Cogn Neurodyn [JOURNAL]
Sun
200 papers
Dynamics study of double-column model and its application in epilepsy EEG.
Xu Y, Du Y, Xu X … +1 more , Wang Y
Cogn Neurodyn · 2025 Dec · PMID 40969785 · Full text
The human brain constitutes a highly complex nonlinear network, comprising billions of interconnected neurons capable of rapid and precise responses to diverse internal and external perturbations. Disruptions in neural c...
The human brain constitutes a highly complex nonlinear network, comprising billions of interconnected neurons capable of rapid and precise responses to diverse internal and external perturbations. Disruptions in neural connectivity or functional impairments within this network can lead to neurological disorders, including epilepsy. In this study, we propose an improved double-column neural model, derived from the Jansen-Rit (JR) framework, to investigate the effects of external stimuli on epileptiform electroencephalogram (EEG) across multiple cortical regions. Our model specifically targets the signal transmission delays and dynamic synaptic interactions within and between cortical columns. Simulations demonstrate that the improved double-column model successfully reproduces diverse EEG phenomena, including alpha rhythms and epileptiform discharges, across distinct cortical layers. When configured within the same cortical region, the model exhibits symmetry dynamics governed by two connection constants, which is predictable within the symmetry framework of the system, validating its plausibility. Notably, in inter-cortical double-column simulations, parametric modulation of coupling strengths generated varied prefrontal cortical epileptiform discharge patterns. Most significantly, applying targeted external stimuli to visual cortex columns induced a state transition in prefrontal cortex column activity, shifting from epileptic like discharges to stable alpha rhythm, which did not occur in the single-column experiment. These findings suggest that focal neuromodulation of specific cortical regions could serve as a potential therapeutic strategy for suppressing pathological activity in epilepsy.
Analyzing mental disorders with a CNN-GRU deep learning model on motor activity.
Gupta U, Bishnu PS, Kumar A … +3 more , Pandey AK, Kumar B, Kumari P
Cogn Neurodyn · 2025 Dec · PMID 40964443 · Full text
Mood disorders can significantly interfere with daily life, ranging from mild to severe, impacting relationships, work, and overall well-being. Globally, the scarcity of mental health resources and the stigma attached to...
Mood disorders can significantly interfere with daily life, ranging from mild to severe, impacting relationships, work, and overall well-being. Globally, the scarcity of mental health resources and the stigma attached to mental illness are significant obstacles. Existing approaches for mood disorder detection often rely on static clinical data or other modalities (e.g., imaging or questionnaires), and the potential of continuous motor activity data remains underexplored. Continuous wearable motor activity recordings represent an objective, non-invasive method that tracks an individual's behavioral patterns relevant to their mood states, while enabling ongoing monitoring in contrast to the episodic clinical assessments. Our primary goal in this paper is to employ a Deep Learning Model utilizing CNN-GRU architecture for analyzing motor activity sequences. Through rigorous experimentation on Depresjon datasets recorded via wrist worn actigraphy, our approach achieves an accuracy of 98.1%, surpassing the accuracy levels achieved by state-of-the-art techniques.
A hybrid deep learning architectures and feature extraction techniques for alzheimer disease recognition.
Nivethitha A, Manigandan T
Cogn Neurodyn · 2025 Dec · PMID 40949178 · Full text
Alzheimer's disease (AD) is one of the common forms of dementia and is tremendously increasing throughout the world. There are many biomarkers currently available to detect the AD progression. In AD, brain cell death occ...
Alzheimer's disease (AD) is one of the common forms of dementia and is tremendously increasing throughout the world. There are many biomarkers currently available to detect the AD progression. In AD, brain cell death occurs, leading to memory loss, impaired calculation ability, and difficulty in remembering recent events. Early detection of AD is crucial for managing the symptoms and providing effective medical intervention. AD symptoms usually develop gradually and become worse over time, and interfere with daily activities. Hence, this research proposes the Fuzzy scoring based ResNet-Convolutional Neural Network (FS-ResNet CNN) to discriminate AD patients having AD, Mild Cognitive Impairment (MCI), and cognitively normal (CN) using a hybrid deep learning architecture to leverage more complete spatial information from the ADNI data. Initially, the pre-processing is carried out using the z-score normalization. To reduce the time complexity and to select the prominent features, the Adaptive Grey Wolf Optimization Algorithm (AGWOA), harnessing the swarm intelligence, has been proposed. Finally, the Hybrid Deep Learning Architecture is applied for the classification of AD. Specifically, the proposed method introduces a novel method known as the Fuzzy Scoring to optimize the network performance. Furthermore, the proposed FS-ResNet CNN model is computationally efficient, less sensitive to noise, and efficiently saves memory. Experimental results demonstrate the effectiveness of the proposed method on the ADNI dataset, showing high classification accuracy of 97.89%, surpassing the other state-of-the-art methods.
Enhancing performance of SSVEP-based visual acuity via exploiting subject-specific information.
Zheng X, Wen B, Yan X … +2 more , Xu G, Zhang R
Cogn Neurodyn · 2025 Dec · PMID 40922979 · Full text
This study sought to enhance visual acuity assessment using steady-state visual evoked potentials (SSVEPs) through subject-specific training methods. SSVEPs were elicited from eleven subjects using the vertical sinusoida...
This study sought to enhance visual acuity assessment using steady-state visual evoked potentials (SSVEPs) through subject-specific training methods. SSVEPs were elicited from eleven subjects using the vertical sinusoidal gratings at six various spatial frequency steps, and then the classical approach of Oz single-channel, the spatial filtering method of canonical correlation analysis (CCA), and five subject-specific training methods, i.e., individual template-based canonical correlation analysis (IT-CCA), multi-way canonical correlation analysis (MwayCCA), multi-set canonical correlation analysis (MsetCCA), task-related component analysis (TRCA), and correlated component analysis (CORCA), were used as preprocessed methods for six-channel SSVEP signals. Subsequently, by comparing the SSVEP response characteristics, MwayCCA and TRCA were selected for further processing with Oz-channel and CCA as the controls. After carrying out the SSVEP visual acuity estimation criterion, Bland-Altman analysis showed an agreement of 0.201, 0.195, 0.188, and 0.196 logMAR between the subjective Freiburg Visual Acuity and Contrast Test (FrACT) and the objective SSVEP visual acuity for Oz-channel, CCA, MwayCCA, and TRCA, respectively, demonstrating that the subject-specific training method of MwayCCA showed the optimal performance in SSVEP-based visual acuity assessment. This study demonstrated that subject-specific training methods enhance SSVEP-based visual acuity assessment and recommended MwayCCA as the preferred approach for signal preprocessing in such assessments.
Redefining cognitive neurodynamics through transdisciplinary innovation.
Villa AEP
Cogn Neurodyn · 2025 Dec · PMID 40919009 · Full text
This paper introduces the concept of -a novel transdisciplinary paradigm designed to advance cognitive neurodynamics by integrating insights from molecular biology, computing, behavioral science, and clinical neuroscienc...
This paper introduces the concept of -a novel transdisciplinary paradigm designed to advance cognitive neurodynamics by integrating insights from molecular biology, computing, behavioral science, and clinical neuroscience. Contrasted with the traditional reductionist approach rooted in classical determinism, neuroheuristics emphasizes a flexible, problem-solving methodology for investigating brain function across multiple levels of complexity. The paper explores the epistemological interplay among genetic, epigenetic, and environmental factors in brain development and pathology. The neuroheuristic framework aims to elucidate complex cognitive phenomena-such as memory, decision-making, and creativity-by bridging bottom-up and top-down research strategies. By incorporating contemporary technologies and recognizing the brain's dynamic, nonlinear properties, neuroheuristics proposes a transformative shift in cognitive neurodynamics, enabling a deeper understanding of human cognition, disease mechanisms, and artificial intelligence. Its applicability is demonstrated through ongoing interdisciplinary research spanning neurophysiological disorders, computational modeling, and data-driven analytical techniques.
CAGCNet: generalized contrastive learning for person identification based on channel aggregated EEG features.
Wang X, Jin X, Kong W … +1 more , Babiloni F
Cogn Neurodyn · 2025 Dec · PMID 40904422 · Full text
Person identification method based on electroencephalograms (EEG) signals, or so called brainprint recognition is a novel way to distinguish identities with advantages of high security. However, existing methods neglect...
Person identification method based on electroencephalograms (EEG) signals, or so called brainprint recognition is a novel way to distinguish identities with advantages of high security. However, existing methods neglect the distribution difference between training and test data, and the large distance between projected features in the latent space makes the performance of the model degrade in the unseen domain data. In this paper, we propose channel aggregated based generalized contrastive learning framework, which combines multiple modules to overcome this challenge. To capture features from different granularities, we involve multi-scale convolution with channel attention block. In face of distribution of unseen domain, we introduce feature enhancement-based generalized contrast learning to improve the model generalization ability. In the generalized contrast learning module, taking the difficulty of reconstructing EEG signals into consideration, we augment the source domain data at the feature level to improve the generalization ability of the model on the unseen domain data. Extensive experiments on two multi-session datasets shows that our model outperformed other baseline methods, demonstrating its capability of better generalization performance to unseen domain.
Current status and challenges in electroencephalography (EEG)-based driver fatigue detection: a comprehensive survey.
Hassan J, Naziullah S, Rashid M … +4 more , Islam T, Islam MN, Islam MS, Mahmud S
Cogn Neurodyn · 2025 Dec · PMID 40904421 · Full text
Driver fatigue is a major contributor to traffic accidents, leading to increased fatality rates and severe damage compared to incidents involving alert drivers. Electroencephalography (EEG) has emerged as a widely used m...
Driver fatigue is a major contributor to traffic accidents, leading to increased fatality rates and severe damage compared to incidents involving alert drivers. Electroencephalography (EEG) has emerged as a widely used method for detecting driver fatigue due to its ability to capture brain activity patterns. This survey provides a thorough analysis of devices that detect driver fatigue using EEG, analyzing existing methodologies, challenges, and future research directions. This study was carried out according to PRISMA criteria. Relevant studies were retrieved from SpringerLink, Web of Science, IEEE Xplore, Scopus, and ScienceDirect, covering research published until February 16, 2025. After 267 publications were identified, 87 scientific papers were fully analyzed based on their relevance and contribution to the identification of driver fatigue using EEG. The review explores the article selection process, followed by an in-depth discussion of driver fatigue detection systems across various domains. Applications of Machine Learning (ML) in EEG-based fatigue evaluation are carefully reviewed, covering data collection, preliminary processing, feature extraction, categorization techniques, and performance assessment. Additionally, a comparative evaluation of cutting-edge research provides a comprehensive visualization of current research trends. This survey highlights the advantages, limitations, and future prospects of EEG-based driver fatigue detection, offering valuable insights for improving road safety. The findings contribute to the development of more reliable and real-time fatigue detection systems by addressing existing challenges and recommending potential solutions.
Happy mouth and fearful eyes: insights into emotional facial features from ERP.
Zhan B, Ren Z, Li S … +3 more , Li Y, Zhang M, He W
Cogn Neurodyn · 2025 Dec · PMID 40904420 · Full text
Facial expressions enable individuals to assess and understand emotions conveyed by others. Two crucial sources of expressive cues on the human face-the eyes and the mouth-capture attention and serve as reliable shortcut...
Facial expressions enable individuals to assess and understand emotions conveyed by others. Two crucial sources of expressive cues on the human face-the eyes and the mouth-capture attention and serve as reliable shortcuts for expression recognition. However, how the brain effectively extracts emotional information from these diagnostic features remains unknown. We investigated this issue using an electroencephalogram combined with a rapid serial visual presentation task in which participants were asked to recognize facial expressions (fear, happiness, and neutrality) from three formats (whole face, eye region, and mouth region). We found that participants recognized happy expressions from the mouth region more accurately than the other expressions, affirming the role of diagnostic features in facilitating bottom-up attentional capture. The isolated eye region with higher visual saliency induced the largest P1 component. Diagnostic features, such as a happy mouth and fearful eyes, elicited a larger N170 component compared to non-diagnostic features, such as a fearful mouth and happy eyes. Source analysis of N170 showed that the fusiform gyrus exhibited similar patterns in response to these emotional features. The P3 was effective in discriminating between different emotional content. When whole faces were visible, fearful and happy expressions were not distinguishable in the N170, while the P3 amplitude was larger when induced by fearful faces than by happy faces. Our study contributes to understanding how facial features play distinct roles in emotional perception, attention, and facial processing.
Astrocytic Kir4.1 channel and account for the transition dynamics between seizure-like discharges and spreading depression.
Zhang Z, Liu S
Cogn Neurodyn · 2025 Dec · PMID 40896411 · Full text
Both experiments and clinical studies have emphasized the complex interplay between astrocytic Kir4.1 channel and oxygen in regulating seizure-like discharges and spreading depression exhibited by neuron, particularly fo...
Both experiments and clinical studies have emphasized the complex interplay between astrocytic Kir4.1 channel and oxygen in regulating seizure-like discharges and spreading depression exhibited by neuron, particularly focusing on their transitional behaviors. However, how astrocytic Kir4.1 conductance and oxygen collaborate to regulate these transitional behaviors remains unclear. Here we proposed a three-compartment model that includes a neuron, an astrocyte, and their extracellular coupling space. This model was designed to explore the effects of astrocytic Kir4.1 conductance and oxygen concentration on the development of seizure-like discharges and spreading depression, as well as the intricate mechanisms underlying dynamical transitions. The simulation results demonstrated that Kir4.1 channel conductance and oxygen levels regulate various neuronal transition phenomena, including special seizures (SZ), tonic-seizures (TS), spreading depression, steady state (SS), tonic firing (TF) and mixed states (MS) involving seizure-like discharges and spreading depression, as defined in this study. And bifurcation analysis of a simplified model is employed to elucidate these internal transition mechanisms. The insights garnered from the proposed model can offer valuable perspectives into the functional intricacies of the brain and its pathological mechanisms.
Resting-state EEG gamma power predicts immediate and delayed recall in healthy adults.
Manippa V, Scaramuzzi GF, Scianatico G … +5 more , Cornacchia E, Spina AC, Taurisano P, Logroscino G, Rivolta D
Cogn Neurodyn · 2025 Dec · PMID 40881024 · Full text
OBJECTIVE: Resting-state EEG (rsEEG) provides insights into neural mechanisms underlying memory by reflecting intrinsic brain activity. This study tested whether rsEEG spectral power and theta-gamma phase-amplitude coupl...
OBJECTIVE: Resting-state EEG (rsEEG) provides insights into neural mechanisms underlying memory by reflecting intrinsic brain activity. This study tested whether rsEEG spectral power and theta-gamma phase-amplitude coupling (PAC) can predict memory performance in healthy adults. METHODS: Twenty-four healthy adults participated in two rsEEG recording sessions, followed by memory tests assessing multimodal Working Memory (WM), Immediate Recall (IR), and Delayed Recall (DR). The predictive value of rsEEG spectral power across frequency bands and theta-gamma PAC was analyzed in relation to memory performance. RESULTS: High-gamma (h-γ, 51-100 Hz) power significantly predicted IR and DR, accounting for over 43% of the variance. Temporal and frontal h-γ power positively correlated with memory performance, while posterior h-γ power showed a negative correlation. Temporal low-gamma (30-49 Hz) power positively predicted DR, and posterior and frontal theta power was significantly linked to IR. Other frequency bands showed marginal associations, and theta-gamma PAC had limited predictive value. CONCLUSIONS: Spontaneous gamma activity emerged as a key predictor of memory performance in healthy adults, highlighting the role of brain networks in encoding and retrieval processes. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11571-025-10313-2.
Graph-based feature learning methods for subject-dependent and subject-independent motor imagery EEG decoding.
Zhang S, Lu Z, Zhang B … +7 more , Zhang Y, Liang Z, Zhang L, Li L, Huang G, Zhang Z, Li Z
Cogn Neurodyn · 2025 Dec · PMID 40881023 · Full text
UNLABELLED: The significant intra-individual variability and inter-individual differences in scalp electroencephalogram (EEG) make it difficult to learn task-distinguishable features, posing a challenge for motor imagery...
UNLABELLED: The significant intra-individual variability and inter-individual differences in scalp electroencephalogram (EEG) make it difficult to learn task-distinguishable features, posing a challenge for motor imagery brain-computer interfaces. Current feature learning methods often produce an incomplete feature space, struggling to accommodate these variations and differences. Additionally, the weak discriminative nature of this feature space results in diminished EEG classification performance. This paper introduces novel graph-based feature learning methods to improve motor imagery decoding performance in both subject-dependent and subject-independent contexts. Firstly, construct a complete time-frequency-spatial-graph (TFSG) feature space. The original EEG signals are segmented into multiple time-frequency units using filter banks and sliding time windows. Spatial and brain network-based graph features are then extracted from each time-frequency unit and fused to create the TFSG features. This fused feature space is larger and more inclusive, effectively accommodating both intra- and inter-individual EEG variations. Secondly, learn a discriminative TFSG feature space. Two advanced methods are proposed. The first method employs a nonconvex sparse optimization model with log function regularization, which reduces bias in model estimation, thereby enabling more accurate learning of EEG patterns. The second method incorporates Fisher's criterion regularization into a sparse optimization framework to improve feature separability. A unified algorithmic framework is developed to solve the two new models. Our methods are validated on two motor imagery EEG datasets, achieving the highest average classification accuracies of 82.93, 68.52, and 71.69% for subject-dependent, subject-independent, and subject-adaptive evaluation methods, respectively. Experimental results demonstrate that the developed TFSG features significantly enhance both subject-dependent and subject-independent decoding performance, while the proposed regularization models improve the discriminability of the feature space, leading to further advancements in motor imagery decoding performance. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11571-025-10291-5.
Understanding face processing in autism spectrum disorder: insights from cognitive neuroscience.
Zhang L, Guan X, Wang D … +4 more , Wang J, Liu X, Liu S, Ming D
Cogn Neurodyn · 2025 Dec · PMID 40860492 · Full text
Faces convey critical information for social communication, such as identity, expression, and eye gaze. Unfortunately, individuals with autism spectrum disorder (ASD) often experience difficulties in processing this info...
Faces convey critical information for social communication, such as identity, expression, and eye gaze. Unfortunately, individuals with autism spectrum disorder (ASD) often experience difficulties in processing this information, and these deficits lead to their suffering from social interactions. Importantly, since face processing is a social skill developed during early childhood, its deficits may be an early symptom of ASD. In recent years, researchers have made great progress in identifying face processing impairments in individuals with ASD and exploring their biological underpinnings. In this paper, we reviewed the research progress on face processing impairments in individuals with ASD. Moreover, we mainly summarized the mechanisms proposed to underlie these impairments, including the changes in brain structure and function, atypical social cognition, and genetic variation. Finally, we discussed the factors leading to the inconsistent results of existing studies. Focused efforts to research the alterations and mechanisms of face processing might improve our knowledge of this complex, heterogeneous neurodevelopmental disorder. The ultimate purpose is to help clinical diagnosis and treatment, thereby improving the function of individuals with ASD.
Neurodynamic evidence reveals identity top-down influences emotional contagion of race.
Kong C, Wei Y, Hu P
Cogn Neurodyn · 2025 Dec · PMID 40860491 · Full text
Faces contain important information about emotion, race, identity, and age. A large body of research has illustrated that emotional contagion is influenced by race. The Categorization-Individuation Model (CIM) suggests t...
Faces contain important information about emotion, race, identity, and age. A large body of research has illustrated that emotional contagion is influenced by race. The Categorization-Individuation Model (CIM) suggests that situational cues (e.g., authority, subjectively important ingroup-outgroup) cause perceivers to shift their attention to identity-diagnostic facial characteristics, especially for other-race faces. The current study is designed to reveal whether identity can top-down influence emotional contagion across races, and the time course of this influence. We recruited 30 Chinese college students to participate in two experiments. Experiment 1 used dynamic emotional faces of Asians and Whites to assess emotional contagion in different races. Experiment 2, based on experiment 1, employed a minimal group paradigm assigning identity information to the racial faces. We used ERP analysis to predict the potential neural mechanism of the influence of identity on racial emotion contagion, and used representation similarity analysis (RSA) to explore the temporal dynamics of the representation of race, emotion, and identity. Our results showed that (1) in experiment 1, Whites produced stronger P1 amplitudes than Asians; in experiment 2, RSA results showed that the time course of representation of race was about 100 ms. (2) In experiments 1 and 2, Happy produced stronger P200 amplitude than Angry; Asians produced stronger P200 amplitude than Whites; The RSA results showed that the time course of representation of emotion and emotional contagion both began about 200 ms after face appearance. (3) In experiment 2, the P300 amplitudes showed a significant interaction of identity and race, and in different group conditions, the P300 amplitude in Asians was stronger than in Whites; however, in the same group conditions, the difference between the two races was insignificant. Results illustrate that identity information top-down influences the neural mechanisms of racial emotional contagion, and the effects are divided into at least three stages: (1) an early stage bottom-up perceptual categorization of other-race; (2) a middle stage emotional and individualization processing; and (3) a late stage top-down modulation by identity cues. Our study is the first to explain the neurodynamics of emotional contagion processing using the Categorization-Individuation Model.
Emotion recognition of CNN bidirectional long short-term memory with center and Softmax loss function (CNN-BiLSTM-CS) EEG -based.
Zhang X, Wang S, Li Y … +3 more , Xu K, Zhao R, Wei W
Cogn Neurodyn · 2025 Dec · PMID 40860490 · Full text
EEG signal is being widely used in the field of emotion recognition, which currently suffers from the difficulty of obtaining highly distinguishable features. We propose CNN-BiLSTM-CS for emotion recognition EEG-based, w...
EEG signal is being widely used in the field of emotion recognition, which currently suffers from the difficulty of obtaining highly distinguishable features. We propose CNN-BiLSTM-CS for emotion recognition EEG-based, which is to address the shortcomings of the traditional LSTM unidirectional propagation and Softmax supervised model in feature extraction. The method firstly employs BiLSTM to CNN, which can bilaterally obtain emotion feature information, and then introduces Center and Softmax to form a joint loss function to minimize the intra-class distance and maximize the inter-class distance, which can improve the recognition ability. DEAP and SEED dataset are employed to test the performance of CNN-BiLSTM-CS. The results of the average accuracy of valence and arousal are 94.22% and 92.16% on DEAP, which is increase by almost 6% to CNN-LSTM. The triple categorization accuracy of the SEED dataset is 95.45%. CNN-BiLSTM-CS significantly improves the recognition performance of deep features of EEG through the improved network structure and combined loss function.
CrossFormerGAN: enhancing pedestrian trajectory prediction in autonomous driving through advanced attention mechanisms and transformer architectures.
Nisha V, Rose GL, Gracewell J
Cogn Neurodyn · 2025 Dec · PMID 40860489 · Full text
Pedestrian trajectory prediction is essential for autonomous driving systems, aiming to foresee pedestrian movements and improve safety by anticipating their future positions and paths. Traditional methods often fail to...
Pedestrian trajectory prediction is essential for autonomous driving systems, aiming to foresee pedestrian movements and improve safety by anticipating their future positions and paths. Traditional methods often fail to capture the full complexity of pedestrian behavior due to their limited ability to account for subtle gestures, environmental factors, and social interactions, which critically affect movement patterns. This lead to the system making incorrect predictions, potentially leading to unsafe driving decisions. To address this, we propose CrossFormerGenerative Adversarial Network (CrossFormerGAN), a model designed to enhance real-time pedestrian trajectory prediction by introducing Gesture-Spatial Interactive Attention and an Adaptive Neighborhood-based CrossFormer transformer within the generator. Gesture-Spatial Interactive Attention combines Slot Attention and Regional Attention to accurately capture subtle movements and relevant context, ensuring the system thoroughly understands pedestrian intentions. Without this mechanism, important cues like a pedestrian's decision to cross the road could be missed, leading to less reliable predictions. The Adaptive Neighborhood-based CrossFormer transformer integrates an Adaptive Neighborhood Bias Module, which captures sudden changes in movement as well as ongoing movement while considering critical environmental factors like road layouts and traffic signals. This ensures that the model adapts to varying conditions in real-time, preventing potential misjudgements. The generator leverages these insights to encode trajectories of pedestrian into feature tensors and decode them into detailed trajectory predictions. Meanwhile, the discriminator uses Grouped Query Attention instead of multi-head attention to enhance its ability to recognize complex patterns by focusing on different aspects of the data, ensuring that the generated trajectories closely mimic real ones. This comprehensive setup allows the CrossFormerGAN to produce highly accurate and reliable pedestrian trajectory predictions, significantly reducing the risk of accidents. Simulation results confirm that our model outperforms existing methods, achieving the best performance with an ADE of 0.10 on the UCY dataset (ZARA 2 scenario) and an FDE of 0.18 on the ETH dataset (HOTEL scenario) when compared to other scenarios. The proposed method improves the general safety and dependability of autonomous vehicles in dynamic, real-world driving situations in addition to improving forecast accuracy.
Effects of physical exercise on cognitive and motor function in patients with Alzheimer's disease: a meta-analysis based on randomized controlled trials.
Gai Y, Dai X, Qian M … +5 more , Lin G, Pan P, Dai T, Luo Y, Su L
Cogn Neurodyn · 2025 Dec · PMID 40860488 · Full text
UNLABELLED: This study investigated the effects of physical activity on cognitive and motor function in Alzheimer's disease patients. This study searched randomized controlled trials (RCTs) from PubMed, EMBASE, Science D...
UNLABELLED: This study investigated the effects of physical activity on cognitive and motor function in Alzheimer's disease patients. This study searched randomized controlled trials (RCTs) from PubMed, EMBASE, Science Direct, and Web of Science databases up to October 2024. The main evaluation tools were Mini-Mental State Examination (MMSE), Timed Up and Go Test (TUG), 6-Minute walk test (6MWT) and Alzheimer's Disease Assessment Scale-cognitive subscale (ADAS-cog). Mean difference (MD) with 95% confidence interval (CI) were calculated. A total of 25 randomized controlled trials involving 2213 participants were included. The MMSE score in exercise group was higher than that in control group (MD = 2.24, = 0.002). Aerobic exercise (MD = 2.83, = 0.01) and combined exercise (MD = 3.09, = 0.03) in exercise group were significantly better than those in control group. There was no significant difference in strength exercise between the two groups (MD = 0.54, = 0.48). At low intensity (MD = 5.75, < 0.001) and moderate intensity (MD = 1.74, = 0.008), MMSE scores in the exercise group were higher than those in the control group, whereas high-intensity exercise showed no benefit (MD = 0, = 0.99). On the 6MWT scale, aerobic exercise scores were higher in the exercise group (MD = 51.55, = 0.03), while there was no significant difference between the two groups under combined exercise (MD = 62.76, = 0.45). The TUG scale (MD = -0.76, = 0.06) and the ADAS-cog scale (MD = -1.99, = 0.23) showed no significant difference between the two groups. Low intensity aerobic exercise improved cognitive and motor function in Alzheimer's disease patients, while strength exercise or high-impact exercise had little effect. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11571-025-10326-x.
Generalized stability and associative memory of delayed recurrent neural networks with variable external input.
Zhang F, Gao P, Huang T … +1 more , Zeng Z
Cogn Neurodyn · 2025 Dec · PMID 40843110 · Full text
The generalized stability and associative memory of delayed recurrent neural networks with variable external inputs are investigated in this paper. Based on the comparison principle, the monostability of normal different...
The generalized stability and associative memory of delayed recurrent neural networks with variable external inputs are investigated in this paper. Based on the comparison principle, the monostability of normal differentiable systems is established, which is extended to neural networks with variable external inputs. Furthermore, the coexistence of multiple equilibrium points in delayed recurrent neural networks is analyzed, and the number of stable equilibrium points is increased by extending the activation functions to enhance storage capacity. Several sufficient conditions are then derived to ensure the generalized stability of these equilibrium points, which extends and encompasses the classical concept of exponential stability. Moreover, an associative memory with high capacity is designed based on stable bipolar patterns with freely chosen components. Finally, the theoretical results and the design of associative memory are verified by two numerical examples.
Global exponential stability of periodic solutions for Cohen-Grossberg neural networks involving generalized piecewise constant delay.
Chiu KS, Jeng JC, Li T … +1 more , Córdova-Lepe F
Cogn Neurodyn · 2025 Dec · PMID 40843109 · Full text
This paper investigates the global exponential stability and periodicity of the Cohen-Grossberg neural network model with generalized piecewise constant delay. By applying Schaefer's fixed-point theorem, a sufficient con...
This paper investigates the global exponential stability and periodicity of the Cohen-Grossberg neural network model with generalized piecewise constant delay. By applying Schaefer's fixed-point theorem, a sufficient condition for the existence of periodic solutions in the model is established. Additionally, by constructing appropriate differential inequalities with generalized piecewise constant delay, sufficient conditions for the global exponential stability of the model are obtained. Finally, computer simulations are conducted to illustrate a globally exponentially stable periodic Cohen-Grossberg neural network model, thereby confirming the feasibility and effectiveness of the proposed results.
Motor imagery EEG classification method using 3D CNN and LSTM for rehabilitation application.
Hao Y, Cheng S
Cogn Neurodyn · 2025 Dec · PMID 40843108 · Full text
Due to the limitations in the accuracy and robustness of current EEG classification methods, applying motor imagery for practical Brain-Computer Interface applications remains challenging. Therefore, an EEG classificatio...
Due to the limitations in the accuracy and robustness of current EEG classification methods, applying motor imagery for practical Brain-Computer Interface applications remains challenging. Therefore, an EEG classification method with high accuracy and strong robustness is of significant importance. This paper proposed a method called 3D CNN and LSTM for Motor Imagery (3D-CLMI), which combines 3D CNN and LSTM network with attention to classify MI-EEG signals. This method combined MI-EEG signals from different channels into 3D features and extracted spatial features through convolution operations with multiple 3D convolutional kernels of different scales. At the same time, in order to ensure the integrity of the extracted temporal features of the MI-EEG signal, 3D-CLMI adopted a parallel structure to obtain spatial and temporal features respectively, and then combined the obtained features for classification. Experimental results showed that this method achieved a classification accuracy of 92.7% and an F1-score of 0.91 on BCI Competition IV 2a, which were both higher than the state-of-the-art methods in the field of MI tasks. Additionally, 12 participants were invited to complete a four-class MI task, and experiments on the collected dataset showed that our method also maintained the highest classification accuracy and F1-score. Our proposed method achieved the best results on both datasets, and we then demonstrated the effectiveness of each part of the proposed method through ablation experiments. Additionally, we designed a rehabilitation application system in a VR environment based on the proposed method, and the experimental results validated that it could assist patients with impaired hand motor function.
HWI encoding/decoding of a non-invasive HWI-BCI paradigm based on temporal variation abundance scale.
Ding P, Wang F, Zhao L … +2 more , Gong A, Fu Y
Cogn Neurodyn · 2025 Dec · PMID 40843107 · Full text
The performance of non-invasive Handwriting Imagery (HWI) input in Brain-computer interface (BCI) systems is highly dependent on the paradigms employed, yet there is limited research on interpretable scales to measure ho...
The performance of non-invasive Handwriting Imagery (HWI) input in Brain-computer interface (BCI) systems is highly dependent on the paradigms employed, yet there is limited research on interpretable scales to measure how HWI-BCI paradigms and neural encoding designs affect performance. This study introduces the "Temporal Variation Abundance" metric and utilizes it to design two classes of handwriting imagery paradigms: Low Temporal Variation Abundance (LTVA) and High Temporal Variation Abundance (HTVA). A dynamic time warping algorithm based on random templates (rt-DTW) is proposed to align HWI velocity fluctuations using EEG. Comprehensive comparisons of these experimental paradigms are conducted in terms of feature space distance, offline and online classification accuracy, and cognitive load assessment using functional near-infrared spectroscopy. Results indicate that HTVA-HWI exhibits lower velocity stability but demonstrates higher spatial distance, offline classification accuracy, online testing classification accuracy, and lower cognitive load. This study provides deep insights into paradigm design for non-invasive HWI-BCI and scales of neural encoding, offering new theoretical support and methodological insights for future advancements in brain-computer interaction.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe