EEG Signal Processing Research Articles

Emotion Detection Based on EEG Signal Processing by Body Sensor 5G Networks Using Deep Learning Architectures

Emotion recognition is the automatic detection of a person’s emotional state through his or her non-physiological or physiological signals. The EEG-related technique was an effectual system, which is typically employed for recognizing feelings in real time. Artificial Intelligence (AI) can be a developing research field which had rapid growth particularly to constitute a bridge between technology and its implementation in solving real-time issues particularly those relevant to the healthcare domain. This study develops a new deep learning-based emotion detection based on EEG signal processing, named DLED-EEGSP technique. The presented DLED-EEGSP technique identifies the distinct kinds of emotions based on the sensors and EEG signals. To perform this, the presented DLED-EEGSP technique exploits multi-head attention based long short-term memory (MHA-LSTM) method for emotion recognition. The MHALSTM model recognizes the emotion states based on the higher order cross feature samples. The experimental result analysis of the DLED-EEGSP technique is investigated on a series of data. A wide-ranging simulation results reported the supremacy of the DLED-EEGSP technique over other existing models.

Exploiting Asymmetric EEG Signals with EFD in Deep Learning Domain for Robust BCI

Motor imagery (MI) is a domineering paradigm in brain–computer interface (BCI) composition, personifying the imaginary limb motion into digital commandments for neural rehabilitation and automation exertions, while many researchers fathomed myriad solutions for asymmetric MI EEG signals classification, the existence of a robust, non-complex, and subject-invariant system is far-reaching. Thereupon, we put forward an MI EEG segregation pipeline in the deep-learning domain in an effort to curtail the existing limitations. Our method amalgamates multiscale principal component analysis (MSPCA), a novel empirical Fourier decomposition (EFD) signal resolution method with Hilbert transform (HT), followed by four pre-trained convolutional neural networks for automatic feature estimation and segregation. The conceived architecture is validated upon three binary class datasets: IVa, IVb from BCI Competition III, GigaDB from the GigaScience repository, and one tertiary class dataset V from BCI competition III. The average 10-fold outcomes capitulate 98.63%, 96.33%, and 89.96%, the highest classification accuracy for the aforesaid datasets accordingly using the AlexNet CNN model in a subject-dependent context, while in subject-independent cases, the highest success score was 97.69%, outperforming the contemporary studies by a fair margin. Further experiments such as the resolution scale of EFD, comparison with other signal decomposition (SD) methods, deep feature extraction, and classification with machine learning methods also accredits the supremacy of our proposed EEG signal processing pipeline. The overall findings imply that pre-trained models are reliable in identifying EEG signals due to their capacity to maintain the time-frequency structure of EEG signals, non-complex architecture, and their potential for robust classification performance.

EEG Signal Processing for Biomedical Applications

Electroencephalography (EEG) signals are used widely in clinical and research settings [...].

WITHDRAWN: Body Sensor 5 G Networks Utilising Deep Learning Architectures for Emotion Detection Based On EEG Signal Processing

Emotion recognition is an automatic detection of a person’s emotional state through non-physiological or physiological signals. The EEG (Electroencephalogram) techniques are typically employed for recognizing feelings in real time and Artificial Intelligence (AI) could constitute a bridge between technology and its implementation in solving real-time issues in healthcare domain. This study develops a new deep learning based emotion detection based on EEG signal processing, named DLED-EEGSP (Direct LED-Electroencephalogram signal processing) technique for identifying the distinct kinds of emotions based on EEG signals by exploiting multi-head attention based long short-term memory (MHA-LSTM) method for emotion recognition. It recognizes the emotion states based on the higher order cross feature samples. The experimental result analysis reveals the supremacy of the DLED-EEGSP technique over other existing models with increased accuracy of 71.66%.

Classification of epileptic EEG based on improved empirical wavelet transform

Electroencephalography (EEG) is the most commonly used method in the diagnosis of epilepsy diseases. In order to identify epilepsy EEG signals more effectively, an automatic identification method of epilepsy EEG signals based on improved empirical wavelet transform (EWT) is proposed. Firstly, in view of the difficulty of spectral division in the EEG signal processing of epilepsy by empirical wavelet transform, an improvement measure is proposed, that is, the average difference spectrum of the signal is obtained to replace the signal spectrum in the empirical wavelet transform, and then a number of component signal with epileptic characteristic can be obtained from the original signal. Afterward, feature extraction and classification are completed through a common spatial pattern and AdaBoost algorithm. Simulation analysis was carried out on the Bonn epilepsy EEG data set, and the EEG signals of healthy people and epilepsy patients were identified and classified in the interictal and ictal periods, and high classification accuracy was achieved.

RNN and BiLSTM Fusion for Accurate Automatic Epileptic Seizure Diagnosis Using EEG Signals.

Epilepsy is a common neurological condition. The effects of epilepsy are not restricted to seizures alone. They comprise a wide spectrum of problems that might impair and reduce quality of life. Even with medication, 30% of epilepsy patients still have recurring seizures. An epileptic seizure is caused by significant neuronal electrical activity, which affects brain activity. EEG shows these changes as high-amplitude spiky and sluggish waves. Recognizing seizures on an electroencephalogram (EEG) manually by a professional neurologist is a time-consuming and labor-intensive process, hence an efficient automated approach is necessary for the identification of epileptic seizure. One technique to increase the speed and accuracy with which a diagnosis of epileptic seizures could be made is by utilizing computer-aided diagnosis systems that are built on deep neural networks, or DNN. This study introduces a fusion of recurrent neural networks (RNNs) and bi-directional long short-term memories (BiLSTMs) for automatic epileptic seizure identification via EEG signal processing in order to tackle the aforementioned informational challenges. An electroencephalogram's (EEG) raw data were first normalized after undergoing pre-processing. A RNN model was fed the normalized EEG sequence data and trained to accurately extract features from the data. Afterwards, the features were passed to the BiLSTM layers for processing so that further temporal information could be retrieved. In addition, the proposed RNN-BiLSTM model was tested in an experimental setting using the freely accessible UCI epileptic seizure dataset. Experimental findings of the suggested model have achieved avg values of 98.90%, 98.50%, 98. 20%, and 98.60%, respectively, for accuracy, sensitivity, precision, and specificity. To further verify the new model's efficacy, it is compared to other models, such as the RNN-LSTM and the RNN-GRU learning models, and is shown to have improved the same metrics by 1.8%, 1.69%, 1.95%, and 2.2% on using 5-fold. Additionally, the proposed method was compared to state-of-the-art approaches and proved to be a more accurate categorization of such techniques.

Lightweight and highly robust memristor-based hybrid neural networks for electroencephalogram signal processing

Memristor-based neuromorphic computing shows great potential for high-speed and high-throughput signal processing applications, such as electroencephalogram (EEG) signal processing. Nonetheless, the size of one-transistor one-resistor (1T1R) memristor arrays is limited by the non-ideality of the devices, which prevents the hardware implementation of large and complex networks. In this work, we propose the depthwise separable convolution and bidirectional gate recurrent unit (DSC-BiGRU) network, a lightweight and highly robust hybrid neural network based on 1T1R arrays that enables efficient processing of EEG signals in the temporal, frequency and spatial domains by hybridizing DSC and BiGRU blocks. The network size is reduced and the network robustness is improved while ensuring the network classification accuracy. In the simulation, the measured non-idealities of the 1T1R array are brought into the network through statistical analysis. Compared with traditional convolutional networks, the network parameters are reduced by 95% and the network classification accuracy is improved by 21% at a 95% array yield rate and 5% tolerable error. This work demonstrates that lightweight and highly robust networks based on memristor arrays hold great promise for applications that rely on low consumption and high efficiency.

A Novel End-to-end Network Based on a bidirectional GRU and a Self-Attention Mechanism for Denoising of Electroencephalography Signals

Electroencephalography (EEG) signals are nonlinear and non-stationary sequences that carry much information. However, physiological signals from other body regions may readily interfere with EEG signal capture, having a significant unfavorable influence on subsequent analysis. Therefore, signal denoising is a crucial step in EEG signal processing. This paper proposes a bidirectional gated recurrent unit (GRU) network based on a self-attention mechanism (BG-Attention) for extracting pure EEG signals from noise-contaminated EEG signals. The bidirectional GRU network can simultaneously capture past and future information while processing continuous time sequence. And by paying different levels of attention to the content of varying importance, the model can learn more significant feature of EEG signal sequences, highlighting the contribution of essential samples to denoising. The proposed model is evaluated on the EEGdenoiseNet data set. We compared the proposed model with a fully connected network (FCNN), the one-dimensional residual convolutional neural network (1D-ResCNN), and a recurrent neural network (RNN). The experimental results show that the proposed model can reconstruct a clear EEG waveform with a decent signal-to-noise ratio (SNR) and the relative root mean squared error (RRMSE) value. This study demonstrates the potential of BG-Attention in the pre-processing phase of EEG experiments, which has significant implications for medical technology and brain-computer interface (BCI) applications.

Enhanced algorithm for energy optimization and improvised synchronization in knee exoskeleton system

The purpose of the study is to develop an augmented algorithm with optimised energy and improvised synchronisation to assist the knee exoskeleton design. This enhanced algorithm is used to estimate the accurate left and right movement signals from the brain and accordingly moves the lower-limb exoskeleton with the help of motors. An optimised deep learning algorithm is developed to differentiate the right and left leg movements from the acquired brain signals. The obtained test signals are then compared with the signals obtained from the conventional algorithm to find the accuracy of the algorithm. The obtained average accuracy rate of about 63% illustrates the improvised differentiation in identifying the right and left leg movement. The future work involves the comparative study of the proposed algorithm with other classification technologies to extract more reliable results. A comparative analysis of the replaceable and rechargeable battery will be done in the future study to exhibit the effectiveness of the proposed model. This study involves the extended study of five frequency regions namely alpha, beta, gamma, delta and theta, to handle the real-time EEG signal processing exoskeleton, model.

EEG signal processing by feature extraction and classification based on biomedical deep learning architecture with wireless communication

The brain is the most important organ in the human body. It transmits a lot of data to many body parts and its health is a prominent topic in e-healthcare. The Electroencefalography (EEG) is used in the biomedical industry to identify brain-related illnesses in which the input was gathered via brain EEG waves to extract brain action features. The band power of each collected signal is seen in Emotive Epoc Pro. Alpha wave (4–8 Hz), theta wave The recorded signal's changes with respect to time are at the frequencies of (4–8 Hz), alpha (8–12 Hz), low beta (12–16 Hz), beta (16–25 Hz), and gamma (25–45 Hz). The kernel extreme learning-based multilayer perceptron (KExL MLP) was used to extract the processed images and the extracted features of brain activity have been classified using Bayesian quadratic discriminant Transfer neural network (BQDTNN) which reflect brain activity. The accuracy of the parametric analysis was 96 %, the precision was 72 %, the recall was 69 %, and the F-1 score was 62 % for the EEG input dataset and 98 %, the precision was 80%, the recall was 73 %, and the F-1 score was 71 % for the SSVEP EEG dataset.

Improved Manual Annotation of EEG Signals through Convolutional Neural Network Guidance.

The development of validated algorithms for automated handling of artifacts is essential for reliable and fast processing of EEG signals. Recently, there have been methodological advances in designing machine-learning algorithms to improve artifact detection of trained professionals who usually meticulously inspect and manually annotate EEG signals. However, validation of these methods is hindered by the lack of a gold standard as data are mostly private and data annotation is time consuming and error prone. In the effort to circumvent these issues, we propose an iterative learning model to speed up and reduce errors of manual annotation of EEG. We use a convolutional neural network (CNN) to train on expert-annotated eyes-open and eyes-closed resting-state EEG data from typically developing children (n = 30) and children with neurodevelopmental disorders (n = 141). To overcome the circular reasoning of aiming to develop a new algorithm and benchmarking to a manually-annotated gold standard, we instead aim to improve the gold standard by revising the portion of the data that was incorrectly learned by the network. When blindly presented with the selected signals for re-assessment (23% of the data), the two independent expert-annotators changed the annotation in 25% of the cases. Subsequently, the network was trained on the expert-revised gold standard, which resulted in improved separation between artifacts and nonartifacts as well as an increase in balanced accuracy from 74% to 80% and precision from 59% to 76%. These results show that CNNs are promising to enhance manual annotation of EEG artifacts and can be improved further with better gold-standard data.

An Intelligent Epileptic Prediction System Based on Synchrosqueezed Wavelet Transform and Multi-Level Feature CNN for Smart Healthcare IoT.

Epilepsy is a common neurological disease worldwide, characterized by recurrent seizures. There is currently no cure for epilepsy. However, seizures can be controlled by drugs and surgeries in about 70% of epileptic patients. A timely and accurate prediction of seizures can prevent injuries during seizures and improve the patients’ quality of life. In this paper, we proposed an intelligent epileptic prediction system based on Synchrosqueezed Wavelet Transform (SWT) and Multi-Level Feature Convolutional Neural Network (MLF-CNN) for smart healthcare IoT network. In this system, we used SWT to map EEG signals to the frequency domain, which was able to measure the energy changes in EEG signals caused by seizures within a well-defined Time-Frequency (TF) plane. MLF-CNN was then applied to extract multi-level features from the processed EEG signals and classify the different seizure segments. The performance of our proposed system was evaluated with the publicly available CHB-MIT dataset and our private ZJU4H dataset. The system achieved an accuracy of 96.99% and 94.25%, a sensitivity of 96.48% and 97.76%, a specificity of 97.46% and 94.07% and a false prediction rate (FPR/h) of 0.031 and 0.049 FPR/h on the CHB-MIT dataset and the ZJU4H dataset, respectively.

BCI-FES With Multimodal Feedback for Motor Recovery Poststroke.

An increasing number of research teams are investigating the efficacy of brain-computer interface (BCI)-mediated interventions for promoting motor recovery following stroke. A growing body of evidence suggests that of the various BCI designs, most effective are those that deliver functional electrical stimulation (FES) of upper extremity (UE) muscles contingent on movement intent. More specifically, BCI-FES interventions utilize algorithms that isolate motor signals—user-generated intent-to-move neural activity recorded from cerebral cortical motor areas—to drive electrical stimulation of individual muscles or muscle synergies. BCI-FES interventions aim to recover sensorimotor function of an impaired extremity by facilitating and/or inducing long-term motor learning-related neuroplastic changes in appropriate control circuitry. We developed a non-invasive, electroencephalogram (EEG)-based BCI-FES system that delivers closed-loop neural activity-triggered electrical stimulation of targeted distal muscles while providing the user with multimodal sensory feedback. This BCI-FES system consists of three components: (1) EEG acquisition and signal processing to extract real-time volitional and task-dependent neural command signals from cerebral cortical motor areas, (2) FES of muscles of the impaired hand contingent on the motor cortical neural command signals, and (3) multimodal sensory feedback associated with performance of the behavioral task, including visual information, linked activation of somatosensory afferents through intact sensorimotor circuits, and electro-tactile stimulation of the tongue. In this report, we describe device parameters and intervention protocols of our BCI-FES system which, combined with standard physical rehabilitation approaches, has proven efficacious in treating UE motor impairment in stroke survivors, regardless of level of impairment and chronicity.

EEG Sinyallerini İşlemek İçin Makine Öğreniminin Kullanıldığı Konular Üzerine Bir İnceleme

Son on yılda, yapay zekâ (YZ) ve makine öğrenimi (MÖ) kullanımlarında bir artış görülmüştür. MÖ alanındaki son gelişmeler, farklı alanlar için elektroensefalografinin (EEG) kullanımına yeniden ilgi duyulmasına yol açmıştır. EEG, zihinsel iş yükünü ve yorgunluğu analiz etmek, beyin tümörlerini teşhis etmek ve merkezi sinir sistemi bozukluklarının rehabilitasyonu gibi tıbbi ve biyomedikal uygulamalarda; EEG tabanlı hareket analizi ve sınıflandırması ise, klinik uygulamalardan beyin-makine ara yüzüne ve robotik uygulamalara kadar birçok alanda yaygın olarak kullanılmaktadır. Bu makale, EEG sinyal işlemede kullanılan birçok MÖ algoritmalarının uygulamalarını gözden geçirmekte, yaygın olarak kullanılan algoritmaları, tipik uygulama senaryolarını, önemli ilerlemeleri ve mevcut sorunları tanıtmaktadır. Çalışmada, beyin-bilgisayar arayüzleri, bilişsel sinirbilim, beyin bozukluklarının teşhisi ve daha farklı konular dahil olmak üzere, EEG'deki mevcut MÖ uygulamaları araştırılmıştır. İlk olarak, evrişimli sinir ağı, destek vektör makineleri, K-en yakın komşu ve çok yönlü evrişim sinir ağı dahil olmak üzere EEG sinyal işlemede kullanılan MÖ algoritmalarının temel ilkeleri kısaca açıklanmıştır. Ayrıca EEG analizinde kullanılan MÖ uygulamalarına dair genel bir araştırma sunulmuştur. Sonuç olarak çalışmalarda en fazla DVM ve CNN yöntemlerinin kullanıldığı, çalışma başlıklarının ise ağırlıklı olarak epilepsi, BCI ve Duygu konularında en az ise Alkol, Uyku Durumları, Algı konularında yapıldığı belirlenmiştir.

VR-oriented EEG signal classification of motor imagery tasks

Virtual Reality (VR) combined with near real-time EEG signal processing can be used as an improvement to already existing rehabilitation techniques, enabling practitioners and therapists to get immersed into a virtual environment together with patients. The goal of this study is to propose a classification model along with all preprocessing and feature extraction steps, able to produce satisfying results while maintaining near real time performance. The proposed solutions are tested on an EEG signal dataset, containing left/right hand motor imagery movement experiments performed by 52 subjects. Performance of different models is measured using accuracy score and execution time both in the testing and training phase. In conclusion, one model is proposed as optimal with respect to the requirements of potential patient rehabilitation procedures.

A Systematic Review on Feature Extraction in Electroencephalography-Based Diagnostics and Therapy in Attention Deficit Hyperactivity Disorder.

A systematic review on electroencephalographic (EEG)-based feature extraction strategies to diagnosis and therapy of attention deficit hyperactivity disorder (ADHD) in children is presented. The analysis is realized at an executive function level to improve the research of neurocorrelates of heterogeneous disorders such as ADHD. The Quality Assessment Tool for Quantitative Studies (QATQS) and field-weighted citation impact metric (Scopus) were used to assess the methodological rigor of the studies and their impact on the scientific community, respectively. One hundred and one articles, concerning the diagnostics and therapy of ADHD children aged from 8 to 14, were collected. Event-related potential components were mainly exploited for executive functions related to the cluster inhibition, whereas band power spectral density is the most considered EEG feature for executive functions related to the cluster working memory. This review identifies the most used (also by rigorous and relevant articles) EEG signal processing strategies for executive function assessment in ADHD.

EEG Identity Authentication in Multi-Domain Features: A Multi-Scale 3D-CNN Approach.

Electroencephalogram (EEG) authentication has become a research hotspot in the field of information security due to its advantages of living, internal, and anti-stress. However, the performance of identity authentication system is limited by the inherent attributes of EEG, such as low SNR, low stability, and strong randomness. Researchers generally believe that the in-depth fusion of features can improve the performance of identity authentication and have explored among various feature domains. This experiment invited 70 subjects to participate in the EEG identity authentication task, and the experimental materials were visual stimuli of the self and non-self-names. This paper proposes an innovative EEG authentication framework, including efficient three-dimensional representation of EEG signals, multi-scale convolution structure, and the combination of multiple authentication strategies. In this work, individual EEG signals are converted into spatial–temporal–frequency domain three-dimensional forms to provide multi-angle mixed feature representation. Then, the individual identity features are extracted by the various convolution kernel of multi-scale vision, and the strategy of combining multiple convolution kernels is explored. The results show that the small-size and long-shape convolution kernel is suitable for ERP tasks, which can obtain better convergence and accuracy. The experimental results show that the classification performance of the proposed framework is excellent, and the multi-scale convolution method is effective to extract high-quality identity characteristics across feature domains. The results show that the branch number matches the EEG component number can obtain the excellent cost performance. In addition, this paper explores the network training performance for multi-scale module combination strategy and provides reference for deep network construction strategy of EEG signal processing.

EEG-based vibrotactile evoked brain-computer interfaces system: A systematic review.

Recently, a novel electroencephalogram-based brain-computer interface (EVE-BCI) using the vibrotactile stimulus shows great potential for an alternative to other typical motor imagery and visual-based ones. (i) Objective: in this review, crucial aspects of EVE-BCI are extracted from the literature to summarize its key factors, investigate the synthetic evidence of feasibility, and generate recommendations for further studies. (ii) Method: five major databases were searched for relevant publications. Multiple key concepts of EVE-BCI, including data collection, stimulation paradigm, vibrotactile control, EEG signal processing, and reported performance, were derived from each eligible article. We then analyzed these concepts to reach our objective. (iii) Results: (a) seventy-nine studies are eligible for inclusion; (b) EEG data are mostly collected among healthy people with an embodiment of EEG cap in EVE-BCI development; (c) P300 and Steady-State Somatosensory Evoked Potential are the two most popular paradigms; (d) only locations of vibration are heavily explored by previous researchers, while other vibrating factors draw little interest. (e) temporal features of EEG signal are usually extracted and used as the input to linear predictive models for EVE-BCI setup; (f) subject-dependent and offline evaluations remain popular assessments of EVE-BCI performance; (g) accuracies of EVE-BCI are significantly higher than chance levels among different populations. (iv) Significance: we summarize trends and gaps in the current EVE-BCI by identifying influential factors. A comprehensive overview of EVE-BCI can be quickly gained by reading this review. We also provide recommendations for the EVE-BCI design and formulate a checklist for a clear presentation of the research work. They are useful references for researchers to develop a more sophisticated and practical EVE-BCI in future studies.

Electroencephalography Signal Power Spectral Density from Measurements in Room with and Without Faraday Cage: A Comparative Study

Electroencephalography (EEG) is a method for recording the brain’s electrical activity through electrodes placed on the scalp’s surface. This EEG has its problem, namely signal interference from outside the system or artifacts. Ways to eliminate this signal interference can be made in various ways, including handling signal sources outside the system or removing interference signals during the EEG signal processing process. One way is to isolate the measurement room from signal interference using a Faraday cage. In this study, we will compare the results of EEG signal processing in the form of power spectral density (PSD) from measurements in a room without a Faraday cage and a room with a Faraday cage. We find that the average value of the change in PSD from the measurement results in the two rooms had a level of difference that varied between 0.71%-66%. The location of the electrodes that have a high difference value is the frontal and parietal areas.

IENet: a robust convolutional neural network for EEG based brain-computer interfaces

Objective. Brain-computer interfaces (BCIs) based on electroencephalogram (EEG) develop into novel application areas with more complex scenarios, which put forward higher requirements for the robustness of EEG signal processing algorithms. Deep learning can automatically extract discriminative features and potential dependencies via deep structures, demonstrating strong analytical capabilities in numerous domains such as computer vision and natural language processing. Making full use of deep learning technology to design a robust algorithm that is capable of analyzing EEG across BCI paradigms is our main work in this paper. Approach. Inspired by InceptionV4 and InceptionTime architecture, we introduce a neural network ensemble named InceptionEEG-Net (IENet), where multi-scale convolutional layer and convolution of length 1 enable model to extract rich high-dimensional features with limited parameters. In addition, we propose the average receptive field (RF) gain for convolutional neural networks (CNNs), which optimizes IENet to detect long patterns at a smaller cost. We compare with the current state-of-the-art methods across five EEG-BCI paradigms: steady-state visual evoked potentials (VEPs), epilepsy EEG, overt attention P300 VEPs, covert attention P300 visual-EPs and movement-related cortical potentials. Main results. The classification results show that the generalizability of IENet is on par with the state-of-the-art paradigm-agnostic models on test datasets. Furthermore, the feature explainability analysis of IENet illustrates its capability to extract neurophysiologically interpretable features for different BCI paradigms, ensuring the reliability of algorithm. Significance. It can be seen from our results that IENet can generalize to different BCI paradigms. And it is essential for deep CNNs to increase the RF size using average RF gain.