Search Results (980)

In low-light, occluded, and cluttered environments, single-modality RGB detectors are prone to false positives and missed detections. While infrared (IR) imaging provides relatively stable target visibility under poor illumination, it lacks texture and color information and is susceptible to background thermal noise and imaging variations. To address these limitations, this paper proposes an RGB–IR object detection network, named MCF-YOLO, consisting of three core components. First, the Cross-Modal Hierarchical Fusion (CMHF) module performs stage-wise alignment and fusion on multi-scale features, jointly modeling RGB texture details and IR thermal responses to exploit the structural and semantic complementarity between the two modalities. Second, the Soft Attention Regularization based on Attention Prior (SAR-AP) module derives attention priors from IR features to impose soft constraints on cross-modal attention maps. This mechanism helps the network maintain attention on target-relevant regions, thereby suppressing attention drift caused by low-light noise and complex backgrounds. Third, the Small-Object-Sensitive Detection Head (SOS-Head) processes high-resolution features to strengthen the representation of small targets, improving detection capability in long-range and occluded scenarios. In evaluations on two RGB–IR benchmarks—M3FD and VEDAI—MCF-YOLO achieves improvements of 2.7% in mAP@0.5 and 1.1% in mAP@0.5:0.95 on M3FD, and 5.4% and 4.4%, respectively, on VEDAI. These results suggest that consistency-guided cross-modal fusion and high-resolution small-target modeling are beneficial for RGB–IR detection in low-visibility and cluttered scenes. Full article

Self-healing biomaterials have attracted significant attention due to their ability to restore structural integrity, extend material lifetime, and reduce maintenance costs without external intervention. In this study, Polyvinyl Alcohol/Graphene Oxide/Eggshell Particle (PVA/GO/ESP) composite hydrogels were synthesized via a freeze–thawing method and characterized using XRD, SEM/EDS, and FTIR analyses. The effect of ESP incorporation on the self-healing and mechanical properties of the hydrogels was systematically investigated. Tensile test results demonstrated that incorporation of 1 wt% ESP improved the tensile strength up to 0.326 MPa while maintaining high strain capacity. Healing efficiency values calculated from recovered tensile strength showed approximately 69%, 47%, and 67% recovery for PVA/GO, PVA/GO/ESP (0.5%), and PVA/GO/ESP (1%) hydrogels, respectively. The developed hydrogels demonstrated rapid self-healing behavior at room temperature without external stimuli. These findings suggest that ESP-reinforced PVA/GO hydrogels may serve as promising candidates for future biomaterial and soft tissue engineering studies. The developed hydrogels demonstrated enhanced tensile strength, rapid self-healing behavior, and promising swelling properties, indicating their potential use in soft tissue engineering and biomaterial applications. Full article

Empirical logic (EL) is a bio-inspired soft computing approach to rule-based decision-making that emphasizes intuitive, experience-based reasoning. While its theoretical foundations have been established in previous work, its practical applicability and accessibility have so far received less attention. This paper addresses this gap by providing two representative application examples from distinct domains: control engineering and cluster analysis. The first example demonstrates the use of EL for the speed control of a DC drive, highlighting its ability to achieve competitive dynamic performance with a small number of intuitive rules. The second example introduces a novel approach to cluster analysis, where cluster structures emerge from the collective interaction of EL rules rather than from the optimization of a predefined objective function. In addition, the paper emphasizes the availability of publicly accessible software realizations of EL, including a Maple-based prototype and a Python framework, which enable direct experimentation and practical use. By combining illustrative applications with executable tools, the paper aims to facilitate the transition from conceptual understanding to practical deployment and to support further exploration of EL in applied soft computing contexts. Full article

Perishable products are usually priced in real-time to volatile market environments, thereby optimizing inventory control, minimizing resource wastage, and maximizing corporate profitability. Based on the public dataset from the 2023 Higher Education Press Cup National College Students Mathematical Modeling Competition, this paper addresses the challenge of multi-product joint pricing for perishable fresh produce and proposes an attention-augmented proximal policy optimization algorithm (termed ATT-PPO), which embeds an attention mechanism into the proximal policy optimization (PPO) framework. The integrated attention mechanism confers three core advantages to the model: first, it dynamically captures inter-product interdependencies, enabling an accurate reflection of cross-price elasticity and demand correlations; second, it reduces feature redundancy and computational overhead in multi-product collaborative pricing strategies; third, it enhances both the interpretability and computational efficiency of the model. Experimental results demonstrate that in the scenario of multi-product pricing, the ATT-PPO algorithm achieves competitive performance compared to PPO, DDPG (Deep Deterministic Policy Gradient), SAC (Soft Actor-Critic), and TD3 (Twin Delayed Deep Deterministic Policy Gradient), with the key advantage lying in its ability to provide interpretable attention weights that reveal dynamic cross-product dependencies in pricing decisions. This study not only expands the applicability of DRL (Deep Reinforcement Learning) to practical economic problems in the fresh produce sector but also provides valuable theoretical insights that can be generalized to other short-lifecycle product domains, including fashion apparel and consumer electronics. Full article

The vitreous body is not only a transparent filling material of the posterior segment; it is a soft, hydrated, and biologically active matrix that supports structural, optical, and biochemical homeostasis. Vitrectomy therefore leaves a functional deficit that current substitutes only partly address. Intraocular gases, silicone oils, and perfluorocarbon liquids remain essential surgical tools, but they mainly provide mechanical tamponade and do not reproduce native viscoelasticity, diffusion control, or protection against oxidative and inflammatory stress. This review considers vitreous replacement as a functional biomaterials challenge. We discuss native vitreous physiology, the limitations of present tamponade agents, and emerging bioengineered substitutes designed to create a more physiological intravitreal environment. Particular attention is given to hydrogel and polymer-based systems, especially hyaluronic acid-based and in situ crosslinked platforms, which are being developed to combine optical clarity, injectability, soft mechanical support, controlled degradation, and favorable tissue interaction. We also emphasize the need for standardized preclinical testing of swelling, enzymatic stability, drug diffusion, rheology, and long-term biocompatibility. Although next-generation materials may move the field beyond passive space filling, manufacturing reproducibility, regulatory validation, chronic safety, and cautious early-phase trials remain major translational barriers. Full article

Single-lead electrocardiogram (ECG) is widely used in wearable devices for atrial fibrillation (AF) screening. Nevertheless, subtle pathological characteristics like P-waves and f-waves in practical signals are vulnerable to noise contamination. Meanwhile, the scarcity of high-quality annotated abnormal data instances leads to severe class imbalance. To mitigate these issues, we present an end-to-end framework designed for arrhythmia diagnosis using single-lead ECG signals, which integrates quality-aware data augmentation with a Peak-Enhanced attention mechanism. First, to mitigate the problem of data imbalance, a Quality-Aware Generative Adversarial Network (QA-GAN) is designed. This network integrates a signal quality evaluation module based on signal kurtosis, together with a dynamic soft-label training scheme, guiding the generator to prioritize learning high-quality morphological features, thereby synthesizing high-fidelity minority class samples. Second, to accurately capture subtle pathological features in electrocardiograms, a Peak-Enhanced Attention Convolutional Network (PEAC-Net) classification model is proposed. This model incorporates a Peak-Enhanced Attention (PE-Att) module, which employs learnable derivative convolutional kernels to precisely identify the transition points in the ECG signal. Furthermore, by integrating one-dimensional multi-scale dilated convolution (DSGC1D) with bidirectional LSTM, the model achieves effective capturing of both fine-grained local morphological features and long-range global rhythm patterns. Experimental results on the PhysioNet 2017 dataset indicate that the presented model attains an accuracy of 0.902 and a macro-F1 score of 0.880, respectively, outperforming other state-of-the-art models and also exhibiting robust data adaptability on the MIT-BIH dataset. Full article

This paper explores how higher education institutions (HEIs) in the Gulf Cooperation Council (GCC) are advancing the Sustainable Development Goals (SDGs) amid rapidly evolving national development agendas. This study reviews publicly available institutional documents and global SDG ranking data to identify patterns of SDG integration: through academic programs, research, and community engagement. The data shows active engagement of the universities in the region linked with varying SDGs. The analysis also reveals that sustainability initiatives in Gulf universities are not purely educational or environmental undertakings; rather, they function as strategic instruments aligned with national visions, international positioning and soft power objectives. Accordingly, this study assesses institutional commitment to the SDGs as expressed through, and made visible by, publicly available reporting, rather than the effectiveness or real-world impact of that engagement, which the available data cannot establish. Guided by theoretical perspectives, the paper argues that SDG engagement remains largely shaped by global ranking frameworks and policy imperatives. While the GCC higher education sector is increasingly embedded in the global sustainability discourse, meaningful localization of SDG practices and data transparency remain limited. By drawing attention to these dynamics, the study contributes to the literature on higher education and sustainable development in the Arab Gulf, emphasizing the need for context-sensitive frameworks and stronger regional collaboration to advance the 2030 Agenda. It calls for strengthened collaboration, capacity development, and tailored policy approaches to fully harness the transformative potential of the SDGs. Future research should explore the sociopolitical drivers of SDG adoption to deepen understanding of HEIs’ contributions to sustainable development in the region. Full article

Soft magnetic composites (SMCs) are attracting increasing attention for electromagnetic applications owing to their three-dimensional shape flexibility and reduced eddy current loss. In this study, the 2-Pressing 1-Annealing (2P1A) process was applied to Fe–5.0 wt.%Si SMC toroidal cores to investigate the effects of pressing temperature and 1st pressing level on densification behavior, interparticle insulation structure, and frequency-dependent electromagnetic response. DEFORM-3D FEM simulations compared relative density distribution, hydrostatic stress, effective strain, and reaction load under single-press and 2P1A conditions. The 1st pressing stage was conducted at 350 °C with 30%, 50%, and 70% pressing levels, followed by final densification at 550 °C. Increasing compaction temperature reduced reaction load and hydrostatic stress range, while the 1st pressing level affected the final density distribution and stress state after 2nd pressing. TEM-EDS confirmed continuous interparticle insulation layers, and thickness measurements were used to compare local boundary structures. Among the 2P1A conditions, the 50% → 100% condition showed the smallest upper/lower relative density difference and the narrowest insulation-layer thickness range, indicating the most balanced condition in terms of densification uniformity and interparticle boundary structure. Compared with the 550 °C single-press condition, the 2P1A compacts showed higher permeability retention and Q-factor values in the 5–20 kHz range. These results indicate that the 1st pressing level influences staged densification behavior, interparticle boundary structure, and frequency-dependent electromagnetic response in Fe–5.0 wt.%Si SMC cores. Full article

Fluorocarbon (FC)/Pd/Mg multilayer thin films have attracted considerable attention as hydrogen-responsive optical materials. However, their performance is strongly limited by interfacial instability and structural degradation during deposition and hydrogen cycling. In this study, Pt/FC/Pd/Mg multilayer thin films were obtained during focused ion beam (FIB) sample preparation, and transmission electron microscopy (TEM) was employed to investigate the FC layer–mediated interfacial effects. The results reveal that Pt deposition on FC leads to the formation of a confined nanocrystalline interfacial region accompanied by a reduced apparent FC thickness and the development of a Pt–FC intermixing zone. This behavior indicates that the FC layer functions as a “soft landing” medium, dissipating kinetic energy and modifying nucleation and growth behavior. Motivated by this finding, the mechanical properties of FC films and their influence on hydrogen-cycling performance in FC/Pd/Mg/FC structures are further examined. The hardness of FC layers can be tuned from 3.03 MPa to 42.8 MPa by adjusting sputtering parameters. Hydrogen-cycling experiments reveal a strong and non-monotonic dependence on FC mechanical properties. When the FC buffer layer is relatively hard, the initial hydrogenation kinetics are improved; however, prolonged cycling leads to poor adhesion and interfacial degradation. In contrast, when the FC buffer layer is soft, hydrogenation kinetics degrade rapidly during cycling, while long-term interfacial adhesion and structural integrity are significantly improved. These results demonstrate a dual and competing role of FC layers in governing hydrogen transport and mechanical stability, highlighting a critical trade-off for the design of durable hydrogen-responsive multilayer thin films. Full article

Accurate customer baseline load (CBL) estimation is crucial for incentive allocation and flexibility potential assessment in demand response (DR) programs. However, residential electricity consumption is highly stochastic, and long-duration DR events often result in missing critical load segments, making it difficult for traditional regression-based and daily load-profile clustering methods to accurately capture the counterfactual baseline pattern. To address this issue, this paper proposes a CBL estimation method that integrates a physics-/domain-informed response-consistency constraint with a conditional generative adversarial network. In the proposed framework, deep soft clustering is employed to extract weekly scale load modes, while mutual information (MI) and autocorrelation coefficient (ACC) are quantified as user-specific conditioning fingerprints to characterize intrinsic consumption behaviors. Comparative experiments on a publicly available real-world dataset demonstrate that the proposed method provides strong event-period accuracy among the recurrent and attention-based benchmark models considered in the main comparison. Under matched response-consistency budgets, PI-ICGAN achieves the lowest constrained DR-period MAE at the tested NRR targets, and the ablation results show that the attention, fingerprint, response-consistency, and GradNorm components contribute to different aspects of the accuracy–consistency trade-off. Full article

In recent years, short video platforms have rapidly developed into important media for cultural dissemination. The interactions of netizens in short video comment sections not only reflect their focus on cultural content but also contain rich emotional attitudes. However, given the vast and fragmented nature of comment data, accurately extracting keywords, identifying cultural themes, and analyzing sentiment tendencies pose significant challenges in understanding netizens’ cultural perceptions. To address these challenges, this study proposes a text analysis framework that integrates keyword extraction, clustering analysis, and sentiment analysis to explore the core topics and emotional characteristics of cultural dissemination in short video comment sections. Firstly, to address the challenge of balancing statistical information and semantic understanding in short-text keyword extraction, this paper proposes the TF-IDF-KeyBERT Integrated Algorithm (TKIA) keyword extraction algorithm, which integrates Term Frequency–Inverse Document Frequency (TF-IDF) and Key Bidirectional Encoder Representations from Transformers (BERT). Experiments on the CSL dataset demonstrate improvement in the F1@5 metric, showing its potential to enhance keyword extraction performance for short texts. Secondly, to address the difficulty of simultaneously considering semantic representation capability and clustering flexibility in short-text clustering analysis, this paper designs the Self-Supervised Contrastive Enhanced Clustering (SCEC) algorithm by integrating self-supervised contrastive learning with a soft clustering strategy. Compared to baseline methods, SCEC improves clustering accuracy (ACC) by 17.5% on AGNews and 6.8% on THUCNews, suggesting a more effective way to reveal the underlying structure of cultural topics. Finally, to address the challenge of effectively leveraging both text structural information and global semantic features in short-text sentiment analysis, this paper develops the BERT-GCN Cross-Attention (BGC) Model, integrating BERT embeddings and Graph Convolutional Network (GCN)-based structural features via a Cross-Attention mechanism. On the My_weibo_senti_100k dataset, the BGC model achieves a 2.45% increase in Macro-F1 and a 2.41% improvement in accuracy over strong baselines, offering its ability for high-precision modeling of user sentiment. This study offers effective data support and technical pathways for applications such as cultural content understanding, personalized recommendation, and user emotion guidance. Full article

Human pose estimation in crowded images remains difficult because the visual evidence around many joints is incomplete, and responses from nearby persons may be mistakenly incorporated into the target skeleton. To address this issue, this paper presents CSPA-Net, a heatmap-based pose estimation framework that controls the propagation of structural information during occluded-joint recovery. The proposed network first estimates joint reliability from coarse heatmaps by considering both the dispersion and the spatial spread of the response distribution. Based on these soft joint locations and uncertainty cues, a Skeleton-consistent Manhattan Constraint is constructed to define a target-oriented spatial prior. This prior limits structural propagation to regions that are more consistent with the estimated target skeleton, reducing the chance of introducing features from adjacent instances. In addition, a Pose-Structured Cross-Axis Attention module is designed to exchange row-wise and column-wise contextual information so that lateral body symmetry and vertical kinematic dependencies can be modeled in a more directed manner. Finally, multiscale adaptive aggregation combines coarse structural cues with fine local details for heatmap prediction. Experiments on COCO val2017 and CrowdPose show that CSPA-Net achieves 75.3% AP and 80.9% AR on COCO val2017 and 69.6% AP on the CrowdPose test set, outperforming the HRNet-W32 baseline under the same input setting. These results suggest that controlled structural propagation is useful for improving pose estimation in occluded and crowded scenes. Full article

Target detection in synthetic aperture radar (SAR) images is constrained by three primary challenges. First, speckle noise overlaps heavily with the high-frequency features of target edges in the frequency domain, so standard convolutions cannot suppress noise without sacrificing edge texture. Second, the scattering signature of a SAR target varies markedly with viewing angle, and a fixed-parameter convolution kernel cannot accommodate this spatial non-stationarity. Third, deep and shallow levels of the feature pyramid differ in semantics and resolution, and a naive element-wise sum either introduces noise interference or loses small-target signals. We propose the Frequency–Spatial Detection Network (FSDNet), whose core FSDBlock cascades three operators to address these failure modes in turn. Wavelet Convolution (WTConv) projects features into Haar sub-bands and applies independent low- and high-frequency kernels prior to inverse-DWT reconstruction, suppressing noise while preserving edges. Receptive-Field Attention Convolution (RFAConv) generates location-conditional kernels and so adapts to non-stationary scattering. Spatial Context Self-Attention (SCSA) aggregates discrete scattering points into coherent target representations via long-range grouped attention. At the fusion stage, CGAFusion replaces FPN element-wise addition with a channel–spatial–pixel triple-attention soft switch that mitigates deep–shallow semantic mismatch. On HRSID, FSDNet attains mAP₅₀ $= 92.3$% and mAP_50:95 $= 68.6$%. On SSDD, it attains mAP₅₀ $= 98.7$% and mAP_50:95 $= 74.2$%. Both sets of results consistently surpass the baseline methods. Against the strongest YOLO baseline (YOLOv11n), FSDNet improves HRSID mAP₅₀ by $+1.7$ percentage points (pp) and mAP_50:95 by $+2.3$ pp, and SSDD mAP₅₀ by $+0.5$ pp and mAP_50:95 by $+2.7$ pp; against the capacity-fair YOLOv11s reference (∼51% more parameters), FSDNet still leads on mAP₅₀, mAP_50:95, recall, and F1. Ablation studies and power-spectral-density analyses corroborate the contribution of each module and confirm WTConv’s role in preserving high-frequency target features. Full article

Small, dispersed, and vegetated creeping landslides in hilly areas of eastern China hinder traditional remote sensing and detection. To address this, this study takes Yixian County (Anhui Province) as a representative area. Based on high-resolution GF-2 satellite images, three deep learning models embedded with the Squeeze-and-Excitation (SE) attention mechanism (ResNet18-SE, VGG13-SE, UNet-SE) were developed and compared with the original UNet model. Combined with field investigation, landslide mapping and accuracy assessment were conducted to evaluate the feature extraction capabilities of four models. The results indicate that the UNet-SE model achieved optimal performance (Precision: 0.911, Recall: 0.685, F1-score: 0.782, Kappa: 0.730, IoU: 0.643). Its F1-score exceeds ResNet18-SE, VGG13-SE, and the original UNet by 8%, 3%, and 5%, respectively, proving superior regional adaptability and generalization performance. Additional verification on creeping landslides in Kecun Town (Yixian County) and post-earthquake landslides in Lushan County (Sichuan Province) further confirms the reliability of the UNet-SE model. Furthermore, Frequency Ratio (FR), Random Forest (RF), and SHapley Additive exPlanations (SHAP) were adopted to reveal the correlation between landslide occurrence and seven geological-environmental factors. Landslides are most susceptible to develop at elevations of 400–500 m, NDVI values of 0.4–0.5, slopes below 10°, east and northeast aspects, 300–500 m away from rivers, 500–1000 m away from faults, and areas covered by soft sedimentary lithology. Distance from faults, distance from rivers, and elevation are identified as the three favorable conditional factors. In conclusion, the proposed landslide detection framework can provide reliable spatial data and technical references for regional geological hazard prevention, ecological conservation and sustainable development in hilly areas. Full article

Artificial muscles are an emerging class of actuators designed to mimic the compliant, efficient, and versatile behavior of biological muscles for fields including the following: soft robotics, prosthetics, wearable enhancements, haptic interfaces, and biomedical devices. These systems encompass various actuation mechanisms, including pneumatic, hydraulic, thermal, ionic, electrochemical, and electrostatic. Each with distinct tradeoffs in voltage, strain, output force, bandwidth, efficiency, and manufacturability. Among them, electrostatic actuators have attracted increased attention due to their fast response times, high energy densities, strong compatibility with soft materials, and scalability from microscale devices to large-area and stacked actuators. However, challenges such as dielectric breakdown, material fatigue, and fabrication complexity continue to limit widespread deployment. This review presents a structured classification of various artificial muscle technologies and an in-depth examination of electrostatic actuators including dielectric elastomers, electrostrictive and ferroelectric polymers, liquid crystal elastomers, electrostatic film motors, stacked architectures, and microscale/milliscale devices. In this review the operating principles, materials, architectures, performance characteristics, and failure modes of electrostatic actuators will be discussed. Additionally, a comparison will highlight tradeoffs across actuator families based on metrics such as voltage, force, strain, bandwidth, and manufacturability. Lastly, we outline future research directions in materials, physics-informed modeling, system integration, and scalable fabrication necessary to advance electrostatic artificial muscles toward practical, real-world deployment. Full article