Search

In brain–computer interface (BCI) systems, motor imagery (MI) electroencephalogram (EEG) is widely used to interpret the human brain. However, MI classification is challenging due to weak signals and a lack of high-quality data. While deep learning (DL) methods have shown significant success in pattern recognition, their application to MI-based BCI systems remains limited. To address these challenges, we propose a novel deep learning algorithm that leverages EEG signal features through a two-branch parallel convolutional neural network (CNN). Our approach incorporates different input signals, such as continuous wavelet transform, short-time Fourier transform, and common spatial patterns, and employs various classifiers, including support vector machines and decision trees, to enhance system performance. We evaluate our algorithm using the BCI Competition IV dataset 2B, comparing it with other state-of-the-art methods. Our results demonstrate that the proposed method excels in classification accuracy, offering improvements for MI-based BCI systems. [ABSTRACT FROM AUTHOR]

Several parameters affect our brain's neuronal system and can be identified by analyzing electroencephalogram (EEG) signals. One of the parameters is alcoholism, which affects the pattern of our EEG signals. By analyzing these EEG signals, one can derive information regarding the alcoholic or normal stage of an individual. Many road accident cases around the world, including drinking and driving scenarios, which result in loss of life, have been reported. Another reason for such incidents is that riders avoid wearing helmets while driving two-wheelers. Many road accident cases involving two-wheelers, including drinking, driving, overspeeding, and nonwearing helmets, have been reported. Therefore, to solve such issues, the present work highlights the features of an intelligent model that can predict the alcoholism level of the subject, wearing of a helmet, vehicle speed, location, etc. The system is designed with the latest technologies and is smart enough to make decisions. The system is based on multilayer perceptron, histogram of oriented gradients (HoG) feature extraction, and random forest to make decisions in real time. The accuracy of the proposed method is approximately 95%, which will reduce the fatality rate due to road accidents. The system is tested under different working environments, i.e., indoor and outdoor, and satisfactory outcomes are observed. [ABSTRACT FROM AUTHOR]

This paper comprehensively reviews hardware acceleration techniques and the deployment of convolutional neural networks (CNNs) for analyzing electroencephalogram (EEG) signals across various application areas, including emotion classification, motor imagery, epilepsy detection, and sleep monitoring. Previous reviews on EEG have mainly focused on software solutions. However, these reviews often overlook key challenges associated with hardware implementation, such as scenarios that require a small size, low power, high security, and high accuracy. This paper discusses the challenges and opportunities of hardware acceleration for wearable EEG devices by focusing on these aspects. Specifically, this review classifies EEG signal features into five groups and discusses hardware implementation solutions for each category in detail, providing insights into the most suitable hardware acceleration strategies for various application scenarios. In addition, it explores the complexity of efficient CNN architectures for EEG signals, including techniques such as pruning, quantization, tensor decomposition, knowledge distillation, and neural architecture search. To the best of our knowledge, this is the first systematic review that combines CNN hardware solutions with EEG signal processing. By providing a comprehensive analysis of current challenges and a roadmap for future research, this paper provides a new perspective on the ongoing development of hardware-accelerated EEG systems. [ABSTRACT FROM AUTHOR]

Abstract Several parameters affect our brain's neuronal system and can be identified by analyzing electroencephalogram (EEG) signals. One of the parameters is alcoholism, which affects the pattern of our EEG signals. By analyzing these EEG signals, one can derive information regarding the alcoholic or normal stage of an individual. Many road accident cases around the world, including drinking and driving scenarios, which result in loss of life, have been reported. Another reason for such incidents is that riders avoid wearing helmets while driving two-wheelers. Many road accident cases involving two-wheelers, including drinking, driving, overspeeding, and nonwearing helmets, have been reported. Therefore, to solve such issues, the present work highlights the features of an intelligent model that can predict the alcoholism level of the subject, wearing of a helmet, vehicle speed, location, etc. The system is designed with the latest technologies and is smart enough to make decisions. The system is based on multilayer perceptron, histogram of oriented gradients (HoG) feature extraction, and random forest to make decisions in real time. The accuracy of the proposed method is approximately 95%, which will reduce the fatality rate due to road accidents. The system is tested under different working environments, i.e., indoor and outdoor, and satisfactory outcomes are observed.

The burgeoning field of neurodegenerative disease detection and management necessitates the development of robust and comprehensive diagnostic approaches. Existing methodologies often fall short in effectively capturing the complex interplay of brain signals and genetic markers, which are crucial in the early detection and progression tracking of such diseases. This paper introduces a novel multimodal framework that leverages advanced signal processing and machine learning techniques to address these limitations, providing a more accurate and holistic understanding of neurodegenerative diseases. Our proposed model integrates multiple modalities: EEG signal analysis using Time-Frequency Analysis and Wavelet Transform, functional Magnetic Resonance Imaging (fMRI) analyzed through Independent Component Analysis (ICA) and Correlation Analysis, Magnetoencephalography (MEG) employing Beamforming and Source Localization Techniques, and Genomic Data analysis using Graph Neural Network for Genetic Pattern Recognition process. This integration is realized through the fusion of modalities using Gated Recurrent Units (GRU) and the classification into disease classes via an efficient 1D Convolutional Neural Network (CNN). The reasons for selecting these methods are twofold: they address the non-stationary characteristics of EEG signals and exploit spatial information of brain activity, while also identifying functional networks and genetic patterns associated with neurodegeneration conditions. The clinical impact of this work is profound. Tested on the BioGPS and BrainLat datasets, our framework demonstrated a 10.4% increase in precision, 8.5% increase in accuracy, 8.3% increase in recall, 9.4% increase in the Area Under the Curve (AUC), 7.5% increase in specificity, and a 2.9% reduction in delay compared to existing methods.

In brain–computer interface (BCI) systems, motor imagery (MI) electroencephalogram (EEG) is widely used to interpret the human brain. However, MI classification is challenging due to weak signals and a lack of high-quality data. While deep learning (DL) methods have shown significant success in pattern recognition, their application to MI-based BCI systems remains limited. To address these challenges, we propose a novel deep learning algorithm that leverages EEG signal features through a two-branch parallel convolutional neural network (CNN). Our approach incorporates different input signals, such as continuous wavelet transform, short-time Fourier transform, and common spatial patterns, and employs various classifiers, including support vector machines and decision trees, to enhance system performance. We evaluate our algorithm using the BCI Competition IV dataset 2B, comparing it with other state-of-the-art methods. Our results demonstrate that the proposed method excels in classification accuracy, offering improvements for MI-based BCI systems.

This paper comprehensively reviews hardware acceleration techniques and the deployment of convolutional neural networks (CNNs) for analyzing electroencephalogram (EEG) signals across various application areas, including emotion classification, motor imagery, epilepsy detection, and sleep monitoring. Previous reviews on EEG have mainly focused on software solutions. However, these reviews often overlook key challenges associated with hardware implementation, such as scenarios that require a small size, low power, high security, and high accuracy. This paper discusses the challenges and opportunities of hardware acceleration for wearable EEG devices by focusing on these aspects. Specifically, this review classifies EEG signal features into five groups and discusses hardware implementation solutions for each category in detail, providing insights into the most suitable hardware acceleration strategies for various application scenarios. In addition, it explores the complexity of efficient CNN architectures for EEG signals, including techniques such as pruning, quantization, tensor decomposition, knowledge distillation, and neural architecture search. To the best of our knowledge, this is the first systematic review that combines CNN hardware solutions with EEG signal processing. By providing a comprehensive analysis of current challenges and a roadmap for future research, this paper provides a new perspective on the ongoing development of hardware-accelerated EEG systems.

EEG signals may be affected by physiological and non-physiological artifacts hindering the analysis of brain activity. Blind source separation methods such as independent component analysis (ICA) are effective ways of improving signal quality by removing components representing non-brain activity. However, most ICA-based artifact removal strategies have limitations, such as individual differences in visual assessment of components. These limitations might be reduced by introducing automatic selection methods for ICA components. On the other hand, new fully automatic artifact removal methods are developed. One of such method is artifact subspace reconstruction (ASR). ASR is a component-based approach, which can be used automatically and with small calculation requirements. The ASR was originally designed to be run not instead of, but in addition to ICA. We compared two automatic signal quality correction approaches: the approach based only on ICA method and the approach where ASR was applied additionally to ICA and run before the ICA. The case study was based on the analysis of data collected from 10 subjects performing four popular experimental paradigms, including resting-state, visual stimulation and oddball task. Statistical analysis of the signal-to-noise ratio showed a significant difference, but not between ICA and ASR followed by ICA. The results show that both methods provided a signal of similar quality, but they were characterised by different usabilities. [ABSTRACT FROM AUTHOR]

This document is an editorial published in Frontiers in Human Neuroscience in 2024. The editorial highlights the rising stars in motor neuroscience and their contributions to the field. It emphasizes the importance of understanding motor function and its neural mechanisms for understanding human behavior. The editorial discusses various topics, including motor learning, rehabilitation of motor disorders, and the use of innovative tools and technologies in motor neuroscience research. It also mentions specific studies on motion analysis in breast cancer patients, multivariate analysis using artificial neural networks, brain-computer interfaces for motor impairments, postural control in athletes, and the neural correlates of upper and lower limb movements. The editorial concludes by emphasizing the valuable insights provided by these researchers and their potential impact on future advancements in motor neuroscience. [Extracted from the article]

The objective of this study is to design an Electroencephalographic (EEG) analytic methodology that allows to develop a variety of analysis and interpretations of brain signals. The initial phase considers the acquisition and filtering of EEG signals, the division into bands in data ranges, and the storage of EEG signals in a cloud data base. Then, an analytical phase considering descriptive, predictive and prescriptive analysis is accomplished. A sequence of analytic intermediate processing steps is done in order to render a graphic visualization of significant correlations between pairs of EEG channels. Pearson correlation is utilized to detect synchronic connectivity through the brain areas. Time series in nearly instantaneous time lapses are treated by using Hilbert Huang Transform. An experimental design by submitting a set of students to an abbreviated version Raven visual test is made providing results in correlation maps of cerebral connectivity. [ABSTRACT FROM AUTHOR]

This manuscript proposes the design of a speech synthesis algorithm based on measured electroencephalographic (EEG) signals previously classified by a class of neural network with continuous dynamics. A novel multilayer differential neural network (MDNN) classifies a database with the EEG studies of 20 volunteers. The database contains information described by input-output pairs corresponding to EEG signals and a corresponding word imagined by the volunteer. The suggested MDNN estimates the unknown relationship between the information instances and suggests the most-likely word that the user wants mentioning. The proposed MDNN satisfactory classifies over 95% a set of words obtained from the suggested EEG study in which, the users have to watch four different geometric figures on a screen. [ABSTRACT FROM AUTHOR]

EEG signals may be affected by physiological and non-physiological artifacts hindering the analysis of brain activity. Blind source separation methods such as independent component analysis (ICA) are effective ways of improving signal quality by removing components representing non-brain activity. However, most ICA-based artifact removal strategies have limitations, such as individual differences in visual assessment of components. These limitations might be reduced by introducing automatic selection methods for ICA components. On the other hand, new fully automatic artifact removal methods are developed. One of such method is artifact subspace reconstruction (ASR). ASR is a component-based approach, which can be used automatically and with small calculation requirements. The ASR was originally designed to be run not instead of, but in addition to ICA. We compared two automatic signal quality correction approaches: the approach based only on ICA method and the approach where ASR was applied additionally to ICA and run before the ICA. The case study was based on the analysis of data collected from 10 subjects performing four popular experimental paradigms, including resting-state, visual stimulation and oddball task. Statistical analysis of the signal-to-noise ratio showed a significant difference, but not between ICA and ASR followed by ICA. The results show that both methods provided a signal of similar quality, but they were characterised by different usabilities.

Epilepsy is a brain abnormality that leads its patients to suffer from seizures, which conditions their behavior and lifestyle. Neurologists use an electroencephalogram (EEG) to diagnose this disease. This test illustrates the signaling behavior of a person's brain, allowing, among other things, the diagnosis of epilepsy. From a visual analysis of these signals, neurologists identify patterns such as peaks or valleys, looking for any indication of brain disorder that leads to the diagnosis of epilepsy in a purely qualitative way. However, by applying a test based on Fourier signal analysis through rapid transformation in the frequency domain, patterns can be quantitatively identified to differentiate patients diagnosed with the disease and others who are not. In this article, an analysis of the EEG signal is performed to extract characteristics in patients already classified as epileptic and non-epileptic, which will be used in the training of models based on classification techniques such as logistic regression, artificial neural networks, support vector machines, and convolutional neural networks. Based on the results obtained with each technique, an analysis is performed to decide which of these behaves better.In this study traditional classification techniques were implemented that had as data frequency data in the channels with distinctive information of EEG examinations, this was done through a feature extraction obtained with Fourier analysis considering frequency bands. The techniques used for classification were implemented in Python and through a comparison of metrics and performance, it was concluded that the best classification technique to characterize epileptic patients are artificial neural networks with an accuracy of 86%.

Diagnosis of epilepsy can be expensive, time-consuming, and often inaccurate. The gold standard diagnostic monitoring is continuous video-electroencephalography (EEG), which ideally captures all epileptic events and dis-charges. Automated monitoring of seizures and epileptic activity from EEG would save time and resources, it is the focus of much EEG-based epilepsy research. The purpose of this paper is to provide a survey in order to understand, classify and benchmark the key parameters of deep learning-based approaches that were applied in the processing of EEG signals for epilepsy monitoring. This survey identifies the availability of data and the black-box nature of DL as the main challenges hindering the clinical acceptance of EEG analysis systems based on Deep Learning and suggests the use of Explainable Artificial Intelligence (XAI) and Transfer Learning to overcome these issues. It also underlines the need for more research to recognize the full potential of big data, Computing Edge, IoT to implement wearable devices that can assist epileptic patients and improve their quality of life.

The focal and non-focal epilepsy is seen to be a chronic neurological brain disorder, which has affected $\approx ~60$ million people in the world. Hence, an early detection of the focal epileptic seizures can be carried out using the EEG signals, which act as a helpful tool for early diagnosis of epilepsy. Several EEG-based approaches have been proposed and developed to understand the underlying characteristics of the epileptic seizures. Despite the fact that the early results were positive, the proposed techniques cannot generate reproducible results and lack a statistical validation, which has led to doubts regarding the presence of the pre-ictal state. Various methodical and algorithmic studies have indicated that the transition to an ictal state is not a random process, and the build-up can lead to epileptic seizures. This study reviews many recently-proposed algorithms for detecting the focal epileptic seizures. Generally, the techniques developed for detecting the epileptic seizures were based on tensors, entropy, empirical mode decomposition, wavelet transform and dynamic analysis. The existing algorithms were compared and the need for implementing a practical and reliable new algorithm is highlighted. The research regarding the epileptic seizure detection research is more focused on the development of precise and non-invasive techniques for rapid and reliable diagnosis. Finally, the researchers noted that all the methods that were developed for epileptic seizure detection lacks standardization, which hinders the homogeneous comparison of the detector performance.

Sleep has great effect on physical health and quality of life. Electroencephalogram (EEG) signal is used in studying sleep process and recently, time–frequency transforms are increasingly utilised in EEG signal analysis. This study proposes an efficient method for sleep stages classification based on a time–frequency transform, namely Stockwell transform. In the introduced method, at first, the Stockwell transform is used to map each 30 s epoch of EEG signal into the time–frequency domains, which results in a complex‐valued matrix. Then, the frequency domain is divided into different non‐overlapping segments, leading to several matrices. After that, entropy features are extracted from the obtained matrices. In order to determine the sleep stage of each epoch, the computed features are applied to classifier. Support vector machine, weighted K ‐nearest neighbour, and ensemble bagged tree classifiers are considered. The Pz–Oz and Fpz–Cz channels of EEG signal from Sleep‐EDF data set and C3–A2 channel from ISRUC‐Sleep data set are used in this research. The results indicate that the proposed method outperforms the recently introduced methods. [ABSTRACT FROM AUTHOR]

This paper takes the cognition and education management method of withdrawal reaction for students with internet addiction as the research objective and adopts the research methods of literature method, brain science experiment and data analysis. This paper also introduces the EEG signal analysis method and use nonlinear dynamic analysis method and event-related potential technology, performing collection and data arrangement of EEG signals, SPN and P300 waveforms of prefrontal lobe of students with Internet addiction, analyzing behavioral characteristics and neurological changes in brain of students with Internet addiction from the perspectives of behavioral and EEG data. On this basis, the management method of withdrawal education for students with Internet addiction is proposed. [ABSTRACT FROM AUTHOR]

This paper reports the results of an experiment to identify EEG patterns specific to different levels of player involvement when playing a video game. To obtain unbiased results, we based our patterns on both raw EEG data and expert knowledge. We used a three-step procedure to identify patterns. First, we looked for clusters in the reduced feature space extracted from EEG data. Next, we assigned experts’ interpretations to the clusters. Finally, we analysed relations between features used to form the clusters and the class labels provided by experts. The most challenging part of the procedure was feature selection simultaneous with unsupervised classification. To accomplish this task, we developed a new approach for simultaneous feature selection and clustering based on modified GAAM (genetic algorithm with aggressive mutation). When the cGAAM algorithm was applied to EEG data, it returned the feature subsets that (a) were highly consistent across subjects and (b) provided 50% more compact clusters than clusters built over the feature subsets returned by a forward selection search strategy. The main cognitive outcome of EEG signal analysis was a set of patterns differentiating players’ involvement in a game. Conclusions included: 1. For a majority of subjects the most discriminative features were activity in the theta band in the left and right frontal areas, and activity in the delta band in the left frontal area; 2. All three features significantly differentiated between low and high, or medium and high engagement; 3. All subjects showed positive correlations between selected feature values and levels of engagement. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to predict rating of video-advertisements based on a multimodal framework combining physiological analysis of the user and global sentiment-rating available on the internet. We have fused Electroencephalogram (EEG) waves of user and corresponding global textual comments of the video to understand the user’s preference more precisely. In our framework, the users were asked to watch the video-advertisement and simultaneously EEG signals were recorded. Valence scores were obtained using self-report for each video. A higher valence corresponds to intrinsic attractiveness of the user. Furthermore, the multimedia data that comprised of the comments posted by global viewers, were retrieved and processed using Natural Language Processing (NLP) technique for sentiment analysis. Textual contents from review comments were analyzed to obtain a score to understand sentiment nature of the video. A regression technique based on Random forest was used to predict the rating of an advertisement using EEG data. Finally, EEG based rating is combined with NLP-based sentiment score to improve the overall prediction. The study was carried out using 15 video clips of advertisements available online. Twenty five participants were involved in our study to analyze our proposed system. The results are encouraging and these suggest that the proposed multimodal approach can achieve lower RMSE in rating prediction as compared to the prediction using only EEG data. [ABSTRACT FROM AUTHOR]

This research aims to develop a driver drowsiness monitoring system by analyzing the electroencephalographic (EEG) signals in a software scripted environment and using a driving simulator. These signals are captured by a multi-channel electrode system. Any muscle movement impacts the EEG signal recording which translates to artifacts. Therefore, noise from the recording is eliminated by subtracting the noisy signal from the original EEG recording. The actual EEG signals are then subjected to band pass filtering with cut-off frequencies 0.5Hz and 100Hz. The filtered signals are analyzed using a time-frequency technique known as the Discrete Wavelet Transform (DWT). A third order Debauchies' wavelet and five level decomposition is utilized to segregate the signal into five sub-bands, namely, delta (0.5 - 4Hz), theta (4 - 8Hz), alpha (8 - 12Hz), beta (12 - 30Hz) and gamma (> 30Hz). First order statistical moments such as mean, median, variance, standard deviation and mode of the sub-bands are calculated and stored as features. These features serve as an input to the next stage of system classification. Unsupervised learning through K-means clustering is employed since the classes of the signals are unknown. This provides a strong decision making tool for a real-time drowsiness detection system. The algorithm developed in this work has been tested on twelve samples from the Physionet sleep-EDF database. [ABSTRACT FROM AUTHOR]