Search Results (420)

Synthetic Aperture Radar (SAR) imagery is inherently degraded by multiplicative speckle noise, rendering traditional superpixel methods—which rely on hard assignment and uniform initialization—suboptimal for boundary preservation. This study proposes a complexity-aware superpixel generation framework featuring differentiable soft-assignment optimization. The approach employs an F-LGRP (Fusion of Local Gradient Pattern Representation) feature descriptor that fuses regional gradient statistics via Gaussian filtering to suppress speckle, coupled with a complexity-driven recursive quadtree initialization strategy yielding non-uniform seed density. A U-Net architecture predicts soft pixel–superpixel association maps within a 9-neighborhood constraint, supervised by a multi-objective loss integrating edge information reconstruction and boundary feature reconstruction. Comprehensive evaluations on simulated and real SAR images (WHU-OPT-SAR and Munich) demonstrate that the proposed method achieves state-of-the-art performance across Boundary Recall, Undersegmentation Error, Compactness, and Achievable Segmentation Accuracy compared to SLIC, SNIC, Mean-Shift, PILS, and SSN. Validation on downstream segmentation tasks further confirms superior accuracy and computational efficiency, establishing the framework as an effective solution for end-to-end SAR image analysis. Full article

The synergistic control of multiple pollutants is critically challenged by complex nonlinear interactions, strong spatiotemporal heterogeneity, and the difficulty of tracing causal drivers. Deep learning offers high predictive power but suffers from the “black-box” problem, limiting its acceptance in environmental decision-making. Explainable Deep Learning (XDL) integrates physical mechanisms with interpretable algorithms, achieving both prediction accuracy and explanatory transparency. This review systematically evaluates the effectiveness and limitations of XDL in analyzing multi-pollutant interactions, with a comparative focus on atmospheric and aquatic environments. Key techniques, including SHAP, attention mechanisms, and physics-informed neural networks, are examined for their roles in synergistic monitoring, source apportionment, and regulatory optimization. The main findings reveal that: (1) XDL, particularly the “tree model + SHAP” paradigm, has become a dominant tool for quantifying driving factors, yet most attributions remain correlational rather than causal; (2) physics-informed fusion (soft vs. hard constraints) improves physical consistency but faces unresolved conflicts between data and physical laws, with current models lacking a conflict detection mechanism; (3) cross-media comparison shows a unified technical logic of “physical mechanism guidance + post hoc feature attribution”, but atmospheric applications lead in embedding advection–diffusion constraints, while aquatic research excels in spatial topology modeling via graph neural networks; (4) critical bottlenecks include the lack of causal inference, uncertainty-unaware interpretations, and data scarcity. Future directions demand a shift from correlation-only to causal-aware attribution, from blind fusion to conflict-detecting systems, and from no evaluation standards to domain-specific validation benchmarks. XDL is poised to transform multi-pollutant governance from experience-driven to intelligence-driven approaches, provided that verifiable interpretability and physical consistency become core design principles. Full article

In industrial environments, robust Temporal Action Localization (TAL) is essential; however, frequent occlusions often compromise the reliability of skeletal data, leading to negative transfer in multimodal fusion. To address this challenge, we propose a Gated Skeleton Refinement Module (Gated SRM), a universal front-end preprocessing module that explicitly incorporates OpenPose confidence scores into the network architecture. By applying these scores as a logarithmic bias within a self-attention mechanism, our method achieves soft suppression—dynamically attenuating the attention weights assigned to unreliable joints—before adaptively fusing the refined skeletal features with RGB representations through a learnable gating network. Extensive experiments on the heavily occluded IKEA ASM dataset demonstrate that our approach effectively prevents the catastrophic accuracy degradation typical of naive and established multimodal fusion strategies, improving the mean Average Precision (mAP) to 21.77%, maintaining parity with the RGB-only baseline while demonstrating superior robustness. Furthermore, the system maintains a practical end-to-end inference speed of approximately 9.2 frames per second (FPS), which is sufficient for monitoring macro-level industrial workflows. By prioritizing confidence-based data selection over data restoration, this sensor-metadata-driven architecture offers a robust and principled approach acting as a critical fail-safe and safety-net for real-world action recognition under occlusion. Full article

Reliable air-quality monitoring is essential for urban exposure assessment and environmental policy, yet many downstream applications are hindered by sparse regulatory stations and noisy real-world measurements. While diffusion models have shown promise for probabilistic spatiotemporal imputation, common conditioning strategies can be brittle: purely input-based conditioning may drift from sparse constraints, whereas hard clamping can introduce a clean–noisy mismatch and propagate corrupted readings during reverse sampling. In this work, we propose STGPD (SpatioTemporal Graph Posterior Diffusion), a probabilistic framework that formulates city-scale pollutant reconstruction as posterior sampling on a graph-structured spatiotemporal field. STGPD enforces noise-aware soft consistency by re-noising visible observations to the current diffusion level and fusing a noise-matched measurement term with the model prior via variance-weighted fusion under an explicit observation-noise model. To improve spatial extrapolation in heterogeneous urban environments, we further construct a dual-view graph that combines geographic proximity with functional similarity derived from static descriptors. Experiments on real-world monitoring data in Augsburg, Germany, for PM₁₀ and NO₂ show that STGPD provides a robust probabilistic reconstruction framework under extreme sparsity, station outages, and synthetic sensor-noise injection in this sparse-monitoring case study. Compared with strong deterministic and diffusion-based baselines, STGPD achieves improved reconstruction accuracy (MAE/RMSE) and better-calibrated uncertainty estimates (CRPS) under the current evaluation protocols. Full article

To solve key challenges in machine vision-driven online defect recognition of soft packaging, such as inadequate ability to capture defect deformation, difficulty in extracting defect features, and limited generalization performance of models, an online detection method for soft packaging defects is proposed by integrating edge computing and domain adaptation. By replacing the backbone network with GhostNet and optimizing feature fusion through an adaptive feature pyramid network (AFPN), the number of model parameters was significantly reduced by approximately 30%. A multi-scale domain adversarial neural network (DANN) was introduced to enable rapid adaptation to target domains by leveraging historical multi-category data. A three-tier edge computing architecture of “terminal–edge–cloud” was built, and the lightweight YOLOv8 model was deployed on edge nodes, significantly reducing detection latency. Experimental results demonstrated that the proposed method achieved an average detection accuracy of 97.5% across five types of soft packaging products, with an inference time of only 10.9 ms and an average system response time of 148 ms. This approach significantly enhances detection speed and accuracy for soft packaging defect recognition, effectively meeting the real-time requirements of industrial inspection. Full article

Apple detection is a core perception task for harvesting robots operating in complex orchard environments. Targets are frequently affected by branch–foliage occlusion, alternating front/side/back lighting, and strong local illumination fluctuations, which blur object boundaries against background textures and substantially increase detection difficulty. To improve target perception under these conditions, we propose an improved detector, YOLOv11-CBMES. First, based on YOLOv11, we replace the original neck with a weighted BiFPN to enhance cross-scale feature fusion under occlusion. Second, we introduce a Contrast-Driven Feature Aggregation (CDFA) module at the P5 stage, using Haar wavelet decomposition to decouple low-frequency illumination components from high-frequency structural components. Third, we reconstruct spatial feature learning and the upsampling pathway using CSP-based multi-scale blocks and efficient upsampling blocks, and embed a zero-parameter Shift-Context strategy to strengthen local neighbourhood interaction. Finally, we formulate apple detection as a three-class occlusion classification task (No Occlusion, Soft Occlusion, and Hard Occlusion) to support occlusion-aware target recognition. On the apple occlusion dataset, YOLOv11-CBMES achieves ${\mathrm{m}\mathrm{A}\mathrm{P}}_{\mathrm{N}\mathrm{O}}$ = 83.50%, ${\mathrm{m}\mathrm{A}\mathrm{P}}_{\mathrm{S}\mathrm{O}}$ = 67.36%, and ${\mathrm{m}\mathrm{A}\mathrm{P}}_{\mathrm{H}\mathrm{O}}$ = 51.90% at IoU = 0.5. Compared with YOLOv11n under the same training protocol, the gains are +2.16 pp (NO), +3.68 pp (SO), and +5.31 pp (HO), with the largest improvement observed in Hard Occlusion (HO). The results indicate that introducing frequency-domain structural processing into the detection framework improves apple occlusion classification and object detection performance, and provides a theoretical basis for designing perception modules for end-effector operations in apple harvesting robots. Full article

Bearings play crucial roles in industrial machinery. Therefore, the continuous monitoring and effective detection of bearing failures are essential to ensure the safety and reliability of motors. Traditional fault diagnosis methods often require information from both the time and frequency domains; however, converting them into a two-dimensional representation significantly increases computational costs. Conversely, utilizing only time-domain features while ignoring frequency-domain features results in incomplete fault information, reducing accuracy under various operating conditions. This study proposes an efficient dual-stream network with soft-gated fusion for bearing fault diagnosis that simultaneously analyzes acoustic emission signals in the time and frequency domains. Our approach employs two separate feature-learning branches: the time-domain branch directly extracts features from the segmented raw acoustic emission signals, and the frequency-domain branch learns features from one-dimensional spectral vectors obtained using the fast Fourier transform. A gated fusion mechanism adaptively balances the contribution of each domain before classifying fault types. The experimental results show that the proposed method significantly reduces the computational cost compared with that of a two-dimensional-representation-based model and improves accuracy over time-only or frequency-only baselines. Full article

Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift. Full article

To address the limitations of insufficient feature representation, large model size, and high deployment cost in network traffic classification, a lightweight classification framework based on multi-teacher knowledge distillation is proposed. The framework consists of two heterogeneous teacher networks and a compact student network to enable end-to-end traffic classification under constrained computational resources. The teacher networks incorporate complementary spatio-temporal modeling strategies, including a bidirectional temporal convolutional network (BiTCN) enhanced with attention mechanisms and convolutional neural network (CNN), and a parallel spatio-temporal fusion architecture integrating bidirectional long short-term memory (BiLSTM) and CNN. Knowledge from the teacher ensemble is distilled into a lightweight CNN-based student network through soft-target supervision, leading to improved generalization capability with significantly reduced model complexity. Experimental results demonstrate that effective knowledge transfer is achieved while reducing model parameters by more than 80%, and performance gains of about 1–3% are obtained compared with baseline methods. These results indicate strong potential for practical deployment in resource-constrained network environments. Full article

This study provides a comprehensive review on monocular metrology and fuzzy random-set portfolio management of financial assets. The findings and conclusions are elaborated as follows. Soft computing and AI have already enhanced and will further empower a variety of applications of monocular metrology and fuzzy random-set portfolio management of financial assets through progressive quantification and capturing of domain situations. The single most significant limitation of monocular metrology lies in its intrinsic incapability of direct measurement of 3D geometry through 2D imagery. The future of monocular metrology lies in deep learning and end-to-end solutions, multi-sensor data fusion, algorithmic optimization and real-time performance, self-supervised learning and generalization, and standardization and practical deployment. Neither statistical validation nor performance optimization alone is sufficient to support decision-makers in making portfolio decisions that are reliably and trust-worthy. A promising portfolio management decision-making framework should integrate the statistical rigor of fuzzy statistics with fuzzy random portfolio optimization techniques to quantitatively account for fuzziness and uncertainty while better balancing computational efficiency, statistical reliability, interpretability, and practical credibility. Full article

Accurate and spatially resolved yield estimation is a critical requirement for precision agriculture and orchard management. This paper presents a geometrically consistent, orchard-scale apple yield estimation framework that integrates GNSS–visual-inertial odometry (VIO) fusion, deep learning-based object detection, multi-frame tracking, three-dimensional triangulation, and incremental factor-graph optimization. Camera poses are obtained using ZED GNSS–VIO fusion and subsequently refined using an iSAM2-based nonlinear smoothing approach that incorporates strong relative-motion constraints and soft global ENU (East-North-Up) translation priors. Apples are detected using a YOLO-based model and associated across frames via CoTracker3, enabling robust multi-view landmark reconstruction. Reprojection factors and landmark priors are incorporated into a unified nonlinear factor graph to jointly optimize camera trajectories and 3D apple positions. The reconstructed apples are spatially aggregated into a grid-based mass map, where individual fruit volumes are estimated assuming spherical geometry and converted to mass using density models. The resulting ENU-referenced yield plot provides a structured representation of orchard production variability. Experimental results demonstrate significant reductions in reprojection error after optimization and improved global consistency of the trajectory, leading to stable and spatially coherent 3D reconstructions. The proposed pipeline bridges perception, geometry, and optimization, providing a scalable solution for orchard-scale yield mapping and decision support in precision agriculture. Full article

Remote sensing (RS) images are often degraded by atmospheric haze, which compromises both visual interpretation and downstream applications. To address this, we introduce CSGL-Former, a novel Cross-Stripes Global–Local Fusion Transformer for RS image dehazing. Our model efficiently captures anisotropic long-range dependencies using cross-stripes attention (CSA) and aggregates hierarchical global semantics via a Multi-Layer Global Aggregation (MLGA) module. In the decoder, global context is adaptively blended with fine-grained local features to restore intricate textures. Finally, inspired by the atmospheric scattering model, a soft reconstruction head restores the clear image by predicting spatially varying affine parameters, strictly preserving content fidelity while effectively removing haze. Trained end-to-end, CSGL-Former demonstrates a compelling balance of accuracy and efficiency. Extensive experiments on the RRSHID and SateHaze1K benchmarks show that our model achieves state-of-the-art or highly competitive performance against representative baselines. Ablation studies further validate the effectiveness of each proposed component. Full article

Decentralized agricultural gasification remains constrained by the thermochemical instability of high-alkali residues, such as straw and stalks. This operational bottleneck is defined by a narrow thermal window: oxidation core temperatures are typically targeted above 1000 °C for effective tar cracking, yet grate temperatures are constrained, often below 850 °C, depending on the specific ash fusion characteristics of the feedstock, to prevent viscous sintering and bed clinkering. This work proposes a conceptual framework for a control strategy designed to address these conflicting requirements through a unified framework integrating inferential soft-sensing, hierarchical Model Predictive Control (MPC), and sensor health monitoring. Machine learning architectures capture temporal dependencies and cumulative thermochemical transformations to reconstruct unobservable internal states. This enables real-time state estimation with reported accuracy levels (average test R² of 0.91–0.97) and 100% physical consistency through monotonicity constraints, effectively managing the critical thermal lag of densified pellets (400–600 s response time). High-fidelity CFD simulations anchor the soft-sensing layer, ensuring model robustness across the inherent variability of agricultural feedstocks. The architecture shifts control logic from reactive adjustments to anticipatory intervention through adaptive multi-mode operation that decouples high-intensity oxidation from grate integrity limits, while dynamic biochar management serves as a multifunctional control variable for tar cracking enhancement and alkali sequestration. Future work will focus on pilot-scale validation under transient feedstock conditions. Full article

Visual perception is fundamental to robotic manipulation for recognizing objects, goals, and contextual details. Third-person cameras provide global views but can miss contact-rich interactions and require calibration. Wrist-mounted egocentric cameras reduce these limitations but introduce occlusion, motion blur, and partial observability, which complicate visuomotor learning. Furthermore, existing perception modules that rely solely on pixels or fuse imagery with proprioception as flat vectors do not explicitly model structured scene representations in dynamic egocentric views. To address these challenges, a multi-slot attention fusion encoder for egocentric manipulation is introduced. Learnable slot queries extract localized visual features from image tokens, and Feature-wise Linear Modulation (FiLM) conditions each slot on the robot’s joint states, producing a structured slot-based latent representation that adapts to viewpoint and configuration changes without requiring object labels or external camera priors. The resulting structured slot-based latent representation is used as input to a Soft Actor–Critic (SAC) agent, which achieves a higher mean cumulative return than pixel-only CNN/DrQ and state-only baselines on a ManiSkill3 egocentric manipulation task. Probing experiments and real-camera evaluation further show that the learned representation remains stable under egocentric viewpoint shifts and partial occlusions, indicating robustness in practical manipulation settings. Full article

Introduction: Myxoid liposarcoma (MLPS) is a rare soft tissue sarcoma comprising 5–10% of adult cases, most often in the thigh. Diagnosis is challenging due to nonspecific imaging findings and resemblance to benign lesions. Case Report: A 42-year-old male presented with a painless, enlarging upper right medial thigh mass. CT and ultrasound suggested a complex solid lesion, possibly benign. Outpatient surgical excision revealed a red, gelatinous, non-encapsulated mass. Frozen section suggested a myxomatous spindle cell tumor. Final pathology confirmed MLPS FNCLCC grade 2 (intermediate grade) with DDIT3 rearrangement on fluorescence in situ hybridization (FISH). Margins were negative but close. Postoperative PET scan and Signatera MRD assay were negative for metastasis. Given the tumor’s size (>10 cm) and known radiosensitivity, adjuvant radiotherapy (60–66 Gy) was initiated. Discussion: MLPS features myxoid stroma, plexiform vasculature, and, in high-grade tumors, a round cell component. The FUS::DDIT3 fusion gene is diagnostic. While MRI offers superior soft tissue characterization, definitive diagnosis requires pathology and molecular testing. Surgical excision with negative margins remains standard, with radiotherapy recommended for large tumors or close margins to reduce recurrence. This case highlights the limitations of preoperative imaging and the value of intraoperative pathology in guiding management. Conclusions: Early recognition, accurate diagnosis, and tailored multimodal treatment are essential for MLPS. Given the potential for recurrence, late extrapulmonary metastases, long-term surveillance with imaging, and molecular assays are critical for optimizing outcomes. Full article