Artifact removal in physiological signals--practices and possibilities

Convolutional neural network framework for EEG-based ADHD diagnosis in children

Purpose

Attention-deficit hyperactivity disorder (ADHD) stands as a significant psychiatric and neuro-developmental disorder with global prevalence. The prevalence of ADHD among school children in India is estimated to range from 5% to 8%. However, certain studies have reported higher prevalence rates, reaching as high as 11%. Utilizing electroencephalography (EEG) signals for the early detection and classification of ADHD in children is crucial.

Methods

In this study, we introduce a CNN architecture characterized by its simplicity, comprising solely two convolutional layers. Our approach involves pre-processing EEG signals through a band-pass filter and segmenting them into 5-s frames. Following this, the frames undergo normalization and canonical correlation analysis. Subsequently, the proposed CNN architecture is employed for training and testing purposes.

Results

Our methodology yields remarkable results, with 100% accuracy, sensitivity, and specificity when utilizing the complete 19-channel EEG signals for diagnosing ADHD in children. However, employing the entire set of EEG channels presents challenges related to the computational complexity. Therefore, we investigate the feasibility of using only frontal brain EEG channels for ADHD detection, which yields an accuracy of 99.08%.

Conclusions

The proposed method yields high accuracy and is easy to implement, hence, it has the potential for widespread practical deployment to diagnose ADHD.

Optimizing EEG Signal Integrity: A Comprehensive Guide to Ocular Artifact Correction

Ocular artifacts, including blinks and saccades, pose significant challenges in the analysis of electroencephalographic (EEG) data, often obscuring crucial neural signals. This tutorial provides a comprehensive guide to the most effective methods for correcting these artifacts, with a focus on algorithms designed for both laboratory and real-world settings. We review traditional approaches, such as regression-based techniques and Independent Component Analysis (ICA), alongside more advanced methods like Artifact Subspace Reconstruction (ASR) and deep learning-based algorithms. Through detailed step-by-step instructions and comparative analysis, this tutorial equips researchers with the tools necessary to maintain the integrity of EEG data, ensuring accurate and reliable results in neurophysiological studies. The strategies discussed are particularly relevant for wearable EEG systems and real-time applications, reflecting the growing demand for robust and adaptable solutions in applied neuroscience.

Exploring Computational Techniques in Preprocessing Neonatal Physiological Signals for Detecting Adverse Outcomes: Scoping Review

BACKGROUND

Computational signal preprocessing is a prerequisite for developing data-driven predictive models for clinical decision support. Thus, identifying the best practices that adhere to clinical principles is critical to ensure transparency and reproducibility to drive clinical adoption. It further fosters reproducible, ethical, and reliable conduct of studies. This procedure is also crucial for setting up a software quality management system to ensure regulatory compliance in developing software as a medical device aimed at early preclinical detection of clinical deterioration.

OBJECTIVE

This scoping review focuses on the neonatal intensive care unit setting and summarizes the state-of-the-art computational methods used for preprocessing neonatal clinical physiological signals; these signals are used for the development of machine learning models to predict the risk of adverse outcomes.

METHODS

Five databases (PubMed, Web of Science, Scopus, IEEE, and ACM Digital Library) were searched using a combination of keywords and MeSH (Medical Subject Headings) terms. A total of 3585 papers from 2013 to January 2023 were identified based on the defined search terms and inclusion criteria. After removing duplicates, 2994 (83.51%) papers were screened by title and abstract, and 81 (0.03%) were selected for full-text review. Of these, 52 (64%) were eligible for inclusion in the detailed analysis.

RESULTS

Of the 52 articles reviewed, 24 (46%) studies focused on diagnostic models, while the remainder (n=28, 54%) focused on prognostic models. The analysis conducted in these studies involved various physiological signals, with electrocardiograms being the most prevalent. Different programming languages were used, with MATLAB and Python being notable. The monitoring and capturing of physiological data used diverse systems, impacting data quality and introducing study heterogeneity. Outcomes of interest included sepsis, apnea, bradycardia, mortality, necrotizing enterocolitis, and hypoxic-ischemic encephalopathy, with some studies analyzing combinations of adverse outcomes. We found a partial or complete lack of transparency in reporting the setting and the methods used for signal preprocessing. This includes reporting methods to handle missing data, segment size for considered analysis, and details regarding the modification of the state-of-the-art methods for physiological signal processing to align with the clinical principles for neonates. Only 7 (13%) of the 52 reviewed studies reported all the recommended preprocessing steps, which could have impacts on the downstream analysis.

CONCLUSIONS

The review found heterogeneity in the techniques used and inconsistent reporting of parameters and procedures used for preprocessing neonatal physiological signals, which is necessary to confirm adherence to clinical and software quality management system practices, usefulness, and choice of best practices. Enhancing transparency in reporting and standardizing procedures will boost study interpretation and reproducibility and expedite clinical adoption, instilling confidence in the research findings and streamlining the translation of research outcomes into clinical practice, ultimately contributing to the advancement of neonatal care and patient outcomes.

Sample Entropy Computation on Signals with Missing Values

Sample entropy embeds time series into m-dimensional spaces and estimates entropy based on the distances between points in these spaces. However, when samples can be considered as missing or invalid, defining distance in the embedding space becomes problematic. Preprocessing techniques, such as deletion or interpolation, can be employed as a solution, producing time series without missing or invalid values. While deletion ignores missing values, interpolation replaces them using approximations based on neighboring points. This paper proposes a novel approach for the computation of sample entropy when values are considered as missing or invalid. The proposed algorithm accommodates points in the m-dimensional space and handles them there. A theoretical and experimental comparison of the proposed algorithm with deletion and interpolation demonstrates several advantages over these other two approaches. Notably, the deviation of the expected sample entropy value for the proposed methodology consistently proves to be lowest one.

Characterization of Cochlear Implant Artifact and Removal Based on Multi-Channel Wiener Filter in Unilateral Child Patients

Cochlear implants (CI) allow deaf patients to improve language perception and improving their emotional valence assessment. Electroencephalographic (EEG) measures were employed so far to improve CI programming reliability and to evaluate listening effort in auditory tasks, which are particularly useful in conditions when subjective evaluations are scarcely appliable or reliable. Unfortunately, the presence of CI on the scalp introduces an electrical artifact coupled to EEG signals that masks physiological features recorded by electrodes close to the site of implant. Currently, methods for CI artifact removal have been developed for very specific EEG montages or protocols, while others require many scalp electrodes. In this study, we propose a method based on the Multi-channel Wiener filter (MWF) to overcome those shortcomings. Nine children with unilateral CI and nine age-matched normal hearing children (control) participated in the study. EEG data were acquired on a relatively low number of electrodes (n = 16) during resting condition and during an auditory task. The obtained results obtained allowed to characterize CI artifact on the affected electrode and to significantly reduce, if not remove it through MWF filtering. Moreover, the results indicate, by comparing the two sample populations, that the EEG data loss is minimal in CI users after filtering, and that data maintain EEG physiological characteristics.

Motion artifacts in capacitive ECG monitoring systems: a review of existing models and reduction techniques

Current research focuses on improving electrocardiogram (ECG) monitoring systems to enable real-time and long-term usage, with a specific focus on facilitating remote monitoring of ECG data. This advancement is crucial for improving cardiovascular health by facilitating early detection and management of cardiovascular disease (CVD). To efficiently meet these demands, user-friendly and comfortable ECG sensors that surpass wet electrodes are essential. This has led to increased interest in ECG capacitive electrodes, which facilitate signal detection without requiring gel preparation or direct conductive contact with the body. This feature makes them suitable for wearables or integrated measurement devices. However, ongoing research is essential as the signals they measure often lack sufficient clinical accuracy due to susceptibility to interferences, particularly Motion Artifacts (MAs). While our primary focus is on studying MAs, we also address other limitations crucial for designing a high Signal-to-Noise Ratio (SNR) circuit and effectively mitigating MAs. The literature on the origins and models of MAs in capacitive electrodes is insufficient, which we aim to address alongside discussing mitigation methods. We bring attention to digital signal processing approaches, especially those using reference signals like Electrode-Tissue Impedance (ETI), as highly promising. Finally, we discuss its challenges, proposed solutions, and offer insights into future research directions.

Conservative method for vertical electrooculogram attenuation based on local suppression of ongoing EEG artifact templates

Eye movement during blinking can be a significant artifact in Event-Related Potentials (ERP) analysis. Blinks produce a positive potential in the vertical electrooculogram (VEOG), spreading towards the posterior direction. Two methods are frequently used to suppress VEOGs: linear regression to subtract the VEOG signal from the electroencephalogram (EEG) and Independent Component Analysis (ICA). However, some information is lost in both. The present algorithm (1) statistically identifies the position of VEOGs in the frontopolar channels; (2) performs EEG averaging for each channel, which results in 'blink templates'; (3) subtracts each template from the respective EEG at each VEOG position, only when the linear correlation index between the template and the segment is greater than a chosen threshold L. The signals from twenty subjects were acquired using a behavioral test and were treated using FilterBlink for subsequent ERP analysis. A model was designed to test the method for each subject using twenty copies of the EEG signal from the subject's mid-central channel (with nearly no VEOG) representing the EEG channels and their respective blink templates. At the same 200 equidistant time points (marks), a signal (2.5 sinusoidal cycles at 1050 ms emulating an ERP) was mixed with each model channel and the respective blink template of that channel, between 500 to 1200 ms after each mark. According to the model, VEOGs interfered with both ERPs and the ongoing EEG, mainly on the anterior medial leads, and no significant effect was observed on the mid-central channel (Cz). FilterBlink recovered approximately 90% (Fp1) to 98% (Fz) of the original ERP and EEG signals for L = 0.1. The method reduced the VEOG effect on the EEG after ERP and blink-artifact averaging in analyzing real signals. The method is straightforward and effective for VEOG attenuation without significant distortion in the EEG signal and embedded ERPs.

Artificial Intelligence-Based Atrial Fibrillation Recognition Method for Motion Artifact-Contaminated Electrocardiogram Signals Preprocessed by Adaptive Filtering Algorithm

Atrial fibrillation (AF) is a common arrhythmia, and out-of-hospital, wearable, long-term electrocardiogram (ECG) monitoring can help with the early detection of AF. The presence of a motion artifact (MA) in ECG can significantly affect the characteristics of the ECG signal and hinder early detection of AF. Studies have shown that (a) using reference signals with a strong correlation with MAs in adaptive filtering (ADF) can eliminate MAs from the ECG, and (b) artificial intelligence (AI) algorithms can recognize AF when there is no presence of MAs. However, no literature has been reported on whether ADF can improve the accuracy of AI for recognizing AF in the presence of MAs. Therefore, this paper investigates the accuracy of AI recognition for AF when ECGs are artificially introduced with MAs and processed by ADF. In this study, 13 types of MA signals with different signal-to-noise ratios ranging from +8 dB to -16 dB were artificially added to the AF ECG dataset. Firstly, the accuracy of AF recognition using AI was obtained for a signal with MAs. Secondly, after removing the MAs by ADF, the signal was further identified using AI to obtain the accuracy of the AF recognition. We found that after undergoing ADF, the accuracy of AI recognition for AF improved under all MA intensities, with a maximum improvement of 60%.

A causal perspective on brainwave modeling for brain-computer interfaces

Objective. Machine learning (ML) models have opened up enormous opportunities in the field of brain-computer Interfaces (BCIs). Despite their great success, they usually face severe limitations when they are employed in real-life applications outside a controlled laboratory setting.Approach. Mixing causal reasoning, identifying causal relationships between variables of interest, with brainwave modeling can change one's viewpoint on some of these major challenges which can be found in various stages in the ML pipeline, ranging from data collection and data pre-processing to training methods and techniques.Main results. In this work, we employ causal reasoning and present a framework aiming to breakdown and analyze important challenges of brainwave modeling for BCIs.Significance. Furthermore, we present how general ML practices as well as brainwave-specific techniques can be utilized and solve some of these identified challenges. And finally, we discuss appropriate evaluation schemes in order to measure these techniques' performance and efficiently compare them with other methods that will be developed in the future.

Uncertainties in the Analysis of Heart Rate Variability: A Systematic Review

Heart rate variability (HRV) is an important metric with a variety of applications in clinical situations such as cardiovascular diseases, diabetes mellitus, and mental health. HRV data can be potentially obtained from electrocardiography and photoplethysmography signals, then computational techniques such as signal filtering and data segmentation are used to process the sampled data for calculating HRV measures. However, uncertainties arising from data acquisition, computational models, and physiological factors can lead to degraded signal quality and affect HRV analysis. Therefore, it is crucial to address these uncertainties and develop advanced models for HRV analysis. Although several reviews of HRV analysis exist, they primarily focus on clinical applications, trends in HRV methods, or specific aspects of uncertainties such as measurement noise. This paper provides a comprehensive review of uncertainties in HRV analysis, quantifies their impacts, and outlines potential solutions. To the best of our knowledge, this is the first study that presents a holistic review of uncertainties in HRV methods and quantifies their impacts on HRV measures from an engineer's perspective. This review is essential for developing robust and reliable models, and could serve as a valuable future reference in the field, particularly for dealing with uncertainties in HRV analysis.

PhysioKit: An Open-Source, Low-Cost Physiological Computing Toolkit for Single- and Multi-User Studies

The proliferation of physiological sensors opens new opportunities to explore interactions, conduct experiments and evaluate the user experience with continuous monitoring of bodily functions. Commercial devices, however, can be costly or limit access to raw waveform data, while low-cost sensors are efforts-intensive to setup. To address these challenges, we introduce PhysioKit, an open-source, low-cost physiological computing toolkit. PhysioKit provides a one-stop pipeline consisting of (i) a sensing and data acquisition layer that can be configured in a modular manner per research needs, and (ii) a software application layer that enables data acquisition, real-time visualization and machine learning (ML)-enabled signal quality assessment. This also supports basic visual biofeedback configurations and synchronized acquisition for co-located or remote multi-user settings. In a validation study with 16 participants, PhysioKit shows strong agreement with research-grade sensors on measuring heart rate and heart rate variability metrics data. Furthermore, we report usability survey results from 10 small-project teams (44 individual members in total) who used PhysioKit for 4-6 weeks, providing insights into its use cases and research benefits. Lastly, we discuss the extensibility and potential impact of the toolkit on the research community.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

Rating by detection: an artifact detection protocol for rating EEG quality with average event duration

Objective. Quantitative evaluation protocols are critical for the development of algorithms that remove artifacts from real electroencephalography (EEG) optimally. However, visually inspecting the real EEG to select the top-performing artifact removal pipeline is infeasible while hand-crafted EEG data allow assessing artifact removal configurations only in a simulated environment. This study proposes a novel, principled approach for quantitatively evaluating algorithmically corrected EEG without access to ground truth in real-world conditions.Approach. Our offline evaluation protocol uses a detector to score the presence of artifacts. It computes their average duration, which measures the recovered EEG's deviation from the modeled background activity with a single score. As we expect the detector to make generalization errors, we employ a generic and configurable Wiener-based artifact removal method to validate the reliability of our detection protocol.Main results. Quantitative experiments extensively compare many Wiener filters and show their consistent rankings agree with their theoretical assumptions and expectations.Significance. The rating-by-detection protocol with the average event duration measure should be of value for EEG practitioners and developers. After removing artifacts from real EEG, the protocol experimentally shows that reliable comparisons between many artifact filtering configurations are possible despite the missing ground-truth neural signals.

Behavior and Task Classification Using Wearable Sensor Data: A Study across Different Ages

In this paper, we face the problem of task classification starting from physiological signals acquired using wearable sensors with experiments in a controlled environment, designed to consider two different age populations: young adults and older adults. Two different scenarios are considered. In the first one, subjects are involved in different cognitive load tasks, while in the second one, space varying conditions are considered, and subjects interact with the environment, changing the walking conditions and avoiding collision with obstacles. Here, we demonstrate that it is possible not only to define classifiers that rely on physiological signals to predict tasks that imply different cognitive loads, but it is also possible to classify both the population group age and the performed task. The whole workflow of data collection and analysis, starting from the experimental protocol, data acquisition, signal denoising, normalization with respect to subject variability, feature extraction and classification is described here. The dataset collected with the experiments together with the codes to extract the features of the physiological signals are made available for the research community.

Online Learning for Wearable EEG-Based Emotion Classification

Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9% (Arousal) and 25.8% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87% (Arousal) and 82% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.

The Feature, Performance, and Prospect of Advanced Electrodes for Electroencephalogram

Recently, advanced electrodes have been developed, such as semi-dry, dry contact, dry non-contact, and microneedle array electrodes. They can overcome the issues of wet electrodes and maintain high signal quality. However, the variations in these electrodes are still unclear and not explained, and there is still confusion regarding the feasibility of electrodes for different application scenarios. In this review, the physical features and electroencephalogram (EEG) signal performances of these advanced EEG electrodes are introduced in view of the differences in contact between the skin and electrodes. Specifically, contact features, biofeatures, impedance, signal quality, and artifacts are discussed. The application scenarios and prospects of different types of EEG electrodes are also elucidated.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

Comparing a Fitbit Wearable to an Electrocardiogram Gold Standard as a Measure of Heart Rate Under Psychological Stress: A Validation Study

BACKGROUND

Wearable devices collect physiological and behavioral data that have the potential to identify individuals at risk of declining mental health and well-being. Past research has mainly focused on assessing the accuracy and the agreement of heart rate (HR) measurement of wearables under different physical exercise conditions. However, the capacity of wearables to sense physiological changes, assessed by increasing HR, caused by a stressful event has not been thoroughly studied.

OBJECTIVE

This study followed 3 objectives: (1) to test the ability of a wearable device (Fitbit Versa 2) to sense an increase in HR upon induction of psychological stress in the laboratory; (2) to assess the accuracy of the wearable device to capture short-term HR variations caused by psychological stress compared to a gold-standard electrocardiogram (ECG) measure (Biopac); and (3) to quantify the degree of agreement between the wearable device and the gold-standard ECG measure across different experimental conditions.

METHODS

Participants underwent the Trier Social Stress Test protocol, which consists of an oral phase, an arithmetic stress phase, an anticipation phase, and 2 relaxation phases (at the beginning and the end). During the stress protocol, the participants wore a Fitbit Versa 2 and were also connected to a Biopac. A mixed-effect modeling approach was used (1) to assess the effect of experimental conditions on HR, (2) to estimate several metrics of accuracy, and (3) to assess the agreement: the Bland-Altman limits of agreement (LoA), the concordance correlation coefficient, the coverage probability, the total deviation index, and the coefficient of an individual agreement. Mean absolute error and mean absolute percent error were calculated as accuracy indices.

RESULTS

A total of 34 university students were recruited for this study (64% of participants were female with a mean age of 26.8 years, SD 8.3). Overall, the results showed significant HR variations across experimental phases. Post hoc tests revealed significant pairwise differences for all phases. Accuracy analyses revealed acceptable accuracy according to the analyzed metrics of accuracy for the Fitbit Versa 2 to capture the short-term variations in psychological stress levels. However, poor indices of agreement between the Fitbit Versa 2 and the Biopac were found.

CONCLUSIONS

Overall, the results support the use of the Fitbit Versa 2 to capture short-term stress variations. The Fitbit device showed acceptable levels of accuracy but poor agreement with an ECG gold standard. Greater inaccuracy and smaller agreement were found for stressful experimental conditions that induced a higher HR. Fitbit devices can be used in research to measure HR variations caused by stress, although they cannot replace an ECG instrument when precision is of utmost importance.

EEGDnet: Fusing non-local and local self-similarity for EEG signal denoising with transformer

Electroencephalogram (EEG) has shown a useful approach to produce a brain-computer interface (BCI). One-dimensional (1-D) EEG signal is yet easily disturbed by certain artifacts (a.k.a. noise) due to the high temporal resolution. Thus, it is crucial to remove the noise in received EEG signal. Recently, deep learning-based EEG signal denoising approaches have achieved impressive performance compared with traditional ones. It is well known that the characteristics of self-similarity (including non-local and local ones) of data (e.g., natural images and time-domain signals) are widely leveraged for denoising. However, existing deep learning-based EEG signal denoising methods ignore either the non-local self-similarity (e.g., 1-D convolutional neural network) or local one (e.g., fully connected network and recurrent neural network). To address this issue, we propose a novel 1-D EEG signal denoising network with 2-D transformer, namely EEGDnet. Specifically, we comprehensively take into account the non-local and local self-similarity of EEG signal through the transformer module. By fusing non-local self-similarity in self-attention blocks and local self-similarity in feed forward blocks, the negative impact caused by noises and outliers can be reduced significantly. Extensive experiments show that, compared with other state-of-the-art models, EEGDnet achieves much better performance in terms of both quantitative and qualitative metrics. Specifically, EEGDnet can achieve 18% and 11% improvements in correlation coefficients when removing ocular artifacts and muscle artifacts, respectively.

A time-frequency denoising method for single-channel event-related EEG

Introduction

Electroencephalogram (EEG) acquisition is easily affected by various noises, including those from electrocardiogram (ECG), electrooculogram (EOG), and electromyogram (EMG). Because noise interference can significantly limit the study and analysis of brain signals, there is a significant need for the development of improved methods to remove this interference for more accurate measurement of EEG signals.

Methods

Based on the non-linear and non-stationary characteristics of brain signals, a strategy was developed to denoise brain signals using a time-frequency denoising algorithm framework of short-time Fourier transform (STFT), bidimensional empirical mode decomposition (BEMD), and non-local means (NLM). Time-frequency analysis can reveal the signal frequency component and its evolution process, allowing the elimination of noise according to the signal and noise distribution. BEMD can be used to decompose the time-frequency signals into sub-time-frequency signals for noise removal at different scales. NLM relies on structural self-similarity to locally smooth an image to remove noise and restore its main geometric structure, making this method appropriate for time-frequency signal denoising.

Results

The experimental results show that the proposed method can effectively suppress the high-frequency components of brain signals, resulting in a smoother brain signal waveform after denoising. The correlation coefficient of the reference signal, a superposition average of multiple trial signals, and the original single trial signal was determined, and then correlation coefficients were calculated between the reference signal and single trial signals processed by time-frequency denoising, ensemble empirical mode decomposition (EEMD)-independent component analysis (ICA), EEMD-canonical correlation analysis (CCA), and wavelet threshold denoising methods. The correlation coefficient was highest for the signal processed by the time-frequency denoising method and the reference signal, indicating that the single trial signal after time-frequency denoising was most similar to the waveform of the reference signal and suggesting this is a feasible strategy to effectively reduce noise and more accurately determine signals.

Discussion

The proposed time-frequency denoising method exhibits excellent performance with promising potential for practical application.

SenseHunger: Machine Learning Approach to Hunger Detection Using Wearable Sensors

The perception of hunger and satiety is of great importance to maintaining a healthy body weight and avoiding chronic diseases such as obesity, underweight, or deficiency syndromes due to malnutrition. There are a number of disease patterns, characterized by a chronic loss of this perception. To our best knowledge, hunger and satiety cannot be classified using non-invasive measurements. Aiming to develop an objective classification system, this paper presents a multimodal sensory system using associated signal processing and pattern recognition methods for hunger and satiety detection based on non-invasive monitoring. We used an Empatica E4 smartwatch, a RespiBan wearable device, and JINS MEME smart glasses to capture physiological signals from five healthy normal weight subjects inactively sitting on a chair in a state of hunger and satiety. After pre-processing the signals, we compared different feature extraction approaches, either based on manual feature engineering or deep feature learning. Comparative experiments were carried out to determine the most appropriate sensor channel, device, and classifier to reliably discriminate between hunger and satiety states. Our experiments showed that the most discriminative features come from three specific sensor modalities: Electrodermal Activity (EDA), infrared Thermopile (Tmp), and Blood Volume Pulse (BVP).

ABOT: an open-source online benchmarking tool for machine learning-based artefact detection and removal methods from neuronal signals

Brain signals are recorded using different techniques to aid an accurate understanding of brain function and to treat its disorders. Untargeted internal and external sources contaminate the acquired signals during the recording process. Often termed as artefacts, these contaminations cause serious hindrances in decoding the recorded signals; hence, they must be removed to facilitate unbiased decision-making for a given investigation. Due to the complex and elusive manifestation of artefacts in neuronal signals, computational techniques serve as powerful tools for their detection and removal. Machine learning (ML) based methods have been successfully applied in this task. Due to ML's popularity, many articles are published every year, making it challenging to find, compare and select the most appropriate method for a given experiment. To this end, this paper presents ABOT (Artefact removal Benchmarking Online Tool) as an online benchmarking tool which allows users to compare existing ML-driven artefact detection and removal methods from the literature. The characteristics and related information about the existing methods have been compiled as a knowledgebase (KB) and presented through a user-friendly interface with interactive plots and tables for users to search it using several criteria. Key characteristics extracted from over 120 articles from the literature have been used in the KB to help compare the specific ML models. To comply with the FAIR (Findable, Accessible, Interoperable and Reusable) principle, the source code and documentation of the toolbox have been made available via an open-access repository.

Extracting synchronized neuronal activity from local field potentials based on a marked point process framework

OBJECTIVE

Brain-machine interfaces (BMIs) translate neural activity into motor commands to restore motor functions for people with paralysis. Local field potentials (LFPs) are promising for long-term BMIs, since the quality of the recording lasts longer than single neuronal spikes. Inferring neuronal spike activity from population activities such as LFPs is challenging, because LFPs stem from synaptic currents flowing in the neural tissue produced by various neuronal ensembles and reflect neural synchronization. Existing studies that combine LFPs with spikes leverage the spectrogram of LFPs, which can neither detect the transient characteristics of LFP features (here, neuromodulation in a specific frequency band) with high accuracy, nor correlate them with relevant neuronal activity with a sufficient time resolution.

APPROACH

We propose a feature extraction and validation framework to directly extract LFP neuromodulations related to synchronized spike activity using recordings from the primary motor cortex of six Sprague Dawley (SD) rats during a lever-press task. We first select important LFP frequency bands relevant to behavior, and then implement a marked point process (MPP) methodology to extract transient LFP neuromodulations. We validate the LFP feature extraction by examining the correlation with the pairwise synchronized firing probability of important neurons, which are selected according to their contribution to behavioral decoding. The highly correlated synchronized firings identified by the LFP neuromodulations are fed into a decoder to check whether they can serve as a reliable neural data source for movement decoding.

MAIN RESULTS

We find that the gamma band (30-80Hz) LFP neuromodulations demonstrate significant correlation with synchronized firings. Compared with traditional spectrogram-based method, the higher-temporal resolution MPP method captures the synchronized firing patterns with fewer false alarms, and demonstrates significantly higher correlation than single neuron spikes. The decoding performance using the synchronized neuronal firings identified by the LFP neuromodulations can reach 90% compared to the full recorded neuronal ensembles.

SIGNIFICANCE

Our proposed framework successfully extracts the sparse LFP neuromodulations that can identify temporal synchronized neuronal spikes with high correlation. The identified neuronal spike pattern demonstrates high decoding performance, which reveals the possibility of using LFP as an effective modality for long-term BMI decoding.

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.

Separation of cardiogenic oscillations from airflow waveforms using singular spectrum analysis

BACKGROUND AND OBJECTIVE

Airflow fluctuations caused by cardiac contraction can trigger inappropriate ventilator pressure support in anesthesia machines and intensive care unit mechanical ventilators. Removal of this cardiogenic artifact from the airflow signal would improve ventilator function. The application of singular spectrum analysis (SSA) to remove cardiogenic oscillations from ventilator airflow signals recorded from intubated, mechanically ventilated patients under general anesthesia was evaluated in this study.

METHODS

Airflow (liters/minute) and CO₂ (mmHg) data were collected at a sampling rate of 125 Hz from the intraoperative monitoring systems using special-purpose software. Simultaneous electrocardiogram signals (mV) were also collected at a sampling rate of 250 Hz. One-dimensional SSA was performed offline on normalized airflow signals using a window length sufficient to span one period of typical respiratory variation. The main components of the airflow waveform are respiratory excursions and cardiogenic oscillations, with respiratory excursions more slowly varying and of higher magnitude. The smooth respiratory waveform was formed from elementary reconstructed series corresponding to the highest singular values obtained with SSA analysis. The quality of respiratory waveform extraction with SSA was determined by calculating the weighted correlation between the selected elementary reconstructed series.

RESULTS

Airflow data was recorded from 6 patients. The respiratory component of the airflow signal without cardiogenic oscillations was reconstructed from elementary series corresponding to singular values of highest magnitude. The weighted correlations obtained were greater than 0.96 in the majority of patients studied. Cardiogenic oscillations were reconstructed from elementary reconstructed series corresponding to singular values of lower magnitude.

CONCLUSIONS

SSA is effective in extracting higher amplitude respiratory excursions while excluding lower amplitude cardiogenic oscillations and noise from the airflow signal. This study demonstrates that suppression of the cardiogenic artefact with SSA is computationally feasible to augment ventilator performance.

Evaluating the Different Stages of Parkinson's Disease Using Electroencephalography With Holo-Hilbert Spectral Analysis

Electroencephalography (EEG) can reveal the abnormalities of dopaminergic subcortico-cortical circuits in patients with Parkinson's disease (PD). However, conventional time-frequency analysis of EEG signals cannot fully reveal the non-linear processes of neural activities and interactions. A novel Holo-Hilbert Spectral Analysis (HHSA) was applied to reveal non-linear features of resting state EEG in 99 PD patients and 59 healthy controls (HCs). PD patients demonstrated a reduction of β bands in frontal and central regions, and reduction of γ bands in central, parietal, and temporal regions. Compared with early-stage PD patients, late-stage PD patients demonstrated reduction of β bands in the posterior central region, and increased θ and δ2 bands in the left parietal region. θ and β bands in all brain regions were positively correlated with Hamilton depression rating scale scores. Machine learning algorithms using three prioritized HHSA features demonstrated "Bag" with the best accuracy of 0.90, followed by "LogitBoost" with an accuracy of 0.89. Our findings strengthen the application of HHSA to reveal high-dimensional frequency features in EEG signals of PD patients. The EEG characteristics extracted by HHSA are important markers for the identification of depression severity and diagnosis of PD.

Motion Artifacts Correction from Single-Channel EEG and fNIRS Signals Using Novel Wavelet Packet Decomposition in Combination with Canonical Correlation Analysis

The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals, highly non-stationary in nature, greatly suffers from motion artifacts while recorded using wearable sensors. Since successful detection of various neurological and neuromuscular disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove/reduce motion artifacts from EEG and fNIRS signals using reliable and robust methods. In this regard, this paper proposes two robust methods: (i) Wavelet packet decomposition (WPD) and (ii) WPD in combination with canonical correlation analysis (WPD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these proposed techniques is tested using a benchmark dataset and the performance of the proposed methods is measured using two well-established performance matrices: (i) difference in the signal to noise ratio ( ) and (ii) percentage reduction in motion artifacts ( ). The proposed WPD-based single-stage motion artifacts correction technique produces the highest average (29.44 dB) when db2 wavelet packet is incorporated whereas the greatest average (53.48%) is obtained using db1 wavelet packet for all the available 23 EEG recordings. Our proposed two-stage motion artifacts correction technique, i.e., the WPD-CCA method utilizing db1 wavelet packet has shown the best denoising performance producing an average and values of 30.76 dB and 59.51%, respectively, for all the EEG recordings. On the other hand, for the available 16 fNIRS recordings, the two-stage motion artifacts removal technique, i.e., WPD-CCA has produced the best average (16.55 dB, utilizing db1 wavelet packet) and largest average (41.40%, using fk8 wavelet packet). The highest average and using single-stage artifacts removal techniques (WPD) are found as 16.11 dB and 26.40%, respectively, for all the fNIRS signals using fk4 wavelet packet. In both EEG and fNIRS modalities, the percentage reduction in motion artifacts increases by 11.28% and 56.82%, respectively when two-stage WPD-CCA techniques are employed in comparison with the single-stage WPD method. In addition, the average also increases when WPD-CCA techniques are used instead of single-stage WPD for both EEG and fNIRS signals. The increment in both and values is a clear indication that two-stage WPD-CCA performs relatively better compared to single-stage WPD. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

Motion Artifacts Correction from Single-Channel EEG and fNIRS Signals Using Novel Wavelet Packet Decomposition in Combination with Canonical Correlation Analysis

The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals, highly non-stationary in nature, greatly suffers from motion artifacts while recorded using wearable sensors. Since successful detection of various neurological and neuromuscular disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove/reduce motion artifacts from EEG and fNIRS signals using reliable and robust methods. In this regard, this paper proposes two robust methods: (i) Wavelet packet decomposition (WPD) and (ii) WPD in combination with canonical correlation analysis (WPD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these proposed techniques is tested using a benchmark dataset and the performance of the proposed methods is measured using two well-established performance matrices: (i) difference in the signal to noise ratio ( ) and (ii) percentage reduction in motion artifacts ( ). The proposed WPD-based single-stage motion artifacts correction technique produces the highest average (29.44 dB) when db2 wavelet packet is incorporated whereas the greatest average (53.48%) is obtained using db1 wavelet packet for all the available 23 EEG recordings. Our proposed two-stage motion artifacts correction technique, i.e., the WPD-CCA method utilizing db1 wavelet packet has shown the best denoising performance producing an average and values of 30.76 dB and 59.51%, respectively, for all the EEG recordings. On the other hand, for the available 16 fNIRS recordings, the two-stage motion artifacts removal technique, i.e., WPD-CCA has produced the best average (16.55 dB, utilizing db1 wavelet packet) and largest average (41.40%, using fk8 wavelet packet). The highest average and using single-stage artifacts removal techniques (WPD) are found as 16.11 dB and 26.40%, respectively, for all the fNIRS signals using fk4 wavelet packet. In both EEG and fNIRS modalities, the percentage reduction in motion artifacts increases by 11.28% and 56.82%, respectively when two-stage WPD-CCA techniques are employed in comparison with the single-stage WPD method. In addition, the average also increases when WPD-CCA techniques are used instead of single-stage WPD for both EEG and fNIRS signals. The increment in both and values is a clear indication that two-stage WPD-CCA performs relatively better compared to single-stage WPD. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

Ensemble Deep Neural Network for Automatic Classification of EEG Independent Components

OBJECTIVE

Independent component analysis (ICA) is commonly used to remove noisy artifacts from multi-channel scalp electroencephalogram (EEG) signals. ICA decomposes EEG into different independent components (ICs) and then, experts remove the noisy ones. This process is highly time-consuming and experts are not always available. To surpass this drawback, research is going on to develop models to automatically conduct IC classification. Current state-of-the-art models use power spectrum densities (PSDs) and topoplots to classify ICs. The performance of these methods may be limited by disregarding the IC time-series that would contribute to fully simulate the visual inspection performed by experts.

METHODS

We present a novel ensemble deep neural network that combines time-series, PSDs, and topoplots to classify ICs. Moreover, we study the ability to use our model in transfer learning approaches.

RESULTS

Experimental results showed that using time-series improves IC classification. Results also indicated that transfer learning obtained higher performance than simply training a new model from scratch.

CONCLUSION

Researchers should develop IC classifiers using the three sources of information. Moreover, transfer learning approaches should be considered when producing new deep learning models.

SIGNIFICANCE

This work improves IC classification, enhancing the automatic removal of EEG artifacts. Additionally, since labelled ICs are generally not publicly available, the possibility of using our model in transfer learning studies may motivate other researchers to develop their own classifiers.

Adaptive single-channel EEG artifact removal for real-time clinical monitoring

OBJECTIVE

Electroencephalography (EEG) has become very common in clinical practice due to its relatively low cost, ease of installation, non-invasiveness, and good temporal resolution. Portable EEG devices are increasingly popular in clinical monitoring applications such as sleep scoring or anesthesia monitoring. In these situations, for reasons of speed and simplicity only few electrodes are used and contamination of the EEG signal by artifacts is inevitable. Visual inspection and manual removal of artifacts is often not possible, especially in real-time applications. Our goal is to develop a flexible technique to remove EEG artifacts in these contexts with minimal supervision.

METHODS

We propose here a new wavelet-based method which allows to remove artifacts from single-channel EEGs. The method is based on a data-driven renormalization of the wavelet components and is capable of adaptively attenuate artifacts of different nature. We benchmark our method against alternative artifact removal techniques.

RESULTS

We assessed the performance of the proposed method on publicly available datasets comprising ocular, muscular, and movement artifacts. The proposed method shows superior performances on different kinds of artifacts and signal-to-noise levels. Finally, we present an application of our method to the monitoring of general anesthesia.

CONCLUSIONS

We show that our method can successfully attenuate various types of artifacts in single-channel EEG.

SIGNIFICANCE

Thanks to its data-driven approach and low computational cost, the proposed method provides a valuable tool to remove artifacts in real-time EEG applications with few electrodes, such as monitoring in special care units.

Neural Decoding of EEG Signals with Machine Learning: A Systematic Review

Electroencephalography (EEG) is a non-invasive technique used to record the brain's evoked and induced electrical activity from the scalp. Artificial intelligence, particularly machine learning (ML) and deep learning (DL) algorithms, are increasingly being applied to EEG data for pattern analysis, group membership classification, and brain-computer interface purposes. This study aimed to systematically review recent advances in ML and DL supervised models for decoding and classifying EEG signals. Moreover, this article provides a comprehensive review of the state-of-the-art techniques used for EEG signal preprocessing and feature extraction. To this end, several academic databases were searched to explore relevant studies from the year 2000 to the present. Our results showed that the application of ML and DL in both mental workload and motor imagery tasks has received substantial attention in recent years. A total of 75% of DL studies applied convolutional neural networks with various learning algorithms, and 36% of ML studies achieved competitive accuracy by using a support vector machine algorithm. Wavelet transform was found to be the most common feature extraction method used for all types of tasks. We further examined the specific feature extraction methods and end classifier recommendations discovered in this systematic review.

Treating Electrical and Biopotential Artifacts in an EEG Pilot Study Experiment

With the increase in life expectancy, as well as in the performance and complexity of healthcare systems, the need for fast and accurate information has also grown. EEG devices have become more accessible and necessary in clinical practice. In daily activity, artifacts are ubiquitous in EEG signals. They arise from: environmental, experimental and physiological factors, degrade signal quality and render the affected part of the signal useless. This paper proposes an artifact cleaning pipeline including filters and algorithms to streamline the analysis process. Moreover, to better characterize and discriminate artifacts from useful EEG data, additional physiological signals and video data are used, which are correlated with subject's behavior. We quantify the performance reached by Peak Signal-to-Noise Ratio and clinical visual inspection. The entire research and data collection took place in the laboratories of XPERI Corporation.Clinical Relevance-Since the occurrence of artifacts cannot be controlled, it is essential to have a precise process of recognition, identification and elimination of noise. Therefore, it is important to distinguish EEG artifacts from abnormal activity in order to minimize the chance of EEG misinterpretation, that can lead to false diagnosis, especially regarding the study of epileptiform activities or other neurologic or psychiatric disorders (e.g. degenerative diseases, dementia, depression, sleep disorders, Alzheimer's disease, schizophrenia, etc.).

Explainable artificial intelligence based analysis for interpreting infant fNIRS data in developmental cognitive neuroscience

In the last decades, non-invasive and portable neuroimaging techniques, such as functional near infrared spectroscopy (fNIRS), have allowed researchers to study the mechanisms underlying the functional cognitive development of the human brain, thus furthering the potential of Developmental Cognitive Neuroscience (DCN). However, the traditional paradigms used for the analysis of infant fNIRS data are still quite limited. Here, we introduce a multivariate pattern analysis for fNIRS data, xMVPA, that is powered by eXplainable Artificial Intelligence (XAI). The proposed approach is exemplified in a study that investigates visual and auditory processing in six-month-old infants. xMVPA not only identified patterns of cortical interactions, which confirmed the existent literature; in the form of conceptual linguistic representations, it also provided evidence for brain networks engaged in the processing of visual and auditory stimuli that were previously overlooked by other methods, while demonstrating similar statistical performance.

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-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications

Brain-Computer interfaces (BCIs) enhance the capability of human brain activities to interact with the environment. Recent advancements in technology and machine learning algorithms have increased interest in electroencephalographic (EEG)-based BCI applications. EEG-based intelligent BCI systems can facilitate continuous monitoring of fluctuations in human cognitive states under monotonous tasks, which is both beneficial for people in need of healthcare support and general researchers in different domain areas. In this review, we survey the recent literature on EEG signal sensing technologies and computational intelligence approaches in BCI applications, compensating for the gaps in the systematic summary of the past five years. Specifically, we first review the current status of BCI and signal sensing technologies for collecting reliable EEG signals. Then, we demonstrate state-of-the-art computational intelligence techniques, including fuzzy models and transfer learning in machine learning and deep learning algorithms, to detect, monitor, and maintain human cognitive states and task performance in prevalent applications. Finally, we present a couple of innovative BCI-inspired healthcare applications and discuss future research directions in EEG-based BCI research.

An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database

Physiological data, such as heart rate and blood pressure, are critical to clinical decision-making in the intensive care unit (ICU). Vital signs data, which are available from electronic health records, can be used to diagnose and predict important clinical outcomes; While there have been some reports on the data quality of nurse-verified vital sign data, little has been reported on the data quality of higher frequency time-series vital signs acquired in ICUs, that would enable such predictive modeling. In this study, we assessed the data quality issues, defined as the completeness, accuracy, and timeliness, of minute-by-minute time series vital signs data within the MIMIC-III data set, captured from 16009 patient-ICU stays and corresponding to 9410 unique adult patients. We measured data quality of four time-series vital signs data streams in the MIMIC-III data set: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), and arterial blood pressure (ABP). Approximately, 30% of patient-ICU stays did not have at least 1 min of data during the time-frame of the ICU stay for HR, RR, and SpO2. The percentage of patient-ICU stays that did not have at least 1 min of ABP data was ∼56%. We observed ∼80% coverage of the total duration of the ICU stay for HR, RR, and SpO2. Finally, only 12.5%%, 9.9%, 7.5%, and 4.4% of ICU lengths of stay had ≥ 99% data available for HR, RR, SpO2, and ABP, respectively, that would meet the three data quality requirements we looked into in this study. Our findings on data completeness, accuracy, and timeliness have important implications for data scientists and informatics researchers who use time series vital signs data to develop predictive models of ICU outcomes.

Advanced Bioelectrical Signal Processing Methods: Past, Present and Future Approach-Part I: Cardiac Signals

Advanced signal processing methods are one of the fastest developing scientific and technical areas of biomedical engineering with increasing usage in current clinical practice. This paper presents an extensive literature review of the methods for the digital signal processing of cardiac bioelectrical signals that are commonly applied in today's clinical practice. This work covers the definition of bioelectrical signals. It also covers to the extreme extent of classical and advanced approaches to the alleviation of noise contamination such as digital adaptive and non-adaptive filtering, signal decomposition methods based on blind source separation and wavelet transform.

Hardware Acceleration of EEG-Based Emotion Classification Systems: A Comprehensive Survey

Recent years have witnessed a growing interest in EEG-based wearable classifiers of emotions, which could enable the real-time monitoring of patients suffering from neurological disorders such as Amyotrophic Lateral Sclerosis (ALS), Autism Spectrum Disorder (ASD), or Alzheimer's. The hope is that such wearable emotion classifiers would facilitate the patients' social integration and lead to improved healthcare outcomes for them and their loved ones. Yet in spite of their direct relevance to neuro-medicine, the hardware platforms for emotion classification have yet to fill up some important gaps in their various approaches to emotion classification in a healthcare context. In this paper, we present the first hardware-focused critical review of EEG-based wearable classifiers of emotions and survey their implementation perspectives, their algorithmic foundations, and their feature extraction methodologies. We further provide a neuroscience-based analysis of current hardware accelerators of emotion classifiers and use it to map out several research opportunities, including multi-modal hardware platforms, accelerators with tightly-coupled cores operating robustly in the near/supra-threshold region, and pre-processing libraries for universal EEG-based datasets.

A Recent Investigation on Detection and Classification of Epileptic Seizure Techniques Using EEG Signal

The benefits of early detection and classification of epileptic seizures in analysis, monitoring and diagnosis for the realization and actualization of computer-aided devices and recent internet of medical things (IoMT) devices can never be overemphasized. The success of these applications largely depends on the accuracy of the detection and classification techniques employed. Several methods have been investigated, proposed and developed over the years. This paper investigates various seizure detection algorithms and classifications in the last decade, including conventional techniques and recent deep learning algorithms. It also discusses epileptiform detection as one of the steps towards advanced diagnoses of disorders of consciousness (DOCs) and their understanding. A performance comparison was carried out on the different algorithms investigated, and their advantages and disadvantages were explored. From our survey, much attention has recently been paid to exploring the efficacy of deep learning algorithms in seizure detection and classification, which are employed in other areas such as image processing and classification. Hybrid deep learning has also been explored, with CNN-RNN being the most popular.

A new automated multi-stage system of non-local means and multi-kernel adaptive filtering techniques for EEG noise and artifacts suppression

Context.Electroencephalography (EEG) signals are contaminated with diverse types of noises and artifacts, which greatly distort EEG recording and increase the difficulty in obtaining accurate diagnosis.Objective.This paper investigates, for the first time, multi-kernel normalized least mean square with coherence-based sparsification (MKNLMS-CS) algorithm for suppressing different artifact components, and the 1D patch-based non-local means (NLM) algorithm for eliminating white and colored noises.Approach.A novel multi-stage system based on combining the NLM algorithm with the MKNLMS-CS algorithm is proposed for eliminating different noise and artifact sources by targeting each noise or artifact component in a single stage.Main Results.The proposed approach is applied to clinical real EEG data, and the results reveal the superior performance of the proposed system in removing white and colored noises, suppressing different artifact components, preserving the important and tiny features of the original EEG signal, and keeping the morphology of EEG frequency components.Significance.The proposed multi-stage design succeeds not only to suppress different artifact components and noise sources under low and high noise conditions, but also to achieve accurate sleep spindle detection from the filtered high-quality EEG signals. This demonstrates the usefulness of the proposed approach for obtaining high-resolution EEG signal from noisy and contaminated EEG recordings.