工程技术最新文献

{"title":"The EEG multi-scale brain network and high-order synergy changes in disorders of consciousness during general anesthesia.","authors":"Yu Chang, Jian Wang, Yong Wang, Yang Bai, Jianghong He, Zhenhu Liang","doi":"10.1007/s11571-026-10567-4","DOIUrl":"https://doi.org/10.1007/s11571-026-10567-4","url":null,"abstract":"<p><p>Brain network alterations during general anesthesia (GA) have been extensively investigated in individuals with intact consciousness. However, network dynamics in patients with disorders of consciousness (DoC) under anesthetic perturbation remain poorly understood. We recorded electroencephalogram (EEG) signals from 33 DoC patients (16 UWS and 17 MCS) during GA across three states (DoC-Resting, DoC-MOSSA, and DoC-Recovery). A multi-scale brain network framework was proposed. Low-order network characteristics were assessed using unbiased minimum spanning tree (MST) and directed phase lag index (dPLI), while high-order organization was evaluated using topological data analysis (TDA) and high-order mutual information (HO-MI). UWS patients exhibited a fragmented, line-like topological backbone with lower leaf fraction (<i>p</i> < 0.05) and tree hierarchy (<i>p</i> < 0.05) than MCS patients. dPLI analysis revealed impaired prefrontal top-down directional communication in UWS patients, whereas MCS patients showed transient disruption and recovery of frontoparietal directional organization during anesthesia. Under anesthesia, TDA revealed reduced H1 maximum Betti number in UWS patients (<i>p</i> < 0.01), indicating impaired topological resilience, while MCS patients showed relatively preserved network organization. Furthermore, HO-MI analysis showed increased total correlation with redundant information processing in UWS patients during anesthesia, whereas MCS patients restored synergistic information integration within the central-parietal network during recovery. GA reveals distinct scale-dependent network alterations between MCS and UWS patients. Persistent impairment of directed communication and high-order synergistic integration characterizes disrupted network organization in UWS. The proposed multi-scale EEG framework integrating MST, dPLI, TDA, and HO-MI provides candidate network biomarkers for perioperative consciousness monitoring and assessment in DoC patients.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at https://doi.org/10.1007/s11571-026-10567-4.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"196"},"PeriodicalIF":4.5,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13650097/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149172142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attention-guided deep learning-machine learning and statistical feature fusion for interpretable mental workload classification from EEG.","authors":"Sukanta Majumder, Dibyendu Patra, Subhajit Gorai, Anindya Halder, Utpal Biswas","doi":"10.1007/s11571-025-10392-1","DOIUrl":"https://doi.org/10.1007/s11571-025-10392-1","url":null,"abstract":"<p><p>Accurate assessment of mental workload (MWL) from electroencephalography (EEG) signals is crucial for real-time cognitive monitoring in safety-critical domains such as aviation and human-computer interaction. Although various computational approaches have been proposed, those mostly suffer from limited robustness, interpretability, or fail to fully exploit both temporal and non-linear neural dynamics. This article introduces a novel hybrid deep learning and XGBoost stacking ensemble framework for reliable and interpretable MWL classification from EEG. The proposed pipeline systematically includes preprocessing of raw EEGs, followed by comprehensive feature extraction (time-domain, frequency-domain, wavelet-based, entropy, and fractal dimension features), and subsequent discriminative feature selection phase using ANOVA F-values, yielding a compact set of 200 highly informative features. The proposed architecture consists of dual processing branches: a CNN-BiLSTM-Attention based deep learning branch for automatic learning of spatiotemporal dynamics, and an XGBoost branch for robust classification from engineered features. Predictions from both branches are integrated using a logistic regression stacking ensemble, maximizing complementary strengths and improving generalization. Experiments are conducted on the STEW (simultaneous workload) and EEGMAT (mental arithmetic task) dataset. Proposed model yields 96.87% and 99.40% of classification accuracy by outperforming 16 and 7 previously published state-of-the-art techniques on STEW and EEGMAT dataset respectively. Attention heatmaps and SHAP value analysis provide intuitive visual explanations and interpretability of the model's decision making, while systematic ablation studies validate the contribution of each architectural module. This work demonstrates that a carefully engineered stacking ensemble, informed by both deep learning and classical machine learning, capable of delivering not only improved performance but also enhanced interpretability for EEG-based MWL assessment in real-world applications.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"18"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12681509/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145707567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fractal Transition and Neuromorphic Physiology of Vanadium Dioxide-Memristor under a FractionalDifferential Framework.","authors":"Kashif Ali Abro, Basma Souayeh","doi":"10.1007/s11571-025-10385-0","DOIUrl":"https://doi.org/10.1007/s11571-025-10385-0","url":null,"abstract":"<p><p>Vanadium dioxide is a well-known candidate for memristor applications due to its insulator-to-metal transition characteristics, this is because vanadium dioxide memristors are versatile devices whose operating mechanism is based on an abrupt and volatile change of resistivity. This manuscript introduces the fractal-fractional framework for a third-order vanadium dioxide memristor neuron model that investigates the role of non-local dynamics on chaotic behavior. The third-order vanadium dioxide memristor neuron model is analyzed under three conditions of fractal-fractional differential operators (i) deviation of fractional parameter with fixed fractal order, (ii) deviation of fractal parameter with fixed fractional order, and (iii) simultaneous deviation of both parameters. The mathematical model of third-order vanadium dioxide memristor neuron has been discretized by means of Adams-Bashforth-Moulton method for the sake of numerical simulations. The results highlight the fractal-fractional framework as a versatile tool for tailoring vanadium dioxide memristor neuron's dynamics namely irregular oscillations, dispersed attractors with enhanced chaoticity, bounded loops with tunable stability and excessive fluctuations. These findings confirm that fractional order acts as a memory controller, while fractal order governs structural scaling, together enabling precise modulation between chaos and stability.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"25"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12743040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145849064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Delay dynamics within the neuroglial electromagnetic coupling system.","authors":"Zhixuan Yuan, Jiangling Song, Peihua Feng, Rui Zhang","doi":"10.1007/s11571-026-10417-3","DOIUrl":"https://doi.org/10.1007/s11571-026-10417-3","url":null,"abstract":"<p><p>Building upon our prior introduction of the Delay concept within a neuron-astrocyte electromagnetic coupling system, this study provides a deeper investigation into this phenomenon. The focus is on a specific time interval, termed Delay, which occurs after the cessation of external stimuli. During this period, neurons continue their firing activity before transitioning to a resting state. We initially elucidate that the prolonged neuronal firing, termed Delay, originates from astrocytic involvement rather than magnetic effects. Moreover, the periodic calcium activity of astrocytes can periodically induce the occurrence of neuronal Delay. Finally, we provide a thorough analysis of the duration and structural composition of the neuron Delay induced by astrocytes. The significance of our findings lies in the potential functional role of the Delay phase in the modulation and processing of neural information. Our findings offer a novel perspective on the complex dynamics governing the transition from active firing to resting in neurons, thereby enhancing the understanding of neural response and adaptability.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"42"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12868550/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146123943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"M3T-attention: a multi-level multi-scale temporal attention transformer for EEG hand movement trajectory decoding.","authors":"Lei Zhu, Peng Jiang, Aiai Huang, Jianhai Zhang, Peng Yuan","doi":"10.1007/s11571-025-10403-1","DOIUrl":"https://doi.org/10.1007/s11571-025-10403-1","url":null,"abstract":"<p><p>In recent years, brain-computer interface (BCI) technology has made significant progress in the fields of neural engineering and human-computer interaction. Among these advances, decoding upper-limb movements from electroencephalography (EEG) signals has become a key research focus. However, most existing studies concentrate on discrete classification tasks (e.g., motor imagery recognition), while the prediction of three-dimensional continuous movement trajectories still faces several major challenges. These include the low signal-to-noise ratio of EEG signals, substantial inter-subject variability that limits generalizability, and the high degrees of freedom in 3D trajectories, which increase decoding complexity. To address these challenges and improve the accuracy of decoding continuous 3D hand movement trajectories from EEG signals, this study proposes a Multi-level Multi-scale Temporal Attention Transformer framework (M3T-Attention). The model is designed to extract temporal features across multiple time scales from EEG signals and integrate them via cross-scale attention mechanisms, enabling a nonlinear mapping from 0.5 to 12 Hz EEG signals to 3D kinematic parameters (position, velocity, and acceleration). The model was trained using EEG and wrist kinematic data from the WAY-EEG-GAL dataset. Experimental results show that the proposed method achieves Pearson correlation coefficients (PCCs) of 0.8816, 0.8841, and 0.8711 on the X, Y, and Z axes, respectively, demonstrating robust prediction performance across all subjects and outperforming existing state-of-the-art approaches. In summary, through comparative experiments, statistical significance analysis, and ablation studies, we have fully verified its ability to capture neural coding patterns. It significantly enhances the decoding performance from EEG signals to movement trajectories, offering new approaches for BCI applications in complex motor control scenarios. We have made the model's source code publicly available on GitHub repository URL: https://github.com/jjspp/M3T_Attention.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"33"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12868320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146124022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"VaeTF-A community-aware perceptual architecture for detecting autism spectrum disorders using fMRI.","authors":"Yan Fan, Lingmei Ai, Yumei Tian","doi":"10.1007/s11571-025-10401-3","DOIUrl":"https://doi.org/10.1007/s11571-025-10401-3","url":null,"abstract":"<p><p>Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder, and the existing clinical diagnosis mainly relies on subjective behavioral assessment and lacks objective biomarkers. This paper proposes a hierarchical deep learning architecture, VaeTF, incorporating community-aware mechanisms based on resting-state functional magnetic resonance imaging (rs-fMRI) data. VaeTF introduces a priori knowledge of the functional community, extracts localized features through a variational auto-encoder (VAE), captures global dependencies across brain regions using the Transformer module, and incorporates an improved pooling mechanism to enhance the expressive power and model generalization performance. Experimental results on the ABIDE database show that VaeTF achieves 71.4% accuracy in ASD and typically performs well in group classification tasks. Further feature weighting analysis reveals that VaeTF is capable of identifying local functional abnormalities and cross-network functional synergistic dysfunctions closely related to ASD, thereby uncovering the underlying neurobiological mechanisms. VaeTF not only improves the classification performance of ASD but also provides a new method and theoretical support for objective assessment and early diagnosis based on fMRI.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"29"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12847550/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146084549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ethical risks and considerations of the integration of Brain-Computer Interfaces with Artificial Intelligence.","authors":"Yuyu Cao, Hengyuan Yang, Yuhang Xue, Fan Wang, Tianwen Li, Lei Zhao, Yunfa Fu","doi":"10.1007/s11571-025-10380-5","DOIUrl":"https://doi.org/10.1007/s11571-025-10380-5","url":null,"abstract":"<p><p>In recent years, with the rapid development of Brain-Computer Interface (BCI) and Artificial Intelligence (AI) technologies, a trend of increasing integration between the two has emerged. In some practical applications, BCI has been combined with AI to enhance the overall performance of systems, including usability, user experience, and satisfaction, especially in terms of intelligent capabilities. However, this technological integration also introduces new or exacerbates existing ethical risks, such as neural privacy breaches, cross-domain misuse, and unclear system responsibility attribution. This paper discusses the novel or more severe ethical challenges arising from the fusion of BCI and AI technologies, as well as measures and strategies to address these ethical issues, calling for the establishment of more comprehensive ethical guidelines and governance frameworks. It is hoped that this paper will contribute to a deeper understanding and reflection on the ethical risks and corresponding regulations related to the integration of BCI and AI technologies.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"46"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12876491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146141208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From nonlinear neuronal dynamics to AI-optimized VLSI hardware: multiplier-free FPGA implementation of memristive FN-HR coupled neural networks for intelligent systems.","authors":"Wei Wu, Wensen Yu, Chaochao Wang, Mohammad Sh Daoud, Abdulilah Mohammad Mayet, Yisu Ge, Xiaotian Pan, Guodao Zhang","doi":"10.1007/s11571-026-10476-6","DOIUrl":"https://doi.org/10.1007/s11571-026-10476-6","url":null,"abstract":"<p><p>This paper proposes an innovative approach to translating the nonlinear dynamics of a memristive FitzHugh-Nagumo-Hindmarsh-Rose (FN-HR) coupled neuron model into an AI-optimized, resource-efficient VLSI implementation on FPGA platforms, advancing intelligent computing paradigms. The bidirectional memristive synapse coupling FN and HR neurons enables rich dynamic behaviors such as mixed-mode oscillations and chaos, which are harnessed to enhance adaptive machine learning and neural network training. A detailed dynamical analysis, including Lyapunov exponent spectra and synchronization properties, identifies parameter regimes suitable for AI applications. Nonlinear operators are approximated using quantized lookup tables and three-term sinusoidal expansions, achieving RMSE values of 0.0105 (FN) and 0.0114 (HR) while eliminating DSP usage. Synthesized on an AMD Zynq UltraScale+ ZCU104 FPGA, a 50-neuron network utilizes 5.3% LUTs and 7% BRAM, delivering 42 million neuron-updates per second at 210 mW. This work establishes a scalable, low-power platform for real-time AI-driven neuromorphic computing and intelligent adaptive control systems.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"113"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13243168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148210407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Memristor-based neuromorphic circuit for visual emotional non-associative learning.","authors":"Yingcong Wang, Shuai Shao, Yanfeng Wang, Junwei Sun","doi":"10.1007/s11571-026-10479-3","DOIUrl":"https://doi.org/10.1007/s11571-026-10479-3","url":null,"abstract":"<p><p>Most of the nonassociative learning neural networks based on memristor only consider habituation or sensitization and ignore the combination with emotions. According to biological characteristics, a nonassociative learning memristive neural network circuit of emotions induced by vision is designed in this paper. The circuit comprises the voltage control module, the synapse module, the potentiation of habituation module and the spontaneous recovery module. The functions such as habituation and spontaneous recovery, habituation of dishabituation, potentiation of habituation and sensitization are implemented by the circuit. Emotions through visual stimuli of different intensities are induced in designed circuit. The designed circuit is able to implement emotional habituation and sensitization like humans after processing the sensory signals from vision. At the same time, based on picture stimuli as inputs, PSpice simulations confirm the feasibility and accuracy of the proposed circuit at the circuit-simulation level. The proposed circuit may serve as a potential neuromorphic module for robotic affective perception and emotional learning, providing a reference for future research on brain-inspired emotional intelligence.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"114"},"PeriodicalIF":3.9,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13243158/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148210450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Olfactory Perception and Neural Rhythms: A Simulation-Based EEG Analysis Using Power Spectral Density Features.","authors":"Aadhitya S V","doi":"10.1007/s11571-026-10511-6","DOIUrl":"https://doi.org/10.1007/s11571-026-10511-6","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1007/s11571-026-10478-4.].</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"20 1","pages":"142"},"PeriodicalIF":4.5,"publicationDate":"2026-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13388599/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148561062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}