Raw EEG Signals Research Articles

Task-oriented EEG denoising generative adversarial network for enhancing SSVEP-BCI performance.


The quality of electroencephalogram (EEG) signals directly impacts the performance of brain-computer interface (BCI) tasks. Many methods have been proposed to eliminate noise from EEG signals, but most of these methods focus solely on signal denoising itself, disregarding the impact on subsequent tasks, which deviates from the original intention of EEG denoising. The main objective of this study is to optimize EEG denoising models with a purpose of improving the performance of BCI tasks.
Approach.
To this end, we proposed an innovative Task-Oriented EEG Denoising Generative Adversarial Network (TOED-GAN) method. This network utilizes the generator of GAN to decompose and reconstruct clean signals from the raw EEG signals, and the discriminator to learn to distinguish the generated signals from the true clean signals, resulting in a remarkable increase of the signal-to-noise ratio (SNR) by simultaneously enhancing task-related components and removing task-irrelevant noise from the original contaminated signals.
Main results.
We evaluated the performance of the model on a public dataset and a self-collected dataset respectively, with canonical correlation analysis (CCA) classification tasks of the steady-state visual evoked potential (SSVEP) based BCI. Experimental results demonstrate that TOED-GAN exhibits excellent performance in removing EEG noise and improving performance for SSVEP-BCI, with accuracy improvement rates reaching 18.47% and 21.33% in contrast to the baseline methods of convolutional neural networks, respectively
Significance.
This work proves that the proposed TOED-GAN, as an EEG denoising method tailored for SSVEP tasks, contributes to enhancing the performance of BCIs in practical application scenarios.

A Lightweight GCT-EEGNet for EEG-Based Individual Recognition Under Diverse Brain Conditions

A robust biometric system is essential to mitigate various security threats. Electroencephalography (EEG) brain signals present a promising alternative to other biometric traits due to their sensitivity, non-duplicability, resistance to theft, and individual-specific dynamics. However, existing EEG-based biometric systems employ deep neural networks, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which face challenges such as high parameter complexity, limiting their practical application. Additionally, their ability to generalize across a large number of subjects remains unclear. Moreover, they have been validated on datasets collected in controlled environments, which do not accurately reflect real-world scenarios involving diverse brain conditions. To overcome these challenges, we propose a lightweight neural network model, GCT–EEGNet, which is based on the design ideas of a CNN model and incorporates an attention mechanism to pay attention to the appropriate frequency bands for extracting discriminative features relevant to the identity of a subject despite diverse brain conditions. First, a raw EEG signal is decomposed into frequency bands and then passed to GCT–EEGNet for feature extraction, which utilizes a gated channel transformation (GCT) layer to selectively emphasize informative features from the relevant frequency bands. The extracted features were used for subject recognition through a cosine similarity metric that measured the similarity between feature vectors of different EEG trials to identify individuals. The proposed method was evaluated on a large dataset comprising 263 subjects. The experimental results demonstrated that the method achieved a correct recognition rate (CRR) of 99.23% and an equal error rate (EER) of 0.0014, corroborating its robustness against different brain conditions. The proposed model maintains low parameter complexity while keeping the expressiveness of representations, even with unseen subjects.

Cramer Distance: A Deep Learning Approach for Better Epileptic Seizure Prediction

Epilepsy is a neurological condition that is found in most people all over the world, and the ability to accurately anticipate seizures in epileptic patients has a significant impact on both their level of protection and their overall quality of life. This research proposes a unique patient specific seizure prediction approach based on Deep Learning (DL) using long-term scalp electroencephalogram (EEG) recordings to predict seizure onset. Preictal brain states should be adequately detected and differentiated from the prevalent interictal brain states as early as possible to make this technology acceptable for real-time use. A single automated system has been designed for the Features Extraction (FE) and classification processes. The raw EEG signal that has not been pre-processed is considered the input to the system, and the signal is further reduced using subsequent computations. An innovative reconstruction approach using Variational Auto-Encoder Generative Adversarial Networks (VAE+C+GAN) with the Cramer Distance (CD) and a Temporal-Spatial-Frequency (TSF) loss function is presented in this research work. The machine that discriminates receives instructions to differentiate between created tests and actual samples, while the generator is verified to produce false samples that the discriminator does not recognize as fake. The proposed VAE+C+GAN’s experimental results have been examined, and a classification accuracy of 95% has been achieved. According to the experiment's findings, the VAE-C-GAN performs better than the current EEG classification system and has excellent potential for real-time applications.

A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection.

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG.The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.

DOCTer: a novel EEG-based diagnosis framework for disorders of consciousness.

Objective. Accurately diagnosing patients with disorders of consciousness (DOC) is challenging and prone to errors. Recent studies have demonstrated that EEG (electroencephalography), a non-invasive technique of recording the spontaneous electrical activity of brains, offers valuable insights for DOC diagnosis. However, some challenges remain: (1) the EEG signals have not been fully used; and (2) the data scale in most existing studies is limited. In this study, our goal is to differentiate between minimally conscious state (MCS) and unresponsive wakefulness syndrome (UWS) using resting-state EEG signals, by proposing a new deep learning framework.Approach. We propose DOCTer, an end-to-end framework for DOC diagnosis based on EEG. It extracts multiple pertinent features from the raw EEG signals, including time-frequency features and microstates. Meanwhile, it takes clinical characteristics of patients into account, and then combines all the features together for the diagnosis. To evaluate its effectiveness, we collect a large-scale dataset containing 409 resting-state EEG recordings from 128 UWS and 187 MCS cases.Main results. Evaluated on our dataset, DOCTer achieves the state-of-the-art performance, compared to other methods. The temporal/spectral features contributes the most to the diagnosis task. The cerebral integrity is important for detecting the consciousness level. Meanwhile, we investigate the influence of different EEG collection duration and number of channels, in order to help make the appropriate choices for clinics.Significance. The DOCTer framework significantly improves the accuracy of DOC diagnosis, helpful for developing appropriate treatment programs. Findings derived from the large-scale dataset provide valuable insights for clinics.

A parallel neural networks for emotion recognition based on EEG signals

Our study proposes a novel Parallel Temporal–Spatial-Frequency Neural Network (PTSFNN) for emotion recognition. The network processes EEG signals in the time, frequency, and spatial domains simultaneously to extract discriminative features. Despite its relatively simple architecture, the proposed model achieves superior performance. Specifically, PTSFNN first applies wavelet transform to the raw EEG signals and then reconstructs the coefficients based on frequency hierarchy, thereby achieving frequency decomposition. Subsequently, the core part of the network performs three independent parallel convolution operations on the decomposed signals, including a novel graph convolutional network. Finally, an attention mechanism-based post-processing operation is designed to effectively enhance feature representation. The features obtained from the three modules are concatenated for classification, with the cross-entropy loss function being adopted. To evaluate the model’s performance, extensive experiments are conducted on the SEED and SEED-IV public datasets. The experimental results demonstrate that PTSFNN achieves excellent performance in emotion recognition tasks, with classification accuracies of 87.63% and 74.96%, respectively. Comparative experiments with previous state-of-the-art methods confirm the superiority of our proposed model, which can efficiently extract emotion information from EEG signals.

EEG-Based Seizure Prediction Using Hybrid DenseNet-ViT Network with Attention Fusion.

Epilepsy seizure prediction is vital for enhancing the quality of life for individuals with epilepsy. In this study, we introduce a novel hybrid deep learning architecture, merging DenseNet and Vision Transformer (ViT) with an attention fusion layer for seizure prediction. DenseNet captures hierarchical features and ensures efficient parameter usage, while ViT offers self-attention mechanisms and global feature representation. The attention fusion layer effectively amalgamates features from both networks, guaranteeing the most relevant information is harnessed for seizure prediction. The raw EEG signals were preprocessed using the short-time Fourier transform (STFT) to implement time-frequency analysis and convert EEG signals into time-frequency matrices. Then, they were fed into the proposed hybrid DenseNet-ViT network model to achieve end-to-end seizure prediction. The CHB-MIT dataset, including data from 24 patients, was used for evaluation and the leave-one-out cross-validation method was utilized to evaluate the performance of the proposed model. Our results demonstrate superior performance in seizure prediction, exhibiting high accuracy and low redundancy, which suggests that combining DenseNet, ViT, and the attention mechanism can significantly enhance prediction capabilities and facilitate more precise therapeutic interventions.

Enhanced EEG seizure recognition after hypoxia-ischemia in fetal sheep using transformer-based wavelet-scalogram deep learning

This study introduces transformer-based deep learning models as superior alternatives to convolutional neural network (CNN) architectures for seizure detection after hypoxia–ischemia (HI) in electroencephalography (EEG) recordings in the developing brain. We further demonstrate that these models excel in classifying of varied and subtle morphologies of electrographic seizures observed in the EEG of fetal sheep after HI. The study explores model training combinations from four cohorts of Romney/Suffolk fetal sheep (HI-normothermia-term (n = 7), HI-hypothermia-term (n = 14), sham-normothermia-term (n = 5), and HI-normothermia-preterm (n = 14)), totalling 31,015 EEG segments from 17,300 h of recordings. We evaluated multiple Transformer architectures using both 2D wavelet-scalograms (WS) and 1D raw EEG signals through leave-one-out and k-fold cross-validation, comparing models’ performance with or without sham-normothermia-term data and contrasting them with CNN-based results from our previous work. The Data-Efficient image Transformer (DeiT) emerged as the top-performing model, achieving 99.60 % accuracy (AUC = 0.992) when fed with WS, surpassing the 2D WS CNN result (98.94 % accuracy, AUC = 0.967) from our prior study. Notably, the Wav2Vec2 transformer model, fed with raw 1D EEG segments, demonstrated comparable performance with 99.60 % accuracy (AUC = 0.992), outperforming the 1D CNN result (98.43 % accuracy, AUC = 0.961) from the previous study. More importantly, the transformers can adeptly distinguish between seizures in both the preterm and term brain, and under the influence of treatment with 99.92 % accuracy (AUC = 0.997). Our findings highlight the superior ability of transformer models to capture long-range dependencies within EEG data, enhancing seizure detection without the added complexity of generating 2D WS images. Transformer models show promise for generalized automated seizure detection, irrespective of the perinatal brain maturation stage and the influence of hypothermia, offering potential improvements for seizure detection after HI in newborns.

Classification of Alzheimer’s dementia EEG signals using deep learning

Alzheimer’s dementia (AD) is a predominant neurological disorder arising from corruptions in brain functions and is characterized by a chronic or progressive nature. While the precise etiology of dementia remains incompletely elucidated, its manifestation is frequently associated with discernible structural and chemical alterations in the brain. Living with dementia significantly impacts individuals’ daily lives due to the resultant loss of cognitive functions. This study presents a novel method to monitor and detect AD using advanced signal processing applied to electroencephalography (EEG) signals. The intrinsic time-scale decomposition (ITD) algorithm is employed to extract proper rotation components (PRCs) from EEG signals, utilizing a 5-second EEG segment duration. The proposed method is compared with the detection of 5-second raw EEG segments using a custom one-dimensional convolutional neural network (1D CNN). Additionally, four different quartiles (Quartile 1 (Q1), Q2, Q3, and Q4) of EEG signals are considered to identify the most significant contributor to AD. Experimental results demonstrate that the ITD-based approach yields better detection performance compared to using raw EEG signals. The most promising result is achieved by the EEG-PRCs method in Q1, with an accuracy of 94.00%, sensitivity of 93.50%, and specificity of 93.90%. In contrast, the highest-performing result of the raw EEG segments method is in Q2, with an accuracy of 88.40%, sensitivity of 89.10%, and specificity of 87.60% in terms of detecting AD.

Wasserstein generative adversarial network with gradient penalty and convolutional neural network based motor imagery EEG classification

Objective.Due to the difficulty in acquiring motor imagery electroencephalography (MI-EEG) data and ensuring its quality, insufficient training data often leads to overfitting and inadequate generalization capabilities of deep learning-based classification networks. Therefore, we propose a novel data augmentation method and deep learning classification model to enhance the decoding performance of MI-EEG further.Approach.The raw EEG signals were transformed into the time-frequency maps as the input to the model by continuous wavelet transform. An improved Wasserstein generative adversarial network with gradient penalty data augmentation method was proposed, effectively expanding the dataset used for model training. Additionally, a concise and efficient deep learning model was designed to improve decoding performance further.Main results.It has been demonstrated through validation by multiple data evaluation methods that the proposed generative network can generate more realistic data. Experimental results on the BCI Competition IV 2a and 2b datasets and the actual collected dataset show that classification accuracies are 83.4%, 89.1% and 73.3%, and Kappa values are 0.779, 0.782 and 0.644, respectively. The results indicate that the proposed model outperforms state-of-the-art methods.Significance.Experimental results demonstrate that this method effectively enhances MI-EEG data, mitigates overfitting in classification networks, improves MI classification accuracy, and holds positive implications for MI tasks.

A model for electroencephalogram emotion recognition: Residual block-gated recurrent unit with attention mechanism.

Electroencephalogram (EEG) signals, serving as a tool to objectively reflect real emotional states, hold a crucial position in emotion recognition research. In recent years, deep learning approaches have been widely applied in emotion recognition research, and the results have demonstrated their effectiveness in this field. Nevertheless, the challenge remains in selecting effective features, ensuring their retention as the network depth increases, and preventing the loss of crucial information. In order to address the issues, a novel emotion recognition method is proposed, which is named Res-CRANN. In the proposed method, the raw EEG signals are transformed into four dimensional spatial-frequency-temporal information, which can provide a more enriched and complex feature representation. First, the residual block is incorporated into the convolutional layers to extract spatial and frequency domain information. Subsequently, gated recurrent unit (GRU) is employed to capture temporal information from the convolutional neural network outputs. Following GRU, attention mechanisms are applied to enhance awareness of key information and diminish interference from irrelevant details. By reducing attention to irrelevant or noisy temporal steps, it ultimately improves the accuracy and robustness of the classification process. The Res-CRANN method exhibits excellent performance on the DEAP dataset, with an accuracy of 96.63% for valence and 96.87% for arousal, confirming its effectiveness.

LANMAO sleep recorder versus polysomnography in neonatal EEG recording and sleep analysis

BackgroundThe field of neonatal sleep analysis is burgeoning with devices that purport to offer alternatives to polysomnography (PSG) for monitoring sleep patterns. However, the majority of these devices are limited in their capacity, typically only distinguishing between sleep and wakefulness. This study aims to assess the efficacy of a novel wearable electroencephalographic (EEG) device, the LANMAO Sleep Recorder, in capturing EEG data and analyzing sleep stages, and to compare its performance against the established PSG standard. MethodsThe study involved concurrent sleep monitoring of 34 neonates using both PSG and the LANMAO device. Initially, the study verified the consistency of raw EEG signals captured by the LANMAO device, employing relative spectral power analysis and Pearson correlation coefficients (PCC) for validation. Subsequently, the LANMAO device’s integrated automated sleep staging algorithm was evaluated by comparing its output with expert-generated sleep stage classifications. ResultsAnalysis revealed that the PCC between the relative spectral powers of various frequency bands during different sleep stages ranged from 0.28 to 0.48. Specifically, the correlation for delta waves was recorded at 0.28. The automated sleep staging algorithm of the LANMAO device demonstrated an overall accuracy of 79.60 %, Cohen kappa of 0.65, and F1 Score of 76.93 %. Individual accuracy for Wake at 87.20 %, NREM at 85.70 %, and REM Sleep at 81.30 %. ConclusionWhile the LANMAO Sleep Recorder’s automated sleep staging algorithm necessitates further refinement, the device shows promise in accurately recording neonatal EEG during sleep. Its potential for minimal invasiveness makes it an appealing option for monitoring sleep conditions in newborns, suggesting a novel approach in the field of neonatal sleep analysis.

S[formula omitted]T-Net: A novel electroencephalogram signals-oriented emotion recognition model

In this paper, a novel skipping spatial–spectral–temporal network (S3T-Net) is developed to handle intra-individual differences in electroencephalogram (EEG) signals for accurate, robust, and generalized emotion recognition. In particular, aiming at the 4D features extracted from the raw EEG signals, a multi-branch architecture is proposed to learn spatial–spectral cross-domain representations, which benefits enhancing the model generalization ability. Time dependency among different spatial–spectral features is further captured via a bi-directional long-short term memory module, which employs an attention mechanism to integrate context information. Moreover, a skip-change unit is designed to add another auxiliary pathway for updating model parameters, which alleviates the vanishing gradient problem in complex spatial–temporal network. Evaluation results show that the proposed S3T-Net outperforms other advanced models in terms of the emotion recognition accuracy, which yields an performance improvement of 0.23% , 0.13%, and 0.43% as compared to the sub-optimal model in three test scenes, respectively. In addition, the effectiveness and superiority of the key components of S3T-Net are demonstrated from various experiments. As a reliable and competent emotion recognition model, the proposed S3T-Net contributes to the development of intelligent sentiment analysis in human–computer interaction (HCI) realm.

MOTOR IMAGERY SIGNAL CLASSIFICATION FOR BRAIN–COMPUTER INTERFACE USING RideNN WITH HOLO-ENTROPY FEATURES

The brain–computer interface (BCI) database’s motor assessment depends heavily on the motor imagery (MI) signal classification. By examining the multiple patterns of different creative tasks in the electroencephalogram (EEG) signals, the intention of humans is translated into computer-based commands in the MI-based signals of BCI data. Nevertheless, low accuracy and efficiency are issues with MI–EEG signals’ classification because of the low signal-to-noise ratio, huge individual differences, overall volatility, and complexity in the signal. To overcome these problems, this research proposes a rider optimization algorithm-based neural network (ROA-based NN) to classify the MI signals effectively. Pre-processing is done after collecting the dataset of raw EEG signals. The suitable electrodes, such as C3, C4, and Cz, are subsequently chosen from the MI signals. Using the holo-entropy-based WPD feature extractor, tunable Q-factor wavelet transform (T-QWT), and common spatial patterns in the model, the pertinent features are extracted from the chosen electrodes. The developed holo-entropy-based WPD feature examines the electrode structure’s association. As a result, the most diverse signals are removed from the chosen electrodes before being input into the proposed RideNN classifier, where the proposed ride optimization algorithm optimizes classification performance and correctly predicts and classes the output from the MI signals that have been analyzed. The developed RideNN classifier recognizes the patterns more accurately processes more data and tackles the noise and incomplete data effectively. Utilizing the parameters of accuracy, sensitivity, and specificity, the results are evaluated. The PROA-based RideNN and the combined features obtain the maximum accuracy of 92.24%, sensitivity of 92.26%, and specificity of 92.14% for the BCI competition-IV 2a database. The qPROA-based RideNN and the combined features obtain the maximum accuracy of 92.11%, sensitivity of 91.98%, and specificity of 92.35% for the BCI competition-IV 2b database.

The Effect of Stress on a Personal Identification System Based on Electroencephalographic Signals.

Personal identification systems based on electroencephalographic (EEG) signals have their own strengths and limitations. The stability of EEG signals strongly affects such systems. The human emotional state is one of the important factors that affects EEG signals' stability. Stress is a major emotional state that affects individuals' capability to perform day-to-day tasks. The main objective of this work is to study the effect of mental and emotional stress on such systems. Two experiments have been performed. In the first, we used hand-crafted features (time domain, frequency domain, and non-linear features), followed by a machine learning classifier. In the second, raw EEG signals were used as an input for the deep learning approaches. Different types of mental and emotional stress have been examined using two datasets, SAM 40 and DEAP. The proposed experiments proved that performing enrollment in a relaxed or calm state and identification in a stressed state have a negative effect on the identification system's performance. The best achieved accuracy for the DEAP dataset was 99.67% in the calm state and 96.67% in the stressed state. For the SAM 40 dataset, the best accuracy was 99.67%, 93.33%, 92.5%, and 91.67% for the relaxed state and stress caused by identifying mirror images, the Stroop color-word test, and solving arithmetic operations, respectively.

GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-Resolved EEG Motor Imagery Signals.

Toward the development of effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by an electroencephalogram (EEG) is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning (DL) framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected (FC) softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and groupwise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet dataset), 96.24% and 80.89% (high gamma dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step toward better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain MI. A DL library for EEG task classification including the code for this study is open source at https://github.com/SuperBruceJia/ EEG-DL for scientific research.

Detection Method of Epileptic Seizures Using a Neural Network Model Based on Multimodal Dual-Stream Networks.

Epilepsy is a common neurological disorder, and its diagnosis mainly relies on the analysis of electroencephalogram (EEG) signals. However, the raw EEG signals contain limited recognizable features, and in order to increase the recognizable features in the input of the network, the differential features of the signals, the amplitude spectrum and the phase spectrum in the frequency domain are extracted to form a two-dimensional feature vector. In order to solve the problem of recognizing multimodal features, a neural network model based on a multimodal dual-stream network is proposed, which uses a mixture of one-dimensional convolution, two-dimensional convolution and LSTM neural networks to extract the spatial features of the EEG two-dimensional vectors and the temporal features of the signals, respectively, and combines the advantages of the two networks, using the hybrid neural network to extract both the temporal and spatial features of the signals at the same time. In addition, a channel attention module was used to focus the model on features related to seizures. Finally, multiple sets of experiments were conducted on the Bonn and New Delhi data sets, and the highest accuracy rates of 99.69% and 97.5% were obtained on the test set, respectively, verifying the superiority of the proposed model in the task of epileptic seizure detection.

Decoding Subject-Driven Cognitive States from EEG Signals for Cognitive Brain–Computer Interface

In this study, we investigated the feasibility of using electroencephalogram (EEG) signals to differentiate between four distinct subject-driven cognitive states: resting state, narrative memory, music, and subtraction tasks. EEG data were collected from seven healthy male participants while performing these cognitive tasks, and the raw EEG signals were transformed into time–frequency maps using continuous wavelet transform. Based on these time–frequency maps, we developed a convolutional neural network model (TF-CNN-CFA) with a channel and frequency attention mechanism to automatically distinguish between these cognitive states. The experimental results demonstrated that the model achieved an average classification accuracy of 76.14% in identifying these four cognitive states, significantly outperforming traditional EEG signal processing methods and other classical image classification algorithms. Furthermore, we investigated the impact of varying lengths of EEG signals on classification performance and found that TF-CNN-CFA demonstrates consistent performance across different window lengths, indicating its strong generalization capability. This study validates the ability of EEG to differentiate higher cognitive states, which could potentially offer a novel BCI paradigm.

ZleepAnlystNet: a novel deep learning model for automatic sleep stage scoring based on single-channel raw EEG data using separating training.

Numerous models for sleep stage scoring utilizing single-channel raw EEG signal have typically employed CNN and BiLSTM architectures. While these models, incorporating temporal information for sequence classification, demonstrate superior overall performance, they often exhibit low per-class performance for N1-stage, necessitating an adjustment of loss function. However, the efficacy of such adjustment is constrained by the training process. In this study, a pioneering training approach called separating training is introduced, alongside a novel model, to enhance performance. The developed model comprises 15 CNN models with varying loss function weights for feature extraction and 1 BiLSTM for sequence classification. Due to its architecture, this model cannot be trained using an end-to-end approach, necessitating separate training for each component using the Sleep-EDF dataset. Achieving an overall accuracy of 87.02%, MF1 of 82.09%, Kappa of 0.8221, and per-class F1-socres (W 90.34%, N1 54.23%, N2 89.53%, N3 88.96%, and REM 87.40%), our model demonstrates promising performance. Comparison with sleep technicians reveals a Kappa of 0.7015, indicating alignment with reference sleep stags. Additionally, cross-dataset validation and adaptation through training with the SHHS dataset yield an overall accuracy of 84.40%, MF1 of 74.96% and Kappa of 0.7785 when tested with the Sleep-EDF-13 dataset. These findings underscore the generalization potential in model architecture design facilitated by our novel training approach.

A single-joint multi-task motor imagery EEG signal recognition method based on Empirical Wavelet and Multi‐Kernel Extreme Learning Machine

BackgroundIn the pursuit of finer Brain-Computer Interface commands, research focus has shifted towards classifying EEG signals for multiple tasks. While single-joint multitasking motor imagery provides support, distinguishing between EEG signals from the same joint remains challenging due to their similar brain spatial distribution. New methodWe designed experiments involving three motor imagery tasks—wrist extension, wrist flexion, and wrist abduction—with six participants. Based on this, a single-joint multi-task motor imagery EEG signal recognition method using Empirical Wavelet Decomposition and Multi-Kernel Extreme Learning Machine is proposed. This method employs Empirical Wavelet Decomposition (EWT) for modal decomposition, screening, and reconstruction of raw EEG signals, feature extraction using Common Spatial Patterns (CSP), and classification using Multi-Kernel Extreme Learning Machine (MKELM). ResultsAfter EWT processing, differences in time and frequency characteristics between EEG signals of different classes were enhanced, with the MKELM model achieving an average recognition accuracy of 91.93 %. Comparison with other methods and conclusionsWe compared EWT with Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), Local Mean Decomposition (LMD), and Wavelet Packet Decomposition (WPD). The results showed that the differences between various types of EEG signals processed by EWT were the most pronounced. The MKELM model outperformed traditional machine learning models such as Extreme Learning Machine (ELM), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA) in terms of recognition performance, and also exhibited faster training speeds than deep learning models such as Bayesian Convolutional Neural Network (BCNN) and Attention-based Dual-scale Fusion Convolutional Neural Network (ADFCNN). In summary, the proposed method provides a new approach for achieving finer Brain-Computer Interface commands.