Search Results (847)

Against the global carbon neutrality target, predictive maintenance (PdM) of automotive engines represents a core technical strategy to advance the sustainable development of the automotive industry. Conventional single-modal diagnostic approaches for engine abnormal sound defects suffer from low accuracy and weak anti-interference capability. Existing multi-modal fusion methods fail to deeply mine the physical coupling between cross-modal features and often entail excessive model complexity, hindering deployment on resource-constrained on-board edge devices. To resolve these limitations, this study proposes a Physical Prior-Embedded Cross-Modal Attention (PPE-CMA) mechanism for lightweight multi-modal fusion diagnosis of engine abnormal sound defects. First, wavelet packet decomposition (WPD) and mel-frequency cepstral coefficients (MFCC) are integrated to extract time-frequency features from engine audio signals, while a channel-pruned ResNet18 is employed to extract spatial features from engine thermal imaging and vibration visualization images. Second, the PPE-CMA module is designed to adaptively assign attention weights to audio and image features by exploiting the physical coupling between engine fault acoustic and visual characteristics, enabling efficient cross-modal feature fusion with redundant information suppression. A rigorous theoretical derivation is provided to link cosine similarity with the physical correlation of engine fault acoustic-visual features, justifying the attention weight constraint (β = 1 − α) from the perspective of fault feature physical coupling. Third, an improved lightweight XGBoost classifier is constructed for fault classification, and a hybrid data augmentation strategy customized for engine multi-modal data is proposed to address the small-sample challenge in industrial applications. Ablation experiments on ResNet18 pruning ratios verify the optimal trade-off between diagnostic performance and computational efficiency, while feature distribution analysis validates the authenticity and effectiveness of the hybrid augmentation strategy. Experimental results on a self-constructed multi-modal dataset show that the proposed method achieves 98.7% diagnostic accuracy and a 98.2% F1-score, retaining 96.5% accuracy under 90 dB high-level environmental noise, with an end-to-end inference speed of 0.8 ms per sample (including preprocessing, feature extraction, and classification). Cross-engine and cross-domain validation on a 2.0T diesel engine small-sample dataset and the open-source SEMFault-2024 dataset yield average accuracies of 94.8% and 95.2%, respectively, demonstrating strong generalization. This method effectively enhances the accuracy and robustness of engine abnormal sound defect diagnosis, offering a lightweight technical solution for on-board real-time fault diagnosis and in-plant online quality inspection. By reducing engine fault-induced energy loss and spare parts waste, it further promotes energy conservation and emission reduction in the automotive industry. Quantified experimental data on fuel efficiency improvement and carbon emission reduction are provided to substantiate the ecological benefits of the proposed framework. Full article

Background: Hearing impairment affects a significant portion of the global population. The development of assistive technologies, particularly wearable devices, has been pivotal in mitigating these challenges. Methods: We present a systematic literature review on wearable assistive technologies for individuals with hearing impairment, analyzing 106 scientific articles identified from diverse sources (IEEE Xplore, ACM Digital Library, and Web of Science). Our comprehensive analysis is structured around device types, body locations, user study methodologies, sensory modalities, and application domains. Results: Findings reveal a strong emphasis on auditory and visual feedback, a mix of traditional hearing aids complemented by smart wearable devices, and experimental evaluations focusing on speech comprehension and usability. Visual analysis highlights a significant anatomical shift towards body-worn and wrist-worn haptic devices. While speech accuracy is rigorously reported, user-centric metrics like comfort and battery life are frequently neglected. Conclusions: Addressing these disparities, we propose the HEAR framework (Hybrid Architectures, Engaging Experiences, Adaptive Systems, Real-world Validation). This strategic roadmap advocates for a diversification of sensory outputs, more extensive longitudinal user studies, and the development of adaptive, multi-modal solutions that seamlessly integrate into users’ everyday lives. Full article

Tactile sensing is an important perceptual modality that enables robots to understand human contact behaviors. Estimating the fingertip contact angle based on tactile pressure distribution provides a simplified representation of the finger’s contact configuration and supports tactile-based perception in human–robot interaction. However, the relationship between tactile pressure distributions and fingertip contact configuration remains insufficiently understood. In this study, a simplified contact mechanics model was employed to investigate the relationship between tactile pressure characteristics and fingertip contact conditions. Theoretical analysis indicates that both the contact area and the contour dimensions of the pressure distribution are influenced by the contact angle and contact force, with varying sensitivities in different directions to these factors. Based on this theory, simplified finite element modeling of the fingertip and multi-subject experiments were conducted. The deformation behavior of the contact region under different contact angles and contact forces was analyzed. The experimental results were generally consistent with the theoretical analysis. Furthermore, contour descriptors were extracted from the tactile pressure distribution to establish a relationship model for estimating the fingertip contact angle, and the model’s accuracy was analyzed. The experimental results indicate that the extracted contour features exhibit systematic variations with contact angle, and the proposed method achieves a mean absolute error (MAE) of 2.73° and a root mean square error (RMSE) of 7.25°. These results demonstrate that tactile pressure contours provide an effective and computationally efficient cue for estimating fingertip contact configuration. This approach may help robots understand human behavior and has potential applications in human–robot interaction and robotic grasping. Full article

Fake news has caused significant harm and disruption across various sectors of society. With the rapid advancement of the Internet and social media platforms, both academic and industrial communities have shown growing interest in multimodal fake news detection. In this work, we propose MERF (Multimodal Evidence Retrieval and Forensics with LVLM), a unified framework for multimodal fake news detection that leverages the reasoning capabilities of Large Vision-Language Models (LVLMs). While LVLMs outperform traditional Large Language Models (LLMs) in processing multimodal content, our study reveals that their reasoning abilities remain limited in the absence of sufficient supporting evidence. MERF addresses this challenge by integrating web-based content retrieval, reverse image search, and image manipulation detection into a coherent pipeline, enabling the model to generate informed and explainable veracity judgments. Specifically, our approach performs cross-modal consistency checking, retrieves corroborative information for both textual and visual content, and applies forensic analysis to detect potential visual forgeries. The aggregated evidence is then fed into the LVLM, facilitating comprehensive reasoning and evidence-based decision-making. Experimental results on two public benchmark datasets—Weibo and Twitter—demonstrate that MERF consistently outperforms state-of-the-art baselines across all major evaluation metrics, achieving substantial improvements in accuracy, robustness, and interpretability. Full article

Scalability of the original test design for the box assembly with removable component (BARC) structure is of interest in the field of experimental structural analysis. As complex structures become increasingly difficult to test experimentally the larger they become, it is a common test practice to use a scaled-down representative model to understand the characteristics of these systems. For complex structures with non-rigid boundary conditions, there exists a gap in understanding the effects of scalability and welding. To gain a better understanding of the outcomes of this phenomenon, the dynamical effects of upscaling the dimensions of the BARC structure are analyzed. Three variations of the BARC are investigated experimentally and computationally, namely, the original BARC system, the BARC system upscaled at 1.5 times the size of the original model, and the BARC system upscaled at two times the size of the original model. The original BARC is tested to investigate the properties of the predetermined boundary conditions. Because the upscaled BARC systems are manufactured using welding, an investigation of the variability of results due to welding imperfections is conducted to evaluate its effects on the vibrational properties of the systems. The dominant resonant frequencies of the three systems are identified through an impact hammer test. The results are then compared to those obtained through finite element analysis, in which both datasets show agreement. In general, as the BARC system is upscaled, the resonant frequencies decrease without inducing mode switching for the selected boundary conditions, indicating that the larger systems are less rigid. To understand the trends of nonlinear softening/hardening and nonlinear damping, forced vibration experiments conducted in the form of true random and controlled stepped-sine excitations are performed. The results show that, in general, as the BARC system is upscaled, changes in the nonlinear properties of the system are induced. With regard to the effects of using welding to manufacture BARC systems, the results prove that variations in welding can lead to non-negligible variations in the vibratory responses of the BARC system. Additionally, several types of harmonic vibrational testing are investigated to understand the physics behind their varied responses. Overall, this work shows that upscaling the BARC system can be beneficial to researchers who require a less rigid system for investigations and that manufacturing of BARC systems by welding can be a cost-effective alternative to subtractive manufacturing. Full article

Background/Objectives: Advanced childhood cerebral X-linked adrenoleukodystrophy (cALD) is traditionally regarded as an irreversible terminal phase of neurodegeneration driven by inflammatory demyelination and axonal loss. Experimental evidence indicates that endogenous bioelectrical fields regulate central nervous system organisation, raising the possibility that functional network collapse in cALD may be biologically modifiable, even in the presence of persistent structural damage. This study examined whether longitudinal modulation of endogenous bioelectrical network organisation is associated with sustained clinical and neurophysiological stabilisation in advanced cALD. Methods: We performed a longitudinal observational analysis of two paediatric patients with advanced childhood cerebral X-linked adrenoleukodystrophy undergoing repeated neuroregenerative treatment cycles. Standardised scalp electroencephalography was recorded during spontaneous wakefulness and repeated over months under comparable vigilance conditions. Multimodal analysis included conventional EEG, quantitative EEG, independent component analysis, and standardised low-resolution electromagnetic tomography (sLORETA). Clinical function was assessed using validated measures of consciousness, swallowing, and voluntary motor behaviour. Results: Across patients, longitudinal recordings demonstrated sustained stabilisation of consciousness, swallowing, and voluntary motor function, accompanied by reproducible reorganisation of pathological brain rhythms. Delta and theta oscillations showed a consistent topographical redistribution from limbic–frontoinsular networks towards sensorimotor and parietal integrative cortices. These changes were observed across modalities and timepoints and are unlikely to reflect spontaneous fluctuation, delayed effects of haematopoietic stem cell transplantation, or state-dependent EEG variation. Conclusions: Advanced childhood cerebral X-linked adrenoleukodystrophy is associated with disorganisation of endogenous bioelectrical network activity. In this longitudinal analysis, large-scale network reorganisation was temporally associated with sustained clinical stabilisation, supporting a view of late-stage cALD as a dynamic disorder of network-level vulnerability, rather than a fixed terminal state. Full article

Continuous monitoring of sitting posture is crucial for ergonomic assessment and fatigue prevention, yet many existing approaches rely on vision-based systems or single-modality sensing that are limited in capturing spatial and temporal biomechanical dynamics. This paper presents a multimodal smart-skin sensing system for spatial and temporal ergonomic fatigue analysis in sitting postures. The proposed platform integrates 42 distributed pressure, temperature, and vibration sensors arranged in 14 trimodal sensing nodes embedded across anatomical seating and back regions to enable real-time multimodal acquisition of human–chair interaction patterns. The study introduces an analytical framework combining anatomical heatmap visualization, temporal evolution analysis, delta pressure mapping, fatigue intensity estimation, and hotspot detection to characterize dynamic pressure redistribution during prolonged sitting. Experimental evaluations were conducted using a biomechanical mannequin and a single human participant with identical anthropometric characteristics (165 cm height and 62 kg body mass) across nine seated conditions, including neutral sitting, reclining, leaning, periodic shifting, and vibration-induced motion. Each posture condition was recorded as a time-series session and segmented into temporal phases to analyze fatigue evolution during prolonged sitting. Statistical analysis of pressure redistribution dynamics indicates significantly higher pressure drift in human measurements compared with the mechanically stable mannequin baseline (p < 0.001). The proposed framework provides a scalable sensing approach for ergonomic monitoring, intelligent seating systems, and human–machine interface applications. Full article

Background/Objectives: Non-invasive radiofrequency (NIRF) therapy is increasingly used in physical rehabilitation. However, its efficacy across different lower limb pathologies remains unclear. This study aimed to evaluate the effects of NIRF on pain intensity and functional status in patients with musculoskeletal, neurological, and vascular conditions of the lower limb. Methods: A systematic review with meta-analysis of randomized controlled trials (RCTs) was conducted following PRISMA guidelines. The PubMed, Scopus, Web of Science, PEDro, and Cochrane Library databases were searched for RCTs comparing NIRF with sham, standard care, or other physical modalities. Methodological quality was assessed using the PEDro scale. Statistical analysis was performed using RevMan 5.4 to calculate Mean Differences (MD) and Standardized Mean Differences (SMD). Results: Nineteen RCTs comprising 911 participants were included in the qualitative review, of which 14 were included in the quantitative meta-analysis. The mean methodological quality was 7.78/10. The meta-analysis revealed favorable results for NIRF in reducing pain intensity compared to control groups (MD = −2.04; 95% CI = −3.14 to −0.93; p = 0.0003; I² = 96%). Functional outcomes also showed significant improvement in favor of the experimental group (SMD = −0.51; 95% CI: −0.85 to −0.16; p = 0.004; I² = 78%). Additionally, narrative synthesis indicated benefits for spasticity management (stroke) and limb volume reduction (lipedema/lymphedema). Conclusions: The results suggest a trend favoring NIRF for reducing pain and improving function in lower limb musculoskeletal conditions, particularly when used as an adjunct to active therapy. Evidence also suggests preliminary beneficial effects for neurological and vascular disorders. However, these findings must be interpreted with caution due to the high statistical heterogeneity observed, the broad diversity of the clinical populations included, and the wide variability in the treatment protocols applied. Further rigorous research with standardized protocols is highly recommended. Full article

Digital inspection technologies are increasingly being adopted in the construction industry to improve efficiency, decision quality, and sustainability performance. Mixed reality (MR) systems can reduce rework, minimise human error, and support resource-efficient inspection processes. However, empirical evidence on how perceptions of efficiency and safety influence professional acceptance of MR technologies remains limited. This study investigates the adoption of MR for construction inspection using an extended technology acceptance model (TAM) that incorporates task efficiency and safety perception as domain-specific human factors. A within-subjects scenario-based experimental design was applied, in which 103 construction professionals evaluated four inspection modalities: HoloLens MR, smart glasses, tablet-based systems, and traditional paper-based methods. Data was analysed using linear mixed-effects models, structural equation modelling, mediation analysis, and dominance analysis. The results show that HoloLens MR achieved the highest perceived efficiency and safety perception, while imposing the lowest cognitive demand. Perceived efficiency was a strong predictor of device preference and significantly predicted perceived usefulness (β = 0.322, p < 0.001), which fully mediated its effect on behavioural intention. Safety perception accounted for a substantial proportion of the variance in user evaluations (η² = 0.237). These findings indicate that sustainable adoption of MR in construction inspection depends on combined perceptions of efficiency gains, usability, and safety support. Full article

Wheel–rail coupled excitation introduces strong low-frequency modulation, random impact interference, and broadband background noise into the vibration system of locomotive gearboxes, causing early weak bearing fault features to become submerged and making traditional deconvolution methods insufficient for effective enhancement. To address this challenge, this study proposes an adaptive parameter optimization method for MCKD based on the weighted envelope spectrum factor (WESF). WESF integrates the Hoyer index, kurtosis, and envelope spectrum energy to jointly characterize sparsity, impulsiveness, and periodicity of signal components. By using WESF as the fitness function, the sparrow search algorithm (SSA) is employed to simultaneously optimize the key MCKD parameters L, T, and M, enabling optimal enhancement of weak periodic impacts. To further mitigate modal aliasing caused by wheel–rail excitation, the original signal is first adaptively decomposed using successive variational mode decomposition (SVMD), and modes with WESF values above the average are selected for signal reconstruction. The reconstructed signal is subsequently enhanced via SSA–MCKD, and fault characteristic frequencies are extracted using envelope spectrum analysis. Experimental validation using gearbox bearing data collected under 40, 50, and 60 Hz operating conditions shows that the proposed method achieves fault feature coefficient (FFC) values of 12.8%, 7.5%, and 7.2%, respectively—representing an average improvement of approximately 156% compared with traditional methods (average FFC of 3.6%). These results demonstrate that the proposed SVMD–WESF–SSA–MCKD approach can significantly enhance weak periodic impact features under strong background noise and wheel–rail excitation, exhibiting strong practical applicability for engineering implementation. Full article

Background: The early detection of autism spectrum disorder (ASD) is imperative for enhancing long-term developmental outcomes. Nevertheless, conventional screening methods depend on time-consuming, expert-driven behavioral assessments and are characterized by limited scalability. Automated video-based analysis provides a noninvasive and objective approach for the extraction of behavioral biomarkers from naturalistic recordings. Methods: A modular multimodal framework was developed that integrates motion-based video analysis and facial feature extraction for the purpose of ASD versus typically developing (TD) classification. The system is capable of processing RGB videos, skeleton/stickman representations, and motion trajectory streams. A comprehensive set of kinematic features was extracted, encompassing joint trajectories, velocity and acceleration profiles, posture variability, movement smoothness, and bilateral asymmetry. The repetitive stereotypical behaviors exhibited by the subjects were characterized using frequency-domain analysis via FFT within the 0.3–7.0 Hz band. Facial expression features derived from normalized face crops and landmark-based morphological descriptors were integrated as complementary modalities. The feature-level fusion process was executed subsequent to z-score normalization, and the classification procedure was conducted using a Random Forest model with stratified 5-fold cross validation. The implementation of GPU acceleration was instrumental in facilitating near real-time inference. Results: The motion-based ComplexVideos pipeline demonstrated a cross-validated accuracy of 94.2 ± 2.1% with an area under the ROC curve (AUC) of 0.93. Skeleton-based KinectStickman inputs demonstrated moderate performance, with an accuracy range of 60–80%. In contrast, facial-only models exhibited an accuracy of approximately 60%. The integration of multiple modalities through feature fusion has been demonstrated to enhance the robustness of classification algorithms and mitigate the occurrence of false negative outcomes, thereby surpassing the performance of single-modality models. The mean inference time remained below one second per video frame under standard operating conditions. Conclusions: The experimental results demonstrate that the integration of multimodal cues, including motion and facial features, facilitates the development of effective and efficient video-based screening methods for autism spectrum disorder (ASD). The proposed framework is designed to offer a scalable, extensible, and computationally efficient solution that can support early screening in clinical and remote assessment settings. Full article

Multimodal sentiment analysis (MSA) has emerged as a prominent research frontier, enabling a comprehensive understanding of complex human emotions through the synergistic integration of heterogeneous multimodal signals. However, most existing approaches rely on idealized signal distribution assumptions, overlooking the detrimental impact of demographic bias on representation fairness and fusion robustness. This paper proposes a Label-Guided Contrastive Decoupling Fusion (LGCDF) framework that enhances model robustness to demographic bias by learning and fusing multimodal representations invariant to Sensitive Attributes (SAs). Specifically, the proposed LGCDF framework employs gender-sensitive attribute information as modality-level constraints to achieve language-centric cross-modal sentiment alignment, which is accomplished by computing contrastive losses between text–audio and text–visual feature pairs. Moreover, it introduces a SA-guided contrastive decoupling mechanism that decomposes multimodal representations into SA-related and -independent components. The SA-independent components are subsequently fused through a cross-modal attention fusion strategy, thereby facilitating fair sentiment representation and enabling efficient and robust multimodal information fusion. Extensive experimental results demonstrate that the proposed LGCDF framework achieves superior performance in fair representation learning and cross-modal information fusion while maintaining strong robustness under varying gender distribution biases. Full article

To investigate the influence of asymmetric support clearances (caused by manufacturing and assembly tolerances in practical engineering) on the fretting wear behavior of steam generator heat exchange tubes, this study focuses on 2.25Cr-1Mo alloy heat exchange tubes and 405 stainless steel anti-vibration bars. A high-precision impact wear test platform with adjustable bilateral clearances was designed, and its dynamic reliability was verified by theoretical calculations, finite element simulations and modal tests. An experimental model with asymmetric clearances (0.15 mm and 0.20 mm) was established to study the nonlinear contact force response and wear evolution under excitation frequencies of 60 Hz, 65 Hz and 70 Hz. The results show that asymmetric clearances induce two contact modes: high-frequency “quasi-static friction” on the small-clearance side and intermittent “collision-rebound-flight” impacts on the large-clearance side. The system exhibits a clear excitation instability threshold that shifts backward with increasing excitation frequency. The 0.20 mm side triggers dynamic instability, with wear volume and rate increasing explosively (106.2% and 41.36% at 65 Hz) beyond the threshold. Microscopic analysis reveals that the wear mechanism on the large-clearance side transitions from mild abrasive wear to severe fatigue delamination when crossing the threshold, with surface morphology deteriorating sharply from faint contact spots to extensive spalling craters. This study clarifies the energy distribution mechanism and identifies the large-clearance side as the core “trigger” for system instability and catastrophic failure, providing a theoretical basis for nuclear heat exchange tube monitoring and anti-vibration design. Full article

Exposure to nature has been associated with benefits to human well-being, commonly evaluated using standardized psychological assessments and, more recently, neuroimaging modalities such as Electroencephalography (EEG), functional Magnetic Resonance Imaging (fMRI), and functional Near-Infrared Spectroscopy (fNIRS). This systematic review and meta-analysis addresses the following questions. (1) How is the impact of nature on well-being studied using psychological and neuroimaging modalities and what does it reveal? (2) What are the challenges and opportunities for the deployment of wearable neuroimaging modalities to understand the impact of nature on the brain’s health and well-being? A search on PubMed, IEEE Xplore, and ClinicalTrials.gov (March 2024) identified 33 studies combining neuroimaging and psychological assessments during exposure to real, virtual or imagined natural environments. Studies were analyzed by tasks, populations, neuroimaging modality, psychological assessment, and methodological quality. Most studies were conducted in Asia (n = 23 or 70%). Healthy participants were the dominant target population (70%). In total, 61% of the studies were conducted in natural settings, while 39% used visual imagery. EEG was the most common modality (82%). STAI (n = 8) and POMS (n = 8) were the most common psychological assessments. Only seven studies included clinical populations. Two separate meta-analyses of nine studies with explicit experimental and control groups revealed a significant positive effect of nature exposure on psychological outcomes (Hedges’ g = 0.30; p = 0.0021), and a larger effect on neurophysiological outcomes (Hedges’ g = 0.43; p = 0.0004), both with moderate-to-high heterogeneity. Overall, exposure to nature was associated with reductions in negative emotions in clinical populations. In contrast, healthy populations showed a more balanced psychological response, with nature exposure being associated with both increases in positive emotions and reductions in negative emotions. Notably, 88% of the studies presented methodological weaknesses, highlighting key opportunities for future neuroengineering research on the neural and psychological effects of nature exposure. Full article

Underwater wireless power transfer (UWPT) enables long-term deep-sea floor exploration by providing contactless energy replenishment for autonomous underwater vehicles (AUVs). However, conventional single-transmitter systems suffer reduced coupling and efficiency caused by high-loss underwater dielectrics and docking-induced perturbations. We propose a parallel-resonant dual-transmitter configuration based on the parity–time (PT) symmetric gain–loss-balanced modal framework. The proposed dual-transmitter single-receiver (DTSR) system forms a stronger and more symmetric field in the receiver than the single-transmitter baseline, counteracting the high-loss dielectric and improving the misalignment tolerance. According to the PT symmetry coupled-mode theory, we analyze how the quality factor and coupling strength determine the admissible PT-unbroken operating region over the docking-induced coupling range. An experimental prototype validates the analysis by comparing operating frequency and efficiency between DTSR and the single-transmitter baseline under distance (4.8–13.5 cm) and load (2.0–4.3 kΩ) variations. The results show that DTSR increases the critical coupling distance by 20–30% and reduces efficiency sensitivity to distance and load variations. These results suggest that the system can provide more robust and stable UWPT for AUV recharging under high-loss dielectric and perturbation, conducive to practically implementing AUV recharging in deep-sea operations. Full article