Search Results (27,628)

Plant diseases have a large impact on agricultural production, leading to crop yield reduction and causing economic losses. For the development of intelligent agriculture, it is very important to identify crop diseases accurately. With the help of image recognition methods, precise prevention and control of diseases can be achieved, which significantly reduces the use of pesticides and ultimately improves crop yield and quality. Therefore, this study proposes a theoretical method that combines Attention-Guided PCA (AG-PCA) dimensionality reduction with a spatial attention mechanism. Our method is verified on the ResNet model. The AG-PCA module dynamically selects principal component features based on attention weights, which greatly preserves key disease features during dimensionality reduction. At the same time, a spatial attention mechanism is embedded in the residual blocks to enhance the representation ability of disease regions and suppress background interference. On the AppleLeaf9 dataset containing 10,211 images of 9 disease categories, the model achieved an accuracy of 93.69%, significantly outperforming the baseline methods. Experimental results indicate that it performs stably in complex backgrounds and fine-grained classification tasks, and demonstrates strong generalization ability, showing promising application potential. Full article

This study introduces GAT-CAMDA, a novel framework for the structural health monitoring (SHM) of composite materials under temperature-induced variability, leveraging the powerful feature extraction capabilities of Graph Attention Networks (GATs) and advanced domain adaptation (DA) techniques. By combining Maximum Mean Discrepancy (MMD) and Correlation Alignment (CORAL) losses with a domain-discriminative adversarial model, the framework achieves scalable alignment of feature distributions across temperature domains, ensuring robust damage detection. A simple yet at the same time efficient data augmentation process extrapolates damage behaviour across unmeasured temperature conditions, addressing the scarcity of damaged-state observations. Hyperparameter optimisation via Optuna not only identifies the optimal settings to enhance model performance, achieving a classification accuracy of 95.83% on a benchmark dataset, but also illustrates hyperparameter significance for explainability. Additionally, the GAT architecture’s attention demonstrates the importance of various sensors, enhancing transparency and reliability in damage detection. The dual use of Optuna serves to refine model accuracy and elucidate parameter impacts, while GAT-CAMDA represents a significant advancement in SHM, enabling precise, interpretable, and scalable diagnostics across complex operational environments. Full article

In mineral processing and metallurgy, total iron grade serves as a critical indicator guiding the entire production chain from crushing to smelting, directly influencing the quality and yield of steel products. To address the limitations of conventional matrix effect correction methods in X-ray fluorescence (XRF) analysis—such as low accuracy, high time consumption, and labor-intensive procedures—this study proposes a novel hybrid model (DSCN-LS) integrating least squares (LS) with dynamically regularized stochastic configuration networks (DSCNs) for total iron ore grade quantification. Through feature analysis, we decompose the grade modeling problem into a linear structural component and nonlinear residual terms. The linear component is resolved by means of LS, while the nonlinear terms are processed by the DSCN with a dynamic regularization strategy. This strategy implements node-specific weighted regularization: weak constraints preserve salient features in high-weight-norm nodes, while strong regularization suppresses redundant information in low-weight-norm nodes, collectively enhancing model generalizability and robustness. Notably, the model was trained and validated using datasets collected directly from industrial sites, ensuring that the results reflect real-world production scenarios. Industrial validation demonstrates that the proposed method achieves an average absolute error of 0.3092, a root mean square error of 0.5561, and a coefficient of determination (R²) of 99.91% in total iron grade estimation. All metrics surpass existing benchmarks, confirming significant improvements in accuracy and operational practicality for XRF detection under complex industrial conditions Full article

Hyperspectral image (HSI) classification requires models that can simultaneously capture spatial structures and spectral continuity. Although state space models (SSMs), particularly Mamba, have shown strong capability in long-sequence modeling, their application to HSI remains limited due to insufficient spectral relation modeling and the constraints of unidirectional processing. To address these challenges, we propose BiMambaHSI, a novel bidirectional spectral-–spatial framework. First, we proposed a joint spectral–-spatial gated mamba (JGM) encoder that applies forward–backward state modeling with input-dependent gating, explicitly capturing bidirectional spectral–-spatial dependencies. This bidirectional mechanism explicitly captures long-range spectral–-spatial dependencies, overcoming the limitations of conventional unidirectional Mamba. Second, we introduced the spatial-–spectral mamba block (SSMB), which employs parallel bidirectional branches to extract spatial and spectral features separately and integrates them through a lightweight adaptive fusion mechanism. This design enhanced spectral continuity, spatial discrimination, and cross-dimensional interactions while preserving the linear complexity of pure SSMs. Extensive experiments on five public benchmark datasets (Pavia University, Houston, Indian Pines, WHU-Hi-HanChuan, and WHU-Hi-LongKou) demonstrate that BiMambaHSI consistently achieves state-of-the-art performance, improving classification accuracy and robustness compared with existing CNN- and Transformer-based methods. Full article

Despite the superior performance of existing anomaly detection methods, they are often limited to single-class detection tasks, requiring separate models for each class. This constraint hinders their detection performance and deployment efficiency when applied to real-world multi-class data. In this paper, we propose a dynamic visual adaptation framework for multi-class anomaly detection, enabling the dynamic and adaptive capture of features based on multi-class data, thereby enhancing detection performance. Specifically, our method introduces a network plug-in, the Hyper AD Plug-in, which dynamically adjusts model parameters according to the input data to extract dynamic features. By leveraging the collaboration between the Mamba block, the CNN block, and the proposed Hyper AD Plug-in, we extract global, local, and dynamic features simultaneously. Furthermore, we incorporate the Mixture-of-Experts (MoE) module, which achieves a dynamic balance across different features through its dynamic routing mechanism and multi-expert collaboration. As a result, the proposed method achieves leading accuracy on the MVTec AD and VisA datasets, with image-level mAU-ROC scores of 98.8% and 95.1%, respectively. Full article

The ability to reconstruct immersive and realistic three-dimensional scenes plays a fundamental role in advancing virtual reality, digital twins, and related fields. With the rapid development of differentiable rendering frameworks, the reconstruction quality of static scenes has been significantly improved. However, we observe that the challenge of insufficient initialization has been largely overlooked in existing studies, while at the same time heavily relying on dense multi-view imagery that is difficult to obtain. To address these challenges, we propose a pipeline for text driven 3D scene generation, which employs panoramic images as an intermediate representation and integrates with 3D Gaussian Splatting to enhance reconstruction quality and efficiency. Our method introduces an improved point cloud initialization using Fibonacci lattice sampling of panoramic images, combined with a dense perspective pseudo label strategy for teacher–student distillation supervision, enabling more accurate scene geometry and robust feature learning without requiring explicit multi-view ground truth. Extensive experiments validate the effectiveness of our method, consistently outperforming state-of-the-art methods across standard reconstruction metrics. Full article

Background: Thalassemia has been recognized as a critical public health issue in Bangladesh, especially among pregnant women, due to its hereditary nature and the lack of early screening infrastructure. Early identification of at-risk individuals is essential to prevent the transmission of this genetic disorder to future generations and to reduce the burden on an already strained healthcare system. Methods: In this study, an innovative framework for thalassemia risk assessment has been developed by integrating Multi-Criteria Decision-Making (MCDM) methods—specifically AHP-TOPSIS—with machine learning algorithms including Random Forest, XGBoost, and CatBoost. Explainable Artificial Intelligence (XAI) techniques such as SHAP and LIME have also been incorporated to improve model transparency and trustworthiness. Real-world clinical and demographic data, consisting of 16 features and 1200 samples, have been collected through a structured survey and processed using rigorous feature selection and ranking methods. Risk stratification has been performed to classify patients into high, medium, and low categories, enabling targeted intervention. Results: Among all models, the XGBoost classifier trained on AHP–TOPSIS–prioritized features achieved a consistent accuracy of 99.28% under stratified 20-fold cross-validation, demonstrating robust diagnostic classification performance. The model predominantly captures hematologic patterns characteristic of thalassemia manifestations, functioning as an assistive diagnostic framework rather than a causal risk predictor. The explainability of predictions, ensured through comprehensive visual and statistical analyses, further enhances the model’s clinical transparency and reliability. Conclusion: The proposed MCDM–machine learning framework demonstrates strong potential for improving thalassemia risk assessment, enabling early detection and informed decision-making in maternal healthcare. The proposed framework should be regarded as a preliminary proof-of-concept system that demonstrates the feasibility of integrating Multi-Criteria Decision-Making (AHP–TOPSIS) with advanced machine learning and explainable-AI techniques for thalassemia assessment. Although the model achieved strong diagnostic performance under nested cross-validation, additional external validation and inclusion of causal predictors are required before clinical deployment. Full article

Synthetic Aperture Radar (SAR) ship detection remains challenging due to background clutter, target sparsity, and fragmented or partially occluded ships, particularly at small scales. To address these issues, we propose the Deformable Recurrent Criss-Cross Attention Network (DRC${}^2$-Net), a lightweight and efficient detection framework built upon the YOLOX-Tiny architecture. The model incorporates two SAR-specific modules: a Recurrent Criss-Cross Attention (RCCA) module to enhance contextual awareness and reduce false positives and a Deformable Convolutional Networks v2 (DCNv2) module to capture geometric deformations and scale variations adaptively. These modules expand the Effective Receptive Field (ERF) and improve feature adaptability under complex conditions. DRC²-Net is trained on the SSDD and iVision-MRSSD datasets, encompassing highly diverse SAR imagery including inshore and offshore scenes, variable sea states, and complex coastal backgrounds. The model maintains a compact architecture with 5.05 M parameters, ensuring strong generalization and real-time applicability. On the SSDD dataset, it outperforms the YOLOX-Tiny baseline with AP@50 of 93.04% (+0.9%), AP${}_s$ of 91.15% (+1.31%), AP${}_m$ of 88.30% (+1.22%), and AP${}_l$ of 89.47% (+13.32%). On the more challenging iVision-MRSSD dataset, it further demonstrates improved scale-aware detection, achieving higher AP across small, medium, and large targets. These results confirm the effectiveness and robustness of DRC${}^2$-Net for multi-scale ship detection in complex SAR environments, consistently surpassing state-of-the-art detectors. Full article

This work presents a mixed reality application for drum learning that combines the PocketDrum virtual drumming device with the Meta Quest 3 headset, integrating hand tracking to provide an immersive, responsive experience without the need for a physical drum set. The system features a modular architecture for real-time strike detection, visual guidance synchronized with music, spatial calibration, and audio rendering. The system additionally makes use of the headset’s color Passthrough during the calibration stage to align the virtual drum kit with the player’s position. To evaluate the system’s performance, a technical analysis was conducted to measure latency, jitter, and sampling rate across the technologies involved. Additionally, a functional validation experiment assessed how spatial hand tracking from Meta Quest 3 improved PocketDrum’s classification accuracy. Results showed that the fused system corrected 19.1% of drum assignment errors made by the inertial-only setup, enhancing consistency in complex rhythmic patterns. These findings demonstrate the effectiveness of sensor fusion for immersive percussion training and support its potential use in accessible, feedback-rich musical learning environments. Full article

In inter-satellite laser communication systems, angular deviations between the boresights of terminals exert an impact on system performance, thereby imposing higher requirements on performance parameters such as the angle measurement accuracy and range of the system. Conventional coherent angle measurement systems feature a fixed baseline, which results in insufficient dynamic adjustment capability for accuracy and range. To address the aforementioned issues, this paper proposes a variable-baseline coherent angle measurement method based on nutation scanning. By altering the baseline length through a nutation scanning strategy, this method achieves dynamic adjustment of angle measurement accuracy and range, enhancing the adaptability of the angle measurement system in different scenarios. For long-distance communication, a small nutation scanning angle (short baseline) is used to adapt to significant satellite relative position changes via a large angle measurement range, while a large nutation scanning angle (long baseline) is adopted for short-distance communication to ensure stable tracking with high angle measurement accuracy. Firstly, a mathematical model of the system is established, and the relationships between the nutation scanning angle, angle measurement accuracy, and angle measurement range are derived. The Monte Carlo method is employed to construct a variable-baseline angle measurement simulation system for data verification, and a tabletop experimental system is built for performance analysis. Experimental results show that when the nutation scanning angle γ increases from 10 μrad to 100 μrad, the baseline length increases from 0.05 μm to 0.5 μm, the angle measurement accuracy improves from 56.9 μrad to 6.35 μrad, and the angle measurement range narrows from 880 μrad to 560 μrad. These results are consistent with the trend of theoretical derivation and correspond to the simulation results. This study verifies the feasibility of dynamically regulating angle measurement accuracy and range via the nutation scanning angle and provides a reference for the design of space laser communication systems. Full article

Cross-view geo-localization allows an agent to determine its own position by retrieving the same scene from images taken from dramatically different perspectives. However, image matching and retrieval face significant challenges due to substantial viewpoint differences, unknown orientations, and considerable geometric distribution disparities between cross-view images. To this end, we propose a cross-view geo-localization framework based on novel view synthesis that generates pseudo aerial-view images from given street-view scenes to reduce the view discrepancies, thereby improving the performance of cross-view geo-localization. Specifically, we first employ 3D Gaussian splatting to generate new aerial images from the street-view image sequence, where COLMAP is used to obtain initial camera poses and sparse point clouds. To identify optimal matching viewpoints from reconstructed 3D scenes, we design an effective camera pose estimation strategy. By increasing the tilt angle between the photographic axis and the horizontal plane, the geometric consistency between the newly generated aerial images and the real ones can be improved. After that, the DINOv2 is employed to design a simple yet efficient mixed feature enhancement module, followed by the InfoNCE loss for cross-view geo-localization. Experimental results on the KITTI dataset demonstrate that our approach can significantly improve cross-view matching accuracy under large viewpoint disparities and achieve state-of-the-art localization performance. Full article

Background: Febrile seizures (FS) are the most common seizures in childhood, yet their clinical, biochemical, and genetic risk factors are still being clarified. This study aimed to provide a comprehensive evaluation of FS from clinical, laboratory, and genetic perspectives. Methods: In this prospective cohort study, 124 children aged 6 months to 5 years presenting with FS and 93 febrile controls without seizures were evaluated. Clinical features, laboratory parameters (including trace elements and hormonal markers), and genetic analysis using a 37-gene epilepsy panel were assessed. Multivariate logistic regression analysis was performed to identify independent predictors of FS, complex FS, and recurrent seizures. Results: Children with FS had significantly lower serum sodium, vitamin D, and zinc levels compared to controls. Multivariate analysis identified low sodium and low vitamin D levels as independent risk factors for FS. In the subgroup analysis, lower sodium and vitamin D levels and elevated ferritin levels were independently associated with complex FS. Lower serum zinc levels were significantly associated with seizure recurrence. Genetic analyses revealed pathogenic or likely pathogenic variants in 15.7% of patients with FS, predominantly involving SCN1A and PCDH19 genes. Patients with pathogenic variants also exhibited significantly lower levels of zinc, and selenium compared to genetically negative patients. Conclusions: This study highlights that metabolic disturbances, particularly involving sodium, vitamin D, and zinc, play a crucial role in FS occurrence, complexity, and recurrence. Ferritin may serve as a more sensitive indicator of inflammatory processes influencing seizure severity compared to CRP. Furthermore, genetic predispositions, especially SCN1A and PCDH19 variants, may underlie susceptibility in a subset of children. Routine evaluation of biochemical markers and consideration of genetic testing in selected cases may enhance individualized management strategies for FS. Full article

As the development of “smart villages” and “sustainable rural tourism” increasingly becomes a focal point on the global policy agenda, tourism-oriented villages are experiencing a growing demand for digital infrastructure transformation. Against this backdrop, smart outdoor furniture emerges as a noteworthy intervention. However, existing designs for smart outdoor furniture predominantly originate from urban contexts, often failing to align with the distinct preferences, behavioural patterns, and cultural identity of rural users. This study employs a mixed-methods approach, combining Q-methodology with an extended Technology Acceptance Model (TAM), to explore rural users’ technology acceptance pathways. Through Q-sorting, four typical attitude structures were identified: Pragmatic Function-Oriented, Cultural Concern-Oriented, Smart Enhancement-Oriented, and Technology Anxiety-Oriented. These qualitative insights were integrated into an extended TAM framework and validated through a structured survey (n = 319) using Partial Least Squares Structural Equation modelling (PLS-SEM). Findings confirm that Perceived Usefulness and Perceived Ease of Use remain the strongest predictors of user attitude and behavioural intention. Among contextual factors, Function Configuration exerts significant positive influence on both PU and PEOU; Cultural Adaptation significantly enhances PU; Social Influence primarily affects PEOU; Smart Features moderately influence both dimensions; and Perceived Cost Structure affects only PU. This research extends the applicability of the TAM model within rural socio-technical contexts. It provides empirical reference for inclusive and sustainable digital infrastructure design in tourism-oriented villages, while offering practical insights and dissemination pathways for smart design strategies in public spaces within similar socio-cultural environments. Full article

Background/Objectives: Breast cancer remains one of the leading causes of mortality among women, necessitating continued advancements in diagnostic methods to enhance early detection and treatment outcomes. This review explores the current landscape of breast cancer classification, focusing on machine learning (ML), deep learning (DL), and hybrid/ensemble models. Methods: A systematic search following PRISMA guidelines identified 50 eligible studies published between 2018 and 2025. Studies were included based on their use of mammogram datasets and implementation of computer-aided diagnosis methods for classification. Models were compared in terms of preprocessing, feature extraction, optimization strategies, and classification performance. Results: Representative high performing models illustrate the strengths and limitations of each approach. In ML, an optimized ELM achieved 100% accuracy on MIAS. DL methods such as Vision Transformers also reached 100% accuracy on DDSM, outperforming conventional CNNs. Hybrid models, particularly IEUNet++, achieved 99.87% accuracy, offering robust multi class classification. Conclusions: While ML and DL approaches can achieve near perfect accuracy, they typically focus on binary classification tasks and require extensive preprocessing, feature extraction, and optimization. In contrast, hybrid methods provide comparable or superior performance while simultaneously addressing multi-classification with fewer handcrafted steps, highlighting their robustness. These findings underscore the need for innovative solutions that balance model accuracy, interpretability, and resource efficiency. By addressing these challenges, future classification systems can better support early breast cancer detection and improve patient outcomes. Full article

Aiming at the problems of complex image background and numerous interference factors faced by visual navigation systems in orchard environments, this paper proposes an orchard navigation line recognition method based on U-Net. Firstly, the drivable areas in the collected images are labeled using Labelme (a graphical tool for image annotation) to create an orchard dataset. Then, the Spatial Attention (SA) mechanism is inserted into the downsampling stage of the traditional U-Net semantic segmentation method, and the Coordinate Attention (CA) mechanism is added to the skip connection stage to obtain complete context information and optimize the feature restoration process of the drivable area in the field, thereby improving the overall segmentation accuracy of the model. Subsequently, the improved U-Net network is trained using the enhanced dataset to obtain the drivable area segmentation model. Based on the detected drivable area segmentation mask, the navigation line information is extracted, and the geometric center points are calculated row by row. After performing sliding window processing and bidirectional interpolation filling on the center points, the navigation line is generated through spline interpolation. Finally, the proposed method is compared and verified with U-Net, SegViT, SE-Net, and DeepLabv3+ networks. The results show that the improved drivable area segmentation model has a Recall of 90.23%, a Precision of 91.71%, a mean pixel accuracy (mPA) of 87.75%, and a mean intersection over union (mIoU) of 84.84%. Moreover, when comparing the recognized navigation line with the actual center line, the average distance error of the extracted navigation line is 56 mm, which can provide an effective reference for visual autonomous navigation in orchard environments. Full article