International journal of neural systems最新文献

Spiking neural membrane systems (SNP systems) are distributed parallel computing models inspired by neuronal spike mechanisms. Traditional SNP systems execute rules serially within each neuron, limiting their efficiency. This paper introduces MNSNP systems, a novel variant where neurons can distinguish spike sources and execute multiple rules in parallel at one time step. MNSNP systems maintain global distributed parallelism while integrating local parallelism, significantly enhancing information processing capabilities. Computational completeness is demonstrated, proving MNSNP systems as Turing universal devices for number generation, acceptance, and function computation. Compared to existing models, MNSNP systems require fewer neurons (only 60 for universal computation), showcasing resource efficiency. An application in smoke detection achieves an AUC value of 0.9840, demonstrating practical utility. This work advances SNP systems by introducing multiplexing, paving the way for applications in robotics, feature recognition, and real-time processing.

Traditional deep neural networks exhibit high computational complexity during training and lack biological interpretability due to their reliance on backpropagation-based methods. Spiking Recurrent Neural Network (SRNN) performs well in processing spatio-temporal information by using discrete spike events. It attracts increasing attention in neural computing due to its biological plausibility and hardware implementation. To improve the performance of SRNN, we propose an excitation-inhibition balanced shallow SRNN (EI-SRNN), which is inspired by the balance of excitation and inhibition in the brain, by optimizing the input currents of reservoir neurons to achieve a tight balanced state. The proposed EI-SRNN achieves optimal accuracy while maintaining low computational complexity, debunking the conventional trade-off between accuracy and robustness. We analyze the neural encoding ability and information memory capacity of the EI-SRNN and compare the performance of the model under different degrees of excitation and inhibition. Our experiments demonstrate that EI-SRNN can have higher neural coding capacity and memory capacity under tight balanced excitatory and inhibitory balanced states, so it can achieve better accuracy while possessing stronger robustness. Furthermore, when the reservoir is dominated by excitatory influences, performance declines faster than when the reservoir is dominated by inhibitory influences.

Electroencephalogram (EEG) plays a vital role in seizure detection, yet existing methods often fail to adequately capture the spatiotemporal characteristics of EEG signals, leading to limited performance. Moreover, most current models depend on supervised learning and thus require large amounts of labeled data. To address these issues, this paper introduces the Long Short-Term Memory-Transformer (LTformer) encoder, designed to model long-term temporal dependencies in EEG signals while retaining spatial information across electrode channels. We further propose a dual-stream self-supervised learning (SSL) strategy to pretrain the model, enabling the LTformer encoder to learn discriminative representations from extensive unlabeled EEG data. After pretext training, the encoder is transferred and fine-tuned for downstream seizure detection. The proposed method, termed Self-Supervised Attention LTformer (SALT), is evaluated on two public EEG datasets using both segment-based and event-based experimental protocols. In the segment-based evaluation, SALT achieves 98.87% sensitivity, 99.15% accuracy, and 99.41% specificity on CHB-MIT, and 98.04% sensitivity, 97.72% accuracy, and 97.62% specificity on Siena. In the event-based evaluation, SALT attains 98.57% sensitivity with a false discovery rate (FDR) of 0.26 on CHB-MIT, and 98.65% sensitivity with an FDR of 0.25 on Siena. The code is publicly available at https://github.com/peutim114/SALT.

Relieving driver fatigue is crucial for ensuring traffic safety. Existing research lacks an exploration of the feasibility and effectiveness of using implicit emotion modulation methods to alleviate driver fatigue. In this study, the effects of Emotional Sensory (olfactory or olfactory-auditory) Stimuli (ESS) on modulating driver fatigue are explored, and the underlying neural mechanisms are analyzed based on the spatio-temporal dynamic patterns of Electroencephalogram (EEG) signals. First, a real-world driver fatigue modulation experiment based on ESS was designed to record EEG signals. Second, brain activation patterns under various ESS were investigated by analyzing brain functional networks. Furthermore, dynamic changes in fatigue-related features were analyzed to examine the strength and persistence of driver fatigue modulation for each ESS. Finally, a fatigue similarity measure method was adopted to quantify the fatigue recovery level under ESS in a more intuitive manner. The results demonstrate that the mint odor-High-Arousal-Low-Valence (HALV) music stimulus exhibits the best driver fatigue modulation effects, and is superior to singular olfactory stimuli. Furthermore, dynamic brain functional connectivity analysis reveals that effective driver fatigue modulation tends to be strongly synchronized in the frontal and parietal lobes. The optimal olfactory-auditory mixed stimuli restores driver fatigue to the level 58-60[Formula: see text]min ago. Our findings shed light on the dynamic characterization of functional connectivity during driver fatigue modulation and demonstrate the potential of using ESS as a reliable implicit tool for modulating driver fatigue.

Generative adversarial network (GAN) architecture search aims to automate the discovery of high-performance network structures. While differentiable search methods like DAMGAN have shown promise, their reliance on inefficient SENet modules and adversarial loss for attention training limits both search efficiency and architecture quality. To address these limitations, we propose EAMGAN, an enhancing differentiable GAN architecture search with efficient attention and Fréchet Inception Distance (FID) guidance. Our approach introduces a lightweight attention module ECA-Net that replaces the fully-connected layers in SENet with a 1D convolution utilizing local context and weight sharing, thereby significantly reducing parameter count. Furthermore, we decouple the attention training from adversarial optimization and introduce a customized loss function based on the FID, which directly guides the architecture selection toward subnets that generate higher-quality images. Experiments on CIFAR-10 show that EAMGAN not only surpasses DAMGAN (Inception Score (IS): 9.03 versus 8.99, FID: 9.43 versus 10.27) but also achieves this with lower search cost (0.08 versus 0.09 GPU days). Competitive results on STL-10 further demonstrate its effectiveness and transferability.

In this study, we aimed to elicit cerebellar activity using a visually cued task involving alternating button presses and foot pedaling at varying speeds. Functional MRI data were acquired using a multiband sequence on a 3T scanner. Thirty-three healthy volunteers participated, and their blood oxygen-level dependent (BOLD) signals were recorded at a spatial resolution of [Formula: see text] [Formula: see text]2.5[Formula: see text]mm³. The fMRI data were analyzed using a general linear model (GLM) to delineate brain regions activated by the button press and foot pedaling conditions, respectively. The BOLD signal changes in each active region of interest (ROI) were then linearly regressed against the mean reaction times (RTs), with age as a covariate, for all participants. All ROIs exhibited a negative relationship with RTs, indicating that higher BOLD activations were associated with faster responses across all conditions. Interestingly, the button press task significantly activated the pyramis (inferior cerebellar vermis), whereas the foot pedaling task activated the superior cerebellar vermis. This finding reflects a functional segmentation along the superior-inferior axis of the cerebellar vermis, corresponding to a foot-hand distribution. Using multiband fMRI, we achieved the spatial resolution necessary to delineate this functional topography within the cerebellum.

Designing effective neural architectures remains a central challenge in deep learning, and Neural Architecture Search (NAS) has become a popular tool for automating this process. However, many existing NAS approaches depend on hand-crafted architecture descriptors or shallow performance predictors, which fail to capture the structural complexity of candidate networks and often lead to unreliable search guidance. We introduce Graph Embedding Comparator with Isomorphic Multi-Comparison (GEC-IMC), an evolutionary NAS framework that learns architecture representations directly from their graph structure. A graph convolutional network encodes architectures into embeddings, while a contrastive learning strategy ensures that architectures with similar accuracy are mapped closer in the embedding space. On top of these embeddings, a comparator estimates the relative performance between two architectures, enabling more precise pairwise assessments during search. To further increase robustness, GEC-IMC incorporates an isomorphic multi-comparison mechanism, which evaluates multiple structurally equivalent variants of each architecture and aggregates their pairwise outcomes into a global score. This ranking score provides consistent feedback for evolutionary selection. Experiments on standard NAS benchmarks demonstrate that GEC-IMC achieves state-of-the-art performance with improved robustness over existing predictors. Ablation studies confirm the complementary roles of embedding learning and multi-comparison in enhancing search efficiency.

Epileptic seizure prediction based on electroencephalogram (EEG) signals is one of the critical applications of medical artificial intelligence (AI), with considerable clinical potential for improving the quality of life of patients through early warnings. However, existing prediction models face dual challenges: insufficient feature representation and limited explainability of the decision. To address these challenges, this study proposes a dynamic multiscale cross-band fusion filter network (MCFNet) for end-to-end seizure prediction. Specifically, the model first decomposes EEG signals into multiscale components and incorporates a cross-band fusion attention mechanism to achieve multi-granularity signal fusion. Subsequently, the synchronous spectral filtering network, comprising both static and dynamic filtering modules, is designed to capture the periodic components and cross-channel dependencies in EEG signals. Notably, two explainable methods are introduced: a joint feature visualization strategy and an efficient feature ablation analysis, helping to bridge the gap between the "black-box" nature of deep learning and clinical needs. Evaluated on the CHB-MIT dataset, MCFNet achieves a sensitivity of 97.13%, a specificity of 97.22%, and a false positive rate (FPR) of 0.0326/h. Experimental results show that MCFNet not only exhibits superior predictive performance but also maintains a low FPR, offering a feasible scheme for clinical application of EEG-based seizure prediction.

The vagus nerve (VN) mediates bidirectional communication between the body and brain to maintain physiological homeostasis; likewise, alterations in ongoing vagal signaling may be indicators of disease and/or contribute to disease pathogenesis. Even though extensively documented in acute experiments, ongoing vagal activity has not been characterized longitudinally, over days or weeks, in mice, a preferred preclinical model. In addition, even though many VN recordings in mice occur during anesthesia, the effects of anesthesia on vagal signaling are unknown. This study uses a chronic implant mouse model to record vagal activity in anesthetized and awake, behaving animals for an average of 10 weeks and up to 6 months. Individual compound action potentials (CAPs) are tracked across multiple days by quantifying comparisons in features, including firing rates, waveform shape, inter-CAP interval histograms, and phase-locking to cardiac and respiratory signals, while demonstrating long-term electrode-nerve interface viability and stable signal-to-noise ratios. Additionally, cytokine challenge experiments produced detectable CAP responses up to 3 months after electrode implantation. Lastly, awake recordings incorporated video analysis to identify and remove motion artifacts to preserve and extract neural and cardiac recordings during daylight in-cage behavior. Results reveal diverse CAP populations with diverse physiological coupling and firing rates modulated by anesthesia. This work highlights the potential of chronic VN recordings to assess long-term changes in vagal activity in health and disease, with implications for the discovery of autonomic markers of disease and closed-loop VNS stimulation strategies.

Deep Learning (DL) models excel at automatically learning intricate patterns within complex data, but their black box nature undermines human trust. To address this, current validation strategies typically focus on the model itself, modifying its architecture to assess the role and importance of the components. However, this model-centric view overlooks the critical learning substrate, which is represented by the data, implicitly assuming that it accurately represents the target phenomenon. This implicit trust in data means that evaluation may fail to detect whether high performance stems from exploiting biases or data quirks rather than learning relevant patterns. We present a novel data-related ablation as a complement to the traditional architectural ablation. Using this framework for Electroencephalography (EEG) signals of Emotional Recognition (ER) and Motor Execution (ME) as a case study, we show that seemingly high-accuracy models often rely heavily on process-irrelevant features, maintaining performance even when key information is eliminated. This shows that a standard, data-independent evaluation can be misleading about whether a model truly captured the intended process; the proposed approach helps distinguish robust learning from leaning on incidental characteristics. Therefore, incorporating data-related ablation is essential for developing reliable and generalizable DL models in fields that rely on data derived from complex and often not completely known phenomena.