Search Results (5,659)

It is well-known that activation functions are crucial in determining spectral expressiveness, training dynamics, and reconstruction accuracy in implicit neural representations (INRs), which employ coordinate-based multilayer perceptrons to represent continuous signals. Despite showing excellent performance, sinusoidal activations, for example SIREN, are limited in their adaptability to diverse signal types due to their fixed harmonic structure. In this paper, we propose two novel periodic activation functions for INRs. (1) Harmonic generalizes sinusoidal activations by combining the fundamental frequency with learned second and third harmonics through per-neuron trainable amplitude coefficients, resulting in a richer spectral basis within the SIREN initialization framework. (2) PM-FINER (Phase-Modulated FINER) extends the variable-periodic FINER activation by embedding frequency modulation synthesis directly into the instantaneous phase, enabling data-driven phase distortion via a learnable modulation index and carrier ratio. We conducted comprehensive experiments spanning nine architectural configurations (including SIREN, WIRE, FINER, Gaussian, Harmonic, PM-FINER, and an additional direct comparison against the Subtractive Modulative Network (SMN)), using six natural images, three learning rate schedulers, and three random seeds, totaling 486 main training runs (534 runs total including an ${\omega }_0$ sensitivity sweep). Our evaluation combined peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and rigorous statistical analysis, such as paired t-tests, Wilcoxon signed-rank tests, Cohen’s d effect sizes, and Friedman rank tests. Under cosine annealing, Harmonic achieves a mean PSNR gain of 6.08 dB over SIREN and 2.57 dB over FINER (both $p<0.001$, Cohen’s $d>3.7$), while PM-FINER ranks statistically on par with Harmonic (mean difference $0.17$ dB, $p=0.36$), outperforming all of the other baselines. Compared with SMN, Harmonic outperforms it by $+7.94$ dB under cosine annealing (Bonferroni-adjusted $p<{10}^{-5}$, Cohen’s $d=12.3$), winning on all six images. Additionally, the Friedman ranking across the six images confirmed Harmonic (with mean rank $=1.33$) and PM-FINER (with mean rank $=1.67$), being the top two methods under cosine annealing. Our results establish interpretable multi-harmonic and phase-modulated activations as real alternatives to the existing INR activation functions. Full article

Accurate detection of field insect pests remains a significant challenge for precision agriculture due to the elongated and variable morphology of the target organisms, their frequent resemblance to complex background textures, and the long-tail distribution of species in natural datasets. While deep convolutional neural networks (CNNs) have advanced the field, they are often constrained by a limited effective receptive field and the entanglement of semantic and spatial features, which can lead to elevated false-positive rates and missed detections for low-contrast or rare targets. This paper introduces a novel detection framework that integrates state space modeling with multi-stream feature disentanglement to address these limitations. First, a visual state space module is employed as the backbone feature extractor, enabling the establishment of a global receptive field with linear computational complexity and thereby improving the perception of long-range morphological structures. Second, a Topological Feature Disentanglement Pyramid Network is proposed. This architecture explicitly separates feature representations into semantic and spatial streams and recombines them through graph convolutional interactions, which serves to suppress background interference and enhance localization precision. A meta-auxiliary detection head, active only during training, is introduced to amplify supervision signals for hard, low-contrast samples via adversarial gradient modulation. Furthermore, an implicit neural radiance field augmentation pipeline is used to generate physically consistent synthetic views of underrepresented pest classes, mitigating the negative effects of long-tail data distributions. Experimental evaluations on the public BAU-Insectv2 benchmark demonstrate that the proposed method achieves a mean average precision (mAP@0.5) of 81.8%, representing a 4.4-percentage-point improvement over a comparable baseline, while maintaining a compact parameter count of 2.33 M and an inference speed of 178.6 FPS. The framework exhibits particular efficacy in detecting elongated, minute, and rare pests, suggesting a promising technical approach for real-time, field-based pest surveillance in precision agriculture. Full article

Extremely low overlap leads to severely scarce local geometric correspondences across frame pairs. Pure geometric descriptors—encoding merely low-level shape signatures—inherently fail to impose sufficient constraints for reliable transformation estimation when matches become critically sparse, rendering registration fundamentally fragile. While recent red-green-blue-depth (RGB-D) attempts have explored visual augmentation, they predominantly rely on low-level chromatic statistics or shallow convolutional neural network (CNN) features, underutilizing the rich hierarchical semantics inherent in RGB imagery. We present V3Reg, a robust registration framework that pioneers the integration of large-scale vision foundation models (DINOv3) with adaptive cross-modal fusion. Specifically, we extract mid-to-deep semantic features (Layer 11) from DINOv3 to transcend low-level texture limitations, and propose a Task-Aware Channel-Wise Gated Adaptive Fusion (TACGAF) module that dynamically calibrates geometric-visual contributions via registration-error-guided channel-wise gating. To rigorously evaluate ultra-low-overlap robustness, we reconstruct RGBD-ZeroMatch, a benchmark with controllable overlap ratios ranging from 1% to 20%. Extensive experiments demonstrate that V3Reg achieves 99.6% Feature Matching Recall and 96.3% Registration Recall on standard benchmarks. Notably, it maintains 50.2% Registration Recall at merely 5% overlap, outperforming prior methods by over 18 percentage points. Full article

The prevention and treatment of cardiovascular disease (CVD) are undergoing a paradigm shift from a lipid-centric approach to a holistic metabolic perspective. Central to this evolution is the gut–fat–heart axis, a sophisticated three-dimensional communication network that integrates neural, endocrine, and immunometabolic signaling to regulate systemic lipid homeostasis. This manuscript systematically explores how the gut microbiota acts as a “metabolic organ” to remotely control host health through the production of bioactive metabolites and the modulation of molecular communication networks. At the physiological level, microbial products such as short-chain fatty acids (SCFAs) and modified bile acids regulate energy balance and lipid synthesis via the FXR-FGF15/19 axis and G protein-coupled receptors. Furthermore, gut hormones like GLP-1 and neuro-reflex pathways involving the vagus nerve provide rapid control over postprandial lipid clearance and feeding behavior. Conversely, pathological dysbiosis triggers the accumulation of harmful metabolites, such as trimethylamine N-oxide (TMAO) and lipopolysaccharides (LPS), which drive lipotoxicity, vascular inflammation, and “dysfunctional HDL” formation. These processes accelerate the progression of atherosclerosis, heart failure, and metabolic syndrome. Finally, the article outlines promising clinical translation strategies, including the development of TMA lyase inhibitors, next-generation probiotics, and the use of phytochemicals to reshape the microbial landscape. By decoding the molecular dialogues within the gut–fat–heart axis, this research provides a novel strategic vantage point for the integrated management of cardiovascular–kidney–metabolic (CKM) syndrome. Full article

Integrating neural and muscular signals into wearable robotics enables adaptive assistance during real-world tasks. This study proposes a multimodal neural interface for passive exoskeletons that combines electroencephalography (EEG) and electromyography (EMG) signals to classify motor gestures and estimate real-time cognitive and muscular effort, supported by finite-element-based biomechanical modeling. The system was implemented on the Ottobock Shoulder X passive exoskeleton© and validated using synchronous EEG–EMG acquisition via the LiveAmp platform©, a commercially available platform that was not developed specifically for this study. A hybrid CNN–LSTM architecture with deep fusion was employed to enhance robustness and responsiveness under realistic operating conditions. This study proposes a multimodal neural interface for the software-level adaptive assistance of passive upper-limb exoskeletons. While the physical device maintains a static mechanical profile, the proposed digital framework achieves adaptation by interpreting the user’s physiological and motor states. Ten healthy participants performed three functional tasks (screwing, moving the box, and lifting the box) under five assistive conditions. Finite element modeling (FEM) was used to characterize the torque–angle relationship of the passive exoskeleton and to support the interpretation of experimentally observed assistive torque profiles. The FEM model, used as an offline biomechanical analysis tool to aid in the interpretation of experimental results, has not been integrated into the real-time control loop. Results showed an average classification accuracy of 90%, an F1-score of 0.85, and inference latency below 180 ms, confirming real-time applicability. Cognitive indices such as the Cognitive Load Index (CLI) and Frontal Asymmetry Index (FAI) enabled adaptive modulation of assistance strategies without requiring active actuation, thereby preserving the device’s intrinsic passive nature. Comparative torque analysis highlighted the ergonomic benefits of passive systems in mid-range postures, while Finite Element Method (FEM) supported analysis clarified their limitations under highly dynamic loads compared to active solutions. These findings advance multimodal brain–machine interfaces for wearable robotics by integrating physiological sensing, deep learning, and biomechanical modeling, offering a safe, energy-efficient, and adaptive approach with potential rehabilitation, occupational ergonomics, and human–robot applications. Full article

Short-term traffic forecasting is a critical component of intelligent transportation systems. While deep learning architectures for this task have proliferated rapidly, the sensor-level data characteristics—zero-value prevalence, distributional heterogeneity, and cross-sensor correlation structure—that drive architecture-specific failure modes remain insufficiently understood, and their implications for evidence-based model selection in real deployments have not been systematically addressed. This study addresses that question through a sensor-network diagnostic framework applied to the METR-LA dataset (Metropolitan Los Angeles; 207 inductive loop detectors, 5-min resolution). The framework integrates systematic characterization of sensor data properties, a controlled benchmark of four representative architectures—Transformer, Spatio-Temporal Graph Convolutional Network (STGCN), Diffusion Convolutional Recurrent Neural Network (DCRNN), and Gated Temporal Convolutional Network (Gated TCN)—under a unified 12→3 prediction setting, and a novel per-sensor regression analysis that quantitatively links zero-value ratios to model-specific prediction errors across all 207 sensors. Building on these findings, this study further proposes Graph-Enhanced Transformer (GETFormer), a lightweight hybrid architecture that augments the Transformer with a single-hop Graph Convolutional Network (GCN) layer and a gated residual fusion module. The diagnostic findings and condition-dependent model-selection guidelines provide an empirically grounded foundation for principled hybrid architecture development in urban traffic sensing. Full article

Instance segmentation of surface defects is one of the research hotspots in the field of image segmentation. Due to limitations such as restricted receptive fields or the loss of fine-grained details, traditional neural network models still struggle to achieve sufficiently high-segmentation accuracy for surface defects. To meet the demand for high precision segmentation of surface defects on copper strips and plates in industrial quality inspection, this paper proposes a feature fusion segmentation network, termed DSFFNet. First, a dual-branch structure is designed in DSFFNet to fuse spatial-domain features with discrete cosine transform (DCT)-domain features, thereby obtaining richer feature information. Second, a 2D-DCT frequency feature extraction module is developed to more effectively capture the edge information of targets. Third, a triplet attention mechanism is introduced into the backbone network to form an attention-centric network. Finally, a bidirectional fusion module and a multi-scale fusion network are designed to capture finer-grained feature information. Comparative experiments conducted on the KUST-SEG-Dataset demonstrate that DSFFNet achieves 94.66% ± 1.07% (mask)mAP${}_{50}$ and 95.38% ± 0.06% (box)mAP${}_{50}$, outperforming several classic image segmentation methods. Furthermore, generalization experiments on the public NEU-Seg dataset yield a (mask)mAP${}_{50}$ of 86.27% ± 0.01%. The generalization results indicate that DSFFNet is robust to datasets with similar defect types. Full article

The durability of reinforced concrete is closely related to the transport behavior of water and aggressive ions within the complex nanoporous network of calcium silicate hydrate. While molecular dynamics simulations provide critical atomistic insights into these confined transport behaviors, their immense computational cost limits their scalability to complex structural and temporal domains. To overcome this bottleneck, we propose a novel, modular computational framework that synergizes high-throughput molecular dynamics with advanced graph neural networks. By rigorously learning the mapping between the local atomic environment and kinetic behaviors, our model achieves high-fidelity predictions of pore water diffusion coefficients in saturated calcium silicate hydrate while improving computational efficiency by three orders of magnitude compared to conventional force field methods. Furthermore, the model demonstrates strong transferability and can accurately capture localized nonlinear diffusion characteristics in multiparticle pore structures with rough surfaces. Building on the interchangeability of this framework’s core modules, we envision a visionary multiscale computational strategy that dynamically couples nanoscale atomistic predictions with mesoscale simulations. This work not only provides an ultrafast, highly accurate tool for screening transport properties across diverse structural configurations but also lays the groundwork for next-generation multiscale modeling of chloride ingress, ultimately advancing the design of resilient and sustainable reinforced concrete. Full article

In this study, we propose a biologically inspired Self-Organizing Map-based Artificial Visual System (SOM-AVS) for unsupervised orientation detection in static images. By combining a biologically motivated front-end visual processing module with an unsupervised SOM layer, the proposed system captures key characteristics of early-stage visual processing, including localized orientation-sensitive responses and structured feature organization. The model enables the structure of distinct orientation-related representations without requiring labeled data, forming organized response patterns across the neural map. Experimental results demonstrate robustness under various conditions, including noise corruption, restricted perceptual experience, and limited training samples. Furthermore, the model shows adaptive behavior when exposed to new stimuli after initial training, indicating its potential to reflect experience-dependent adjustments in representation. These findings suggest that SOM-AVS provides a useful framework for exploring self-organization mechanisms in artificial visual systems and for developing biologically inspired perception models. Full article

Background/Objectives: Brain dysfunction and symptoms can be improved with a sensory trick (ST) in more than 80% of patients with cervical dystonia (CD). This study aimed to investigate the functional connectivity (FC) of CD patients with different types of STs using functional near-infrared spectroscopy (fNIRS) and to explore the underlying neural mechanisms of STs. Methods: In this study, 35 CD patients (including 15 with classic STs, 15 with forcible STs, 5 with non-STs) and 29 healthy controls (HCs) underwent resting-state fNIRS. We subsequently analyzed FC differences between the groups and their correlations with clinical characteristics. Results: The grand-average FC was significantly higher in the non-ST group than in the forcible ST group. Furthermore, compared to the ST group, the non-ST group exhibited significantly increased FC, primarily involving the prefrontal and sensorimotor networks. In the forcible ST group, this hypoconnectivity was negatively correlated with disease severity scores. Conclusions: This study supports the concept of CD as a networkopathy, suggesting that both the severity and topology of cortical coherence impairment are modulated by the ST phenotype. Full article

The performance of the aircraft anti-skid braking system is critical to the ground operational safety of an aircraft. Conventional Pressure Bias Modulation (PBM) can suffer from deep skidding under low runway friction coefficients or low aircraft speeds. To address these issues, a composite control strategy based on Gaussian Quantum Particle Swarm Optimization (GQPSO) is proposed. This strategy employs the GQPSO algorithm for offline Proportional–Integral–Derivative (PID) parameter optimization, followed by real-time adaptive scheduling through a lookup table to accommodate varying speed domains and runway conditions. Simultaneously, by integrating the main-wheel dynamics model and friction characteristics, a runway identification function based on a Back Propagation Neural Network (BPNN) is designed to provide runway status information. The stability of the controller is verified via phase-plane analysis and Monte Carlo simulation. Subsequently, comparative Hardware-in-the-Loop (HIL) tests are conducted among PBM, PSO-PID, and the proposed GQPSO-PID controller under various runway conditions. The experimental results demonstrate that this composite controller can adapt to different speed domains and runway conditions, stably track the target slip ratio, effectively suppress skidding, and significantly improve braking efficiency, as well as exhibiting excellent robustness and control performance. Full article

Beef cattle behavior provides valuable information regarding their health status. Recently, deep convolutional network-based methods have achieved considerable results in beef cattle behavior recognition. However, their robustness under low-light or dark conditions remains limited, which restricts their application in real farm environments. To address this issue, this study constructed a realistic beef cattle behavior dataset in the dark, named Dark Beef Cattle Actions, which was collected under real nighttime farm conditions. The constructed dataset contains 1097 video clips collected from 30 beef cattle and covers 6 behavioral classes, including running, feeding, drinking, grooming, mounting, and fighting. Based on this dataset, we proposed a novel neural network architecture based on spatio-temporal dark enhancement and dynamic fusion for beef cattle behavior recognition in the dark. First, a spatio-temporal dark enhancement module was designed to improve dark video quality while preserving motion features. Second, a dynamic fusion module was introduced to adaptively fuse features from different branches and obtain more discriminative representations. In addition, a joint loss was adopted to optimize both dark enhancement and action recognition. Experimental results on the constructed dataset show that the proposed method achieved a weighted-averaged precision score of 88.47%, a weighted-averaged recall score of 80.18%, an accuracy score of 83.80%, and a weighted-averaged F1-score of 84.12%. Compared with other state-of-the-art methods, the proposed method achieved competitive performance in the recognition of night-time beef cattle behavior. These findings would provide support for intelligent livestock behavior recognition and monitoring in precision farming. Full article

Accumulation of aggregated amyloid beta (Aβ) species is a defining pathological hallmark of Alzheimer’s disease and is associated with extensive neuronal structural abnormalities. Mild cognitive impairment (MCI), a transitional stage between normal aging and the onset of dementia, is thought to represent an early phase of this pathological continuum. Studies at the cellular level suggest that the conditions impair the maintenance of established neuronal processes/networks and restrict their capacity for elongation or re-elongation. They may also attenuate the activation and process extension of quiescent neural progenitor or stem-like cells. These early cellular changes precede overt neurodegeneration in neural tissue and are likely to contribute to cognitive decline. They highlight the importance of in vitro models for identifying molecular targets involved in recovery from disease. In this study, we investigated the effects of aggregated Aβ (25–35) on neuronal process elongation and associated intracellular events in the N1E-115 cell line, a widely used model of neuronal differentiation. Addition of aggregated Aβ to cultured N1E-115 cells attenuated process elongation in a concentration-dependent manner. This morphological impairment was accompanied by decreased expression of neuronal differentiation markers. In contrast, at the half-maximal inhibitory concentration for process elongation, long-term cultured cells did not exhibit apparent process retraction or degenerative morphology. This mild but progressive impairment, without extensive cell death, is consistent with the cellular features of early-stage conditions rather than advanced Alzheimer’s pathologies. Similar results were observed in primary cortical neurons. Aβ also decreased the level of GTP-bound Ras and phosphorylation of the downstream mitogen-activated protein kinase/extracellular signal-regulated kinase (MAPK/ERK). Furthermore, treatment with hesperetin, a bioactive flavonoid compound, recovered the Aβ-induced inhibition of neuronal process elongation. Hesperetin also restored Ras and MAPK/ERK states, suggesting that its effects are associated, at least in part, with modulation of signaling through Ras and MAPK/ERK. Our findings suggest that hesperetin may serve as a useful molecular probe for modulating early cellular responses associated with Alzheimer’s disease-related pathology. This in vitro model might serve as a useful platform for investigating the molecular target candidates involved in recovery from nervous system disorders. Full article

Signals generated during tool wear are nonlinear, non-stationary, and easily affected by machining noise, which makes reliable tool condition monitoring difficult in intelligent manufacturing. To address this issue, this study proposes a tool wear degree classification framework, FCTrans-CA, that fuses time-domain and frequency-domain information through a lightweight cross-attention (CA) bridge. Fast Fourier transform (FFT) is first used to obtain frequency-domain representations. The raw time-domain signals are processed by a multi-scale one-dimensional convolutional neural network (MS-CNN) to extract temporal wear features, while the FFT-derived representations provide complementary spectral cues. These two feature streams are fused by an asymmetric CA module in which frequency-domain features guide the selection of wear-sensitive temporal features. K-means clustering is used to divide the measured flank wear (VB) trajectory of each tool into initial-, normal-, and severe-wear stages, thereby reducing subjectivity in label generation. Experiments on the PHM2010 milling dataset show that FCTrans-CA achieves 99.43% classification accuracy on 40,648 test samples. The results indicate that cross-domain feature interaction improves the separability of wear states and provides a reproducible data-driven route for tool wear monitoring. Full article

All-in-one weather-degraded image restoration aims to restore clean images from diverse weather-degraded observations (such as rain, haze, and snow) using a unified model. However, this topic remains challenging due to its ill-posed nature and the scarcity of large-scale paired training data. This article develops a novel semi-supervised learning framework, termed Semi-Supervised Degradation-Aware Learning (S²DAL), to adjust the feature space to align with the unified parameter space for all-in-one adverse weather removal. Specifically, the proposed S²DAL consists of two backbone networks: a Degradation-guided Histogram Transformer (DHformer) for weather-degraded image restoration and a Degradation-guided Convolutional Neural Network (DCNN) for degradation generation. A key component, the Degradation-guided Histogram Transformer (DHT) block, is designed to effectively capture intrinsic image features while suppressing diverse degradation interference through channel shuffling modulation, dynamic-range histogram self-attention, and dual-scale gated feed forward. Furthermore, a Monte Carlo-based Expectation-Maximization (EM) algorithm is introduced to jointly optimize latent variables and network parameters under both labeled and unlabeled data. Extensive quantitative and qualitative results on synthetic and real-world datasets consistently demonstrate that the proposed S²DAL achieves superior restoration performance compared to multiple state-of-the-art fully supervised and semi-supervised approaches. Full article