International journal of neural systems最新文献

Clinically, epilepsy manifests as a chronic condition marked by unprovoked, recurrent seizures, plaguing over 70 million individuals with debilitating seizures and life-threatening complications. Approximately 30% of patients with epilepsy do not respond to conventional antiepileptic drugs, indicating the limited efficacy of these medications in controlling seizures universally. Therefore, seizure prediction has become a key factor in enabling timely intervention for epilepsy patients, which can provide crucial time for clinical treatment and preventive measures. This study aimed to propose a lightweight seizure prediction model integrating a residual network (ResNet) with a kernel-enhanced global temporal attention Block (GTA Block). The ResNet extracts electroencephalogram (EEG) features while maintaining gradient stability, and the GTA mechanism constructs full-sequence temporal association matrices to capture the dynamic evolution of EEG patterns. Then a kernel function is embedded into GTA Block for mapping EEG samples into a high-dimensional space in which the distinction between preictal and interictal states is enhanced. The model significantly outperforms existing methods while maintaining a lightweight architecture suitable for embedded systems. With only 1.94 million parameters and an inference time of 0.00207[Formula: see text]s, this lightweight design facilitates real-time deployment on wearable devices, enhancing feasibility for continuous clinical monitoring in resource-constrained settings.

This study aims to develop a multimodal driver emotion recognition system that accurately identifies a driver's emotional state during the driving process by integrating facial expressions, ElectroCardioGram (ECG) and ElectroEncephaloGram (EEG) signals. Specifically, this study proposes a model that employs a Conformer for analyzing facial images to extract visual cues related to the driver's emotions. Additionally, two Autoformers are utilized to process ECG and EEG signals. The embeddings from these three modalities are then fused using a cross-attention mechanism. The integrated features from the cross-attention mechanism are passed through a fully connected layer and classified to determine the driver's emotional state. The experimental results demonstrate that the fusion of visual, physiological and neurological modalities significantly improves the reliability and accuracy of emotion detection. The proposed approach not only offers insights into the emotional processes critical for driver assistance systems and vehicle safety but also lays the foundation for further advancements in emotion recognition area.

Accurate localization of the theoretical epileptogenic zone in cingulate epilepsy is particularly challenging due to the region's deep anatomical location and complex connectivity. While invasive stereoelectroencephalography (sEEG) methodology offers excellent spatiotemporal sampling of deep intracerebral structures, interpretation of these high-dimensional recordings remains largely qualitative and subject to interpretation by clinician experts. To address this limitation, we propose a quantitative, biomarker-based framework using phase-amplitude coupling (PAC) to investigate 25 seizures recorded from four patients with complex cingulate epilepsy who underwent sEEG followed by surgical treatment (either laser ablation or open resection), achieving ≥ 1 year of sustained seizure freedom. PAC values were computed from sEEG electrode contacts across multiple seizures during pre-ictal and ictal phases, employing wide-frequency and band-specific frequency coupling approaches. Among frequency pairs, theta-beta ([Formula: see text]-[Formula: see text]) coupling consistently demonstrated the most robust differentiation between surgically-treated and untreated contact sites. Our findings highlight frequency-specific PAC-based metrics as a potential tool for mapping dynamic epileptiform activity in brain networks, offering quantitative insight that may refine surgical planning and decision-making in challenging cases of cingulate epilepsy.

Automatic seizure detection holds significant importance for epilepsy diagnosis and treatment. Convolutional neural networks (CNNs) have shown immense potential in seizure detection. Though traditional CNN-based seizure detection models have achieved significant advancements, they often suffer from excessive parameters and limited interpretability, thus hindering their reliability and practical deployment on edge computing devices. Therefore, this study introduces an innovative Morlet convolutional neural network (Morlet-CNN) framework with its effectiveness demonstrated in seizure detection tasks. Unlike traditional CNNs, the convolutional kernels in the Morlet-CNN contain only two learnable parameters, allowing for a lightweight architecture. Additionally, we propose a frequency-domain-response-based kernel pruning algorithm for Morlet-CNN and implement an INT8 quantization algorithm by incorporating Kullback-Leibler (KL) divergence calibration with a Morlet lookup table (LUT). With the pruning and quantization algorithms, the model's parameter scale achieves over 90% reduction while maintaining minimal accuracy loss. Furthermore, the model exhibits enhanced interpretability from a signal processing perspective, distinguishing it from many previous CNN models. Extensive experimental validation on the Bonn and CHB-MIT datasets confirms the Morlet-CNN model's efficacy with a compact Kilobyte (KB)-level model size, making it highly suitable for real-world applications.

Knowledge graphs (KGs) which represent entities and their relations in a structured manner, have become a fundamental resource for various natural language processing tasks. However, the incompleteness of KGs significantly hinders their effectiveness, thereby reducing their practical utility. The challenge of predicting missing relations between entities and performing these predictions efficiently has become a focal point of research. To address the challenge of incomplete KGs, we propose GEGS, a novel KG embedding framework that enhances scalability and expressiveness for relation prediction. GEGS introduces GAT-SNP, a graph attention network that, for the first time, integrates nonlinear spiking neural P (SNP) mechanisms into graph attention models and applies them to the KG domain, effectively capturing complex relational structures. The GAT-SNP network assigns distinct attention weights to each node, enabling the model to focus on the most relevant nodes in the graph. To mitigate information loss in long-range and sequential path features, we incorporate a BiLSTM-SNP component, which alleviates long-term dependency issues while preserving global path information. By leveraging GAT-SNP and BiLSTM-SNP, GEGS achieves superior performance in link prediction tasks, paving the way for applications in large-scale knowledge base completion. Kinship, FB15k-237, and WN18RR are used to evaluate the proposed GEGS model. The experimental results indicate that the proposed GEGS model has achieved state-of-the-art results in multiple evaluation metrics(e.g. Hits@10 and MRR).

High inter- and intra-individual variation is a prominent characteristic of electroencephalography (EEG) signals and a significant inhibitor to the practical implementation of brain-computer interfaces (BCIs) outside of research laboratories. However, a few methods exist to assess EEG signal variability. Here, a novel multi-class intra-trial trajectory (MITT) analysis to study EEG variability for mental imagery BCIs is presented. The methods yield insight into different aspects of signal variation, specifically (i) inter-individual, (ii) inter-task, (iii) inter-trial, and (iv) intra-trial. A novel representation of the time evolution of EEG signals was developed. Task trials were segmented into short temporal windows and represented in a feature space derived from unsupervised clustering of trial covariance matrices. Using this representation, temporal trajectories through the feature space were constructed. Two metrics were defined to assess user performance based on these trajectories: (1) InterTaskDiff, based on time-varying distances between the mean trajectories of different tasks, and (2) InterTrialVar, which measured the inter-trial variation of the temporal trajectories along the feature dimensions. Analysis of three-class BCI data from 14 adolescents revealed both metrics correlated significantly with classification results. Further analysis of intra-trial trajectories suggested the existence of characteristic task- and user-specific temporal dynamics. The participant-specific insights provided by MITT analysis could be used to overcome EEG-variability challenges impeding practical implementation of BCIs by elucidating avenues to improve user training feedback or selection of user-optimal classifiers and hyperparameters.

Multivariate workload prediction in cloud computing environments is a critical research problem. Effectively capturing inter-variable correlations and temporal patterns in multivariate time series is key to addressing this challenge. To address this issue, this paper proposes a convolutional model based on a Nonlinear Spiking Neural P System (ConvNSNP), which enhances the ability to process nonlinear data compared to conventional convolutional models. Building upon this, a hybrid forecasting model is developed by integrating ConvNSNP with a Bidirectional Long Short-Term Memory (BiLSTM) network. ConvNSNP is first employed to extract temporal and cross-variable dependencies from the multivariate time series, followed by BiLSTM to further strengthen long-term temporal modeling. Comprehensive experiments are conducted on three public cloud workload traces from Alibaba and Google. The proposed model is compared with a range of established deep learning approaches, including CNN, RNN, LSTM, TCN and hybrid models such as LSTNet, CNN-GRU and CNN-LSTM. Experimental results on three public datasets demonstrate that our proposed model achieves up to 9.9% improvement in RMSE and 11.6% improvement in MAE compared with the most effective baseline methods. The model also achieves favorable performance in terms of MAPE, further validating its effectiveness in multivariate workload prediction.

Advancements in artificial intelligence have propelled affective computing toward unprecedented accuracy and real-world impact. By leveraging the unique strengths of brain signals and ocular dynamics, we introduce a novel multimodal framework that integrates EEG and eye-movement (EM) features synergistically to achieve more reliable emotion recognition. First, our EEG Feature Encoder (EFE) uses a convolutional architecture inspired by the human visual cortex's eccentricity-receptive-field mapping, enabling the extraction of highly discriminative neural patterns. Second, our EM Feature Encoder (EMFE) employs a Kolmogorov-Arnold Network (KAN) to overcome the sparse sampling and dimensional mismatch inherent in EM data; through a tailored multilayer design and interpolation alignment, it generates rich, modality-compatible representations. Finally, the core Multimodal Iterative Attentional Feature Fusion (MIAFF) module unites these streams: alternating global and local attention via a Hierarchical Channel Attention Module (HCAM) to iteratively refine and integrate features. Comprehensive evaluations on SEED (3-class) and SEED-IV (4-class) benchmarks show that our method reaches leading-edge accuracy. However, our experiments are limited by small homogeneous datasets, untested cross-cultural robustness, and potential degradation in noisy or edge-deployment settings. Nevertheless, this work not only underscores the power of biomimetic encoding and iterative attention but also paves the way for next-generation brain-computer interface applications in affective health, adaptive gaming, and beyond.

Visual neural decoding not only aids in elucidating the neural mechanisms underlying the processing of visual information but also facilitates the advancement of brain-computer interface technologies. However, most current decoding studies focus on developing separate decoding models for individual subjects and specific tasks, an approach that escalates training costs and consumes a substantial amount of computational resources. This paper introduces a Prompt-Guided Generative Visual Language Decoding Model (PG-GVLDM), which uses prompt text that includes information about subjects and tasks to decode both primary categories and detailed textual descriptions from the visual response activities of multiple individuals. In addition to visual response activities, this study also incorporates a multi-head cross-attention module and feeds the model with whole-brain response activities to capture global semantic information in the brain. Experiments on the Natural Scenes Dataset (NSD) demonstrate that PG-GVLDM attains an average category decoding accuracy of 66.6% across four subjects, reflecting strong cross-subject generalization, and achieves text decoding scores of 0.342 (METEOR), 0.450 (Sentence-Transformer), 0.283 (ROUGE-1), and 0.262 (ROUGE-L), establishing state-of-the-art performance in text decoding. Furthermore, incorporating whole-brain response activities significantly enhances decoding performance by enabling the integration of distributed neural signals into coherent global semantic representations, underscoring its methodological importance for unified neural decoding. This research not only represents a breakthrough in visual neural decoding methodologies but also provides theoretical and technical support for the development of generalized brain-computer interfaces.

This study proposes a novel adaptive DBS control strategy for epilepsy treatment based on deep reinforcement learning. By establishing a random disturbance model of the cortical-thalamus loop, the neural modulation problem is successfully transformed into a Markov decision process. Deep Deterministic Policy Gradient (DDPG) algorithm is employed to achieve adaptive dynamic regulation of stimulation parameters, significantly reducing seizure frequency and duration in various epilepsy simulation scenarios. Experimental results demonstrate that the closed-loop control system can further reduce energy loss by [Formula: see text] ([Formula: see text]) compared to conventional open-loop system, while increase the proportion of non-epileptic states by [Formula: see text] ([Formula: see text]). Furthermore, we innovatively integrate Model-Agnostic Meta-Learning (MAML) with DDPG to develop a collaborative control strategy with transfer learning capabilities. This strategy demonstrates significant advantages across different epilepsy patient scenarios, which offers crucial technical support for the precise and adaptive development of epilepsy treatment.