Search Results (9,953)

Single-sensor-based fault diagnosis of rolling bearings often suffers from noise sensitivity, installation-dependent performance, and incomplete fault characterization. To address these limitations, this paper proposes a multi-task multimodal attention graph convolutional network (MTMAGNet) that integrates acoustic and vibration signals for bearing fault diagnosis. First, one-dimensional convolutional neural networks are used to extract modality-specific features. These features are then fused through a multi-modal attention mechanism to exploit the complementary information contained in the two signal sources. Based on the fused representations, a dynamic k-nearest neighbor graph is constructed to model relationships among samples, and a graph convolutional network is employed to learn discriminative structural features. Moreover, a multi-task learning scheme is introduced, in which fault classification serves as the primary task and modal classification is used as an auxiliary task to enhance feature learning and improve model generalization. Experimental results on a self-built acoustic–vibration test bench collected under three rotational speeds (1800 rpm, 2400 rpm, and 3000 rpm) demonstrate that the proposed method achieves high diagnostic accuracy and strong generalization performance under different fault conditions. Full article

This paper presents a novel system-oriented counterfactual deep learning framework, termed Hybrid Prediction–Intervention Neural Architecture (HPINA) for intelligent traffic accident risk prediction and proactive safety intervention in smart transportation systems. Unlike conventional data-driven models that rely solely on observational correlations, the proposed system integrates multi-domain data fusion, temporal deep representation learning, a continuous spatio-temporal risk field, and a latent-space counterfactual reasoning module within a unified decision-support architecture. The framework enables accurate prediction of traffic accident risk and simulation of “what-if” intervention scenarios to support real-time safety optimization in intelligent transportation environments. By leveraging heterogeneous inputs, including traffic dynamics, environmental conditions, road attributes, and temporal patterns, the system constructs a high-dimensional representation that captures complex nonlinear dependencies and evolving risk propagation across the network. A key innovation lies in the integration of a causal intervention mechanism and policy-guided decision layer, which jointly quantify intervention impact and identify optimal strategies for minimizing risk. The experimental results demonstrate that HPINA achieves a Test F1-score of 0.958 and an AUC of 0.989, outperforming strong baselines by up to 5.0% and 3.4%, while achieving a relative risk reduction of 0.091 and improved convergence stability with a validation loss of 0.042. These findings highlight the effectiveness of the proposed framework as an intelligent, scalable, and deployable system for real-world traffic safety management and smart city applications. Full article

Background: Lumbar disc herniation (LDH) is the most common etiological cause of low back pain (LBP). Objective and precise pain evaluation is of significant clinical value. Functional near-infrared spectroscopy (fNIRS) as a noninvasive neuroimaging modality, has been increasingly validated to reflect subjective pain perception through hemodynamic correlates. This study aimed to analyze the fNIRS changes in patients with LDH about to receive Unilateral Biportal Endoscopy and to further explore the feasibility of fNIRS as an objective biomarkers for clinical assessment of LDH. Methods: Resting-state fNIRS data were acquired from 67 preoperative LDH patients and 20 healthy controls (HC). Brain functional maps—including z-standardized fractional amplitude of low-frequency fluctuations (zfALFF) and seed-based functional connectivity (FC)—were extracted and quantified. Group-level comparisons were performed between LDH and HC groups across four predefined regions of interest; additionally, correlation analyses were conducted between fNIRS metrics and clinical assessment scores within the LDH cohort. Results: Compared with HC, LDH patients exhibited significantly altered zfALFF in the medial prefrontal cortex (mPFC): decreased amplitude at channel CH12 (t = −2.031, p = 0.045) and increased amplitude at CH21 (t = 2.462, p = 0.016). Whole-brain FC analysis further revealed widespread changes—particularly between the parietal somatosensory cortex and prefrontal regions. Among all tested FC–clinical indicator associations, 56 reached statistical significance after FDR correction (q < 0.05). VAS_ lumbar and SF-36_SF exhibited the highest number of significant connections. Conclusions: LDH patients with LBP exhibit notable alterations in prefrontal resting-state ALFF and FC between the parietal somatosensory cortex and prefrontal cortex relative to HC. Importantly, these neural alterations exhibit significant associations with both pain severity (VAS) and long-term health-related quality of life (SF-36), thereby strengthening their candidacy as neural correlates meriting prospective validation as objective, mechanism-informed biomarkers for clinical evaluation of lumbar disc herniation (LDH). Moreover, these findings highlight candidate neural targets for future longitudinal studies investigating early prognostic prediction and treatment response monitoring in LDH. Full article

Significant Wave Height (SWH) is a critical parameter for ocean observation. SWH retrieval using GNSS-R data faces challenges including difficult feature selection, insufficient temporal dependency modeling, and limitations due to single-modality data. This paper proposes a novel Multimodal Transformer Network (MultTransNet) to enhance the accuracy of GNSS-R SWH retrieval. To optimize the feature set, we designed an XGBoost-based iterative feature selection module that effectively eliminates redundant features. To capture complex temporal dependencies and global context, the model employs a Transformer encoder utilizing its self-attention mechanism. Furthermore, to overcome the constraints of single-modality data, we innovatively fused 2D DDM image data with 1D auxiliary parameters, enabling multi-source information integration. Simulation results show that the Transformer architecture reduces Root Mean Square Error (RMSE) by 8.91% and increases Correlation Coefficient (CC) by 4.05% compared to a conventional Deep Neural Network (DNN) model. More significantly, the proposed multimodal algorithm further improves retrieval accuracy by 27.05% (RMSE reduction) and 7.21% (CC increase) compared to its single-modality Transformer counterpart, demonstrating superior performance, especially in complex sea-state conditions. Full article

COPD remains a prevalent and debilitating respiratory condition, necessitating early and accurate diagnosis for optimal clinical intervention. In this study, we propose a novel deep learning-based diagnostic framework that employs the ECAPA-TDNN (Emphasized Channel Attention, Propagation and Aggregation—Time Delay Neural Network) architecture to classify respiratory sound signals from the ICBHI dataset. Originally designed for speaker verification, ECAPA-TDNN introduces channel attention and multi-scale feature aggregation, which we adapt for the first time to the domain of medical acoustic analysis. This architecture allows the model to effectively capture subtle and discriminative patterns in pathological breathing sounds, overcoming the limitations of conventional CNN-based methods. Our methodology integrates rigorous signal preprocessing, log-Mel spectrogram extraction, and data augmentation to enhance robustness and generalization. An Attentive Statistics Pooling mechanism is employed for temporal feature summarization, while Grad-CAM-based explainability is incorporated to improve the interpretability of the diagnostic predictions. The model is rigorously validated using a five-fold cross-validation scheme, achieving a mean validation accuracy of 96.8% with consistently high F1-scores and recall rates across all folds. Comparative analysis with prior methods highlights the superiority of our ECAPA-TDNN-based approach in terms of diagnostic precision, robustness, and potential clinical applicability. To the best of our knowledge, this is the first work to adapt ECAPA-TDNN for COPD detection from respiratory sounds, establishing a new benchmark in interpretable and high-performance acoustic-based respiratory disease screening. Full article

The prediction of metal fatigue life has evolved from classical empirical approaches to advanced, data-driven computational models. However, traditional methods struggle with large data scatter, complex variable-amplitude loading, and the cost of experimental testing. These limitations are particularly pronounced in additively manufactured (AM) components, which exhibit random porosity and are highly sensitive to process parameters. This review integrates classical fatigue mechanics with modern data-driven methodologies. It evaluates fatigue-life prediction for metallic alloys, welded assemblies, and AM materials. We review classical prediction tools, machine learning (ML) algorithms, deep learning architectures, and physics-informed neural networks (PINNs). ML models capture nonlinear degradation patterns but suffer from limited interpretability (“black-box” behavior) and are unable to extrapolate from small datasets. Embedding governing physical laws into PINNs helps mitigate these limitations. This approach enhances physical consistency, reduces training-data requirements, and strengthens extrapolation capability. In additively manufactured metals, defect location is often a more critical predictor of fatigue failure than defect size or morphology. To address data scarcity, we highlight the use of generative adversarial networks and transfer learning. Integrated models, combined with real-time structural health monitoring data, enable accurate, dynamic digital twins and preemptive fatigue prognosis. Full article

Reliable quantification of industrial energy savings requires accurate detection of non-routine events (NREs) that distort post-retrofit baselines. Conventional statistical and rule-based anomaly detection methods often misinterpret operational variability, leading to biased or overstated savings under the International Performance Measurement and Verification Protocol (IPMVP). This study develops a novel IPMVP-compliant hybrid deep learning framework that integrates a deterministic Deep Neural Network (DNN) for baseline modeling with stochastic architectures, namely the Factored Conditional Restricted Boltzmann Machine (FCRBM) and Generative Adversarial Network (GAN), to capture probabilistic reconstruction patterns. Their outputs are fused using a hybrid thresholding mechanism that balances detection sensitivity and specificity. Using high-resolution data from an industrial glove manufacturing facility, the hybrid DNN–FCRBM model achieved the best trade-off, demonstrating an accuracy of 94.3%, a precision of 91.1%, and a low false positive rate of 5.1%. This model validated 11.32% industrial energy savings (approximately 478,050 kWh), equivalent to 237 tonnes of CO₂ avoided. The integration of stochastic generative learning within a deterministic framework strengthens transparency, auditability, and IPMVP compliance, offering a scalable pathway for credible industrial energy savings verification. Full article

Continuous monitoring of railway bridges is essential for ensuring safety and operational reliability, considering aging mechanisms, rising traffic, and elevated speeds of railway vehicles. Frequently, traditional vibration-based approaches, including modal identification and data-driven diagnostic strategies, are strongly influenced by environmental and operational variability, requiring labeled damaged datasets or numerical simulations to provide reliable outcomes. However, the acquisition of complete and representative datasets for training neural networks in structural health monitoring remains a challenging task, particularly for large-scale civil structures such as bridges. In these cases, unsupervised learning approaches represent promising solutions. An unsupervised anomaly detection methodology for railway bridge monitoring based on a long short-term memory (LSTM) autoencoder (AE) trained exclusively on bridge accelerations under healthy structural conditions is proposed in the present work. Specifically, the acceleration responses are obtained from simulations made on a calibrated finite element model of the bridge, reproducing realistic train–bridge interaction scenarios. The multi-channel acceleration signals are reconstructed by the proposed LSTM AE to produce the Root Mean Square Error (RMSE) between measured and reconstructed acceleration responses as indicators of potential structural anomalies. A dual-threshold strategy is adopted for damage detection purposes, including a global threshold for identifying anomalies in the overall dynamic response and per-sensor thresholds derived from the healthy-condition RMSE distribution for detecting localized damages. Only healthy-condition data are required for employing the proposed technique, avoiding labeled damaged data for training purposes. The LSTM AE constitutes an effective and computationally efficient tool for anomaly detection and continuous structural health monitoring of railway bridges, as demonstrated by the obtained results, representing a promising alternative to classical modal-based approaches and existing deep learning-based methods. Full article

The phenomenon of CO₂ corrosion of downhole tubing is widespread in oil and gas extraction. Currently, there is a lack of applicable prediction methods for the corrosion rates of different metal tubing in the liquid phase CO₂ environment. To address this issue, this paper systematically investigates the anti-corrosion mechanisms and influencing factors of different metal casings and proposes a deep learning model combining convolutional neural networks and long short-term memory networks. Based on laboratory corrosion experimental data, the model extracts spatial features of parameters affecting the corrosion rate through CNN and captures their temporal dependencies through LSTM. This paper builds a pipe corrosion rate prediction model based on the TensorFlow framework and compares the prediction results with those of the traditional D-W empirical model and the SRV machine learning model. The results showed that the CNN-LSTM model maintained high prediction accuracy regardless of high or low chromium content, with R² reaching 0.83 and 0.94 respectively, solving the problem that existing models have difficulty effectively simulating complex corrosion behavior under flowing corrosive media conditions. The model was verified using the remaining wall thickness of the actual application casing in the field, and the accuracy was over 80%. The established prediction method can be extended to predict the corrosion rate of pipes under similar corrosion conditions. Full article

Modern cattle comprise two major evolutionary lineages: intensively selected commercial breeds and locally adapted native populations. To investigate their genomic divergence, we performed a comparative population genomic analysis by integrating whole-genome resequencing (WGS) data from multiple representative native breeds and major European commercial breeds. Population genetic analyses showed clear phylogenetic separation between the two groups, with distinct patterns of genetic diversity. Chinese native cattle exhibited generally higher nucleotide diversity (π), lower inbreeding levels, and geographically structured admixed ancestry. Comparative analyses of selection signatures identified 886 candidate selected genes in European commercial breeds, which were primarily enriched in pathways related to production traits, including protein turnover, reproductive regulation, lipid metabolism, and neuro-regulation. In contrast, 50 candidate selected genes in Chinese native cattle were significantly enriched in nervous system functions, particularly ligand-gated ion channel activity and chloride transport (e.g., GRID2, GLRA2/4, GABRD), suggesting neural/ionic regulation may contribute to local adaptation alongside other polygenic mechanisms. Additionally, the two groups also differed in patterns of deleterious mutation load. These findings indicate partially distinct evolutionary trajectories between “production-optimized” and “environment-adapted” cattle and highlight the value of conserving the genetic diversity and adaptive alleles of Chinese native cattle. Full article

Deep-learning-based vulnerability detection has made substantial progress, but two limitations remain prominent. Sequence-based methods linearize source code and thus weaken the explicit modeling of control-flow and data-flow dependencies. Graph-based methods preserve program structure, yet conventional graph neural networks still have difficulty capturing long-range interactions in large code property graphs (CPGs). In addition, standard CPGs usually lack explicit variable semantics and security-critical node roles, which limits their ability to represent vulnerability-relevant program behavior. To address these issues, we propose SV-GEN, a vulnerability detection framework that combines large-language-model-driven semantic enhancement with hybrid sequence-graph learning. The novelty of SV-GEN lies in introducing a semantically enriched code property graph, termed Sem-CPG, which augments conventional CPGs with variable semantic roles and security-oriented node labels, and in coupling this representation with an adaptive fusion mechanism over structural and sequential views. Specifically, we use a large language model as an external semantic annotator to assign variable roles and identify source, sink, and sanitizer nodes, and then encode the resulting Sem-CPG with a Graph Transformer while modeling the code sequence with GraphCodeBERT. A learnable gating module is further used to adaptively fuse the graph-level and sequence-level representations for final prediction. Experiments on Devign, ReVeal, and DiverseVul show that SV-GEN achieves competitive or superior overall performance across benchmarks, with particularly strong improvements on the large and highly imbalanced DiverseVul dataset. Full article

Memory is generally thought to be stored within centralized neural circuits. However, whether learned behaviors can persist in the absence of a brain remains unresolved. Planaria (Girardia spp.) possess a primitive cephalic ganglion and a remarkable capacity for regeneration, providing a unique system to examine non-cephalic memory retention. The primary aim of this study was to determine whether sucrose-induced conditioned place preference (CPP) is retained in posterior, brainless planarian fragments. Planaria were trained using a Pavlovian conditioning paradigm in which an initially unpreferred surface was paired with a 10% sucrose solution, resulting in a robust shift in surface preference. Following amputation, anterior fragments containing the cephalic ganglion as well as posterior fragments lacking the brain preserved the conditioned preference, demonstrating that reward-associated memory is stored even outside the cephalic nervous system. As a secondary objective, we examined the role of dopaminergic reinforcement using a D1 dopamine receptor antagonist during training. While antagonist-treated planaria failed to develop a CPP, posterior fragments from these amputated planaria likewise showed no conditioned preference, indicating that dopamine-dependent signaling is essential for sucrose-associated memory formation across the body. These results provide support for the hypothesis that reward-associated memory in planaria is distributed beyond the brain and can be modulated by dopaminergic pathways, highlighting the utility of this model for exploring fundamental mechanisms of reward, memory, and potential pharmacological interventions. Full article

Large language models (LLMs) seem to demonstrate human-like understanding and generalization of language content. These arise from the capabilities of the models to memorize and generalize the training content. In this paper, we review the recent literature and theories on the mechanisms in self-attention neural networks. We also report three computational experiments that give insights into the underlying mechanisms and capabilities of the models. We also report three computational experiments showing that memorization capacity in compact transformers can be empirically linked to architectural parameters, that structured domain knowledge can be retained in small decoder-only models, and that in-context abstraction requires sufficient architectural depth. These findings suggest that the current models are superfluous for many specific applications, especially in on-edge use cases. A better understanding of application requirements and architecture details can be expected to help in building new LLM architectures that can be efficiently implemented on dedicated on-edge circuits. Full article

Objectives: This systematic review aims to evaluate the effects of Edible Bird’s Nest (EBN) extract on cognitive function and neuroprotection in animal models and systematically review the relevant research evidence. Methods: A systematic search was conducted in the databases of PubMed, Scopus, Web of Science, EMBASE, Taylor Francis, Wiley, and Cochrane Library for relevant research published up to October 2025. Search terms included “Edible Bird’s Nest”, “Bird’s Nest Extract”, “EBN”, “Swiftlet nest”, “Collocalia”, “Cognitive”, “Memory”, “Learning”, “Neuroprotection”, “Brain”, “Neural”, “Neurotrophic”, “Animal”, “Mice”, “Mouse”, “Rat”, “Rats”, “In vivo”, and “Model”. Two researchers independently screened all the relevant articles, extracted relevant data, and assessed the quality of included studies using the Systematic Review Centre for Laboratory Animal Experimentation (SYRCLE) risk of bias assessment tool. Results: This systematic review included 11 animal studies, primarily focused on rodent models. Preclinical evidence suggests that Edible Bird’s Nest extract (EBN) may improve performance in several cognitive function tests. Animals treated with EBN appeared to show enhanced spatial memory and learning abilities in experimental settings. At the molecular level, the EBN treatment group showed improved antioxidant capacity and reduced neuroinflammation. Additionally, EBN promoted the expression of neuroprotective factors and enhanced synaptic plasticity. Research suggests that appropriate doses of EBN may have beneficial effects on cognitive enhancement and can alleviate cognitive dysfunction and neuropathological changes. Conclusions: Preliminary evidence from this systematic review suggests that EBN appears to show protective and potentially enhancing effects on cognitive function in animal models. EBN works through multiple mechanisms, including antioxidant and anti-inflammatory effects, as well as promoting the expression of neurotrophic factors and synaptic plasticity. These findings provide initial support for further investigation of EBN as a potential neuroprotective agent and cognitive enhancer. However, there is heterogeneity and methodological limitations in the research, and more standardized studies and preclinical translational research are needed to further validate the application potential of EBN in neuroprotection. These results provide an important reference for developing EBN-based functional foods and supplements for the prevention and adjuvant treatment of cognitive impairment and neurodegenerative diseases. Full article

This paper introduces the Quantum-Inspired Impulsive Continuous Hopfield Network (Q-ICHN), a novel hybrid control framework designed to handle non-smooth, high-energy perturbations in nonlinear dynamical systems. Standard Continuous Hopfield Networks (CHNs) rely on sigmoidal activation functions that are prone to gradient saturation, which leads to an insufficient corrective response when the system undergoes large deviations from equilibrium. To overcome this shortcoming, the proposed Q-ICHN adopts a wave-packet-based activation function grounded in the stationary Schrödinger equation, yielding a non-monotonic and oscillatory activation profile that sustains effective compensatory dynamics across a broad range of states. Furthermore, the proposed framework incorporates Madelung’s quantum potential into the control architecture, thereby enabling a fundamental reshaping of the system’s energy landscape. Specifically, this induces a tunneling-like mechanism that allows the system to circumvent local minima and rapidly recover from impulsive disturbances, manifested as a sharpened attractor structure in the phase-space domain. Together, these properties yield enhanced convergence behavior and improved robustness over traditional neural control approaches. To rigorously assess its merits, the performance of the Q-ICHN is evaluated through a large-scale benchmark involving 20 established control methods, including Sliding Mode Control (SMC), Model Predictive Control (MPC), and Backstepping. The experimental results obtained across 20 heterogeneous scenarios demonstrate that the proposed model achieves a 48% reduction in Mean Squared Error (MSE) relative to the classical ICHN. In addition, the Q-ICHN exhibits improved smoothness, reflected in a 30% reduction in jerk with respect to high-gain robust controllers, and enhanced reliability, validated by superior spectral purity and a 34% reduction in integrated variance under stochastic perturbations. Collectively, these results underscore the potential of quantum-inspired activation mechanisms to favorably balance control responsiveness and harmonic stability, providing a robust framework for handling both continuous dynamics and impulsive effects. Full article