Search Results (409)

This study investigates the structural sensitivity of a large-span steel space frame at Yanjiao Station to environmental disturbances during the critical “flexible suspension” stage of asymmetric hydraulic lifting. First, by analyzing the offset between the center of mass and the center of stiffness—induced by the asymmetric lifting configuration—the study systematically examines the spatial eccentric amplification effect under a coupled thermal-wind field. To this end, a non-uniform solar radiation model based on the Axis-Aligned Bounding Box (AABB) algorithm is integrated with a refined finite element model, enabling a full-factor parametric analysis under 20 coupled load conditions. The results reveal a significant time lag in the structural temperature field, with 12:00 identified as the critical time for maximum thermal deformation. The wind-induced response follows a “bimodal evolution” pattern, and the maximum translational-torsional coupling effect occurs at wind direction angles of 60° and 120°. Further analysis of the multi-field coupling mechanism indicates that the wind field dominates the deformation mode, while the temperature field amplifies the resulting response. Consequently, the peak displacement reaches 192.50 mm, which represents a 360.81% increase compared to the dead load baseline. The cantilever end is identified as the primary vulnerable region. Based on these findings, a “wind direction–time” two-dimensional monitoring strategy is proposed. This strategy provides scientific quantitative criteria and theoretical support for the construction safety of large-span structures, as well as for the development of a comprehensive early warning and health monitoring system. Full article

In the intelligent transportation system of smart cities, object detection from UAV aerial imagery serves as the core technical support for traffic flow monitoring, violation detection, and emergency response. However, traffic objects captured from UAV perspectives typically exhibit extremely low pixel occupancy and are embedded in complex backgrounds, leading to three fundamental limitations in existing detection methods: insufficient utilization of global context information, inaccurate weak feature enhancement, and severe feature scale confusion. To address these challenges, this paper proposes ContextTiny-Net, an ultra-tiny object detection network built upon multi-dimensional symmetry design principles for urban UAV scenarios. Specifically, we first construct a global–local perception symmetric MetaFormer backbone and a hierarchical scale symmetric four-layer detection head, which achieves full-coverage detection from ultra-tiny to regular traffic objects with minimal computational overhead. Second, we design an information-theoretic and spatial-distribution-complementary symmetric-weak feature enhancement module, which accurately locates and strengthens weakly activated regions of small objects from two mutually complementary and symmetric dimensions. Finally, we propose a cross-scale decoupling symmetric feature fusion module and a symmetric Gaussian distribution-based normalized Wasserstein distance loss, which effectively eliminate scale confusion and significantly improve the robustness of small object bounding box regression. Extensive experiments on three mainstream benchmarks (AI-TOD, VisDrone, and COCO) demonstrate that ContextTiny-Net outperforms state-of-the-art methods in both overall detection accuracy and ultra-tiny object detection performance, verifying the effectiveness of the proposed symmetry-enhanced design paradigm. Full article

Recent advances in artificial intelligence (AI), machine learning (ML), deep learning (DL), and remote sensing technologies have transformed agricultural monitoring, precision farming, and climate-resilient decision-making. However, the widespread adoption of AI-driven agricultural systems remains constrained by the black-box nature of advanced predictive models, particularly deep neural networks. Explainable Artificial Intelligence (XAI) has emerged as a critical solution for improving transparency, interpretability, accountability, and trust in AI-based agricultural remote sensing systems. This review provides a comprehensive synthesis of the recent developments in XAI applications within smart agriculture, with emphasis on interpretable remote sensing analytics and sustainable decision-making. The review discusses the evolution of AI in agriculture, major remote sensing platforms, explainability frameworks, and the integration of XAI with satellite imagery, unmanned aerial vehicles (UAVs), Internet of Things (IoT), and geospatial big data. Key agricultural applications, including crop classification, yield prediction, disease detection, soil property assessment, irrigation management, carbon monitoring, and climate adaptation, are critically evaluated. Furthermore, the review compares intrinsic and post hoc explainability methods such as attention mechanisms, saliency maps, and counterfactual explanations. The interpretation of model outputs and reported results from recent studies is discussed to demonstrate how XAI improves model reliability and stakeholder confidence. Challenges related to data heterogeneity, scalability, uncertainty, ethics, fairness, and computational complexity are also analyzed. Finally, future perspectives are presented regarding hybrid explainable frameworks, physics-informed AI, edge computing, digital twins, and trustworthy autonomous agricultural systems. The review emphasizes the central role of XAI in enabling transparent and sustainable agricultural intelligence under rapidly changing climatic and environmental conditions. Full article

The Vortex Ring State (VRS) is a critical aerodynamic hazard for rotorcraft, characterized by highly unsteady fluid–structure interactions and severe low-frequency vibrations. While data-driven deep learning models have shown promise in aviation state monitoring, their inherent “black-box” nature fundamentally contradicts the stringent interpretability requirements of airworthiness certification. To address this, we propose an “AI for Science” paradigm, investigating whether advanced Vision Transformers (ViT) can autonomously discover underlying aerodynamic mechanisms without human physical priors. First, to ensure absolute data fidelity, flight test datasets of a coaxial unmanned aerial vehicle were rigorously labeled using cross-validation from high-fidelity Computational Fluid Dynamics (CFD) simulations and wind tunnel tests. One-dimensional vibration signals were then transformed into two-dimensional Continuous Wavelet Transform (CWT) spectrograms. By employing Target-Layer Gradient Adaptation (Grad-CAM) techniques, we conducted a systematic comparison between traditional Convolutional Neural Networks (ResNet50) and ViT. The results demonstrate that while CNNs suffer from diffuse attention caused by high-frequency noise, the frozen-backbone ViT model achieves a physically interpretable accuracy of $93.24\%$, while autonomously locking its global attention onto a perfectly horizontal feature band centered at $41.7$ Hz. Crucially, this autonomously discovered feature precisely aligns with the theoretically derived once-per-revolution (1P) fundamental frequency of the rotor’s flap-lag coupling response under VRS aerodynamic turbulence. This research provides direct visual evidence bridging black-box AI decisions with classical fluid mechanics, proposing a “Mechanism-Guided Verification” framework that offers a trustworthy pathway for the future certification of AI in safety-critical aerospace systems. Full article

Marine pollution monitoring increasingly relies on Biological Early Warning Systems (BEWSs), which use living organisms as continuous, integrative sentinels of water quality. The moon jellyfish Aurelia aurita is a sensitive but under-exploited candidate for this role. We present a computer-vision BEWS pipeline that is unsupervised at inference time and operates without labelled pollution-response data, converting side-view aquarium video of single A. aurita medusae into a binary pollution alarm. Per-frame YOLO bounding-box detections are reduced to a continuous bell-area signal and a centroid trajectory, from which eleven pulsation, kinematic, and detection-quality features are extracted on 60 s sliding windows. A per-animal baseline is fitted on a clean-water baseline (recommended ≥15 min), and a two-layer detector—fast outlier detection on the mean absolute z-score with a k-of-N rule, plus one-sided CUSUM (cumulative sum) accumulation—flags any sustained deviation. Validation on six adult medusae exposed to diesel-WAF detected all six animals (95% CI 54–100%) and produced no false alarms in 203 clean-window opportunities (exact 95% upper bound 1.8%; rule-of-three estimate ≈1.5%). First-alarm latencies ranged from 1.0 to 23.7 min, and the observed responses were described as three descriptive patterns in this pilot dataset: sharp step-change, slow drift, and mixed. The deployed anomaly scoring step contains no neural-network weights, runs in under 300 lines of Python, and is designed for field-portable use in settings where a stationary side-view camera can be positioned alongside an aquarium, although field validation remains required. Per-animal anomaly detection accommodates the strong inter-individual variability of the diesel-WAF response that limits supervised clean-versus-polluted classification at this sample size. Full article

Road quality monitoring is necessary for safety, ride comfort, and driver-assistance systems. The knowledge of road features enables preventive and corrective actions at vehicle and infrastructure levels. While deep learning models are effective for surface classification, transitioning them to real-time embedded environments requires optimization. This study deploys a model based on convolutional and long short-term memory neural networks to classify five road conditions using continuous vibration data from multiple inertial measurement units. Executed on a MicroAutoBox III Embedded PC, the system preprocesses data at vehicle speeds between 5.0 and 25.0 km/h. Compared to the offline baseline deployment, this edge-optimized architecture reduced inference latency by 88% (from 33.8 ms to 4.05 ms) while maintaining a fair weighted-average F1-score of 0.8751 in real-world, cross-platform conditions (against the offline baseline average F1-score of 0.9338). This processing time operates within the 11.6 ms limit required by the 86 Hz sensor polling rate. Additionally, geospatial mapping was able to localize structural anomalies, showing robustness to environmental lighting conditions, which frequently affect vision-based systems. This cyber-physical deployment suggests the feasibility of executing temporal deep learning real-time models. Future work will target highway-speed validation and domain adaptation to assess transferability across diverse vehicle suspensions. Full article

Accurate monitoring of hydrological dynamics in complex perennial landscapes is a cornerstone for tropical agricultural sustainability. Traditional energy balance models based on orbital optical data often face methodological bottlenecks due to cloud cover and the “greening myth,” where optical indices fail to capture immediate water stress due to the non-linear decoupling between stomatal closure and pigment loss. This study developed a cloud-integrated multisensor framework to estimate actual evapotranspiration (ET_a) at a refined 100 m resolution in mountain coffee systems, utilizing active microwave proxies from Sentinel-1. We fused polarimetric metrics—Degree of Polarization (DoP) and Shannon Entropy (SE)—with land surface temperature and soil moisture data. Multiple Linear Regression (MLR) was compared against non-linear algorithms (Random Forest and SVR) to prioritize model parsimony and physical interpretability. The results show that MLR emerged as the most parsimonious and suitable model within this localized dataset scope (R² = 0.872; RMSE = 2.916 mm/8-day), outperforming complex “black-box” architectures. Soil moisture emerged as the dominant environmental driver of ET_a variability, while SAR-based metrics served as sensitive mechanical proxies for canopy geometric heterogeneity and macro-structural variations. Cross-correlation analysis revealed a 16-day lag, empirically indicating that biophysical water shifts temporally precede geometric canopy alterations. Operationally, this framework ensures temporal continuity under persistent cloud cover and provides high-fidelity spatial detailing for precision water management. This approach offers an auditable and scalable tool for watershed planning and climate resilience in tropical agriculture. Full article

The early and accurate recognition of fruit tree pests and diseases is essential for safeguarding fruit yield, quality, and sustainable agricultural production. Conventional manual inspection methods are inadequate for meeting the demands of continuous, objective, and real-time monitoring in large-scale orchards. Following the framework of “model evolution–key challenges–edge-intelligent deployment,” this review systematically summarizes advances in deep learning-based recognition of fruit tree pests and diseases, and compares the effectiveness and limitations of representative methods from the perspectives of data complexity, model generalization and robustness, real-time inference, cross-modal fusion, and trustworthy diagnosis. Existing studies indicate that CNNs, attention mechanisms, Transformers, multimodal fusion, and lightweight networks have promoted the transition of fruit tree pest and disease recognition from image classification to object detection, lesion segmentation, and edge deployment; however, sample scarcity, class imbalance, insufficient cross-domain generalization, black-box decision-making, energy constraints, and long-term robustness remain major bottlenecks for field application. Future research should focus on open orchard environments and develop data-efficient, interpretable, low-power, and continuously updatable edge-intelligent recognition systems, thereby advancing precision agriculture and smart orchards. Full article

Fraud detection models often achieve a strong ranking performance through black-box ensembles, but operational deployment also requires calibration, low explanation cost, and auditable scoring logic. This study develops an interpretable fraud-detection pipeline for IEEE-CIS by combining a 63-variable causal concept bank with teacher-guided additive Explainable Boosting Machine (EBM) students. The concept bank summarizes the temporal state, entity history, novelty/reuse, identity missingness, and aggregate deviation. Experiments use a chronological out-of-time split and a stricter pseudo-entity-disjoint holdout. In the main three-seed evaluation, the CatBoost predictive ceiling and XGBoost teacher achieved PR-AUC 0.489 ± 0.001 and 0.478 ± 0.003, respectively. Among interpretable models, concept-only EBM reached 0.189 ± 0.000, raw-only EBMs reached 0.372 ± 0.005 (top-k = 8) and 0.383 ± 0.002 (top-k = 12), and hybrid EBMs reached 0.407 ± 0.003 (top-k = 8) and 0.407 ± 0.004 (top-k = 12), consistently improving over matched raw-only additive baselines. The final top-k = 8 hybrid reduced input features from 154 to 71, achieved about 9.7× faster inference than XGBoost, remained close to XGBoost in ECE-15 calibration (0.01587 vs. 0.01611) while having a higher Brier score, and produced native local explanations far faster than XGBoost + SHAP. The results position CatBoost as the predictive ceiling and hybrid EBM as a benchmark-supported, deployment-relevant interpretable compromise for applied financial risk-screening workflows, rather than as a production-validated fraud-monitoring system. Full article

Currently, devices such as solar insecticidal lamps are widely used in agricultural pest control, but routine trapping is insufficient to meet the demands of precision agriculture. Therefore, determining the nocturnal phototactic rhythm of pests to optimize the control strategies of insecticidal lamps has become key to achieving precise pest control. However, existing automated monitoring and forecasting devices struggle to effectively monitor the nocturnal phototactic rhythm of small pests. To address this issue, this study developed an automated monitoring system for phototactic rhythm based on sticky traps and machine vision. For the hardware, an image acquisition device integrating a darkroom and scheduled supplementary lighting was designed to obtain stable time-series images of nocturnal pests. For the algorithm, the YOLO-STP detection model was proposed by improving upon the baseline YOLOv11 model. This model introduces a P2 detection layer, a Coordinate Attention (CA) mechanism, and a hybrid bounding box regression loss function integrating WIoU and NWD. Combined with a sliding window cropping method, it further enhances the detection capability for small objects. Additionally, an incremental counting method based on spatial cascade matching was proposed to mitigate counting errors caused by target occlusion or detachment in the time-series images. Experimental results indicate that the mean average precision (mAP) of the detection model was 93.2%. For the counting method, the coefficient of determination ($R^2$) was 0.98, with an RMSE of 1.97 and an MAE of 1.60. Field validation in real-world paddy fields demonstrated that the system can accurately record the abundance changes of 12 pest species, intuitively visualizing the differences in phototactic rhythms among various species. This study provides a viable automated monitoring tool for acquiring the nocturnal activity rhythm data of agricultural pests in the field. Full article

Accurate and reliable prediction of lettuce fresh weight is essential for optimising protected cultivation management and improving the yield and quality. Multimodal data combined with machine learning models have been widely used for monitoring crop growth. However, existing approaches often fail to capture dynamic physiological changes during crop growth, whereas conventional machine learning models are frequently limited by their black-box nature and thus cannot reveal the intrinsic relationships between features and targets. To address the above issues, this study developed a stationary, multi-sensor integrated data acquisition platform under controlled greenhouse conditions. By fusing multi-view morphological structure, color and texture, and multispectral features, the study constructed interpretable machine learning models for predicting the fresh weight of lettuce. Based on the data collected by the platform, 66 initial features covering morphology, color texture, and vegetation indices were extracted from the data. A two-stage feature-selection strategy combining Pearson correlation screening and variance inflation factor (VIF)-based multicollinearity elimination was used to select nine optimal input variables for the model. To achieve an accurate estimation of the fresh weight of lettuce, the system compared six models: Support Vector Regression (SVR), Random Forest Regression (RFR), Gradient Boosted Decision Tree Regression (GBDT), K-nearest neighbour regression (KNN), XGBoost, and Backpropagation Neural Network (BPNN). The results indicate that the SVR model based on multimodal data fusion performed best, with an R² of 0.93, an RMSE of 3.23 g, an RMSEn of 5.60%, and an MAE of 2.31 g, demonstrating a significantly higher prediction accuracy than the other models. Furthermore, the SHAP interpretation method was used to reveal the contributions of key features to fresh weight estimation and their interaction mechanisms. This study provides a feasible approach and technical guidance for non-destructive estimation of fresh weight in lettuce under controlled conditions, and offers a preliminary basis for the development of phenotypic monitoring models for protected cultivation. Full article

Currently, mining material transportation in warehouses relies heavily on manual operations, which pose safety hazards and suffer from low standardization and automation. Existing automated attempts using single-sensor perception or single-arm manipulators lack robustness and adaptability in harsh mine environments. To address these gaps, this paper proposes an intelligent loading system for standardized mining material transportation based on multimodal perception and multi-arm collaboration. First, the overall architecture of the transportation and loading system is introduced, comprising five modules: a standardized carrier platform and modular transport boxes, a box locking and spreader module, a multi-sensor recognition and positioning module, a multi-manipulator collaborative loading/unloading module, and a perception feedback and (human-controlled) overhead crane module. Next, a standardized hardware system is designed, focusing on the standardization of the separable and easily detachable carrier platform and the modularization of transport boxes, along with the locking mechanism between them, establishing the hardware foundation for the system. Subsequently, a multimodal perception data fusion and recognition positioning technology based on multiple depth cameras, UWB, and IMU is investigated to provide perceptual feedback for automated loading/unloading. Following this, a multi-manipulator collaborative control technology based on multi-agent error consensus is developed, designing a “two-master, two-slave” structure and a collaborative control algorithm to achieve automated loading/unloading of transport boxes. An information-based interactive monitoring software is then designed to monitor system perception data in real time and control the system’s operational status, ensuring safety and controllability. Finally, the feasibility and effectiveness of the system are validated through simulations and prototype experiments. This work provides a foundation for standardized transportation and storage of mining materials and outlines a practical system-level approach. Full article

Heap bioleaching is widely used to extract copper from low-grade sulfide ores thanks to its operational simplicity, low cost, and environmental sustainability. However, current control strategies rely primarily on single-factor optimization and often overlook the synergistic interactions of multiple key parameters, such as ore particle size, pore structure, pH, temperature, microbial activity, and oxygen transfer efficiency. As a result, issues such as low recovery rates, extended leaching periods, and high operational costs persist. Moreover, the “gray-box” nature of heap systems impedes real-time monitoring of internal physical, chemical, and biological processes. In addition, empirical multi-parameter optimization is time-consuming and inadequate for capturing complex interdependencies. This review was conducted to systematically examine the key factors influencing heap bioleaching efficiency and critically evaluate recent advances in numerical simulation and intelligent control strategies. As a result, we identified a major research gap: the existing models—including microscale shrinking core models (SCMs), mesoscale pore-network models based on CT reconstruction, and macroscale continuum models—have inherent limitations. SCMs assume idealized spherical particles with uniform mineral distribution while neglecting pore structure evolution and biofilm dynamics. Mesoscale models offer detailed pore characterization but lack robust multi-physics coupling (thermal–hydro–mechanical–chemical–biological, or THMCB). Macroscale models rely on homogenization assumptions that oversimplify spatial heterogeneity and temporal variations in permeability. This analysis covers the relevant literature from 1985 to 2025, with a focus on three methodological scales (micro, meso, and macro) and their integration with machine learning approaches. A notable finding is that hybrid neural network models (e.g., BP and RBF architectures) outperform purely physics-based models in predicting leaching kinetics under varying operational conditions. However, their accuracy depends heavily on high-quality field data—a limitation rarely addressed in prior reviews. By clearly delineating these model-specific limitations and scale-dependent trade-offs, this review makes two unique contributions: a structured framework for selecting and coupling numerical methods according to process requirements and a roadmap for integrating artificial neural networks with multi-physics simulations to achieve real-time intelligent control of heap bioleaching. The findings offer both theoretical guidance and practical references for optimizing the processing of low-grade copper sulfide ores. Full article

With the increasing demand for reliable structural safety assessment in service, high-precision, non-contact, and long-term deformation monitoring has become increasingly urgent for large civil engineering structures. To address this need, this study proposes and validates a system-level non-contact monitoring framework that integrates an embedded vision-based deformation sensor with intelligent algorithms. Rather than treating individual techniques as isolated components, the proposed framework integrates high-precision optical imaging, subpixel localization, and intelligent image processing into a unified monitoring workflow. By continuously imaging and tracking targets on the structural surface, high-precision acquisition of two-dimensional dynamic displacements is achieved. To address issues such as image jitter, environmental disturbances, and camera-induced vibrations under long-distance imaging conditions, a hybrid algorithm based on signal processing and image correction is introduced to effectively compensate and filter the monitoring data, thereby significantly improving the stability and accuracy of deflection measurements. In engineering applications, a girder bridge and an integral open-box sluice structure were selected as monitoring objects, and field experiments were conducted over multiple periods under different working conditions. The results indicate that the proposed system can stably capture small structural displacements, achieving sub-millimeter measurement accuracy. The findings verify the feasibility and reliability of the proposed intelligent vision-based deformation monitoring technology in complex engineering environments, and provide a new technical approach for structural safety assessment and operational monitoring of infrastructure such as bridges and hydraulic structures. Full article

Artificial intelligence (AI) is increasingly transforming gastrointestinal endoscopy by supporting lesion detection, lesion characterization, quality assessment, and clinical risk prediction. Hemostatic decision-making represents a particularly complex field for AI integration, as therapeutic decisions are often made rapidly in the presence of active bleeding, impaired visualization, unstable patients, and variable lesion accessibility. This review critically examines the current evidence for AI-assisted decision-making in gastrointestinal endoscopy and endoscopic hemostasis, with emphasis on gastrointestinal bleeding, prediction of hemostatic therapy requirements, bleeding-risk stratification, rebleeding prediction, transfusion support, and post-procedural monitoring. Available studies suggest that machine learning and deep learning models may outperform conventional scoring systems in selected retrospective or validation cohorts, improve recognition of high-risk lesions, support less experienced endoscopists, and contribute to more individualized management of non-variceal bleeding, variceal bleeding, and capsule endoscopy findings. However, prospective interventional evidence remains sparse, and most available models are limited by retrospective design, single-center datasets, incomplete external validation, black-box decision-making, heterogeneous reporting, workflow barriers, and uncertain cost-effectiveness. AI should therefore be regarded as an adjunctive decision-support tool rather than an autonomous replacement for clinical judgment. Its future value will depend on prospective multicenter validation, explainability, real-time usability, regulatory clarity, post-deployment surveillance, and evidence of improved patient-centered outcomes before widespread implementation in emergency endoscopy practice. Full article