International journal of neural systems最新文献

{"title":"Differentiable Generative Adversarial Network Architecture Search Guided by Efficient Attention and Fréchet Distance.","authors":"Yandan Xu, Qianjin Zhang, Yu Xue","doi":"10.1142/S0129065726500115","DOIUrl":"10.1142/S0129065726500115","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650011"},"PeriodicalIF":6.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146032458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring Cerebral and Cerebellar Blood Oxygenation-Level Dependent Activations During Visually Cued Alternating Hand and Foot Movements with 3T Multiband fMRI.","authors":"Jeng-Ren Duann, Yun-Chieh Wang, Siao-Jhen Wu, Chun-Ming Chen","doi":"10.1142/S0129065726500152","DOIUrl":"10.1142/S0129065726500152","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650015"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Channel Graph Neural Network Revealing Multimodal Brain Connectivity Abnormalities in Schizophrenia.","authors":"Jinnan Gong, Rui Ma, Roberto Rodriguez-Labrada, Yanbing Zhu, Hongrui Lin, Yufan Zhou, Yafeng Wang, Dongrui Gao, Dezhong Yao, Sisi Jiang, Cheng Luo","doi":"10.1142/S0129065726500073","DOIUrl":"10.1142/S0129065726500073","url":null,"abstract":"<p><p>Investigating abnormal brain network characteristics in schizophrenia can improve our understanding of disease mechanisms and help identify potential intervention targets. Graph learning techniques can capture high-dimensional features of large-scale brain networks and offer an inherent advantage for integrating multimodal data. To better integrate multimodal data and accurately localize network abnormalities associated with the disorder, this study proposes a channel-based graph neural network (C-GNN) model. First, node embedding of brain regions was constructed to capture structural connectivity patterns. Second, a branched attention module was introduced to adaptively identify important brain regions through channel attention. Finally, a graph feature-constraint module was developed to extract salient features by computing difference scores across feature channels. The C-GNN model achieved an accuracy of 84.37% in classifying individuals with schizophrenia. Interpretability analysis revealed key abnormal brain regions (e.g. orbital cortex, temporal fusiform cortex, lingual gyrus) and multimodal metrics (such as cortical thickness and ReHo) that contributed substantially to the classification. These findings offer insights into the underlying neural alterations in schizophrenia and may inform the development of targeted intervention strategies.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":"36 5","pages":"2650007"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147277871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph Embedding Comparator for Evolutionary Neural Architecture Search with Isomorphic Multi-Comparison.","authors":"Xiaolei Zhang, Yu Xue, Ferrante Neri","doi":"10.1142/S0129065726500097","DOIUrl":"10.1142/S0129065726500097","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650009"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146047668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Longitudinal Characterization of Compound Action Potentials in Chronic Vagus Nerve Recordings in Mice.","authors":"Shubham Debnath, Ibrahim T Mughrabi, Todd J Levy, Fylaktis Fylaktou, Nilay Kumar, Yousef Al-Abed, Stavros Zanos, Theodoros P Zanos","doi":"10.1142/S0129065726500085","DOIUrl":"10.1142/S0129065726500085","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650008"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145902027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable End-to-End Seizure Prediction via Dynamic Multiscale Cross-Band Fusion Filter Network.","authors":"Jie Wang, Yingchao Wang, Weiwei Nie, Qi Yuan","doi":"10.1142/S0129065726500103","DOIUrl":"10.1142/S0129065726500103","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650010"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146004906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-related Ablation for Reinforcing Deep Learning in Explaining Complex Phenomena.","authors":"Romeo Lanzino, Luigi Cinque, Gian Luca Foresti, Giuseppe Placidi","doi":"10.1142/S0129065726500061","DOIUrl":"10.1142/S0129065726500061","url":null,"abstract":"<p><p>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 <i>data-related ablation</i> 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.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650006"},"PeriodicalIF":6.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146088546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating the Speed of Nearby Vehicles with a Single Onboard Camera by Smooth Kernel Regression.","authors":"Mónica López-Pola, Iván García-Aguilar, Jorge García-González, Ezequiel López-Rubio","doi":"10.1142/S0129065726500012","DOIUrl":"10.1142/S0129065726500012","url":null,"abstract":"<p><p>Estimating the speed of nearby vehicles is essential for driver assistance. A real-time, camera-only pipeline is presented that uses an onboard monocular camera: vehicles are detected and tracked with an off-the-shelf one-stage CNN (YOLOv8); distance is approximated from bounding-box angular width using class-dependent priors (2.0[Formula: see text]m cars; 2.5[Formula: see text]m larger vehicles) and camera intrinsics; a Nadaraya-Watson kernel smooths the distance sequence, and its analytic derivative yields relative speed. The approach supports multiple targets without dedicated ranging hardware. Evaluation on CARLA synthetic video with ground truth analyzes estimated versus ground-truth distance, estimate/ground-truth ratio versus image-center displacement, and kernel-based speed versus a polynomial trend. Results show a positional bias away from the image center and a stability-lag trade-off due to smoothing. The contribution is a detector-agnostic distance-speed head that couples angular geometry with analytic Nadaraya-Watson smoothing and differentiation for real-time operation, positioned as a low-cost alternative or complement to active sensors, with limitations and paths to real-world validation outlined.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650001"},"PeriodicalIF":6.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145835657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scalp Electroencephalography Markers of Hidden Interictal Epileptiform Discharges in the Mesial Temporal Lobe.","authors":"Takahiro Yamaguchi, Taira Uehara, Toshiki Okadome, Takahiko Mukaino, Takafumi Shimogawa, Nobutaka Mukae, Hiroshi Shigeto, Noriko Isobe","doi":"10.1142/S0129065726500024","DOIUrl":"10.1142/S0129065726500024","url":null,"abstract":"<p><p>Interictal epileptiform discharges (IEDs) are crucial for epilepsy diagnosis but are often undetectable on scalp EEG (scEEG). This study aims to develop a Support Vector Machine classifier to detect mesial temporal lobe (MTL) IEDs invisible on scEEG using simultaneous intracranial EEG (iEEG) and scEEG recordings and to identify contributing scEEG features. Data from 17 patients with epilepsy were analyzed. IED epochs were extracted where IEDs were present on iEEG but absent on scEEG. Control epochs were selected from periods without IEDs on both Electroencephalographies (EEGs). Feature selection was performed, and a classifier was developed and validated with external data from 35 MTL epilepsy (MTLE) and 33 nonepileptic patients. The classifier used 58 selected features and achieved an accuracy of 0.70 and an area under the receiver operating characteristic curve of 0.78 on holdout validation. External validation revealed significant differences in IED-classified epoch frequencies before and after drug withdrawal in patients with MTLE, and between MTLE and nonepileptic groups. Feature analysis identified high-frequency power suppression, increased ipsilateral connectivity, and enhanced cross-frequency coupling as markers of IEDs that were undetectable in scEEG. This study shows that machine learning can detect MTL IEDs invisible to scEEG, revealing related scEEG changes and aiding EEG analysis.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":"36 4","pages":"2650002"},"PeriodicalIF":6.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146151536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Interpretable Hybrid Neural Network Integrating Sinc-Convolution and Transformer for EEG-Based Depression Detection.","authors":"Minmin Miao, Qianqian Tan, Ke Zhang, Zhenzhen Sheng, Jiayi Hu, Baoguo Xu","doi":"10.1142/S0129065726500048","DOIUrl":"10.1142/S0129065726500048","url":null,"abstract":"<p><p>EEG recordings obtained before medication are regarded as valuable biological indicators for depression detection. Currently, depression diagnosis based on EEG using convolutional neural networks (CNNs) has achieved relatively high detection performance, but some issues remain unresolved. CNNs are constrained by their limited receptive fields, which restrict them to capturing local rather than global dependencies. In addition, the complex features learned by CNNs are often hard to interpret and typically require a substantial number of trainable parameters. To tackle these issues, an interpretable hybrid neural network named SINCFORMER-SHAP is proposed. SINCFORMER-SHAP comprises two main components, namely the spatial-frequency and temporal feature extraction modules. The spatial-frequency feature extraction module leverages a hybrid design, where temporal filtering through a sinc-based convolution is coupled with spatial convolution, enabling the model to learn fine-grained spatial-spectral patterns. The sinc-convolutional layer helps constrain the parameter count, enhancing model efficiency. Subsequently, the temporal domain feature extraction module utilizes Transformer to capture global time-domain dependencies. Kernel visualization is used to provide direct insights into the spectral features learned by the spatial-frequency feature extraction module. To further enhance interpretability on the spatial domain, a post-hoc analysis is conducted using SHAP method. Based on the results of interpretability analysis, potential biomarkers have been observed within alpha and gamma rhythms across the frontal, parietal, temporal, and occipital areas. Comprehensive experiments conducted on public MODMA, EDRA and Mumtaz datasets were used to assess the performance of the proposed approach. The experimental outcomes provide compelling evidence that the proposed method not only surpasses multiple state-of-the-art approaches in performance, but also contributes a significant advancement toward the development of interpretable diagnostic technique for depression, thereby bridging the gap between computational methodologies and practical psychiatric applications.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2650004"},"PeriodicalIF":6.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145936790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}