A Spiking Neural Network With Adaptive Graph Convolution and LSTM for EEG-Based Brain-Computer Interfaces

Sg-snn: a self-organizing spiking neural network based on temporal information

Neurodynamic observations indicate that the cerebral cortex evolved by self-organizing into functional networks, These networks, or distributed clusters of regions, display various degrees of attention maps based on input. Traditionally, the study of network self-organization relies predominantly on static data, overlooking temporal information in dynamic neuromorphic data. This paper proposes Temporal Self-Organizing (TSO) method for neuromorphic data processing using a spiking neural network. The TSO method incorporates information from multiple time steps into the selection strategy of the Best Matching Unit (BMU) neurons. It enables the coupled BMUs to radiate the weight across the same layer of neurons, ultimately forming a hierarchical self-organizing topographic map of concern. Additionally, we simulate real neuronal dynamics, introduce a glial cell-mediated Glial-LIF (Leaky Integrate-and-fire) model, and adjust multiple levels of BMUs to optimize the attention topological map.Experiments demonstrate that the proposed Self-organizing Glial Spiking Neural Network (SG-SNN) can generate attention topographies for dynamic event data from coarse to fine. A heuristic method based on cognitive science effectively guides the network's distribution of excitatory regions. Furthermore, the SG-SNN shows improved accuracy on three standard neuromorphic datasets: DVS128-Gesture, CIFAR10-DVS, and N-Caltech 101, with accuracy improvements of 0.3%, 2.4%, and 0.54% respectively. Notably, the recognition accuracy on the DVS128-Gesture dataset reaches 99.3%, achieving state-of-the-art (SOTA) performance.

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.

A Reinforced, Event-Driven, and Attention-Based Convolution Spiking Neural Network for Multivariate Time Series Prediction

Despite spiking neural networks (SNNs) inherently exceling at processing time series due to their rich spatio-temporal information and efficient event-driven computing, the challenge of extracting complex correlations between variables in multivariate time series (MTS) remains to be addressed. This paper proposes a reinforced, event-driven, and attention-based convolution SNN model (REAT-CSNN) with three novel features. First, a joint Gramian Angular Field and Rate (GAFR) coding scheme is proposed to convert MTS into spike images, preserving the inherent features in MTS, such as the temporal patterns and spatio-temporal correlations between time series. Second, an advanced LIF-pooling strategy is developed, which is then theoretically and empirically proved to be effective in preserving more features from the regions of interest in spike images than average-pooling strategies. Third, a convolutional block attention mechanism (CBAM) is redesigned to support spike-based input, enhancing event-driven characteristics in weighting operations while maintaining outstanding capability to capture the information encoded in spike images. Experiments on multiple MTS data sets, such as stocks and PM2.5 data sets, demonstrate that our model rivals, and even surpasses, some CNN- and RNN-based techniques, with up to 3% better performance, while consuming significantly less energy.

A synergistic approach for enhanced eye blink detection using wavelet analysis, autoencoding and Crow-Search optimized k-NN algorithm

This research endeavor introduces a state-of-the-art, assimilated approach for eye blink detection from Electroencephalography signals. It combines the prominent strategies of wavelet analysis, autoencoding, and a Crow-Search-optimized k-Nearest Neighbors to enhance the performance of eye blink detection from EEG signals. This procedure is initiated by escalating the robustness of EEG data through jittering, which integrates noise into the dataset. Consequently, the wavelet transform is highly demanded during feature extraction in identifying the essential time-frequency components of the signals. These features are further distilled using an autoencoder to provide a dense, yet informative representation. Prior to introducing these features into the machine learning system, they were adjusted. Evidently, the hyperparameters of the k-Nearest Neighbors model have been fine-tuned using Crow Search Algorithm, inspired by the hunting characteristics of crows. This optimization method actively samples the search space to balance exploration and exploitation to identify the optimal configuration for the model. The k-NN model that has been optimized using the proposed method demonstrates significantly higher performance in the eye blink detection process in comparison to the deep learning models when equipped with decorous feature extraction and fine tuning. The effectiveness of the developed system has been ascertained according to the assessment indices such as accuracy, classification reports, and confusion matrix. Thus, the present work offers an optimal method of detecting the eye blink from the EEG signals assisting in the development of further EEG applications including user interfaces, fatigue level identification, and neurological disorders analysis through the enhancement of signal processing and optimization methods. It becomes evident after a detailed evaluation that conventional machine learning algorithms if implemented with correct feature extraction and fine-tuning surpass the deep learning approaches including the frameworks composed of Convolutional Neural Network and Principal Component Analysis and empirical mode decomposition by approximately 96% across all datasets. This proves the advantage of optimized traditional Machine Learning models over the Deep Learning models in realistic EEG-based eye blink detection.

DC-ASTGCN: EEG Emotion Recognition Based on Fusion Deep Convolutional and Adaptive Spatio-Temporal Graph Convolutional Networks

Thanks to advancements in artificial intelligence and brain-computer interface (BCI) research, there has been increasing attention towards emotion recognition techniques based on electroencephalogram (EEG) recently. The complexity of EEG data poses a challenge when it comes to accurately classifying emotions by integrating time, frequency, and spatial domain features. To address this challenge, this paper proposes a fusion model called DC-ASTGCN, which combines the strengths of deep convolutional neural network (DCNN) and adaptive spatio-temporal graphic convolutional neural network (ASTGCN) to comprehensively analyze and understand EEG signals. The DCNN focuses on extracting frequency-domain and local spatial features from EEG signals to identify brain region activity patterns, while the ASTGCN, with its spatio-temporal attention mechanism and adaptive brain topology layer, reveals the functional connectivity features between brain regions in different emotional states. This integration significantly enhances the model's ability to understand and recognize emotional states. Extensive experiments conducted on the DEAP and SEED datasets demonstrate that the DC-ASTGCN model outperforms existing state-of-the-art methods in terms of emotion recognition accuracy.

LAST-PAIN: Learning Adaptive Spike Thresholds for Low Back Pain Biosignals Classification

Spiking neural networks (SNNs) present the potential for ultra-low-power computation, especially when implemented on dedicated neuromorphic hardware. However, a significant challenge is the efficient conversion of continuous real-world data into the discrete spike trains required by SNNs. In this paper, we introduce Learning Adaptive Spike Thresholds (LAST), a novel, trainable encoding strategy designed to address this challenge. The LAST encoder learns adaptive thresholds to transform continuous signals of varying dimensionality-ranging from time series data to high dimensional tensors-into sparse spike trains. Our proposed encoder effectively preserves temporal dynamics and adapts to the characteristics of the input. We validate the LAST approach in a demanding healthcare application using the EmoPain dataset. This dataset contains multimodal biosignal analysis for assessing chronic lower back pain (CLBP). Despite the dataset's small sample size and class imbalance, our LAST-driven SNN framework achieves a competitive Matthews Correlation Coefficient of 0.44 and an accuracy of 80.43% in CLBP classification. The experimental results also indicate that the same framework can achieve an F1-score of 0.65 in detecting protective behaviour. Furthermore, the LAST encoder outperforms conventional rate and latency-based encodings while maintaining sparse spike representations. This achievement shows promises for energy-efficient and real-time biosignal processing in resource-limited environments.

Graph convolution network-based eeg signal analysis: a review

With the advancement of artificial intelligence technology, more and more effective methods are being used to identify and classify Electroencephalography (EEG) signals to address challenges in healthcare and brain-computer interface fields. The applications and major achievements of Graph Convolution Network (GCN) techniques in EEG signal analysis are reviewed in this paper. Through an exhaustive search of the published literature, a module-by-module discussion is carried out for the first time to address the current research status of GCN. An exhaustive classification of methods and a systematic analysis of key modules, such as brain map construction, node feature extraction, and GCN architecture design, are presented. In addition, we pay special attention to several key research issues related to GCN. This review enhances the understanding of the future potential of GCN in the field of EEG signal analysis. At the same time, several valuable development directions are sorted out for researchers in related fields, such as analysing the applicability of different GCN layers, building task-oriented GCN models, and improving adaptation to limited data.

Joint hybrid recursive feature elimination based channel selection and ResGCN for cross session MI recognition

In the field of brain-computer interface (BCI) based on motor imagery (MI), multi-channel electroencephalography (EEG) data is commonly utilized for MI task recognition to achieve sensory compensation or precise human-computer interaction. However, individual physiological differences, environmental variations, or redundant information and noise in certain channels can pose challenges and impact the performance of BCI systems. In this study, we introduce a channel selection method utilizing Hybrid-Recursive Feature Elimination (H-RFE) combined with residual graph neural networks for MI recognition. This channel selection method employs a recursive feature elimination strategy and integrates three classification methods, namely random forest, gradient boosting, and logistic regression, as evaluators for adaptive channel selection tailored to specific subjects. To fully exploit the spatiotemporal information of multi-channel EEG, this study employed a graph neural network embedded with residual blocks to achieve precise recognition of motor imagery. We conducted algorithm testing using the SHU dataset and the PhysioNet dataset. Experimental results show that on the SHU dataset, utilizing 73.44% of the total channels, the cross-session MI recognition accuracy is 90.03%. Similarly, in the PhysioNet dataset, using 72.5% of the channel data, the classification result also reaches 93.99%. Compared to traditional strategies such as selecting three specific channels, correlation-based channel selection, mutual information-based channel selection, and adaptive channel selection based on Pearson coefficients and spatial positions, the proposed method improved classification accuracy by 34.64%, 10.8%, 3.25% and 2.88% on the SHU dataset, and by 46.96%, 5.04%, 5.81% and 2.32% on the PhysioNet dataset, respectively.

Spiking neural networks for biomedical signal analysis

Artificial intelligence (AI) has had a significant impact on human life because of its pervasiveness across industries and its rapid development. Although AI has achieved superior performance in learning and reasoning, it encounters challenges such as substantial computational demands, privacy concerns, communication delays, and high energy consumption associated with cloud-based models. These limitations have facilitated a paradigm change in on-device AI processing, which offers enhanced privacy, reduced latency, and improved power efficiency through the direct execution of computations on devices. With advancements in neuromorphic systems, spiking neural networks (SNNs), often referred to as the next generation of AI, are currently in focus as on-device AI. These technologies aim to mimic the human brain efficiency and provide promising real-time processing with minimal energy. This study reviewed the application of SNNs in the analysis of biomedical signals (electroencephalograms, electrocardiograms, and electromyograms), and consequently, investigated the distinctive attributes and prospective future paths of SNNs models in the field of biomedical signal analysis.

A Dual-Adversarial Model for Cross-Time and Cross-Subject Cognitive Workload Decoding

Electroencephalogram (EEG) signals are widely utilized in the field of cognitive workload decoding (CWD). However, when the recognition scenario is shifted from subject-dependent to subject-independent or spans a long period, the accuracy of CWD deteriorates significantly. Current solutions are either dependent on extensive training datasets or fail to maintain clear distinctions between categories, additionally lacking a robust feature extraction mechanism. In this paper, we tackle these issues by proposing a Bi-Classifier Joint Domain Adaptation (BCJDA) model for EEG-based cross-time and cross-subject CWD. Specifically, the model consists of a feature extractor, a domain discriminator, and a Bi-Classifier, containing two sets of adversarial processes for domain-wise alignment and class-wise alignment. In the adversarial domain adaptation, the feature extractor is forced to learn the common domain features deliberately. The Bi-Classifier also fosters the feature extractor to retain the category discrepancies of the unlabeled domain, so that its classification boundary is consistent with the labeled domain. Furthermore, different adversarial distance functions of the Bi-Classifier are adopted and evaluated in this model. We conduct classification experiments on a publicly available BCI competition dataset for recognizing low, medium, and high cognitive workload levels. The experimental results demonstrate that our proposed BCJDA model based on cross-gradient difference maximization achieves the best performance.

Enhancing Classification Accuracy with Integrated Contextual Gate Network: Deep Learning Approach for Functional Near-Infrared Spectroscopy Brain-Computer Interface Application

Brain-computer interface (BCI) systems include signal acquisition, preprocessing, feature extraction, classification, and an application phase. In fNIRS-BCI systems, deep learning (DL) algorithms play a crucial role in enhancing accuracy. Unlike traditional machine learning (ML) classifiers, DL algorithms eliminate the need for manual feature extraction. DL neural networks automatically extract hidden patterns/features within a dataset to classify the data. In this study, a hand-gripping (closing and opening) two-class motor activity dataset from twenty healthy participants is acquired, and an integrated contextual gate network (ICGN) algorithm (proposed) is applied to that dataset to enhance the classification accuracy. The proposed algorithm extracts the features from the filtered data and generates the patterns based on the information from the previous cells within the network. Accordingly, classification is performed based on the similar generated patterns within the dataset. The accuracy of the proposed algorithm is compared with the long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM). The proposed ICGN algorithm yielded a classification accuracy of 91.23 ± 1.60%, which is significantly (p < 0.025) higher than the 84.89 ± 3.91 and 88.82 ± 1.96 achieved by LSTM and Bi-LSTM, respectively. An open access, three-class (right- and left-hand finger tapping and dominant foot tapping) dataset of 30 subjects is used to validate the proposed algorithm. The results show that ICGN can be efficiently used for the classification of two- and three-class problems in fNIRS-based BCI applications.

TBEEG: A Two-Branch Manifold Domain Enhanced Transformer Algorithm for Learning EEG Decoding

The electroencephalogram-based (EEG) brain-computer interface (BCI) has garnered significant attention in recent research. However, the practicality of EEG remains constrained by the lack of efficient EEG decoding technology. The challenge lies in effectively translating intricate EEG into meaningful, generalizable information. EEG signal decoding primarily relies on either time domain or frequency domain information. There lacks a method capable of simultaneously and effectively extracting both time and frequency domain features, as well as efficiently fuse these features. Addressing these limitations, a two-branch Manifold Domain enhanced transformer algorithm is designed to holistically capture EEG's spatio-temporal information. Our method projects the time-domain information of EEG signals into the Riemannian spaces to fully decode the time dependence of EEG signals. Using wavelet transform, the time domain information is converted into frequency domain information, and the spatial information contained in the frequency domain information of EEG signal is mined through the spectrogram. The effectiveness of the proposed TBEEG algorithm is validated on BCIC-IV-2a dataset and MAMEM-SSVEP-II datasets.

Music emotion recognition based on temporal convolutional attention network using EEG

Music is one of the primary ways to evoke human emotions. However, the feeling of music is subjective, making it difficult to determine which emotions music triggers in a given individual. In order to correctly identify emotional problems caused by different types of music, we first created an electroencephalogram (EEG) data set stimulated by four different types of music (fear, happiness, calm, and sadness). Secondly, the differential entropy features of EEG were extracted, and then the emotion recognition model CNN-SA-BiLSTM was established to extract the temporal features of EEG, and the recognition performance of the model was improved by using the global perception ability of the self-attention mechanism. The effectiveness of the model was further verified by the ablation experiment. The classification accuracy of this method in the valence and arousal dimensions is 93.45% and 96.36%, respectively. By applying our method to a publicly available EEG dataset DEAP, we evaluated the generalization and reliability of our method. In addition, we further investigate the effects of different EEG bands and multi-band combinations on music emotion recognition, and the results confirm relevant neuroscience studies. Compared with other representative music emotion recognition works, this method has better classification performance, and provides a promising framework for the future research of emotion recognition system based on brain computer interface.

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Voice-controlled devices are in demand due to their hands-free controls. However, using voice-controlled devices in sensitive scenarios like smartphone applications and financial transactions requires protection against fraudulent attacks referred to as "speech spoofing". The algorithms used in spoof attacks are practically unknown; hence, further analysis and development of spoof-detection models for improving spoof classification are required. A study of the spoofed-speech spectrum suggests that high-frequency features are able to discriminate genuine speech from spoofed speech well. Typically, linear or triangular filter banks are used to obtain high-frequency features. However, a Gaussian filter can extract more global information than a triangular filter. In addition, MFCC features are preferable among other speech features because of their lower covariance. Therefore, in this study, the use of a Gaussian filter is proposed for the extraction of inverted MFCC (iMFCC) features, providing high-frequency features. Complementary features are integrated with iMFCC to strengthen the features that aid in the discrimination of spoof speech. Deep learning has been proven to be efficient in classification applications, but the selection of its hyper-parameters and architecture is crucial and directly affects performance. Therefore, a Bayesian algorithm is used to optimize the BiLSTM network. Thus, in this study, we build a high-frequency-based optimized BiLSTM network to classify the spoofed-speech signal, and we present an extensive investigation using the ASVSpoof 2017 dataset. The optimized BiLSTM model is successfully trained with the least epoch and achieved a 99.58% validation accuracy. The proposed algorithm achieved a 6.58% EER on the evaluation dataset, with a relative improvement of 78% on a baseline spoof-identification system.