifier that builds upon a multi-view perspective, with each view dedicated to a specific frequency band. Adopting a standard machine learning procedure, and using a set of trials (training data) in conjunction with the associated behavior labels ("buy"/ "not buy"), we train a battery of classifiers accordingly. Each classifier is designed to operate in the space recovered from the inter-trial distances of SCMs and to cast a rhythm-depended decision that is eventually combined with the predictions of the rest ones. The demonstration and evaluation of the proposed approach are performed in 2 neuromarketing-related datasets of different nature. The first is employed to showcase the potential of the suggested descriptor, while the second to showcase the decoder's superiority against popular alternatives in the field.

Multimodal resting-state connectivity predicts affective neurofeedback performance

Neurofeedback has been suggested as a potential complementary therapy to different psychiatric disorders. Of interest for this approach is the prediction of individual performance and outcomes. In this study, we applied functional connectivity-based modeling using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) modalities to (i) investigate whether resting-state connectivity predicts performance during an affective neurofeedback task and (ii) evaluate the extent to which predictive connectivity profiles are correlated across EEG and fNIRS techniques. The fNIRS oxyhemoglobin and deoxyhemoglobin concentrations and the EEG beta and gamma bands modulated by the alpha frequency band (beta-m-alpha and gamma-m-alpha, respectively) recorded over the frontal cortex of healthy subjects were used to estimate functional connectivity from each neuroimaging modality. For each connectivity matrix, relevant edges were selected in a leave-one-subject-out procedure, summed into "connectivity summary scores" (CSS), and submitted as inputs to a support vector regressor (SVR). Then, the performance of the left-out-subject was predicted using the trained SVR model. Linear relationships between the CSS across both modalities were evaluated using Pearson's correlation. The predictive model showed a mean absolute error smaller than 20%, and the fNIRS oxyhemoglobin CSS was significantly correlated with the EEG gamma-m-alpha CSS (r = -0.456, p = 0.030). These results support that pre-task electrophysiological and hemodynamic resting-state connectivity are potential predictors of neurofeedback performance and are meaningfully coupled. This investigation motivates the use of joint EEG-fNIRS connectivity as outcome predictors, as well as a tool for functional connectivity coupling investigation.

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.

Wavelet Based Filters for Artifact Elimination in Electroencephalography Signal: A Review

Electroencephalography (EEG) is a diagnostic test that records and measures the electrical activity of the human brain. Research investigating human behaviors and conditions using EEG has increased from year to year. Therefore, an efficient approach is vital to process the EEG dataset to improve the output signal quality. The wavelet is one of the well-known approaches for processing the EEG signal in time-frequency domain analysis. The wavelet is better than the traditional Fourier Transform because it has good time-frequency localized properties and multi-resolution analysis where the transient information of an EEG signal can be extracted efficiently. Thus, this review article aims to comprehensively describe the application of the wavelet method in denoising the EEG signal based on recent research. This review begins with a brief overview of the basic theory and characteristics of EEG and the wavelet transform method. Then, several wavelet-based methods commonly applied in EEG dataset denoising are described and a considerable number of the latest published EEG research works with wavelet applications are reviewed. Besides, the challenges that exist in current EEG-based wavelet method research are discussed. Finally, alternative solutions to mitigate the issues are recommended.

Single channel approach for filtering electroencephalographic signals strongly contaminated with facial electromyography

Eliminating facial electromyographic (EMG) signal from the electroencephalogram (EEG) is crucial for the accuracy of applications such as brain computer interfaces (BCIs) and brain functionality measurement. Facial electromyography typically corrupts the electroencephalogram. Although it is possible to find in the literature a number of multi-channel approaches for filtering corrupted EEG, studies employing single-channel approaches are scarce. In this context, this study proposed a single-channel method for attenuating facial EMG noise from contaminated EEG. The architecture of the method allows for the evaluation and incorporation of multiple decomposition and adaptive filtering techniques. The decomposition method was responsible for generating EEG or EMG reference signals for the adaptive filtering stage. In this study, the decomposition techniques CiSSA, EMD, EEMD, EMD-PCA, SSA, and Wavelet were evaluated. The adaptive filtering methods RLS, Wiener, LMS, and NLMS were investigated. A time and frequency domain set of features were estimated from experimental signals to evaluate the performance of the single channel method. This set of characteristics permitted the characterization of the contamination of distinct facial muscles, namely Masseter, Frontalis, Zygomatic, Orbicularis Oris, and Orbicularis Oculi. Data were collected from ten healthy subjects executing an experimental protocol that introduced the necessary variability to evaluate the filtering performance. The largest level of contamination was produced by the Masseter muscle, as determined by statistical analysis of the set of features and visualization of topological maps. Regarding the decomposition method, the SSA method allowed for the generation of more suitable reference signals, whereas the RLS and NLMS methods were more suitable when the reference signal was derived from the EEG. In addition, the LMS and RLS methods were more appropriate when the reference signal was the EMG. This study has a number of practical implications, including the use of filtering techniques to reduce EEG contamination caused by the activation of facial muscles required by distinct types of studies. All the developed code, including examples, is available to facilitate a more accurate reproduction and improvement of the results of this study.

Challenges and new perspectives of developmental cognitive EEG studies

Despite shared procedures with adults, electroencephalography (EEG) in early development presents many specificities that need to be considered for good quality data collection. In this paper, we provide an overview of the most representative early cognitive developmental EEG studies focusing on the specificities of this neuroimaging technique in young participants, such as attrition and artifacts. We also summarize the most representative results in developmental EEG research obtained in the time and time-frequency domains and use more advanced signal processing methods. Finally, we briefly introduce three recent standardized pipelines that will help promote replicability and comparability across experiments and ages. While this paper does not claim to be exhaustive, it aims to give a sufficiently large overview of the challenges and solutions available to conduct robust cognitive developmental EEG studies.

HAPPILEE: HAPPE In Low Electrode Electroencephalography, a standardized pre-processing software for lower density recordings

Lower-density Electroencephalography (EEG) recordings (from 1 to approximately 32 electrodes) are widely-used in research and clinical practice and enable scalable brain function measurement across a variety of settings and populations. Though a number of automated pipelines have recently been proposed to standardize and optimize EEG pre-processing for high-density systems with state-of-the-art methods, few solutions have emerged that are compatible with lower-density systems. However, lower-density data often include long recording times and/or large sample sizes that would benefit from similar standardization and automation with contemporary methods. To address this need, we propose the HAPPE In Low Electrode Electroencephalography (HAPPILEE) pipeline as a standardized, automated pipeline optimized for EEG recordings with lower density channel layouts of any size. HAPPILEE processes task-free (e.g., resting-state) and task-related EEG (including event-related potential data by interfacing with the HAPPE+ER pipeline), from raw files through a series of processing steps including filtering, line noise reduction, bad channel detection, artifact correction from continuous data, segmentation, and bad segment rejection that have all been optimized for lower density data. HAPPILEE also includes post-processing reports of data and pipeline quality metrics to facilitate the evaluation and reporting of data quality and processing-related changes to the data in a standardized manner. Here the HAPPILEE steps and their optimization with both recorded and simulated EEG data are described. HAPPILEE's performance is then compared relative to other artifact correction and rejection strategies. The HAPPILEE pipeline is freely available as part of HAPPE 2.0 software under the terms of the GNU General Public License at: https://github.com/PINE-Lab/HAPPE.

A Machine Learning Algorithm to Discriminating Between Bipolar and Major Depressive Disorders Based on Resting EEG Data

Distinguishing major depressive disorder (MDD) from bipolar disorder (BD) is a crucial clinical challenge due to the lack of known biomarkers. Conventional methods of diagnosis rest exclusively on symptomatic presentation, and personal and family history. As a result, BD-depressed episode (BD-DE) is often misdiagnosed as MDD, and inappropriate therapy is given. Electroencephalography (EEG) has been widely studied as a potential source of biomarkers to differentiate these disorders. Previous attempts using machine learning (ML) methods have delivered insufficient sensitivity and specificity for clinical use, likely as a consequence of the small training set size, and inadequate ML methodology. We hope to overcome these limitations by employing a training dataset of resting-state EEG from 71 MDD and 71 BD patients. We introduce a robust 3 steps ML technique: 1) a multi-step preprocessing method is used to improve the quality of the EEG signal 2) symbolic transfer entropy (STE), which is an effective connectivity measure, is applied to the resultant EEG signals 3) the ML algorithm uses the extracted STE features to distinguish MDD from BD patients. Clinical Relevance--- The accuracy of our algorithm, derived from a large sample of patients, suggests that this method may hold significant promise as a clinical tool. The proposed method delivered total accuracy, sensitivity, and specificity of 84.9%, 83.4%, and 87.1%, respectively.

ICA With CWT and k-means for Eye-Blink Artifact Removal From Fewer Channel EEG

In recent years, there has been an increase in the usage of consumer based EEG devices with fewer channel configuration. Although independent component analysis has been a popular approach for eye-blink artifact removal from multichannel EEG signals, several studies showed that there is a leak of neural information into the eye-blink artifact associated independent components (ICs). Furthermore, the leak increases as the number of input EEG channels decreases and leads to loss of valuable EEG information. To overcome this problem, we developed a new framework that combines ICA with continuous wavelet transform (CWT), k- means and singular spectrum analysis (SSA) methods. In contrast to the existing approaches, the artifact region in the identified eye-blink artifact IC is detected and suppressed rather than setting it to zero as in classical ICA. As most of the energy in the eye-blink artifact IC is concentrated in the artifact region, CWT and k- means algorithms exploits this feature to detect the eye-blink artifact region. Support vector machine (SVM) based classifier is finally designed for automatic detection of the eye blink artifact ICs. The performance of proposed method is evaluated on synthetic and two real EEG datasets for various EEG channels setting. Results highlight that for fewer channel EEG signals, the proposed method provides accurate separation without any neural information loss as compared to the existing methods.

Recommendations and publication guidelines for studies using frequency domain and time-frequency domain analyses of neural time series

Since its beginnings in the early 20th century, the psychophysiological study of human brain function has included research into the spectral properties of electrical and magnetic brain signals. Now, dramatic advances in digital signal processing, biophysics, and computer science have enabled increasingly sophisticated methodology for neural time series analysis. Innovations in hardware and recording techniques have further expanded the range of tools available to researchers interested in measuring, quantifying, modeling, and altering the spectral properties of neural time series. These tools are increasingly used in the field, by a growing number of researchers who vary in their training, background, and research interests. Implementation and reporting standards also vary greatly in the published literature, causing challenges for authors, readers, reviewers, and editors alike. The present report addresses this issue by providing recommendations for the use of these methods, with a focus on foundational aspects of frequency domain and time-frequency analyses. It also provides publication guidelines, which aim to (1) foster replication and scientific rigor, (2) assist new researchers who wish to enter the field of brain oscillations, and (3) facilitate communication among authors, reviewers, and editors.

Improved Cognitive Vigilance Assessment after Artifact Reduction with Wavelet Independent Component Analysis

Vigilance level assessment is of prime importance to avoid life-threatening human error. Critical working environments such as air traffic control, driving, or military surveillance require the operator to be alert the whole time. The electroencephalogram (EEG) is a very common modality that can be used in assessing vigilance. Unfortunately, EEG signals are prone to artifacts due to eye movement, muscle contraction, and electrical noise. Mitigating these artifacts is important for an accurate vigilance level assessment. Independent Component Analysis (ICA) is an effective method and has been extensively used in the suppression of EEG artifacts. However, in vigilance assessment applications, it was found to suffer from leakage of the cerebral activity into artifacts. In this work, we show that the wavelet ICA (wICA) method provides an alternative for artifact reduction, leading to improved vigilance level assessment results. We conducted an experiment in nine human subjects to induce two vigilance states, alert and vigilance decrement, while performing a Stroop Color-Word Test for approximately 45 min. We then compared the performance of the ICA and wICA preprocessing methods using five classifiers. Our classification results showed that in terms of features extraction, the wICA method outperformed the existing ICA method. In the delta, theta, and alpha bands, we obtained a mean classification accuracy of 84.66% using the ICA method, whereas the mean accuracy using the wICA methodwas 96.9%. However, no significant improvement was observed in the beta band. In addition, we compared the topographical map to show the changes in power spectral density across the brain regions for the two vigilance states. The proposed method showed that the frontal and central regions were most sensitive to vigilance decrement. However, in this application, the proposed wICA shows a marginal improvement compared to the Fast-ICA.

Validation of Continuous Monitoring System for Epileptic Users in Outpatient Settings

Epilepsy is a chronic disease with a significant social impact, given that the patients and their families often live conditioned by the possibility of an epileptic seizure and its possible consequences, such as accidents, injuries, or even sudden unexplained death. In this context, ambulatory monitoring allows the collection of biomedical data about the patients’ health, thus gaining more knowledge about the physiological state and daily activities of each patient in a more personalized manner. For this reason, this article proposes a novel monitoring system composed of different sensors capable of synchronously recording electrocardiogram (ECG), photoplethysmogram (PPG), and ear electroencephalogram (EEG) signals and storing them for further processing and analysis in a microSD card. This system can be used in a static and/or ambulatory way, providing information about the health state through features extracted from the ear EEG signal and the calculation of the heart rate variability (HRV) and pulse travel time (PTT). The different applied processing techniques to improve the quality of these signals are described in this work. A novel algorithm used to compute HRV and PTT robustly and accurately in ambulatory settings is also described. The developed device has also been validated and compared with other commercial systems obtaining similar results. In this way, based on the quality of the obtained signals and the low variability of the computed parameters, even in ambulatory conditions, the developed device can potentially serve as a support tool for clinical decision-taking stages.

Automatic Classification of Subjects of the PSEN1-E280A Family at Risk of Developing Alzheimer’s Disease Using Machine Learning and Resting State Electroencephalography

Background: The study of genetic variant carriers provides an opportunity to identify neurophysiological changes in preclinical stages. Electroencephalography (EEG) is a low-cost and minimally invasive technique which, together with machine learning, provide the possibility to construct systems that classify subjects that might develop Alzheimer’s disease (AD). Objective: The aim of this paper is to evaluate the capacity of the machine learning techniques to classify healthy Non-Carriers (NonCr) from Asymptomatic Carriers (ACr) of PSEN1-E280A variant for autosomal dominant Alzheimer’s disease (ADAD), using spectral features from EEG channels and brain-related independent components (ICs) obtained using independent component analysis (ICA). Methods: EEG was recorded in 27 ACr and 33 NonCr. Statistical significance analysis was applied to spectral information from channels and group ICA (gICA), standardized low-resolution tomography (sLORETA) analysis was applied over the IC as well. Strategies for feature selection and classification like Chi-square, mutual informationm and support vector machines (SVM) were evaluated over the dataset. Results: A test accuracy up to 83% was obtained by implementing a SVM with spectral features derived from gICA. The main findings are related to theta and beta rhythms, generated in the parietal and occipital regions, like the precuneus and superior parietal lobule. Conclusion: Promising models for classification of preclinical AD due to PSEN-1-E280A variant can be trained using spectral features, and the importance of the beta band and precuneus region is highlighted in asymptomatic stages, opening up the possibility of its use as a screening methodology.

Scorepochs: A Computer-Aided Scoring Tool for Resting-State M/EEG Epochs

M/EEG resting-state analysis often requires the definition of the epoch length and the criteria in order to select which epochs to include in the subsequent steps. However, the effects of epoch selection remain scarcely investigated and the procedure used to (visually) inspect, label, and remove bad epochs is often not documented, thereby hindering the reproducibility of the reported results. In this study, we present Scorepochs, a simple and freely available tool for the automatic scoring of resting-state M/EEG epochs that aims to provide an objective method to aid M/EEG experts during the epoch selection procedure. We tested our approach on a freely available EEG dataset containing recordings from 109 subjects using the BCI2000 64 channel system.

Independent evaluation of the harvard automated processing pipeline for Electroencephalography 1.0 using multi-site EEG data from children with Fragile X Syndrome

BACKGROUND

The Harvard Automatic Processing Pipeline for Electroencephalography (HAPPE) is a computerized EEG data processing pipeline designed for multiple site analysis of populations with neurodevelopmental disorders. This pipeline has been validated in-house by the developers but external testing using real-world datasets remains to be done.

NEW METHOD

Resting and auditory event-related EEG data from 29 children ages 3-6 years with Fragile X Syndrome as well as simulated EEG data was used to evaluate HAPPE's noise reduction techniques, data standardization features, and data integration compared to traditional manualized processing.

RESULTS

For the real EEG data, HAPPE pipeline showed greater trials retained, greater variance retained through independent component analysis (ICA) component removal, and smaller kurtosis than the manual pipeline; the manual pipeline had a significantly larger signal-to-noise ratio (SNR). For simulated EEG data, correlation between the pure signal and processed data was significantly higher for manually-processed data compared to HAPPE-processed data. Hierarchical linear modeling showed greater signal recovery in the manual pipeline with the exception of the gamma band signal which showed mixed results.

COMPARISON WITH EXISTING METHODS

SNR and simulated signal retention was significantly greater in the manually-processed data than the HAPPE-processed data. Signal reduction may negatively affect outcome measures.

CONCLUSIONS

The HAPPE pipeline benefits from less active processing time and artifact reduction without removing segments. However, HAPPE may bias toward elimination of noise at the cost of signal. Recommended implementation of the HAPPE pipeline for neurodevelopmental populations depends on the goals and priorities of the research.

Altered brain network topology during speech tracking in developmental dyslexia

Developmental dyslexia is often accompanied by altered phonological processing of speech. Underlying neural changes have typically been characterized in terms of stimulus- and/or task-related responses within individual brain regions or their functional connectivity. Less is known about potential changes in the more global functional organization of brain networks. Here we recorded electroencephalography (EEG) in typical and dyslexic readers while they listened to (a) a random sequence of syllables and (b) a series of tri-syllabic real words. The network topology of the phase synchronization of evoked cortical oscillations was investigated in four frequency bands (delta, theta, alpha and beta) using minimum spanning tree graphs. We found that, compared to syllable tracking, word tracking triggered a shift toward a more integrated network topology in the theta band in both groups. Importantly, this change was significantly stronger in the dyslexic readers, who also showed increased reliance on a right frontal cluster of electrodes for word tracking. The current findings point towards an altered effect of word-level processing on the functional brain network organization that may be associated with less efficient phonological and reading skills in dyslexia.

Gamma-band Enhancement of Functional Brain Connectivity Following Transcutaneous Electrical Nerve Stimulation

OBJECTIVE

Transcutaneous electrical nerve stimulation (TENS) has been suggested as a possible non-invasive pain treatment. However, the underlying mechanism of the analgesic effect of TENS and how brain network functional connectivity is affected following the use of TENS is not yet fully understood. The purpose of this study was to investigate the effect of high-frequency TENS on the alternation of functional brain network connectivity and the corresponding topographical changes, besides perceived sensations.

APPROACH

Forty healthy subjects participated in this study. EEG data and sensory profiles were recorded before and up to an hour following high-frequency TENS (100 Hz) in sham and intervention groups. Brain source activity from EEG data was estimated using the LORETA algorithm. In order to generate the brain connectivity network, the Phase lag index was calculated for all pair-wise connections of eight selected brain areas over six different frequency bands (i.e., δ, θ, α, β, γ, and 0.5-90 Hz).

MAIN RESULTS

The results suggested that the functional connectivity between the primary somatosensory cortex (SI) and the anterior cingulate cortex (ACC), in addition to functional connectivity between S1 and the medial prefrontal cortex (mPFC), were significantly increased in the gamma-band, following the TENS intervention. Additionally, using graph theory, several significant changes were observed in global and local characteristics of functional brain connectivity in gamma-band.

SIGNIFICANCE

Our observations in this paper open a neuropsychological window of understanding the underlying mechanism of TENS and the corresponding changes in functional brain connectivity, simultaneously with alternation in sensory perception.

Natural Infant-Directed Speech Facilitates Neural Tracking of Prosody

Infants prefer to be addressed with infant-directed speech (IDS). IDS benefits language acquisition through amplified low-frequency amplitude modulations. It has been reported that this amplification increases electrophysiological tracking of IDS compared to adult-directed speech (ADS). It is still unknown which particular frequency band triggers this effect. Here, we compare tracking at the rates of syllables and prosodic stress, which are both critical to word segmentation and recognition. In mother-infant dyads (n=30), mothers described novel objects to their 9-month-olds while infants' EEG was recorded. For IDS, mothers were instructed to speak to their children as they typically do, while for ADS, mothers described the objects as if speaking with an adult. Phonetic analyses confirmed that pitch features were more prototypically infant-directed in the IDS-condition compared to the ADS-condition. Neural tracking of speech was assessed by speech-brain coherence, which measures the synchronization between speech envelope and EEG. Results revealed significant speech-brain coherence at both syllabic and prosodic stress rates, indicating that infants track speech in IDS and ADS at both rates. We found significantly higher speech-brain coherence for IDS compared to ADS in the prosodic stress rate but not the syllabic rate. This indicates that the IDS benefit arises primarily from enhanced prosodic stress. Thus, neural tracking is sensitive to parents' speech adaptations during natural interactions, possibly facilitating higher-level inferential processes such as word segmentation from continuous speech.

SSA with CWT and k-Means for Eye-Blink Artifact Removal from Single-Channel EEG Signals

Recently, the use of portable electroencephalogram (EEG) devices to record brain signals in both health care monitoring and in other applications, such as fatigue detection in drivers, has been increased due to its low cost and ease of use. However, the measured EEG signals always mix with the electrooculogram (EOG), which are results due to eyelid blinking or eye movements. The eye-blinking/movement is an uncontrollable activity that results in a high-amplitude slow-time varying component that is mixed in the measured EEG signal. The presence of these artifacts misled our understanding of the underlying brain state. As the portable EEG devices comprise few EEG channels or sometimes a single EEG channel, classical artifact removal techniques such as blind source separation methods cannot be used to remove these artifacts from a single-channel EEG signal. Hence, there is a demand for the development of new single-channel-based artifact removal techniques. Singular spectrum analysis (SSA) has been widely used as a single-channel-based eye-blink artifact removal technique. However, while removing the artifact, the low-frequency components from the non-artifact region of the EEG signal are also removed by SSA. To preserve these low-frequency components, in this paper, we have proposed a new methodology by integrating the SSA with continuous wavelet transform (CWT) and the k-means clustering algorithm that removes the eye-blink artifact from the single-channel EEG signals without altering the low frequencies of the EEG signal. The proposed method is evaluated on both synthetic and real EEG signals. The results also show the superiority of the proposed method over the existing methods.

Spectral decomposition of EEG microstates in post-traumatic stress disorder

•

EEG microstates reveal significant temporal differences in PTSD.

•

Microstate E (with centro-posterior maximum) is temporally underrepresented in PTSD.

•

In PTSD, microstate E has a reduced occurrence and a shorter mean duration.

•

Spectral decomposition of EEG microstates improves microstate-based classification.

•

Alpha band SVM features yield the highest classification accuracy of PTSD (76%).

Microstates offer a promising framework to study fast-scale brain dynamics in the resting-state electroencephalogram (EEG). However, microstate dynamics have yet to be investigated in post-traumatic stress disorder (PTSD), despite research demonstrating resting-state alterations in PTSD. We performed microstate-based segmentation of resting-state EEG in a clinical population of participants with PTSD (N = 61) and a non-traumatized, healthy control group (N = 61). Microstate-based measures (i.e., occurrence, mean duration, time coverage) were compared group-wise using broadband (1–30 Hz) and frequency-specific (i.e., delta, theta, alpha, beta bands) decompositions. In the broadband comparisons, the centro-posterior maximum microstate (map E) occurred significantly less frequently (d = -0.64, pFWE = 0.03) and had a significantly shorter mean duration in participants with PTSD as compared to controls (d = -0.71, pFWE < 0.01). These differences were reflected in the narrow frequency bands as well, with lower frequency bands like delta (d = -0.78, pFWE < 0.01), theta (d = -0.74, pFWE = 0.01), and alpha (d = -0.65, pFWE = 0.02) repeating these group-level trends, only with larger effect sizes. Interestingly, a support vector machine classification analysis comparing broadband and frequency-specific measures revealed that models containing only alpha band features significantly out-perform broadband models. When classifying PTSD, the classification accuracy was 76 % and 65 % for the alpha band and the broadband model, respectively (p = 0.03). Taken together, we provide original evidence supporting the clinical utility of microstates as diagnostic markers of PTSD and demonstrate that filtering EEG into distinct frequency bands significantly improves microstate-based classification of a psychiatric disorder.

Neural response to repeated auditory stimuli and its association with early language ability in male children with Fragile X syndrome

Background

Fragile X syndrome (FXS) is the most prevalent form of inherited intellectual disability and is commonly associated with autism. Previous studies have linked the structural and functional alterations in FXS with impaired sensory processing and sensory hypersensitivity, which may hinder the early development of cognitive functions such as language comprehension. In this study, we compared the P1 response of the auditory evoked potential and its habituation to repeated auditory stimuli in male children (2-7 years old) with and without FXS, and examined their association with clinical measures in these two groups.

Methods

We collected high-density electroencephalography (EEG) data in an auditory oddball paradigm from 12 male children with FXS and 11 age- and sex-matched typically developing (TD) children. After standardized EEG pre-processing, we conducted a spatial principal component (PC) analysis and identified two major PCs-a frontal PC and a temporal PC. Within each PC, we compared the P1 amplitude and inter-trial phase coherence (ITPC) between the two groups, and performed a series of linear regression analysis to study the association between these EEG measures and several clinical measures, including assessment scores for language abilities, non-verbal skills, and sensory hypersensitivity.

Results

At the temporal PC, both early and late standard stimuli evoked a larger P1 response in FXS compared to TD participants. For temporal ITPC, the TD group showed greater habituation than the FXS group. However, neither group showed significant habituation of the frontal or temporal P1 response. Despite lack of habituation, exploratory analysis of brain-behavior associations observed that within the FXS group, reduced frontal P1 response to late standard stimuli, and increased frontal P1 habituation were both associated with better language scores.

Conclusion

We identified P1 amplitude and ITPC in the temporal region as a contrasting EEG phenotype between the FXS and the TD groups. However, only frontal P1 response and habituation were associated with language measures. Larger longitudinal studies are required to determine whether these EEG measures could be used as biomarkers for language development in patients with FXS.

Binaural sound therapy for tinnitus treatment: A psychometric and neurophysiological evaluation

INTRODUCTION

Tinnitus is an annoying buzz that manifests itself in many ways. In addition, it can provoke anxiety, stress, depression, and fatigue. The acoustic therapies have become the most commonly applied treatment for tinnitus, either self-administered or clinically prescribed. Binaural Sound Therapy (BST) and Music Therapy (MT) aim to reverse the neuroplasticity phenomenon related to tinnitus by adequately stimulating the auditory path-way. The goal of this research is to evaluate the feasibility of applying BST for tinnitus treatment by comparing its effect with MT effect.

MATERIALS AND METHODS

34 patients with tinnitus from 29 to 60 years were informed about the experimental procedure and consented their participation. Patients were divided into two groups: 1) MT and 2) BST. They applied their sound-based treatment for one hour every day along eight weeks. Each treatment was adjusted to Hearing Loss (HL) and tinnitus characteristics of each participant. To record EEG data, a bio-signal amplifier with sixteen EEG channels was used. The system recorded data at a sampling frequency of 256 Hz within a bandwidth between 0.1 and 100 Hz.

RESULTS

The questionnaire-monitoring reported that MT increased tinnitus perception in 30% of the patients, and increased anxiety and stress in 8% of them. Regarding EEG-monitoring, major neural synchronicity over the frontal lobe was found after the treatment. In the case of BST reduced stress in 23% of patients. Additionally, BST reduced tinnitus perception similar to MT (15% of patients). With respect to EEG-monitoring, slightly major neural synchronicity over the right frontal lobe was found after the treatment.

CONCLUSIONS

MT should be applied with caution since it could be worsening the tinnitus sufferer condition. On the other hand, BST is recommended for tinnitus sufferers who have side effects concerning stress but no anxiety.

On effective cognitive state classification using novel feature extraction strategies

Investigating new features for human cognitive state classification is an intiguing area of research with Electroencephalography (EEG) based signal analysis. We plan to develop a cost-effective system for cognitive state classification using ambulatory EEG signals. A novel event driven environment is created using external stimuli for capturing EEG data using a 14-channel Emotiv neuro-headset. A new feature extraction method, Gammatone Cepstrum Coefficients (GTCC) is introduced for ambulatory EEG signal analysis. The efficacy of this technique is compared with other feature extraction methods such as Discrete Wavelet Transformation (DWT) and Mel-Frequency Cepstral Coefficients (MFCC) using statistical metrics such as Fisher Discriminant Ratio (FDR) and Logistic Regression (LR). We obtain higher values for GTCC features, demonstrating its discriminative power during classification. A superior performance is achieved for the EEG dataset with a novel ensemble feature space comprising of GTCC and MFCC. Furthermore, the ensemble feature sets are passed through a proposed 1D Convolution Neural Networks (CNN) model to extract novel features. Various classification models like Probabilistic neural network (P-NN), Linear Discriminant Analysis (LDA), Multi-Class Support Vector Machine (MCSVM), Decision Tree (DT), Random Forest (RF) and Deep Convolutional Generative Adversarial Network (DCGAN) are employed to observe best accuracy on extracted features. The proposed GTCC, (GTCC+MFCC) & (GTCC +MFCC +CNN) features outperform the state-of-the-art techniques for all cases in our work. With GTCC+MFCC feature space and GTCC+MFCC+CNN features, accuracies of 96.42% and 96.14% are attained with the DCGAN classifier. Higher classification accuracies of the proposed system makes it a cynosure in the field of cognitive science.

EEG-connectivity: A fundamental guide and checklist for optimal study design and evaluation

Brain connectivity can be estimated through many analyses applied to electroencephalographic (EEG) data. However, substantial heterogeneity in the implementation of connectivity methods exist. Heterogeneity in conceptualization of connectivity measures, data collection, or data pre-processing may be associated with variability in robustness of measurement. While it is difficult to compare the results of studies using different EEG connectivity measures, standardization of processing and reporting may facilitate the task. We discuss how factors such as referencing, epoch length and number, controls for volume conduction, artefact removal, and statistical control of multiple comparisons influence the EEG connectivity estimate for connectivity measures, and what can be done to control for potential confounds associated with these factors. Based on the results reported in previous literature, this article presents recommendations and a novel checklist developed for quality assessment of EEG connectivity studies. This checklist and its recommendations are made in an effort to draw attention to factors that may influence connectivity estimates and factors that need to be improved in future research. Standardization of procedures and reporting in EEG connectivity may lead to EEG connectivity studies to be made more synthesisable and comparable despite variations in the methodology underlying connectivity estimates.

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.

Automated Detection and Removal of Cardiac and Pulse Interferences from Neonatal EEG Signals

Electrical cardiac and pulsatile interference is very difficult to remove from electroencephalographic (EEG) signals, especially if recorded in neonates, for which a small number of EEG channels is used. Several methods were proposed, including Blind Source Separation (BSS) methods that required the use of artificial cardiac-related signals to improve the separation of artefactual components. To optimize the separation of cardiac-related artefactual components, we propose a method based on Independent Component Analysis (ICA) that exploits specific features of the real electrocardiographic (ECG) signals that were simultaneously recorded with the neonatal EEG. A total of forty EEG segments from 19-channel neonatal EEG recordings with and without seizures were used to test and validate the performance of our method. We observed a significant reduction in the number of independent components (ICs) containing cardiac-related interferences, with a consequent improvement in the automated classification of the separated ICs. The comparison with the expert labeling of the ICs separately containing electrical cardiac and pulsatile interference led to an accuracy = 0.99, a false omission rate = 0.01 and a sensitivity = 0.93, outperforming existing methods. Furthermore, we verified that true brain activity was preserved in neonatal EEG signals reconstructed after the removal of artefactual ICs, demonstrating the effectiveness of our method and its safe applicability in a clinical context.

Progress and Challenges in Physiological Artifacts' Detection in Electroencephalographic Readings

BACKGROUND

Electroencephalographic (EEG) recordings are used to trace neural activity within the cortex to study brain functioning over time.

INTRODUCTION

During data acquisition, the unequivocal way to reduce artifact is to avoid artifact stimulating events. Though there are certain artifacts that make this task challenging due to their association with the internal human mechanism, in the human-computer interface, these physiological artifacts are of great assistance and act as a command signal for controlling a device or an application (communication). That is why pre-processing of electroencephalographic readings has been a progressive area of exploration, as none of the published work can be viewed as a benchmark for constructive artifact handling.

METHOD

This review offers a comprehensive insight into state of the art physiological artifact removal techniques listed so far. The study commences from the single-stage traditional techniques to the multistage techniques, examining the pros and cons of each discussed technique. Also, this review paper gives a general idea of various datasets available and briefs the topical trend in EEG signal processing.

RESULT

Comparing the state of the art techniques with hybrid ones on the basis of performance and computational complexity, it has been observed that the single-channel techniques save computational time but lack in effective artifact removal especially physiological artifacts. On the other hand, hybrid techniques merge the essential characteristics resulting in increased performance, but time consumption and complexity remain an issue.

CONCLUSION

Considering the high probability of the presence of multiple artifacts in EEG channels, a trade-off between performance, time and computational complexity is the only key for effective processing of artifacts in the time ahead. This paper is anticipated to facilitate upcoming researchers in enriching the contemporary artifact handling techniques to mitigate the expert's burden.

EEG feature fusion for motor imagery: A new robust framework towards stroke patients rehabilitation

Stroke is the second foremost cause of death worldwide and is one of the most common causes of disability. Several approaches have been proposed to manage stroke patient rehabilitation such as robotic devices and virtual reality systems, and researchers have found that the brain-computer interfaces (BCI) approaches can provide better results. Therefore, the most challenging tasks with BCI applications involve identifying the best technique(s) that can reveal the neuron stimulus information from the patients' brains and extracting the most effective features from these signals as well. Accordingly, the main novelty of this paper is twofold: propose a new feature fusion method for motor imagery (MI)-based BCI and develop an automatic MI framework to detect the changes pre- and post-rehabilitation. This study investigated the electroencephalography (EEG) dataset from post-stroke patients with upper extremity hemiparesis. All patients performed 25 MI-based BCI sessions with follow up assessment visits to examine the functional changes before and after EEG neurorehabilitation. In the first stage, conventional filters and automatic independent component analysis with wavelet transform (AICA-WT) denoising technique were used. Next, attributes from time, entropy and frequency domains were computed, and the effective features were combined into time-entropy-frequency (TEF) attributes. Consequently, the AICA-WT and the TEF fusion set were utilised to develop an AICA-WT-TEF framework. Then, support vector machine (SVM), k-nearest neighbours (kNN) and random forest (RF) classification technique were tested for MI-based BCI rehabilitation. The proposed AICA-WT-TEF framework with RF classifier achieves the best results compared with other classifiers. Finally, the proposed framework and feature fusion set achieve a significant performance in terms of accuracy measures compared to the state-of-the-art. Therefore, the proposed methods could be crucial for improving the process of automatic MI rehabilitation and are recommended for implementation in real-time applications.

Choosing Strategies to Deal with Artifactual EEG Data in Children with Cognitive Impairment

Rett syndrome is a disease that involves acute cognitive impairment and, consequently, a complex and varied symptomatology. This study evaluates the EEG signals of twenty-nine patients and classify them according to the level of movement artifact. The main goal is to achieve an artifact rejection strategy that performs well in all signals, regardless of the artifact level. Two different methods have been studied: one based on the data distribution and the other based on the energy function, with entropy as its main component. The method based on the data distribution shows poor performance with signals containing high amplitude outliers. On the contrary, the method based on the energy function is more robust to outliers. As it does not depend on the data distribution, it is not affected by artifactual events. A double rejection strategy has been chosen, first on a motion signal (accelerometer or EEG low-pass filtered between 1 and 10 Hz) and then on the EEG signal. The results showed a higher performance when working combining both artifact rejection methods. The energy-based method, to isolate motion artifacts, and the data-distribution-based method, to eliminate the remaining lower amplitude artifacts were used. In conclusion, a new method that proves to be robust for all types of signals is designed.

WeDea: A New EEG-based Framework for Emotion Recognition

With the development of sensing technologies and machine learning, techniques that can identify emotions and inner states of a human through physiological signals, known as electroencephalography (EEG), have been actively developed and applied to various domains, such as automobiles, robotics, healthcare, and customer-support services. Thus, the demand for acquiring and analyzing EEG signals in real-time is increasing. In this paper, we aimed to acquire a new EEG dataset based on the discrete emotion theory, termed as WeDea (Wireless-based eeg Data for emotion analysis), and propose a new combination for WeDea analysis. For the collected WeDea dataset, we used video clips as emotional stimulants that were selected by 15 volunteers. Consequently, WeDea is a multi-way dataset measured while 30 subjects are watching the selected 79 video clips under five different emotional states using a convenient portable headset device. Furthermore, we designed a framework for recognizing human emotional state using this new database. The practical results for different types of emotions have proven that WeDea is a promising resource for emotion analysis and can be applied to the field of neuroscience.

Probability mapping based artifact detection and removal from single-channel EEG signals for brain-computer interface applications

BACKGROUND

Different types of artifacts in the electroencephalogram (EEG) signals can considerably reduce the performance of the later-stage EEG analysis algorithms for making decisions, such as those for brain-computer interfacing (BCI) classification. In this paper, we address the problem of artifact detection and removal from single-channel EEG signals.

NEW METHOD

We propose a novel approach that maps the probability of an EEG epoch to be artifactual based on four different statistical measures: entropy (a measure of uncertainty), kurtosis (a measure of peakedness), skewness (a measure of asymmetry), and periodic waveform index (a measure of periodicity). Then, a stationary wavelet transform based artifact removal is proposed that employs a particular probability threshold provided by the user.

RESULTS

We have executed our experiments with both synthetic and real EEG data. It is observed that the proposed method exhibits a superior performance for suppressing the artifact contaminated from EEG with minimum distortion. Moreover, evaluation of the algorithm using EEG dataset for BCI experiments reveals that artifact removal can considerably improve the BCI output in both event-related potential and motor-imagery based BCI applications.

COMPARISON WITH EXISTING METHODS

The proposed algorithm has been applied to both real and synthesized data testing and compared with other state-of-the-art automated artifact removal methods. Its superior performance is verified in terms of various performance metrics including computational complexity for justifying its use in BCI-like real-time applications.

CONCLUSION

Our work is expected to be useful for future research EEG signal processing and eventually to develop more accurate real-time EEG-based BCI applications.

On the estimate of music appraisal from surface EEG: a dynamic-network approach based on cross-sensor PAC measurements

Objective.The aesthetic evaluation of music is strongly dependent on the listener and reflects manifold brain processes that go well beyond the perception of incident sound. Being a high-level cognitive reaction, it is difficult to predict merely from the acoustic features of the audio signal and this poses serious challenges to contemporary music recommendation systems. We attempted to decode music appraisal from brain activity, recorded via wearable EEG, during music listening.Approach.To comply with the dynamic nature of music stimuli, cross-frequency coupling measurements were employed in a time-evolving manner to capture the evolving interactions between distinct brain-rhythms during music listening. Brain response to music was first represented as a continuous flow of functional couplings referring to both regional and inter-regional brain dynamics and then modelled as an ensemble of time-varying (sub)networks. Dynamic graph centrality measures were derived, next, as the final feature-engineering step and, lastly, a support-vector machine was trained to decode the subjective music appraisal. A carefully designed experimental paradigm provided the labeled brain signals.Main results.Using data from 20 subjects, dynamic programming to tailor the decoder to each subject individually and cross-validation, we demonstrated highly satisfactory performance (MAE= 0.948,R²= 0.63) that can be attributed, mostly, to interactions of left frontal gamma rhythm. In addition, our music-appraisal decoder was also employed in a part of the DEAP dataset with similar success. Finally, even a generic version of the decoder (common for all subjects) was found to perform sufficiently.Significance.A novel brain signal decoding scheme was introduced and validated empirically on suitable experimental data. It requires simple operations and leaves room for real-time implementation. Both the code and the experimental data are publicly available.