Complex networks and deep learning for EEG signal analysis

BISNN: bio-information-fused spiking neural networks for enhanced EEG-based emotion recognition

Spiking neural networks (SNNs), known for their rich spatio-temporal dynamics, have recently gained considerable attention in EEG-based emotion recognition. However, conventional model training approaches often fail to fully exploit the capabilities of SNNs, posing challenges for effective EEG data analysis. In this work, we propose a novel bio-information-fused SNN (BISNN) model to enhance EEG-based emotion recognition. The BISNN model incorporates biologically plausible intrinsic parameters into spiking neurons and is initialized with a structurally equivalent pre-trained ANN model. By constructing a bio-information-fused loss function, the BISNN model enables simultaneous training under dual constraints. Extensive experiments on benchmark EEG-based emotion datasets demonstrate that the BISNN model achieves competitive performance compared to state-of-the-art methods. Additionally, ablation studies investigating various components further elucidate the mechanisms underlying the model's effectiveness and evolution, aligning well with previous findings.

Deep neural networks and stochastic methods for cognitive modeling of rat behavioral dynamics in T -mazes

Modeling animal decision-making requires mathematical rigor and computational analysis to capture underlying cognitive mechanisms. This study presents a cognitive model for rat decision-making behavior in T -mazes by combining stochastic methods with deep neural architectures. The model adapts Wyckoff's stochastic framework, originally grounded in Bush's discrimination learning theory, to describe probabilistic transitions between directional choices under reinforcement contingencies. The existence and uniqueness of solutions are demonstrated via fixed-point theorems, ensuring the formulation is well-posed. The asymptotic properties of the system are examined under boundary conditions to understand the convergence behavior of decision probabilities across trials. Empirical validation is performed using Monte Carlo simulations to compare expected trajectories with the model's predictive output. The dataset comprises spatial trajectory recordings of rats navigating toward food rewards under controlled experimental protocols. Trajectories are preprocessed through statistical filtering, augmented to address data imbalance, and embedded using t-SNE to visualize separability across behavioral states. A hybrid convolutional-recurrent neural network (CNN-LSTM) is trained on these representations and achieves a classification accuracy of 82.24%, outperforming conventional machine learning models, including support vector machines and random forests. In addition to discrete choice prediction, the network reconstructs continuous paths, enabling full behavioral sequence modeling from partial observations. The integration of stochastic dynamics and deep learning develops a computational basis for analyzing spatial decision-making in animal behavior. The proposed approach contributes to computational models of cognition by linking observable behavior to internal processes in navigational tasks.

Self-supervised spatial-temporal contrastive network for EEG-based brain network classification

Electroencephalogram (EEG)-based brain network analysis has shown promise in brain disease research by revealing the complex connectivity among brain regions. However, existing methods struggle to fully utilize the large amounts of unlabeled data to capture both spatial and temporal relationships across the brain. To mitigate the costs associated with annotating brain data and to extract advanced feature representations, we introduce a novel Self-Supervised Spatial-Temporal Contrastive Network (SS-STCN) framework tailored for brain network classification. Within this framework, the pre-processed unlabeled data are perturbed with transformations and fed into a pre-training contrastive module to train attention-driven two-stream encoders which comprise a Spatial Graph Attention Network (SGAT) and a Temporal Bi-directional Long Short-Term Memory (TBLSTM) network. After optimization, the hybrid networks are then utilized to extract salient features from each labeled sample, achieving spatial-temporal feature fusion. Extensive experiments on the CHB-MIT and Deap datasets show that SS-STCN outperforms existing supervised and unsupervised methods, demonstrating strong accuracy and generalizability across epilepsy classification and emotion recognition tasks.

On construction of data preprocessing for real-life SoyLeaf dataset & disease identification using Deep Learning Models

The vast volumes of data are needed to train Deep Learning Models from scratch to identify illnesses in soybean leaves. However, there is still a lack of sufficient high-quality samples. To overcome this problem, we have developed the real-life SoyLeaf dataset and used the pre-trained Deep Learning Models to identify leaf diseases. In this paper, we have initially developed the real-life SoyLeaf dataset collected from the ICAR-Indian Institute of Soybean Research (IISR) Center, Indore field. This SoyLeaf dataset contains 9786 high-quality soybean leaf images, including healthy and diseased leaves. Following this, we have adapted data preprocessing techniques to enhance the quality of images. In addition, we have utilized several Deep Learning Models, i.e., fourteen Keras Transfer Learning Models, to determine which model best fits the dataset on SoyLeaf diseases. The accuracies of the proposed fine-tuned models using the Adam optimizer are as follows: ResNet50V2 achieves 99.79%, ResNet101V2 achieves 99.89%, ResNet152V2 achieves 99.59%, InceptionV3 achieves 99.83%, InceptionResNetV2 achieves 99.79%, MobileNet achieves 99.82%, MobileNetV2 achieves 99.89%, DenseNet121 achieves 99.87%, and DenseNet169 achieves 99.87%. Similarly, the accuracies of the proposed fine-tuned models using the RMSprop optimizer are as follows: ResNet50V2 achieves 99.49%, ResNet101V2 achieves 99.45%, ResNet152V2 achieves 99.45%, InceptionV3 achieves 99.58%, InceptionResNetV2 achieves 99.88%, MobileNet achieves 99.73%, MobileNetV2 achieves 99.83%, DenseNet121 achieves 99.89%, and DenseNet169 achieves 99.77%. The experimental results of the proposed fine-tuned models show that only ResNet50V2, ResNet101V2, InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, DenseNet121, and DenseNet169 have performed better in terms of training, validation, and testing accuracies than other state-of-the-art models.

SleepEEGpy: a Python-based software integration package to organize preprocessing, analysis, and visualization of sleep EEG data

Sleep research uses electroencephalography (EEG) to infer brain activity in health and disease. Beyond standard sleep scoring, there is growing interest in advanced EEG analysis that requires extensive preprocessing to improve the signal-to-noise ratio and specialized analysis algorithms. While many EEG software packages exist, sleep research has unique needs (e.g., specific artifacts, event detection). Currently, sleep investigators use different libraries for specific tasks in a 'fragmented' configuration that is inefficient, prone to errors, and requires the learning of multiple software environments. This complexity creates a barrier for beginners. Here, we present SleepEEGpy, an open-source Python package that simplifies sleep EEG preprocessing and analysis. SleepEEGpy builds on MNE-Python, PyPREP, YASA, and SpecParam to offer an all-in-one, beginner-friendly package for comprehensive sleep EEG research, including (i) cleaning, (ii) independent component analysis, (iii) sleep event detection, (iv) spectral feature analysis, and visualization tools. A dedicated dashboard provides an overview to evaluate data and preprocessing, serving as an initial step prior to detailed analysis. We demonstrate SleepEEGpy's functionalities using overnight high-density EEG data from healthy participants, revealing characteristic activity signatures typical of each vigilance state: alpha oscillations in wakefulness, spindles and slow waves in NREM sleep, and theta activity in REM sleep. We hope that this software will be adopted and further developed by the sleep research community, and constitute a useful entry point tool for beginners in sleep EEG research.

Analysis of Epilepsy Treatment Strategies Based on an Astrocyte-Neuron-Coupled Network Model

Background/Objectives: Epilepsy is a common neurological disorder that not only severely impacts patients' health but also imposes a significant burden on families and society. However, its pathogenesis remains unclear. Astrocytes play a crucial role in epileptic seizures and may serve as potential therapeutic targets. Establishing a network model of epileptic seizures based on the astrocyte-neuron cell coupling and the clinical electroencephalographic (EEG) characteristics of epilepsy can facilitate further research on refractory epilepsy and the development of treatment strategies. Methods: This study constructs a neuronal network dynamic model of epileptic seizures based on the Watts-Strogatz small-world network, with a particular emphasis on the biological mechanisms of astrocyte-neuron coupling. The phase-locking value (PLV) is used to quantify the degree of network synchronization and to identify the key nodes or connections influencing synchronous seizures, such that two epilepsy treatment strategies are proposed: seizure suppression through stimulation and surgical resection simulation therapy. The therapeutic effects are evaluated based on the PLV-quantified network synchronization. Results: The results indicate that the desynchronization effect of random noise and sinusoidal wave stimulation is limited, while square wave stimulation is the most effective. Among the four surgical resection strategies, the effectiveness is the highest when resecting nodes exhibiting epileptic discharges. These findings contribute to the development of rational seizure suppression strategies and provide insights into precise epileptic focus localization and personalized treatment approaches.

Task-Independent Cognitive Workload Discrimination Based on EEG with Stacked Graph Attention Convolutional Networks

In the field of neuroeconomics, the assessment of cognitive workload is a crucial issue with significant implications for real-world applications. Previous research has made progress in task-based germane cognitive load classification, but decentralized studies focusing on task-independent assessment have often produced less than optimal results. In this study, we present a stacked graph attention convolutional networks (SGATCNs) model to tackle the challenges related to task-independent cognitive workload assessment using EEG spatial information. The model employs the differential entropy (DE) and power spectral density (PSD) features of each EEG channel across four frequency bands (delta, theta, alpha, and beta) as node information. For the construction of the network structure, phase-locked values (PLVs), phase-lag indices (PLIs), Pearson correlation coefficients (PCCs), and mutual information (MI) are utilized and evaluated to generate a functional brain network. Specifically, the model aggregates spatial information on the dynamic map by stacking the graph attention layers and utilizes the convolution module to extract the frequency domain information from between the networks under each frequency band. We conducted a cognitive workload experiment with 15 subjects and selected three representative psychological experimental task paradigms (N-back, mental arithmetic, and Sternberg) to induce different levels of cognitive workload (low, medium, and high). Our framework achieved an average accuracy of 65.11% in recognizing the task-independent cognitive workload across the three scenarios.

Exploiting adaptive neuro-fuzzy inference systems for cognitive patterns in multimodal brain signal analysis

The analysis of cognitive patterns through brain signals offers critical insights into human cognition, including perception, attention, memory, and decision-making. However, accurately classifying these signals remains a challenge due to their inherent complexity and non-linearity. This study introduces a novel method, PCA-ANFIS, which integrates Principal Component Analysis (PCA) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS), to enhance cognitive pattern recognition in multimodal brain signal analysis. PCA reduces the dimensionality of EEG data while retaining salient features, enabling computational efficiency. ANFIS combines the adaptability of neural networks with the interpretability of fuzzy logic, making it well-suited to model the non-linear relationships within brain signals. Performance metrics of our proposed method, such as accuracy, sensitivity, and computational efficiency. These additions highlight the effectiveness of the method and provide a concise summary of the findings. The proposed method achieves superior classification performance, with an unprecedented accuracy of 99.5%, significantly outperforming existing approaches. Comprehensive experiments were conducted using a diverse multimodal EEG dataset, demonstrating the method's robustness and sensitivity. The integration of PCA and ANFIS addresses key challenges in multimodal brain signal analysis, such as EEG artifact contamination and non-stationarity, ensuring reliable feature extraction and classification. This research has significant implications for both cognitive neuroscience and clinical practice. By advancing the understanding of cognitive processes, the PCA-ANFIS method facilitates accurate diagnosis and treatment of cognitive disorders and neurological conditions. Future work will focus on testing the approach with larger and more diverse datasets and exploring its applicability in domains such as neurofeedback, neuromarketing, and brain-computer interfaces. This study establishes PCA-ANFIS as a capable tool for the precise and efficient classification of cognitive patterns in brain signal processing.

A novel approach to enhancing biomedical signal recognition via hybrid high-order information bottleneck driven spiking neural networks

Biomedical signals, encapsulating vital physiological information, are pivotal in elucidating human traits and conditions, serving as a cornerstone for advancing human-machine interfaces. Nonetheless, the fidelity of biomedical signal interpretation is frequently compromised by pervasive noise sources such as skin, motion, and equipment interference, posing formidable challenges to precision recognition tasks. Concurrently, the burgeoning adoption of intelligent wearable devices illuminates a societal shift towards enhancing life and work through technological integration. This surge in popularity underscores the imperative for efficient, noise-resilient biomedical signal recognition methodologies, a quest that is both challenging and profoundly impactful. This study proposes a novel approach to enhancing biomedical signal recognition. The proposed approach employs a hierarchical information bottleneck mechanism within SNNs, quantifying the mutual information in different orders based on the depth of information flow in the network. Subsequently, these mutual information, together with the network's output and category labels, are restructured based on information theory principles to form the loss function used for training. A series of theoretical analyses and substantial experimental results have shown that this method can effectively compress noise in the data, and on the premise of low computational cost, it can also significantly outperform its vanilla counterpart in terms of classification performance.

A Novel Recognition and Classification Approach for Motor Imagery Based on Spatio-Temporal Features

Motor imagery, as a paradigm of brain-computer interface, holds vast potential in the field of medical rehabilitation. Addressing the challenges posed by the non-stationarity and low signal-to-noise ratio of EEG signals, the effective extraction of features from motor imagery signals for accurate recognition stands as a key focus in motor imagery brain-computer interface technology. This paper proposes a motor imagery EEG signal classification model that combines functional brain networks with graph convolutional networks. First, functional brain networks are constructed using different brain functional connectivity metrics, and graph theory features are calculated to deeply analyze the characteristics of brain networks under different motor tasks. Then, the constructed functional brain networks are combined with graph convolutional networks for the classification and recognition of motor imagery tasks. The analysis based on brain functional connectivity reveals that the functional connectivity strength during the both fists task is significantly higher than that of other motor imagery tasks, and the functional connectivity strength during actual movement is generally superior to that of motor imagery tasks. In experiments conducted on the Physionet public dataset, the proposed model achieved a classification accuracy of 88.39% under multi-subject conditions, significantly outperforming traditional methods. Under single-subject conditions, the model effectively addressed the issue of individual variability, achieving an average classification accuracy of 99.31%. These results indicate that the proposed model not only exhibits excellent performance in the classification of motor imagery tasks but also provides new insights into the functional connectivity characteristics of different motor tasks and their corresponding brain regions.

Multivariate Modelling and Prediction of High-Frequency Sensor-Based Cerebral Physiologic Signals: Narrative Review of Machine Learning Methodologies

Monitoring cerebral oxygenation and metabolism, using a combination of invasive and non-invasive sensors, is vital due to frequent disruptions in hemodynamic regulation across various diseases. These sensors generate continuous high-frequency data streams, including intracranial pressure (ICP) and cerebral perfusion pressure (CPP), providing real-time insights into cerebral function. Analyzing these signals is crucial for understanding complex brain processes, identifying subtle patterns, and detecting anomalies. Computational models play an essential role in linking sensor-derived signals to the underlying physiological state of the brain. Multivariate machine learning models have proven particularly effective in this domain, capturing intricate relationships among multiple variables simultaneously and enabling the accurate modeling of cerebral physiologic signals. These models facilitate the development of advanced diagnostic and prognostic tools, promote patient-specific interventions, and improve therapeutic outcomes. Additionally, machine learning models offer great flexibility, allowing different models to be combined synergistically to address complex challenges in sensor-based data analysis. Ensemble learning techniques, which aggregate predictions from diverse models, further enhance predictive accuracy and robustness. This review explores the use of multivariate machine learning models in cerebral physiology as a whole, with an emphasis on sensor-derived signals related to hemodynamics, cerebral oxygenation, metabolism, and other modalities such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) where applicable. It will detail the operational principles, mathematical foundations, and clinical implications of these models, providing a deeper understanding of their significance in monitoring cerebral function.

Decoding of movement-related cortical potentials at different speeds

The decoding of electroencephalogram (EEG) signals, especially motion-related cortical potentials (MRCP), is vital for the early detection of motor intent before movement execution. To enhance the decoding accuracy of MRCP and promote the application of early motion intention in active rehabilitation training, we propose a method for decoding MRCP signals. Specifically, an experimental paradigm is designed for the efficient capture of MRCP signals. Moreover, a feature extraction method based on differentiation is proposed to effectively characterize action variability. Six subjects were recruited to validate the effectiveness of the decoding method. Experiments such as fixed-window classification, sliding-window detection, and asynchronous analysis demonstrate that the method can detect motion intention 316 milliseconds before action execution and is capable of continuously detecting both rapid and slow movements.

Deep learning-assisted single-atom detection of copper ions by combining click chemistry and fast scan voltammetry

Cell ion channels, cell proliferation and metastasis, and many other life activities are inseparable from the regulation of trace or even single copper ion (Cu+ and/or Cu2+). In this work, an electrochemical sensor for sensitive quantitative detection of 0.4-4 amol L-1 copper ions is developed by adopting: (1) copper ions catalyzing the click-chemistry reaction to capture numerous signal units; (2) special adsorption assembly method of signal units to ensure signal generation efficiency; and (3) fast scan voltammetry at 400 V s-1 to enhance signal intensity. And then, the single-atom detection of copper ions is realized by constructing a multi-layer deep convolutional neural network model FSVNet to extract hidden features and signal information of fast scan voltammograms for 0.2 amol L-1 of copper ions. Here, we show a multiple signal amplification strategy based on functionalized nanomaterials and fast scan voltammetry, together with a deep learning method, which realizes the sensitive detection and even single-atom detection of copper ions.

Objective assessment of cognitive fatigue: a bibliometric analysis

Aim

The objective of this study was to gain insight into the nature of cognitive fatigue and to identify future trends of objective assessment techniques in this field.

Methods

One thousand and eighty-five articles were retrieved from the Web of Science Core Collection database. R version 4.3.1, VOSviewer 1.6.20, CiteSpace 6.2.R4, and Microsoft Excel 2019 were used to perform the analysis.

Results

A total of 704 institutes from 56 countries participated in the relevant research, while the People's Republic of China contributed 126 articles and was the leading country. The most productive institute was the University of Gothenburg. Johansson Birgitta from the University of Gothenburg has posted the most articles (n = 13). The PLOS ONE published most papers (n = 38). The Neurosciences covered the most citations (n = 1,094). A total of 3,116 keywords were extracted and those with high frequency were mental fatigue, performance, quality-of-life, etc. Keywords mapping analysis indicated that cognitive fatigue caused by continuous work and traumatic brain injury, as well as its rehabilitation, have become the current research trend. The most co-cited literature was published in Sports Medicine. The strongest citation burst was related to electroencephalogram (EEG) event-related potential and spectral power analysis.

Conclusion

Publication information of related literature on the objective assessment of cognitive fatigue from 2007 to 2024 was summarized, including country and institute of origin, authors, and published journal, offering the current hotspots and novel directions in this field.

Global and multi-partition local network analysis of scalp EEG in West syndrome before and after treatment

West syndrome is an epileptic disease that seriously affects the normal growth and development of infants in early childhood. Based on the methods of brain topological network and graph theory, this article focuses on three clinical states of patients before and after treatment. In addition to discussing bidirectional and unidirectional global networks from the perspective of computational principles, a more in-depth analysis of local intra-network and inter-network characteristics of multi-partitioned networks is also performed. The spatial feature distribution based on feature path length is introduced for the first time. The results show that the bidirectional network has better significant differentiation. The rhythmic feature change trend and spatial characteristic distribution of this network can be used as a measure of the impact on global information processing in the brain after treatment. And localized brain regions variability in features and differences in the ability to interact with information between brain regions have potential as biomarkers for medication assessment in WEST syndrome. The above shows specific conclusions on the interaction relationship and consistency of macro-network and micro-network, which may have a positive effect on patients' treatment and prognosis management.

Correlation change analysis and NDVI prediction in the Yellow River Basin of China using complex networks and GRNN-PSRLSTM

The Normalized Difference Vegetation Index (NDVI) is affected by various environmental factors, and its relationship with these factors is complex. In order to explore the complex relationship between NDVI and environmental factors, this paper adopts the complex network method to construct a correlation fluctuation network and analyze the interaction between them. It is found that temperature, precipitation, soil moisture, sunshine duration, and PM2.5 are all correlated with NDVI to varying degrees, and their combined correlation with NDVI varies over time. The correlation typically takes 3 to 6 months to change, and it tends to persist to some extent. Moreover, we fuse a generalized regression neural network (GRNN) with a long-short-term memory (LSTM) network combining phase space reconstruction (PSR) to propose a GRNN-PSRLSTM prediction model. The model achieves the prediction of monthly NDVI using the five environmental factors of the fluctuation network. The results indicate that the averages of root mean squared error (RMSE) and mean absolute percentage error (MAPE) predicted by the GRNN-PSRLSTM model in the nine provinces are 0.0232 and 0.0564 respectively. This model performs better in the assessment metrics for monthly NDVI forecasts. These findings are significant for evaluating vegetation changes and have some theoretical value for the ecological protection of the Yellow River Basin.

Setting a double-capacitive neuron coupled with Josephson junction and piezoelectric source

Perception of voice means acoustic electric conversion in the auditory system, and changes of external magnetic field can affect the neural activities by taming the channel current via some field components including memristor and Josephson junction. Combination of two capacitors via an electric component is effective to describe the physical property of artificial cell membrane, which is often used to reproduce the characteristic of electric activities in cell membrane. Involvement of two capacitive variables for two capacitors in the neural circuit can discern the effect of field diversity in the media in two sides of the cell membrane in theoretical way. A Josephson junction is used to couple a piezoelectric neural circuit composed of two capacitors, one inductor and one nonlinear resistor. Field energy is mainly kept in the capacitive and inductive components, and it is obtained and converted into dimensionless energy function. The Hamilton energy function in an equivalent auditory neuron is verified by using the Helmholtz theorem. Noisy excitation on the neural circuit can be detected via the Josephson junction channel and similar stochastic resonance is detected by regulating the noise intensity, as a result, the average energy reaches a peak value under stochastic resonance. An adaptive law controls the bifurcation parameter, which is relative to the membrane property, and energy shift controls the mode selection during continuous growth of the bifurcation parameter. That is, external energy injection derived from acoustic wave or magnetic field will control the energy level, and then suitable firing patterns are controlled effectively.

A grid fault diagnosis framework based on adaptive integrated decomposition and cross-modal attention fusion

In large-scale power systems, accurately detecting and diagnosing the type of faults when they occur in the grid is a challenging problem. The classification performance of most existing grid fault diagnosis methods depends on the richness and reliability of the data, in addition, it is difficult to obtain sufficient feature information from unimodal circuit signals. To address these issues, we propose a deep residual convolutional neural network (DRCNN)-based framework for grid fault diagnosis. First, we design a comprehensive information entropy value (CIEV) evaluation metric that combines fuzzy entropy (FuzEn) and mutual approximation entropy (MutEn) to integrate multiple decomposition subsequences. Then, DRCNN and heterogeneous graph transformer (HGT) are constructed for extracting multimodal features and considering modal variability. In addition, to obtain the implicit information of multimodal features and control the degree of their performance, we propose to incorporate the cross-modal attention fusion (CMAF) mechanism in the synthesis framework. We validate the proposed method on the three-phase transmission line dataset and VSB power line dataset with accuracies of 99.4 % and 99.0 %, respectively. The proposed method also achieves superior performance compared to classical and state-of-the-art methods.

Classification algorithm for motor imagery fusing CNN and attentional mechanisms based on functional near-infrared spectroscopy brain image

With the continuing development of brain-computer interface technology, the analysis and interpretation of brain signals are becoming increasingly important. In the field of brain-computer interfaces, motor imagery (MI) is an important paradigm for generating specific brain signals through thought alone, rather than actual movement, for computer decoding. Functional near-infrared spectroscopy (fNIRS) imaging technology has been increasingly used in brain-computer interfaces due to its advantages of non-invasiveness, low resource requirements, low cost, and high spatial resolution. Scientists have done a lot of work in channel selection, feature selection, and then applying traditional machine learning methods for classification, but the results achieved so far are still insufficient to meet the conditions for realizing fNIRS brain-computer interfaces. To achieve a higher level of classification of fNIRS signals, we propose a method that fuses CNN and attention mechanisms to analyze the near-infrared signals of motor imagery and mental arithmetic data, which is fed into a neural network by deriving signals of changes in oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (HbR) concentrations through the modified Beer-Lambert law, and then applied to the fNIRS dataset of 29 healthy subjects to validate the proposed method. In the fNIRS-based BCI, the average classification accuracy of the MI signal from HbR and HbO reaches 85.92% and 86.21%, respectively, and the average classification accuracy of the MA signal reaches 89.66% and 88.79%, respectively. The advantage of our approach is that it is lightweight and improves the classification accuracy of current BCI fNIRS signals.

Attention-based cross-frequency graph convolutional network for driver fatigue estimation

Fatigue driving significantly contributes to global vehicle accidents and fatalities, making driver fatigue level estimation crucial. Electroencephalography (EEG) is a proven reliable predictor of brain states. With Deep Learning (DL) advancements, brain state estimation algorithms have improved significantly. Nonetheless, EEG's multi-domain nature and the intricate spatial-temporal-frequency correlations among EEG channels present challenges in developing precise DL models. In this work, we introduce an innovative Attention-based Cross-Frequency Graph Convolutional Network (ACF-GCN) for estimating drivers' reaction times using EEG signals from theta, alpha, and beta bands. This method utilizes a multi-head attention mechanism to detect long-range dependencies between EEG channels across frequencies. Concurrently, the transformer's encoder module learns node-level feature maps from the attention-score matrix. Subsequently, the Graph Convolutional Network (GCN) integrates this matrix with feature maps to estimate driver reaction time. Our validation on a publicly available dataset shows that ACF-GCN outperforms several state-of-the-art methods. We also explore the brain dynamics within the cross-frequency attention-score matrix, identifying theta and alpha bands as key influencers in fatigue estimating performance. The ACF-GCN method advances brain state estimation and provides insights into the brain dynamics underlying multi-channel EEG signals.

Automatic detection of Alzheimer's disease from EEG signals using an improved AFS-GA hybrid algorithm

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by energy diffusion and partial disconnection in the brain, with its main feature being an insidious onset and subtle clinical symptoms. Electroencephalogram (EEG) as a primary tool for assessing and aiding in the diagnosis of brain diseases has been widely used in AD detection. Accurate diagnosis is crucial for preventing the transition from early cognitive impairment to AD and providing early treatment for AD patients. This study aims to establish a hybrid model based on the Improved Artificial Fish Swarm Algorithm (IAFS) and Genetic Algorithm (GA)-IAFS-GA, to determine the optimal channel combination for AD detection under multiple EEG signals. Geometric features and complexity features of AD EEG signals were extracted using Second Order Difference Plot (SODP) and entropy analysis across the full frequency band. Subsequently, Pearson correlation was used for feature ranking, selecting the six least correlated features for each channel. The Relief algorithm was then used to fuse these selected features, with one fused feature representing one channel. Based on this, a feature selection optimization algorithm, IAFS-GA, combining the improved artificial fish swarm algorithm and genetic algorithm, was proposed. Finally, the feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. The feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. Using a five-fold cross-validation strategy across the entire frequency band, the classification accuracy reached 93.53%, with a sensitivity of 98.74%, specificity of 98.25%, and an AUC area of 97.82%. This framework can quickly select appropriate brain channels to enhance the efficiency of detecting AD and other neurological diseases. Moreover, it is the first time that an improved artificial fish swarm genetic combination algorithm and SODP features has been used for channel selection in EEG, proving to be an effective method for AD detection. It is based on SODP analysis, entropy analysis, and intelligent algorithms, which can assist clinicians in rapidly diagnosing AD, reducing the misdiagnosis rate of false positives, and expanding our understanding of brain function in patients with neurological diseases.

Emotion recognition of EEG signals based on contrastive learning graph convolutional model

Objective.Electroencephalogram (EEG) signals offer invaluable insights into the complexities of emotion generation within the brain. Yet, the variability in EEG signals across individuals presents a formidable obstacle for empirical implementations. Our research addresses these challenges innovatively, focusing on the commonalities within distinct subjects' EEG data.Approach.We introduce a novel approach named Contrastive Learning Graph Convolutional Network (CLGCN). This method captures the distinctive features and crucial channel nodes related to individuals' emotional states. Specifically, CLGCN merges the dual benefits of CL's synchronous multisubject data learning and the GCN's proficiency in deciphering brain connectivity matrices. Understanding multifaceted brain functions and their information interchange processes is realized as CLGCN generates a standardized brain network learning matrix during a dataset's learning process.Main results.Our model underwent rigorous testing on the Database for Emotion Analysis using Physiological Signals (DEAP) and SEED datasets. In the five-fold cross-validation used for dependent subject experimental setting, it achieved an accuracy of 97.13% on the DEAP dataset and surpassed 99% on the SEED and SEED_IV datasets. In the incremental learning experiments with the SEED dataset, merely 5% of the data was sufficient to fine-tune the model, resulting in an accuracy of 92.8% for the new subject. These findings validate the model's efficacy.Significance.This work combines CL with GCN, improving the accuracy of decoding emotional states from EEG signals and offering valuable insights into uncovering the underlying mechanisms of emotional processes in the brain.

Augmented Recognition of Distracted Driving State Based on Electrophysiological Analysis of Brain Network

In this study, we propose an electrophysiological analysis-based brain network method for the augmented recognition of different types of distractions during driving. Driver distractions, such as cognitive processing and visual disruptions during driving, lead to distinct alterations in the electroencephalogram (EEG) signals and the extracted brain networks. We designed and conducted a simulated experiment comprising 4 distracted driving subtasks. Three connectivity indices, including both linear and nonlinear synchronization measures, were chosen to construct the brain network. By computing connectivity strengths and topological features, we explored the potential relationship between brain network configurations and states of driver distraction. Statistical analysis of network features indicates substantial differences between normal and distracted states, suggesting a reconfiguration of the brain network under distracted conditions. Different brain network features and their combinations are fed into varied machine learning classifiers to recognize the distracted driving states. The results indicate that XGBoost demonstrates superior adaptability, outperforming other classifiers across all selected network features. For individual networks, features constructed using synchronization likelihood (SL) achieved the highest accuracy in distinguishing between cognitive and visual distraction. The optimal feature set from 3 network combinations achieves an accuracy of 95.1% for binary classification and 88.3% for ternary classification of normal, cognitively distracted, and visually distracted driving states. The proposed method could accomplish the augmented recognition of distracted driving states and may serve as a valuable tool for further optimizing driver assistance systems with distraction control strategies, as well as a reference for future research on the brain-computer interface in autonomous driving.

A novel method of swin transformer with time-frequency characteristics for ECG-based arrhythmia detection

Introduction

Arrhythmia is an important indication of underlying cardiovascular diseases (CVD) and is prevalent worldwide. Accurate diagnosis of arrhythmia is crucial for timely and effective treatment. Electrocardiogram (ECG) plays a key role in the diagnosis of arrhythmia. With the continuous development of deep learning and machine learning processes in the clinical field, ECG processing algorithms have significantly advanced the field with timely and accurate diagnosis of arrhythmia.

Methods

In this study, we combined the wavelet time-frequency maps with the novel Swin Transformer deep learning model for the automatic detection of cardiac arrhythmias. In specific practice, we used the MIT-BIH arrhythmia dataset, and to improve the signal quality, we removed the high-frequency noise, artifacts, electromyographic noise and respiratory motion effects in the ECG signals by the wavelet thresholding method; we used the complex Morlet wavelet for the feature extraction, and plotted wavelet time-frequency maps to visualise the time-frequency information of the ECG; we introduced the Swin Transformer model for classification and achieve high classification accuracy of ECG signals through hierarchical construction and self attention mechanism, and combines windowed multi-head self-attention (W-MSA) and shifted window-based multi-head self-attention (SW-MSA) to comprehensively utilise the local and global information.

Results

To enhance the confidence of the experimental results, we evaluated the performance using intra-patient and inter-patient paradigm analyses, and the model classification accuracies reached 99.34% and 98.37%, respectively, which are better than the currently available detection methods.

Discussion

The results reveal that our proposed method is superior to currently available methods for detecting arrhythmia ECG. This provides a new idea for ECG based arrhythmia diagnosis.

Instantaneous estimation of momentary affective responses using neurophysiological signals and a spatiotemporal emotional intensity regression network

Previous studies in affective computing often use a fixed emotional label to train an emotion classifier with electroencephalography (EEG) from individuals experiencing an affective stimulus. However, EEGs encode emotional dynamics that include varying intensities within a given emotional category. To investigate these variations in emotional intensity, we propose a framework that obtains momentary affective labels for fine-grained segments of EEGs with human feedback. We then model these labeled segments using a novel spatiotemporal emotional intensity regression network (STEIR-Net). It integrates temporal EEG patterns from nine predefined cortical regions to provide a continuous estimation of emotional intensity. We demonstrate that the STEIR-Net outperforms classical regression models by reducing the root mean square error (RMSE) by an average of 4∼9 % and 2∼4 % for the SEED and SEED-IV databases, respectively. We find that the frontal and temporal cortical regions contribute significantly to the affective intensity's variation. Higher absolute values of the Spearman correlation coefficient between the model estimation and momentary affective labels under happiness (0.2114) and fear (0.2072) compared to neutral (0.1694) and sad (0.1895) emotions were observed. Besides, increasing the input length of the EEG segments from 4 to 20 s further reduces the RMSE from 1.3548 to 1.3188.

Optimization of epilepsy detection method based on dynamic EEG channel screening

To decrease the interference in the process of epileptic feature extraction caused by insufficient detection capability in partial channels of focal epilepsy, this paper proposes a novel epilepsy detection method based on dynamic electroencephalogram (EEG) channel screening. This method not only extracts more effective epilepsy features but also finds common features among different epilepsy subjects, providing an effective approach and theoretical support for across-subject epilepsy detection in clinical scenarios. Firstly, we use the Refine Composite Multiscale Dispersion Entropy (RCMDE) to measure the complexity of EEG signals between normal and seizure states and realize the dynamic EEG channel screening among different subjects, which can enhance the capability of feature extraction and the robustness of epilepsy detection. Subsequently, we discover common epilepsy features in 3-15 Hz among different subjects by the screened EEG channels. By this finding, we construct the Residual Convolutional Long Short-Term Memory (ResCon-LSTM) neural network to accomplish across-subject epilepsy detection. The experiment results on the CHB-MIT dataset indicate that the highest accuracy of epilepsy detection in the single-subject experiment is 98.523 %, improved by 5.298 % compared with non-channel screening. In the across-subject experiment, the average accuracy is 96.596 %. Therefore, this method could be effectively applied to different subjects by dynamically screening optimal channels and keep a good detection performance.

Inter-hospital moderate and advanced Alzheimer's disease detection through convolutional neural networks

Electroencephalography (EEG) has been a fundamental technique in the identification of health conditions since its discovery. This analysis specifically centers on machine learning (ML) and deep learning (DL) methodologies designed for the analysis of electroencephalogram (EEG) data to categorize individuals with Alzheimer's Disease (AD) into two groups: Moderate or Advanced Alzheimer's dementia. Our study is based on a comprehensive database comprising 668 volunteers from 5 different hospitals, collected over a decade. This diverse dataset enables better training and validation of our results. Among the methods evaluated, the CNN (deep learning) approach outperformed others, achieving a remarkable classification accuracy of 97.45% for patients with Moderate Alzheimer's Dementia (ADM) and 97.03% for patients with Advanced Alzheimer's Dementia (ADA). Importantly, all the compared methods were rigorously assessed under identical conditions. The proposed DL model, specifically CNN, effectively extracts time domain features from EEG data in time, resulting in a significant reduction in learnable parameters and data redundancy.

Mental Workload Classification and Tasks Detection in Multitasking: Deep Learning Insights from EEG Study

While the term task load (TL) refers to external task demands, the amount of work, or the number of tasks to be performed, mental workload (MWL) refers to the individual's effort, mental capacity, or cognitive resources utilized while performing a task. MWL in multitasking scenarios is often closely linked with the quantity of tasks a person is handling within a given timeframe. In this study, we challenge this hypothesis from the perspective of electroencephalography (EEG) using a deep learning approach. We conducted an EEG experiment with 50 participants performing NASA Multi-Attribute Task Battery II (MATB-II) under 4 different task load levels. We designed a convolutional neural network (CNN) to help with two distinct classification tasks. In one setting, the CNN was used to classify EEG segments based on their task load level. In another setting, the same CNN architecture was trained again to detect the presence of individual MATB-II subtasks. Results show that, while the model successfully learns to detect whether a particular subtask is active in a given segment (i.e., to differentiate between different subtasks-related EEG patterns), it struggles to differentiate between the two highest levels of task load (i.e., to distinguish MWL-related EEG patterns). We speculate that the challenge comes from two factors: first, the experiment was designed in a way that these two highest levels differed only in the quantity of work within a given timeframe; and second, the participants' effective adaptation to increased task demands, as evidenced by low error rates. Consequently, this indicates that under such conditions in multitasking, EEG may not reflect distinct enough patterns to differentiate higher levels of task load.

The applied principles of EEG analysis methods in neuroscience and clinical neurology

Electroencephalography (EEG) is a non-invasive measurement method for brain activity. Due to its safety, high resolution, and hypersensitivity to dynamic changes in brain neural signals, EEG has aroused much interest in scientific research and medical fields. This article reviews the types of EEG signals, multiple EEG signal analysis methods, and the application of relevant methods in the neuroscience field and for diagnosing neurological diseases. First, three types of EEG signals, including time-invariant EEG, accurate event-related EEG, and random event-related EEG, are introduced. Second, five main directions for the methods of EEG analysis, including power spectrum analysis, time-frequency analysis, connectivity analysis, source localization methods, and machine learning methods, are described in the main section, along with different sub-methods and effect evaluations for solving the same problem. Finally, the application scenarios of different EEG analysis methods are emphasized, and the advantages and disadvantages of similar methods are distinguished. This article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives, provide references for subsequent research, and summarize current issues and prospects for the future.

Human behavior in free search online shopping scenarios can be predicted from EEG activation using Hjorth parameters

The present work investigates whether and how decisions in real-world online shopping scenarios can be predicted based on brain activation. Potential customers were asked to search through product pages on e-commerce platforms and decide, which products to buy, while their EEG signal was recorded. Machine learning algorithms were then trained to distinguish between EEG activation when viewing products that are later bought or put into the shopping card as opposed to products that are later discarded. We find that Hjorth parameters extracted from the raw EEG can be used to predict purchase choices to a high level of accuracy. Above-chance predictions based on Hjorth parameters are achieved via different standard machine learning methods with random forest models showing the best performance of above 80% prediction accuracy in both 2-class (bought or put into card vs. not bought) and 3-class (bought vs. put into card vs. not bought) classification. While conventional EEG signal analysis commonly employs frequency domain features such as alpha or theta power and phase, Hjorth parameters use time domain signals, which can be calculated rapidly with little computational cost. Given the presented evidence that Hjorth parameters are suitable for the prediction of complex behaviors, their potential and remaining challenges for implementation in real-time applications are discussed.

A comprehensive survey of complex brain network representation

Recent years have shown great merits in utilizing neuroimaging data to understand brain structural and functional changes, as well as its relationship to different neurodegenerative diseases and other clinical phenotypes. Brain networks, derived from different neuroimaging modalities, have attracted increasing attention due to their potential to gain system-level insights to characterize brain dynamics and abnormalities in neurological conditions. Traditional methods aim to pre-define multiple topological features of brain networks and relate these features to different clinical measures or demographical variables. With the enormous successes in deep learning techniques, graph learning methods have played significant roles in brain network analysis. In this survey, we first provide a brief overview of neuroimaging-derived brain networks. Then, we focus on presenting a comprehensive overview of both traditional methods and state-of-the-art deep-learning methods for brain network mining. Major models, and objectives of these methods are reviewed within this paper. Finally, we discuss several promising research directions in this field.

MI-DAGSC: A domain adaptation approach incorporating comprehensive information from MI-EEG signals

Non-stationarity of EEG signals leads to high variability between subjects, making it challenging to directly use data from other subjects (source domain) for the classifier in the current subject (target domain). In this study, we propose MI-DAGSC to address domain adaptation challenges in EEG-based motor imagery (MI) decoding. By combining domain-level information, class-level information, and inter-sample structure information, our model effectively aligns the feature distributions of source and target domains. This work is an extension of our previous domain adaptation work MI-DABAN (Li et al., 2023). Based on MI-DABAN, MI-DAGSC designs Sample-Feature Blocks (SFBs) and Graph Convolution Blocks (GCBs) to focus on intra-sample and inter-sample information. The synergistic integration of SFBs and GCBs enable the model to capture comprehensive information and understand the relationship between samples, thus improving representation learning. Furthermore, we introduce a triplet loss to enhance the alignment and compactness of feature representations. Extensive experiments on real EEG datasets demonstrate the effectiveness of MI-DAGSC, confirming that our method makes a valuable contribution to the MI-EEG decoding. Moreover, it holds great potential for various applications in brain-computer interface systems and neuroscience research. And the code of the proposed architecture in this study is available under https://github.com/zhangdx21/MI-DAGSC.

Investigation of frequency components embedded in EEG recordings underlying neuronal mechanism of cognitive control and attentional functions

Attentional cognitive control regulates the perception to enhance human behaviour. The current study examines the atltentional mechanisms in terms of time and frequency of EEG signals. The cognitive load is higher for processing local attentional stimulus, thereby demanding higher response time (RT) with low response accuracy (RA). On the other hand, the global attentional mechanisms broadly promote the perception while demanding a low cognitive load with faster RT and high RA. Attentional mechanisms refer to perceptual systems that afford and allocate the adaptive behaviours for prioritizing the processing of relevant stimuli based on the local and global features. The early sensory component of C1, which was associated with the local attentional mechanism, showed higher amplitudes than the global attentional mechanisms in parieto-occipital regions. Further, the local attentional mechanisms were also sustained in N2 and P3 components increasing higher amplitude in the left and right hemispheric sides of temporal regions (T7 and T8). Theta band frequency had shown higher power spectrum density (PSD) values while processing local attentional mechanisms. However, the significance of other frequency bands was noticeably minute. Hence, integrating the attentional mechanisms in terms of ERP and frequency signatures, a hybrid custom weight allocation model (CWAM) was built to assess and predict the contribution of insignificant channels to significant ones. The CWAM model was formulated based on the computational linear regression derivatives. All the derivatives are computationally derived the significant score while channelizing the hierarchical performance of each channel with respect to the frequent and deviant occurrences of global-local stimulus. This model enables us to configure the neural dynamicity of cognitive allocation of resources within the different locations of the human brain while processing the attentional stimulus. CWAM is reported to be the first model to evaluate the performance of the non-significant channels for enhancing the response of significant channels. The findings of the CWAM model suggest that the brain's performance may be determined by the underlying contribution of the non-significant channels.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09888-x.

Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017-2023

Cardiovascular diseases are a leading cause of mortality globally. Electrocardiography (ECG) still represents the benchmark approach for identifying cardiac irregularities. Automatic detection of abnormalities from the ECG can aid in the early detection, diagnosis, and prevention of cardiovascular diseases. Deep Learning (DL) architectures have been successfully employed for arrhythmia detection and classification and offered superior performance to traditional shallow Machine Learning (ML) approaches. This survey categorizes and compares the DL architectures used in ECG arrhythmia detection from 2017-2023 that have exhibited superior performance. Different DL models such as Convolutional Neural Networks (CNNs), Multilayer Perceptrons (MLPs), Transformers, and Recurrent Neural Networks (RNNs) are reviewed, and a summary of their effectiveness is provided. This survey provides a comprehensive roadmap to expedite the acclimation process for emerging researchers willing to develop efficient algorithms for detecting ECG anomalies using DL models. Our tailored guidelines bridge the knowledge gap allowing newcomers to align smoothly with the prevailing research trends in ECG arrhythmia detection. We shed light on potential areas for future research and refinement in model development and optimization, intending to stimulate advancement in ECG arrhythmia detection and classification.

Portable deep-learning decoder for motor imaginary EEG signals based on a novel compact convolutional neural network incorporating spatial-attention mechanism

Due to high computational requirements, deep-learning decoders for motor imaginary (MI) electroencephalography (EEG) signals are usually implemented on bulky and heavy computing devices that are inconvenient for physical actions. To date, the application of deep-learning techniques in independent portable brain-computer-interface (BCI) devices has not been extensively explored. In this study, we proposed a high-accuracy MI EEG decoder by incorporating spatial-attention mechanism into convolution neural network (CNN), and deployed it on fully integrated single-chip microcontroller unit (MCU). After the CNN model was trained on workstation computer using GigaDB MI datasets (52 subjects), its parameters were then extracted and converted to build deep-learning architecture interpreter on MCU. For comparison, EEG-Inception model was also trained using the same dataset, and was deployed on MCU. The results indicate that our deep-learning model can independently decode imaginary left-/right-hand motions. The mean accuracy of the proposed compact CNN reaches 96.75 ± 2.41% (8 channels: Frontocentral3 (FC3), FC4, Central1 (C1), C2, Central-Parietal1 (CP1), CP2, C3, and C4), versus 76.96 ± 19.08% of EEG-Inception (6 channels: FC3, FC4, C1, C2, CP1, and CP2). To the best of our knowledge, this is the first portable deep-learning decoder for MI EEG signals. The findings demonstrate high-accuracy deep-learning decoding of MI EEG in a portable mode, which has great implications for hand-disabled patients. Our portable system can be used for developing artificial-intelligent wearable BCI devices, as it is less computationally expensive and convenient for real-life application.

EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning

Introduction

This study examines the state and trait effects of short-term mindfulness-based stress reduction (MBSR) training using convolutional neural networks (CNN) based deep learning methods and traditional machine learning methods, including shallow and deep ConvNets as well as support vector machine (SVM) with features extracted from common spatial pattern (CSP) and filter bank CSP (FBCSP).

Methods

We investigated the electroencephalogram (EEG) measurements of 11 novice MBSR practitioners (6 males, 5 females; mean age 35.7 years; 7 Asians and 4 Caucasians) during resting and meditation at early and late training stages. The classifiers are trained and evaluated using inter-subject, mix-subject, intra-subject, and subject-transfer classification strategies, each according to a specific application scenario.

Results

For MBSR state effect recognition, trait effect recognition using meditation EEG, and trait effect recognition using resting EEG, from shallow ConvNet classifier we get mix-subject/intra-subject classification accuracies superior to related previous studies for both novice and expert meditators with a variety of meditation types including yoga, Tibetan, and mindfulness, whereas from FBSCP + SVM classifier we get inter-subject classification accuracies of 68.50, 85.00, and 78.96%, respectively.

Conclusion

Deep learning is superior for state effect recognition of novice meditators and slightly inferior but still comparable for both state and trait effects recognition of expert meditators when compared to the literatures. This study supports previous findings that short-term meditation training has EEG-recognizable state and trait effects.

Automatic Calcification Morphology and Distribution Classification for Breast Mammograms With Multi-Task Graph Convolutional Neural Network

The morphology and distribution of microcalcifications are the most important descriptors for radiologists to diagnose breast cancer based on mammograms. However, it is very challenging and time-consuming for radiologists to characterize these descriptors manually, and there also lacks of effective and automatic solutions for this problem. We observed that the distribution and morphology descriptors are determined by the radiologists based on the spatial and visual relationships among calcifications. Thus, we hypothesize that this information can be effectively modelled by learning a relationship-aware representation using graph convolutional networks (GCNs). In this study, we propose a multi-task deep GCN method for automatic characterization of both the morphology and distribution of microcalcifications in mammograms. Our proposed method transforms morphology and distribution characterization into node and graph classification problem and learns the representations concurrently. We trained and validated the proposed method in an in-house dataset and public DDSM dataset with 195 and 583 cases,respectively. The proposed method reaches good and stable results with distribution AUC at 0.812 ± 0.043 and 0.873 ± 0.019, morphology AUC at 0.663 ± 0.016 and 0.700 ± 0.044 for both in-house and public datasets. In both datasets, our proposed method demonstrates statistically significant improvements compared to the baseline models. The performance improvements brought by our proposed multi-task mechanism can be attributed to the association between the distribution and morphology of calcifications in mammograms, which is interpretable using graphical visualizations and consistent with the definitions of descriptors in the standard BI-RADS guideline. In short, we explore, for the first time, the application of GCNs in microcalcification characterization that suggests the potential of using graph learning for more robust understanding of medical images.

Differentiating brain states via multi-clip random fragment strategy-based interactive bidirectional recurrent neural network

EEG is widely adopted to study the brain and brain computer interface (BCI) for its non-invasiveness and low costs. Specifically EEG can be applied to differentiate brain states, which is important for better understanding the working mechanisms of the brain. Recurrent neural network (RNN)-based learning strategy has been widely utilized to differentiate brain states, because its optimization architectures improve the classification performance for differentiating brain states at the group level. However, present classification performance is still far from satisfactory. We have identified two major focal points for improvements: one is about organizing the input EEG signals, and the other is related to the design of the RNN architecture. To optimize the above-mentioned issues and achieve better brain state classification performance, we propose a novel multi-clip random fragment strategy-based interactive bidirectional recurrent neural network (McRFS-IBiRNN) model in this work. This model has two advantages over previous methods. First, the McRFS component is designed to re-organize the input EEG signals to make them more suitable for the RNN architecture. Second, the IBiRNN component is an innovative design to model the RNN layers with interaction connections to enhance the fusion of bidirectional features. By adopting the proposed model, promising brain states classification performances are obtained. For example, 96.97% and 99.34% of individual and group level four-category classification accuracies are successfully obtained on the EEG motor/imagery dataset, respectively. A 99.01% accuracy can be observed for four-category classification tasks with new subjects not seen before, which demonstrates the generalization of our proposed method. Compared with existing methods, our model outperforms them with superior results. Overall, the proposed McRFS-IBiRNN model demonstrates great superiority in differentiating brain states on EEG signals.

A novel framework of MOPSO-GDM in recognition of Alzheimer's EEG-based functional network

Background

Most patients with Alzheimer's disease (AD) have an insidious onset and frequently atypical clinical symptoms, which are considered a normal consequence of aging, making it difficult to diagnose AD medically. But then again, accurate diagnosis is critical to prevent degeneration and provide early treatment for AD patients.

Objective

This study aims to establish a novel EEG-based classification framework with deep learning methods for AD recognition.

Methods

First, considering the network interactions in different frequency bands (δ, θ, α, β, and γ), multiplex networks are reconstructed by the phase synchronization index (PSI) method, and fourteen topology features are extracted subsequently, forming a high-dimensional feature vector. However, in feature combination, not all features can provide effective information for recognition. Moreover, combining features by manual selection is time-consuming and laborious. Thus, a feature selection optimization algorithm called MOPSO-GDM was proposed by combining multi-objective particle swarm optimization (MOPSO) algorithm with Gaussian differential mutation (GDM) algorithm. In addition to considering the classification error rates of support vector machine, naive bayes, and discriminant analysis classifiers, our algorithm also considers distance measure as an optimization objective.

Results

Finally, this method proposed achieves an excellent classification error rate of 0.0531 (5.31%) with the feature vector size of 8, by a ten-fold cross-validation strategy.

Conclusion

These findings show that our framework can adaptively combine the best brain network features to explore network synchronization, functional interactions, and characterize brain functional abnormalities, which can improve the recognition efficiency of diseases. While improving the classification accuracy of application algorithms, we aim to expand our understanding of the brain function of patients with neurological disorders through the analysis of brain networks.

Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals

Stress has an impact, not only on a person's physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

The performance of a convolutional neural network (CNN) heavily depends on its hyperparameters. However, finding a suitable hyperparameters configuration is difficult, challenging, and computationally expensive due to three issues, which are 1) the mixed-variable problem of different types of hyperparameters; 2) the large-scale search space of finding optimal hyperparameters; and 3) the expensive computational cost for evaluating candidate hyperparameters configuration. Therefore, this article focuses on these three issues and proposes a novel estimation of distribution algorithm (EDA) for efficient hyperparameters optimization, with three major contributions in the algorithm design. First, a hybrid-model EDA is proposed to efficiently deal with the mixed-variable difficulty. The proposed algorithm uses a mixed-variable encoding scheme to encode the mixed-variable hyperparameters and adopts an adaptive hybrid-model learning (AHL) strategy to efficiently optimize the mixed-variables. Second, an orthogonal initialization (OI) strategy is proposed to efficiently deal with the challenge of large-scale search space. Third, a surrogate-assisted multi-level evaluation (SME) method is proposed to reduce the expensive computational cost. Based on the above, the proposed algorithm is named s urrogate-assisted hybrid-model EDA (SHEDA). For experimental studies, the proposed SHEDA is verified on widely used classification benchmark problems, and is compared with various state-of-the-art methods. Moreover, a case study on aortic dissection (AD) diagnosis is carried out to evaluate its performance. Experimental results show that the proposed SHEDA is very effective and efficient for hyperparameters optimization, which can find a satisfactory hyperparameters configuration for the CIFAR10, CIFAR100, and AD diagnosis with only 0.58, 0.97, and 1.18 GPU days, respectively.

Frequency-dependent effective connections between local signals and the global brain signal during resting-state

The psychological and physiological meanings of resting-state global brain signal (GS) and GS topography have been well confirmed. However, the causal relationship between GS and local signals was largely unknown. Based on the Human Connectome Project dataset, we investigated the effective GS topography using the Granger causality (GC) method. In consistent with GS topography, both effective GS topographies from GS to local signals and from local signals to GS showed greater GC values in sensory and motor regions in most frequency bands, suggesting that the unimodal superiority is an intrinsic architecture of GS topography. However, the significant frequency effect for GC values from GS to local signals was primarily located in unimodal regions and dominated at slow 4 frequency band whereas that from local signals to GS was mainly located in transmodal regions and dominated at slow 6 frequency band, consisting with the opinion that the more integrated the function, the lower the frequency. These findings provided valuable insight for the frequency-dependent effective GS topography, improving the understanding of the underlying mechanism of GS topography.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09831-0.

A Greedy Optimized Intelligent Framework for Early Detection of Alzheimer's Disease Using EEG Signal

Recent researchers have been drawn to the analysis of electroencephalogram (EEG) signals in order to confirm the disease and severity range by viewing the EEG signal which has complicated the dataset. The conventional models such as machine learning, classifiers, and other mathematical models achieved the lowest classification score. The current study proposes to implement a novel deep feature with the best solution for EEG signal analysis and severity specification. A greedy sandpiper-based recurrent neural system (SbRNS) model for predicting Alzheimer's disease (AD) severity has been proposed. The filtered data are used as input for the feature analysis and the severity range is divided into three classes: low, medium, and high. The designed approach was then implemented in the matrix laboratory (MATLAB) system, and the effectiveness score was calculated using key metrics such as precision, recall, specificity, accuracy, and misclassification score. The validation results show that the proposed scheme achieved the best classification outcome.

A memristive neuron and its adaptability to external electric field

Connecting memristors into any neural circuit can enhance its potential controllability under external physical stimuli. Memristive current along a magnetic flux-controlled memristor can estimate the effect of electromagnetic induction on neural circuits and neurons. Here, a charge-controlled memristor is incorporated into one branch circuit of a simple neural circuit to estimate the effect of an external electric field. The field energy kept in each electric component is respectively calculated, and equivalent dimensionless energy function H is obtained to discern the firing mode dependence on the energy from capacitive, inductive, and memristive channels. The electric field energy H_M in a memristive channel occupies the highest proportion of Hamilton energy H, and neurons can present chaotic/periodic firing modes because of large energy injection from an external electric field, while bursting and spiking behaviors emerge when magnetic field energy H_L holds maximal proportion of Hamilton energy H. The memristive current is modified to control the firing modes in this memristive neuron accompanying with a parameter shift and shape deformation resulting from energy accommodation in the memristive channel. In the presence of noisy disturbance from an external electric field, stochastic resonance is induced in the memristive neuron. Exposed to stronger electromagnetic field, the memristive component can absorb more energy and behave as a signal source for energy shunting, and negative Hamilton energy is obtained for this neuron. The new memristive neuron model can address the main physical properties of biophysical neurons, and it can further be used to explore the collective behaviors and self-organization in networks under energy flow and noisy disturbance.

End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network

Fatigue driving is one of the leading causes of traffic accidents, so fatigue driving detection technology plays a crucial role in road safety. The physiological information-based fatigue detection methods have the advantage of objectivity and accuracy. Among many physiological signals, EEG signals are considered to be the most direct and promising ones. Most traditional methods are challenging to train and do not meet real-time requirements. To this end, we propose an end-to-end temporal and graph convolution-based (MATCN-GT) fatigue driving detection algorithm. The MATCN-GT model consists of a multi-scale attentional temporal convolutional neural network block (MATCN block) and a graph convolutional-Transformer block (GT block). Among them, the MATCN block extracts features directly from the original EEG signal without a priori information, and the GT block processes the features of EEG signals between different electrodes. In addition, we design a multi-scale attention module to ensure that valuable information on electrode correlations will not be lost. We add a Transformer module to the graph convolutional network, which can better capture the dependencies between long-distance electrodes. We conduct experiments on the public dataset SEED-VIG, and the accuracy of the MATCN-GT model reached 93.67%, outperforming existing algorithms. Furthermore, compared with the traditional graph convolutional neural network, the GT block has improved the accuracy rate by 3.25%. The accuracy of the MATCN block on different subjects is higher than the existing feature extraction methods.

Higuchi fractal dimension is a unique indicator of working memory content represented in spiking activity of visual neurons in extrastriate cortex

Working memory has been identified as a top-down modulation of the average spiking activity in different brain parts. However, such modification has not yet been reported in the middle temporal (MT) cortex. A recent study showed that the dimensionality of the spiking activity of MT neurons increases after deployment of spatial working memory. This study is devoted to analyzing the ability of nonlinear and classical features to capture the content of the working memory from the spiking activity of MT neurons. The results suggest that only the Higuchi fractal dimension can be considered as a unique indicator of working memory while the Margaos-Sun fractal dimension, Shannon entropy, corrected conditional entropy, and skewness are perhaps indicators of other cognitive factors such as vigilance, awareness, and arousal as well as working memory.