Search Results (2,049)

Sign language recognition plays a crucial role in enabling communication for deaf individuals, yet current methods face limitations such as sensitivity to lighting conditions, occlusions, and lack of adaptability in diverse environments. This study presents a wearable multi-channel tactile sensing system based on smart textiles, designed to capture subtle wrist and finger motions for static sign language recognition. The system leverages triboelectric yarns sewn into gloves and sleeves to construct a skin-conformal tactile sensor array, capable of detecting biomechanical interactions through contact and deformation. Unlike vision-based approaches, the proposed sensor platform operates independently of environmental lighting or occlusions, offering reliable performance in diverse conditions. Experimental validation on American Sign Language letter gestures demonstrates that the proposed system achieves high signal clarity after customized filtering, leading to a classification accuracy of 94.66%. Experimental results show effective recognition of complex gestures, highlighting the system’s potential for broader applications in human-computer interaction. Full article

Synthetic Aperture Radar (SAR) provides all-weather, all-time imaging capabilities, enabling reliable maritime ship detection under challenging weather and lighting conditions. However, most high-precision detection models rely on complex architectures and large-scale parameters, limiting their applicability to resource-constrained platforms such as satellite-based systems, where model size, computational load, and power consumption are tightly restricted. Thus, guided by the principles of lightweight design, robustness, and energy efficiency optimization, this study proposes a three-stage collaborative multi-level feature fusion framework to reduce model complexity without compromising detection performance. Firstly, the backbone network integrates depthwise separable convolutions and a Convolutional Block Attention Module (CBAM) to suppress background clutter and extract effective features. Building upon this, a cross-layer feature interaction mechanism is introduced via the Multi-Scale Coordinated Fusion (MSCF) and Bi-EMA Enhanced Fusion (Bi-EF) modules to strengthen joint spatial-channel perception. To further enhance the detection capability, Efficient Feature Learning (EFL) modules are embedded in the neck to improve feature representation. Experiments on the Synthetic Aperture Radar (SAR) Ship Detection Dataset (SSDD) show that this method, with only 1.6 M parameters, achieves a mean average precision (mAP) of 98.35% in complex scenarios, including inshore and offshore environments. It balances the difficult problem of being unable to simultaneously consider accuracy and hardware resource requirements in traditional methods, providing a new technical path for real-time SAR ship detection on satellite platforms. Full article

Accurate segmentation of densely stacked and weakly textured objects remains a core challenge in robotic depalletizing for industrial applications. To address this, we propose MaskNet, an instance segmentation network tailored for RGB-D input, designed to enhance recognition performance under occlusion and low-texture conditions. Built upon a Vision Transformer backbone, MaskNet adopts a dual-branch architecture for RGB and depth modalities and integrates multi-modal features using an attention-based fusion module. Further, spatial and channel attention mechanisms are employed to refine feature representation and improve instance-level discrimination. The segmentation outputs are used in conjunction with regional depth to optimize the grasping sequence. Experimental evaluations on camshaft depalletizing tasks demonstrate that MaskNet achieves a precision of 0.980, a recall of 0.971, and an F1-score of 0.975, outperforming a YOLO11-based baseline. In an actual scenario, with a self-designed flexible magnetic gripper, the system maintains a maximum grasping error of 9.85 mm and a 98% task success rate across multiple camshaft types. These results validate the effectiveness of MaskNet in enabling fine-grained perception for robotic manipulation in cluttered, real-world scenarios. Full article

Background: Sodium–glucose cotransporter 2 (SGLT2) inhibitors have transformed type 2 diabetes mellitus (T2DM) management by promoting glucosuria, lowering glycated hemoglobin (HbA1c), blood pressure, and weight; however, their use is limited by genitourinary infections and ketoacidosis. Phytocannabinoids—bioactive compounds from Cannabis sativa—exhibit multi-target pharmacology, including interactions with cannabinoid receptors, Peroxisome Proliferator-Activated Receptors (PPARs), Transient Receptor Potential (TRP) channels, and potentially SGLT2. Objective: To evaluate the potential of phytocannabinoids as novel modulators of renal glucose reabsorption via SGLT2 and to compare their efficacy, safety, and pharmacological profiles with synthetic SGLT2 inhibitors. Methods: We performed a narrative review encompassing the following: (1) the molecular and physiological roles of SGLT2; (2) chemical classification, natural sources, and pharmacokinetics/pharmacodynamics of major phytocannabinoids (Δ⁹-Tetrahydrocannabinol or Δ⁹-THC, Cannabidiol or CBD, Cannabigerol or CBG, Cannabichromene or CBC, Tetrahydrocannabivarin or THCV, and β-caryophyllene); (3) in silico docking and drug-likeness assessments; (4) in vitro assays of receptor binding, TRP channel modulation, and glucose transport; (5) in vivo rodent models evaluating glycemic control, weight change, and organ protection; (6) pilot clinical studies of THCV and case reports of CBD/BCP; (7) comparative analysis with established synthetic inhibitors. Results: In silico studies identify high-affinity binding of several phytocannabinoids within the SGLT2 substrate pocket. In vitro, CBG and THCV modulate SGLT2-related pathways indirectly via TRP channels and CB receptors; direct IC₅₀ values for SGLT2 remain to be determined. In vivo, THCV and CBD demonstrate glucose-lowering, insulin-sensitizing, weight-reducing, anti-inflammatory, and organ-protective effects. Pilot clinical data (n = 62) show that THCV decreases fasting glucose, enhances β-cell function, and lacks psychoactive side effects. Compared to synthetic inhibitors, phytocannabinoids offer pleiotropic benefits but face challenges of low oral bioavailability, polypharmacology, inter-individual variability, and limited large-scale trials. Discussion: While preclinical and early clinical data highlight phytocannabinoids’ potential in SGLT2 modulation and broader metabolic improvement, their translation is impeded by significant challenges. These include low oral bioavailability, inconsistent pharmacokinetic profiles, and the absence of standardized formulations, necessitating advanced delivery system development. Furthermore, the inherent polypharmacology of these compounds, while beneficial, demands comprehensive safety assessments for potential off-target effects and drug interactions. The scarcity of large-scale, well-controlled clinical trials and the need for clear regulatory frameworks remain critical hurdles. Addressing these aspects is paramount to fully realize the therapeutic utility of phytocannabinoids as a comprehensive approach to T2DM management. Conclusion: Phytocannabinoids represent promising multi-target agents for T2DM through potential SGLT2 modulation and complementary metabolic effects. Future work should focus on pharmacokinetic optimization, precise quantification of SGLT2 inhibition, and robust clinical trials to establish efficacy and safety profiles relative to synthetic inhibitors. Full article

The integration of heterogeneous spatio-temporal datasets presents a critical challenge in geospatial data science, particularly when combining large-scale, passively collected “big” data with precise but sparse “small” data. In this study, we propose a novel framework—Multi-Channel Spatio-Temporal Data Fusion (MCST-DF)—that leverages transformer-based deep learning to fuse these data sources for accurate network flow estimation. Our approach introduces a Residual Spatio-Temporal Transformer Network (RSTTNet), equipped with a layered attention mechanism and multi-scale embedding architecture to capture both local and global dependencies across space and time. We evaluate the framework using real-world mobile sensing and loop detector data from the London road network, demonstrating over 89% prediction accuracy and outperforming several benchmark deep learning models. This work provides a generalisable solution for spatio-temporal fusion of diverse geospatial data sources and has direct relevance to smart mobility, urban infrastructure monitoring, and the development of spatially informed AI systems. Full article

Reconfigurable Intelligent Surface (RIS) has emerged as a promising enabling technology for wireless communications, which significantly enhances system performance through real-time manipulation of electromagnetic wave reflection characteristics. In RIS-assisted communication systems, existing deep learning-based channel state information (CSI) feedback methods often suffer from excessive parameter requirements and high computational complexity. To address this challenge, this paper proposes LwCSI-Net, a lightweight autoencoder network specifically designed for RIS-assisted multiple-input single-output (MISO) systems, aiming to achieve efficient and low-complexity CSI feedback. The core contribution of this work lies in an innovative lightweight feedback architecture that deeply integrates multi-layer convolutional neural networks (CNNs) with attention mechanisms. Specifically, the network employs 1D convolutional operations with unidirectional kernel sliding, which effectively reduces trainable parameters while maintaining robust feature-extraction capabilities. Furthermore, by incorporating an efficient channel attention (ECA) mechanism, the model dynamically allocates weights to different feature channels, thereby enhancing the capture of critical features. This approach not only improves network representational efficiency but also reduces redundant computations, leading to optimized computational complexity. Additionally, the proposed cross-channel residual block (CRBlock) establishes inter-channel information-exchange paths, strengthening feature fusion and ensuring outstanding stability and robustness under high compression ratio (CR) conditions. Our experimental results show that for CRs of 16, 32, and 64, LwCSI-Net significantly improves CSI reconstruction performance while maintaining fewer parameters and lower computational complexity, achieving an average complexity reduction of 35.63% compared to state-of-the-art (SOTA) CSI feedback autoencoder architectures. Full article

Underwater acoustic (UWA) communication supports many critical applications but still faces several physical-layer signal processing challenges. In response, recent advances in machine learning (ML) and deep learning (DL) offer promising solutions to improve signal detection, modulation adaptability, and classification accuracy. These developments highlight the need for a systematic evaluation to compare various ML/DL models and assess their performance across diverse underwater conditions. However, most existing reviews on ML/DL-based UWA communication focus on isolated approaches rather than integrated system-level perspectives, which limits cross-domain insights and reduces their relevance to practical underwater deployments. Consequently, this systematic literature review (SLR) synthesizes 43 studies (2020–2025) on ML and DL approaches for UWA communication, covering channel estimation, adaptive modulation, and modulation recognition across both single- and multi-carrier systems. The findings reveal that models such as convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and generative adversarial networks (GANs) enhance channel estimation performance, achieving error reductions and bit error rate (BER) gains ranging from ${10}^{-3}$ to ${10}^{-6}$. Adaptive modulation techniques incorporating support vector machines (SVMs), CNNs, and reinforcement learning (RL) attain classification accuracies exceeding 98% and throughput improvements of up to 25%. For modulation recognition, architectures like sequence CNNs, residual networks, and hybrid convolutional–recurrent models achieve up to 99.38% accuracy with latency below 10 ms. These performance metrics underscore the viability of ML/DL-based solutions in optimizing physical-layer tasks for real-world UWA deployments. Finally, the SLR identifies key challenges in UWA communication, including high complexity, limited data, fragmented performance metrics, deployment realities, energy constraints and poor scalability. It also outlines future directions like lightweight models, physics-informed learning, advanced RL strategies, intelligent resource allocation, and robust feature fusion to build reliable and intelligent underwater systems. Full article

Crop disease identification is a pivotal research area in smart agriculture, forming the foundation for disease mapping and targeted prevention strategies. Among the most prevalent global wheat diseases, powdery mildew—caused by fungal infection—poses a significant threat to crop yield and quality, making early and accurate detection crucial for effective management. In this study, we present QY-SE-MResNet34, a deep learning-based classification model that builds upon ResNet34 to perform multi-class classification of wheat leaf images and assess powdery mildew severity at the single-leaf level. The proposed methodology begins with dataset construction following the GBT 17980.22-2000 national standard for powdery mildew severity grading, resulting in a curated collection of 4248 wheat leaf images at the grain-filling stage across six severity levels. To enhance model performance, we integrated transfer learning with ResNet34, leveraging pretrained weights to improve feature extraction and accelerate convergence. Further refinements included embedding a Squeeze-and-Excitation (SE) block to strengthen feature representation while maintaining computational efficiency. The model architecture was also optimized by modifying the first convolutional layer (conv1)—replacing the original 7 × 7 kernel with a 3 × 3 kernel, adjusting the stride to 1, and setting padding to 1—to better capture fine-grained leaf textures and edge features. Subsequently, the optimal training strategy was determined through hyperparameter tuning experiments, and GrabCut-based background processing along with data augmentation were introduced to enhance model robustness. In addition, interpretability techniques such as channel masking and Grad-CAM were employed to visualize the model’s decision-making process. Experimental validation demonstrated that QY-SE-MResNet34 achieved an 89% classification accuracy, outperforming established models such as ResNet50, VGG16, and MobileNetV2 and surpassing the original ResNet34 by 11%. This study delivers a high-performance solution for single-leaf wheat powdery mildew severity assessment, offering practical value for intelligent disease monitoring and early warning systems in precision agriculture. Full article

With the rising automation and complexity level of industrial systems, the efficiency and accuracy of fault diagnosis have become a critical challenge. The convolutional neural network (CNN) has shown some success in the fault diagnosis field. However, typical convolutional kernels are commonly fixed-sized, which makes it difficult to capture multi-scale features simultaneously. Additionally, the use of numerous fixed-size convolutional filters often results in redundant parameters. During the feature extraction process, the CNN often struggles to take inter-channel dependencies and spatial location information into consideration. There are also limitations in extracting various time-scale features. To address these issues, a fault diagnosis method on the basis of a dual-path mixed convolutional attention-BiGRU network (DMCA-BiGRUN) is proposed for industrial processes. Firstly, a dual-path mixed CNN (DMCNN) is designed to capture features at multiple scales while effectively reducing the parameter count. Secondly, a coordinate attention mechanism (CAM) is designed to help the network to concentrate on main features more effectively during feature extraction by combining the channel relationship and position information. Finally, a bidirectional gated recurrent unit (BiGRU) is introduced to process sequences in both directions, which can effectively learn the long-range temporal dependencies of sequence data. To verify the fault diagnosis performance of the proposed method, simulation experiments are implemented on the Tennessee Eastman (TE) and Continuous Stirred Tank Reactor (CSTR) datasets. Some deep learning methods are compared in the experiments, and the results confirm the feasibility and superiority of DMCA-BiGRUN. Full article

Rolling element bearings serve as critical transmission components in industrial automation systems, yet their fault signatures are susceptible to interference from strong background noise, complex operating conditions, and nonlinear impact characteristics. Addressing the limitations of conventional methods in adaptive parameter optimization and weak feature enhancement, this paper proposes an innovative diagnostic framework integrating Improved Goose optimized Variational Mode Decomposition (IGOOSE-VMD), RobustICA, and CYCBD. First, to mitigate modal aliasing issues caused by empirical parameter dependency in VMD, we fuse a refraction-guided reverse learning mechanism with a dynamic mutation strategy to develop the IGOOSE. By employing an energy-feature-driven fitness function, this approach achieves synergistic optimization of the mode number and penalty factor. Subsequently, a multi-channel observation model is constructed based on optimal component selection. Noise interference is suppressed through the robust separation capabilities of RobustICA, while CYCBD introduces cyclostationarity-based prior constraints to formulate a blind deconvolution operator with periodic impact enhancement properties. This significantly improves the temporal sparsity of fault-induced impact components. Experimental results demonstrate that, compared to traditional time–frequency analysis techniques (e.g., EMD, EEMD, LMD, ITD) and deconvolution methods (including MCKD, MED, OMEDA), the proposed approach exhibits superior noise immunity and higher fault feature extraction accuracy under high background noise conditions. Full article

Concrete is extensively utilized in infrastructure projects. However, issues like construction quality and external loads can lead to the formation of thin-plate-like voids with considerable aspect ratios, posing serious safety risks and highlighting the need for effective boundary detection. This paper addresses the challenges of traditional acoustic detection methods, which often suffer from low efficiency, poor adaptability to environmental conditions, and difficulties in measuring defect sizes. It explores a spatially diverse MIC Array system. Unlike single-point MIC that can only capture multi-directional sound field information from one excitation point, this array improves efficiency through simultaneous multi-channel data acquisition. This study develops a vibration model for a circular thin plate with fixed boundaries, examines the gradient relationships in various directions, and introduces a method that integrates MIC array technology with acoustic vibration techniques. The focus is on identifying concrete defect boundaries, where a single excitation at the same measurement point can yield different first-order vibration modes recorded by various MICs. A gradient-based approach is proposed to determine defect boundaries based on the locations of different MICs in the array. Experiments were carried out using circular thin-plate concrete samples with pre-existing voids. For instance, at boundary measurement point 15, the first-order modal data collected by MIC0 and MIC4 were $7.80\times {10}^{-4}\mathrm{P}\mathrm{a}$ and $5.42\times {10}^{-6}\mathrm{P}\mathrm{a}$, respectively, exhibiting a significant gradient difference, which verified the accuracy and rapidity of identifying concrete void boundaries. Full article

Detecting defects in transmission line insulators is crucial to prevent power grid failures as power systems continue to expand. This study introduces YOL011n-SSA, an enhanced insulator defect detection technique method that addresses the challenges of effectively identifying flaws in complex environments. First, this study incorporates the StarNet network into the backbone of the model. By stacking multiple layers of star operations, the model reduces both parameter count and model size, improving its adaptability to real-time object detection tasks. Secondly, the SOPN feature pyramid network is introduced into the neck part of the model. By optimizing the multi-scale feature fusion of the richer information obtained after expanding the channel dimension, the detection efficiency for low-resolution images and small objects is improved. Then, the ADown module was adopted to improve the backbone and neck parts of the model. It effectively reduces parameter count and significantly lowers the computational cost by implementing downsampling operations between different layers of the feature map, thereby enhancing the practicality of the model. Meanwhile, by introducing the NWD to improve the evaluation index of the loss function, the detection model’s capability in assessing the similarities among various small-object defects is enhanced. Experimental results were obtained using an expanded dataset based on a public dataset, incorporating three types of insulator defects under complex environmental conditions. The results demonstrate that the YOLO11n-SSA algorithm achieved an mAP@0.5 of 0.919, an mAP@0.5:0.95 of 70.7%, a precision of 0.95, and a recall of 0.875, representing improvements of 3.9%, 5.5%, 2%, and 5.7%, respectively, when compared to the original YOLO1ln method. The detection time per image is 0.0134 s. Compared to other mainstream algorithms, the YOLO11n-SSA algorithm demonstrates superior detection accuracy and real-time performance. Full article

Riverbed dynamics are natural processes that are strongly driven by human and climatic factors. In the last two centuries, the anthropogenic influence and impact of climate change on European rivers has resulted in significant degradation of riverbeds. This research paper aims to determine the historical evolution (1856–2021) and future trends of the Ialomița riverbed (Romania) under the influence of anthropogenic impact and climate change. The case study is a reach of 66 km between the confluences with the Ialomicioara and Pâscov rivers. The localisation in a contact zone between the Curvature Subcarpathians and the Târgoviște Plain, the active recent tectonic uplift of the area, and the intense anthropogenic intervention gives to this river reach favourable conditions for pronounced riverbed dynamics over time. To achieve the aim of the study, we developed a complex methodology which involves the use of Geographical Information System (GIS) techniques, hierarchical cluster analysis (HCA), the Mann–Kendall test (MK), and R programming. The results indicate that the evolution of the Ialomița River aligns with the general trends observed across Europe and within Romania, characterised by a reduction in riverbed geomorphological complexity and a general transition from a braided, multi-thread into a sinuous, single-thread fluvial style. The main processes consist of channel narrowing and incision alternating with intense meandering. However, specific temporal and spatial evolution patterns were identified, mainly influenced by the increasingly anthropogenic local influences and confirmed climate changes in the study area since the second half of the 20th century. Future evolutionary trends suggest that, in the absence of river restoration interventions, the Ialomița riverbed is expected to continue degrading on a short-term horizon, following both climatic and anthropogenic signals. The findings of this study may contribute to a better understanding of recent river behaviours and serve as a valuable tool for the management of the Ialomița River. Full article

The challenge of accurately diagnosing mechanical failures in high-voltage circuit breakers is exacerbated by the non-stationary characteristics of vibration signals. This study proposes a Dual-Channel Convolutional Neural Network (DC-CNN) framework based on the Gramian Angular Field (GAF) transformation, which effectively captures both global and local information about faults. Specifically, vibration signals from circuit breaker sensors are firstly transformed into Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF) images. These images are then combined into multi-channel inputs for parallel CNN modules to extract and fuse complementary features. Experimental validation under six operational conditions of a 220 kV high-voltage circuit breaker demonstrates that the GAF-DC-CNN method achieves a fault diagnosis accuracy of 99.02%, confirming the model’s effectiveness. This work provides substantial support for high-precision and reliable fault diagnosis in high-voltage circuit breakers within power systems. Full article

The design of materials with programmable degradation profiles presents a fundamental challenge in pattern recognition across molecular space, requiring the identification of complex structure–property relationships within an exponentially large chemical domain. This paper introduces a novel physics-informed deep learning framework that integrates multi-scale molecular sensing data with reinforcement learning algorithms to enable intelligent characterization and prediction of polymer degradation dynamics. Our method combines three key innovations: (1) a dual-channel sensing architecture that fuses spectroscopic signatures from Graph Isomorphism Networks with temporal degradation patterns captured by transformer-based models, enabling comprehensive molecular state detection across multiple scales; (2) a physics-constrained policy network that ensures sensor measurements adhere to thermodynamic principles while optimizing the exploration of degradation pathways; and (3) a hierarchical signal processing system that balances multiple sensing modalities through adaptive weighting schemes learned from experimental feedback. The framework employs curriculum-based training that progressively increases molecular complexity, enabling robust detection of degradation markers linking polymer architectures to enzymatic breakdown kinetics. Experimental validation through automated synthesis and in situ characterization of 847 novel polymers demonstrates the framework’s sensing capabilities, achieving a 73.2% synthesis success rate and identifying 42 structures with precisely monitored degradation profiles spanning 6 to 24 months. Learned molecular patterns reveal previously undetected correlations between specific spectroscopic signatures and degradation susceptibility, validated through accelerated aging studies with continuous sensor monitoring. Our results establish that physics-informed constraints significantly improve both the validity (94.7%) and diversity (0.82 Tanimoto distance) of generated molecular structures compared with unconstrained baselines. This work advances the convergence of intelligent sensing technologies and materials science, demonstrating how physics-informed machine learning can enhance real-time monitoring capabilities for next-generation sustainable materials. Full article