Search Results (723)

The tip-of-the-tongue (TOT) phenomenon is a transient state in which speakers momentarily fail to retrieve a known word despite preserved semantic knowledge and a strong sense of imminent recall. This review integrates cognitive and neural evidence with emerging neurochemical perspectives to develop a comprehensive biomedical framework for word-finding failures. Cognitive models of semantic–phonological transmission and interloper interference have been refined through structural, functional, and metabolic imaging to elucidate the mechanisms underlying TOT states across the lifespan. Functional neuroimaging implicates a left-lateralized fronto-temporal network, particularly the inferior frontal gyrus (IFG), anterior cingulate cortex (ACC), and temporal pole, in retrieval monitoring and conflict resolution. Structural MRI and diffusion imaging link increased TOT frequency to reduced integrity of the arcuate and uncinate fasciculi and diminished network efficiency. Proton magnetic resonance spectroscopy (¹H-MRS) introduces a neurochemical dimension, with studies of related language tasks implicating lower γ-aminobutyric acid (GABA) and altered glutamate concentrations in frontal and temporal cortices as potential contributors to slower naming and heightened retrieval interference. Together, these findings converge on a model in which transient lexical blocks arise from local disruptions in excitation–inhibition (E/I) balance that impair signal propagation within language circuits. By uniting behavioral, neuroimaging, and neurochemical perspectives, TOT research reveals how subtle perturbations in cortical homeostasis manifest as everyday cognitive lapses and highlights potential biomedical strategies to maintain communicative efficiency across the lifespan. Full article

Automatic sleep staging technology based on wearable photoplethysmography can provide a non-invasive and continuous solution for large-scale sleep health monitoring. This study accordingly developed a novel cross-scale dynamically coupled extended long short-term memory network (SleepXLSTM) to realize automatic sleep staging based on heart rate signals collected by wearable devices. SleepXLSTM models the relationship between heart rate fluctuations and sleep stage labels by correlating physiological features with clinical semantics using a knowledge graph neural network. Furthermore, an excitation–inhibition dual-effect regulator is applied in an improved multiplicative long short-term memory network along with memory mixing in a scalar long short-term memory network to extract and strengthen the key heart rate timing features while filtering out noise produced by motion artifacts, thereby facilitating subsequent high-precision sleep staging. The benefits and functions of this comprehensive heart rate feature extraction were demonstrated using sleep staging prediction and ablation experiments. The proposed model exhibited a superior accuracy of 91.25% and Cohen’s kappa coefficient of 0.876 compared to an extant state-of-the-art neural network sleep staging model with an accuracy of 69.80% and kappa coefficient of 0.040. On the ISRUC-Sleep dataset, the model achieved an accuracy of 87.51% and F1 score of 0.8760. The dynamic coupling strategy employed by SleepXLSTM for automatic sleep staging using the heterogeneous temporal representation of heart rate data can promote the development of smart wearable devices to provide early warning of sleep disorders and realize cost-effective technical support for sleep health management. Full article

This work investigates a data-driven approach for detecting structural damage in the wing of a Cessna 172 aircraft using reduced-order finite element (FE) models. This study focuses on the ability of machine learning methods to generalize across different structural conditions, aiming to support reliable Structural Health Monitoring (SHM) in aeronautical applications. The wing was first modeled in detail using the FiniteElement Method, followed by the development of a simplified FE model to reduce computational cost while maintaining accuracy. The similarity between the two models was evaluated through modal analysis and the Modal Assurance Criterion (MAC). Dynamic excitation representing turbulence effects was applied to simulate healthy and damaged conditions, producing acceleration data used to train one-dimensional and two-dimensional neural network classifiers. The 1D models processed raw vibration signals, while the 2D models used image representations of the same data. Both architectures were tested against results from the detailed FE model to assess their generalization capability. The 2D networks achieved higher classification accuracy, demonstrating improved robustness in identifying both minor and severe damage. The findings highlight the potential of combining reduced FE models with data-driven methods for efficient and accurate aircraft wing damage detection. Full article

Spinal Cord Injury (SCI) rehabilitation is undergoing a transformative shift with the emergence of new treatment strategies. Historically, treatment options were limited, and few offered meaningful recovery. Recent work in human models has shown that neuromodulation specifically with spinal cord epidural stimulation (SCES) paired with task-specific training (TsT) can partially restore motor function such as the ability to stand, step, and perform volitional movements. Despite these advances, the recovery has been shown to plateau even with the combination of therapies. The recovery process typically leads to partial rather than complete restoration of function. This limitation arises because current approaches primarily reactivate existing circuits rather than repair the disrupted pathways. Scar tissue and loss of descending and ascending connections remain major barriers to full recovery, restricting the transmission of neural signals. We argue that the next phase of research should be a synergistic strategy building upon the successes of neuromodulation and TsT while incorporating a regenerative therapy such as stem-cell-based interventions. Whereas neuromodulation and task-specific training increases excitability and reorganizes existing networks, stem cells have the potential to repair structural damage and re-establish communication across injured regions or facilitating the establishment of dormant pathways. The future of SCI recovery relies on multi-modal synergistic interventions that are likely to maximize long-term functional outcomes. In the current perspective, we summarized the basic findings on applications of SCES on restoration of sensory-motor functions. We then projected on current interventions on utilizing stem cell therapy intervention. We highlighted the outcomes of randomized clinical trials, and the major barriers for considering the synergistic approach between SCES and stem cell intervention. We are hopeful that this perspective may lead to roundtable scientific discussion to bridge the gap on how to conduct numerous clinical trials in the field. Full article

Millimeter-wave (mmWave) massive multiple-input, multiple-output (MIMO) systems are a cornerstone technology for integrated sensing and communication (ISAC) in sixth-generation (6G) mobile networks. These systems provide high-capacity backhaul while simultaneously enabling high-resolution environmental sensing. However, accurate channel estimation remains highly challenging due to intrinsic noise sensitivity and clustered sparse multipath structures. These challenges are particularly severe under limited pilot resources and low signal-to-noise ratio (SNR) conditions. To address these difficulties, this paper proposes HASwinNet, a deep learning (DL) framework designed for mmWave channel denoising. The framework integrates a hierarchical Swin Transformer encoder for structured representation learning. It further incorporates two complementary branches. The first branch performs sparse token extraction guided by angular-domain significance. The second branch focuses on angular-domain refinement by applying discrete Fourier transform (DFT), squeeze-and-excitation (SE), and inverse DFT (IDFT) operations. This generates a mask that highlights angularly coherent features. A decoder combines the outputs of both branches with a residual projection from the input to yield refined channel estimates. Additionally, we introduce an angular-domain perceptual loss during training. This enforces spectral consistency and preserves clustered multipath structures. Simulation results based on the Saleh–Valenzuela (S–V) channel model demonstrate that HASwinNet achieves significant improvements in normalized mean squared error (NMSE) and bit error rate (BER). It consistently outperforms convolutional neural network (CNN), long short-term memory (LSTM), and U-Net baselines. Furthermore, experiments with reduced pilot symbols confirm that HASwinNet effectively exploits angular sparsity. The model retains a consistent advantage over baselines even under pilot-limited conditions. These findings validate the scalability of HASwinNet for practical 6G mmWave backhaul applications. They also highlight its potential in ISAC scenarios where accurate channel recovery supports both communication and sensing. Full article

Brain–computer interface-based (BCI) training induces neural plasticity and promotes motor recovery in stroke patients by pairing movement intentions with congruent electrical stimulation of the affected limb, eliciting somatosensory afferent feedback. However, this training can potentially be refined further to enhance rehabilitation outcomes. It is not known how specific the afferent feedback needs to be with respect to the efferent activity from the brain. This study investigated how corticospinal excitability, a marker of neural plasticity, was modulated by four types of BCI-like interventions that varied in the specificity of afferent feedback relative to the efferent activity. Fifteen able-bodied participants performed four interventions: (1) wrist extensions paired with radial nerve peripheral electrical stimulation (PES) (matching feedback), (2) wrist extensions paired with ulnar nerve PES (non-matching feedback), (3) wrist extensions paired with sham radial nerve PES (no feedback), and (4) palmar grasps paired with radial nerve PES (partially matching feedback). Each intervention consisted of 100 pairings between visually cued movements and PES. The PES was triggered based on the peak of maximal negativity of the movement-related cortical potential associated with the visually cued movement. Before, immediately after, and 30 min after the intervention, transcranial magnetic stimulation-elicited motor-evoked potentials were recorded to assess corticospinal excitability. Only wrist extensions paired with radial nerve PES significantly increased the corticospinal excitability with 57 ± 49% and 65 ± 52% immediately and 30 min after the intervention, respectively, compared to the pre-intervention measurement. In conclusion, maximizing the induction of neural plasticity with an associative BCI requires that the afferent feedback be precisely matched to the efferent brain activity. Full article

Ergogenic aids have long attracted scientific interest for their potential to enhance neuromuscular performance, with caffeine being among the most extensively studied. While traditionally attributed to peripheral actions on skeletal muscle, accumulating evidence indicates that, at physiological doses, caffeine’s ergogenic effects are predominantly mediated by antagonism of central adenosine receptors. This antagonism leads to increased arousal, reduced inhibitory neuromodulation, enhanced corticospinal excitability, and altered motor unit recruitment and firing behavior. Importantly, the concentrations required to elicit direct effects on excitation–contraction coupling via ryanodine receptors exceed those compatible with human safety, rendering such mechanisms unlikely in vivo. This narrative review synthesizes contemporary neurophysiological evidence to propose that caffeine acts primarily by “tuning” motor system gain through central neurotransmitter modulation, rather than by directly augmenting muscle contractile properties. Additionally, we highlight unresolved questions regarding persistent inward currents, sex-dependent neuromodulatory influences—including the potential role of estrogen in regulating adenosine receptor expression—and the implications of repeated caffeine use during training for neural adaptation and motor control. Finally, we outline key methodological and conceptual directions for future research aimed at refining our understanding of caffeine’s neuromuscular effects in both acute and chronic contexts. Full article

Background: Aging is traditionally characterized by progressive structural and cognitive decline; however, increasing evidence shows that the aging brain retains a remarkable capacity for reorganization. This adaptive neuroplasticity supports cognitive resilience—defined as the ability to maintain efficient cognitive performance despite age-related neural vulnerability. Objective: To synthesize current molecular, cellular, neuroimaging, and electrophysiological neuromarkers that characterize adaptive neuroplasticity and to examine how these mechanisms contribute to cognitive resilience across aging. Methods: This narrative review integrates findings from molecular neuroscience, multimodal neuroimaging (fMRI, DTI, PET), electrophysiology (EEG, MEG, TMS), and behavioral research to outline multiscale biomarkers associated with compensatory and efficient neural reorganization in older adults. Results: Adaptive neuroplasticity emerges from the coordinated interaction of neurotrophic signaling (BDNF, CREB, IGF-1), glial modulation (astrocytic lactate metabolism, regulated microglial activity), synaptic remodeling, and neurovascular support (VEGF, nitric oxide). Multimodal neuromarkers—including preserved frontoparietal connectivity, DMN–FPCN coupling, synaptic density (SV2A-PET), theta–gamma coherence, and LTP-like excitability—consistently correlate with resilience in executive functions, memory, and processing speed. Behavioral enrichment, physical activity, and cognitive training further enhance these biomarkers, creating a bidirectional loop between experience and neural adaptability. Conclusions: Adaptive neuroplasticity represents a fundamental mechanism through which older adults maintain cognitive function despite biological aging. Integrating molecular, imaging, electrophysiological, and behavioral neuromarkers provides a comprehensive framework to identify resilience trajectories and to guide personalized interventions aimed at preserving cognition. Understanding these multilevel adaptive mechanisms reframes aging not as passive decline but as a dynamic continuum of biological compensation and cognitive preservation. Full article

This paper presents a simulation-based artificial neural network (ANN) model to predict bit-rock interaction forces during drilling. Drill string vibration poses a significant challenge in the oil, gas, and geothermal industries, leading to non-productive time and substantial financial losses. This research addresses the challenge of modelling bit-rock interaction excitation forces, which is crucial for predicting vibration and component fatigue life. For a PDC bit with multiple cutters, the cutter tangential velocities at various drilling speeds are calculated, and individual cutter forces are predicted with a two-dimensional discrete element method simulation in which a single cutter moves in a straight line through rock modelled as bonded particles. This data is then used to train an ANN model that characterizes the bit-rock force time series in terms of frequency, amplitude, and distribution of force peaks. Once inserted into a dynamic simulation of the drill string, the algorithm reconstructs the expected bit-rock force time series. A case study using a rigid segment axial and torsional drill string model was used to show that the bit-rock model outputs lead to the expected bit-bounce and stick-slip under certain drilling conditions. Next, the model was implemented in a 3D deviated well drill string simulation with non-linear friction and contact, generating complex stress states with good computational efficiency. Full article

Quantitative precipitation estimation (QPE) from radar reflectivity is fundamental for weather nowcasting and water resource management. Conventional Z-R relationship formulas, derived from Rayleigh scattering theory, rely heavily on empirical parameter fitting, which limits the estimation accuracy and generalization across different precipitation regimes. Recent deep learning (DL)-based QPE methods can capture the complex nonlinear relationships between radar reflectivity and rainfall. However, most of them overlook fundamental physical constraints, resulting in reduced robustness and interpretability. To address these issues, this paper proposes FusionQPE, a novel Physics-Constrained DL framework that integrates an adaptive Z-R formula. Specifically, FusionQPE employs a Dense convolutional neural network (DenseNet) backbone to extract multi-scale spatial features from radar echoes, while a modified squeeze-and-excitation (SE) network adaptively learns the parameters of the Z-R relationship. The final rainfall estimate is obtained through a linear combination of outputs from both the DenseNet backbone and the adaptive Z-R branch, where the trained linear weight and Z-R parameters provide interpretable insights into the model’s physical reasoning. Moreover, a physical-based constraint derived from the Z-R branch output is incorporated into the loss function to further strengthen physical consistency. Comprehensive experiments on real radar and rain gauge observations from Guangzhou, China, demonstrate that FusionQPE consistently outperforms both traditional and state-of-the-art DL-based QPE models across multiple evaluation metrics. The ablation and interpretability analysis further confirms that the adaptive Z-R branch improves both the physical consistency and credibility of the model’s precipitation estimation. Full article

This paper presents a modular mathematical model of neuronal activity, designed to simulate the dynamics of main molecular targets of antiepileptic drugs and their pharmacological effects. The model was developed based on several existing synaptic transmission models that capture cellular processes crucial to the pathology of epilepsy. It incorporates the primary molecular mechanisms involved in regulating excitation and inhibition within the neural network. Special attention is given to the dynamics of ion currents (Na⁺, K⁺, Ca²⁺), receptors (AMPA, NMDA, GABA_A, GABA_B and mGlu), and neurotransmitters (glutamate and GABA). Examples of simulations illustrating the inhibitory effects on synaptic transmission are provided. The numerical results are consistent with experimental data reported in the literature. Full article

Traffic state estimation (TSE) is crucial for intelligent transportation systems, as it provides unobserved parameters for traffic management and control. In this paper, we propose a novel physics-guided graph neural network for TSE that integrates traffic flow theory into an estimation framework. First, we constructed wave-informed anisotropic temporal graphs to capture the time-delayed correlations across the road network, which were then merged with spatial graphs into a unified spatiotemporal structure for subsequent graph convolution operations. Then, we designed a four-layer diffusion graph convolutional network. Each layer is enhanced with squeeze-and-excitation attention mechanism to adaptively capture dynamic directional correlations. Furthermore, we introduced the fundamental diagram equation into the loss function, which guided the model toward physically consistent estimations. Experimental evaluations on a real-world highway dataset demonstrated that the proposed model achieved a higher accuracy than benchmark methods, confirming its effectiveness in capturing complex traffic dynamics. Full article

This paper establishes an integrated framework combining self-induced vibration measurements with deep learning for vibration-based remaining useful life (RUL) prediction of mechanical frame structures in mobile robots. The main innovations comprise (1) a self-induced vibration excitation system that utilizes the robot’s drive wheels to generate controlled mechanical oscillations, using a five-sensor micro-electro-mechanical system (MEMS) accelerometer array to capture non-uniform vibration mode shapes across the robot’s structure, and (2) a processing pipeline for RUL prediction using accelerometer data and early feature fusion in two machine-learning models (long short-term memory (LSTM) and a convolutional neural network (CNN)). Our research methodology includes (i) modal analysis to identify the robot’s natural frequencies, (ii) verification platform evaluation, comparing low-cost MEMS accelerometers against a reference integrated electronic piezoelectric (IEPE) accelerometer, demonstrating industrial-grade measurement quality (coherence > 98%, uncertainty 4.79–7.21%), and (iii) data-driven validation using real data from the mechanical frame, showing that the LSTM model outperforms the CNN with a 2.61× root-mean-square error (RMSE) improvement (R² = 0.99). Our solution demonstrates that early feature fusion provides sufficient information to model degradation and detect faults early at a lower cost, offering a feasible alternative to classical maintenance procedures through combined hardware validation and lightweight software suitable for Industrial Internet-of-Things (IIoT) deployment. Full article

In industrial inspection and experimental data-acquisition scenarios, the accuracy and efficiency of digital tubes, which are commonly used display components, directly affect the intelligence of the system. However, models trained on data from specific environments may experience a significant drop in recognition accuracy when applied to different environments derived from impacts of various specific scenarios (e.g., temperature changes, changes in light intensity, changes in rate, and color contrast between equipment displays and environments, among others), which may affect model accuracy. To ensure recognition accuracy, we may need to collect data from specific environments to retrain the model for each specific environment, but manual annotation is often inefficient. To address these issues, this article proposes a solution integrating image processing with deep learning within specific scenarios, encompassing the entire workflow from data acquisition to model training. Employing image processing techniques to provide high-quality training data for models, we construct a semi-supervised adversarial learning framework based on an improved self-training algorithm. The framework employs the k-means clustering algorithm for stratified sampling preparation, adds the Squeeze-and-Excitation B Block to the Convolutional Neural Network backbone, and employs the Adversarial Generative Adversarial Network to generate adversarial examples for adversarial training, thus enhancing both classification accuracy and robustness. Full article

Although Adaptive Traffic Signal Control (ATSC) can alleviate congestion issues to some extent in traditional signal control systems, it still faces challenges in dealing with complex and dynamic traffic environments, such as difficulties in agent coordination, high computational complexity, and unstable optimization results. To address these challenges, this paper proposes a multi-agent deep reinforcement learning algorithm based on SENet, called SE-A3C. The SE-A3C algorithm enhances the feature extraction capability and adaptability of the neural network by introducing the Squeeze-and-Excitation (SE) module from SENet. This allows the model to focus more precisely on high-information features and capture interdependencies between different channels, thereby improving the model’s discriminative ability and decision-making performance. Additionally, the algorithm incorporates Nash equilibrium concepts to maintain a relative balance among agents during coordinated control, avoiding suboptimal competition between agents and significantly improving system stability and efficiency. Experimental results show that, compared to traditional A3C, DQN, and Ape-X algorithms, the SE-A3C algorithm significantly improves the efficiency of traffic signal control and the overall throughput of traffic flow in complex traffic scenarios. Full article