Search Results (302)

Foggy traffic scenes pose significant challenges for object detection because reduced contrast, blurred object boundaries, and the loss of local details weaken discriminative feature representations. These degradations are particularly detrimental to lightweight detectors used in intelligent transportation and vehicle perception systems, where both accuracy and real-time efficiency are required. To address this problem, this paper proposes YOLO-GCM, a lightweight detector-side feature enhancement framework built upon YOLO11n. Instead of relying on an external image dehazing stage, YOLO-GCM improves the internal feature representation of the detector through three complementary modules: a gated additive feature block (GAFB) for adaptive channel-wise feature selection and noise suppression, a context-aware feature enhancement module (CAFEM) for strengthening high-level semantic context, and a multi-scale adaptive fusion (MSAF) module for enhancing cross-scale feature interaction. By integrating these modules into a unified one-stage detector, the proposed method improves detection robustness under low-visibility traffic conditions while maintaining a compact architecture. Experiments on the FoggyCar dataset show that YOLO-GCM achieved 89.81% mAP@0.5 and 67.99% mAP@0.5:0.95, outperforming standard YOLO baselines and dehazing-assisted detection pipelines under a consistent evaluation protocol. Additional evaluation on Foggy Cityscapes further verified the generalization capability of the proposed method under domain shift. The results demonstrate that detector-side feature enhancement provides an effective and efficient alternative to multi-stage dehazing-plus-detection pipelines for foggy traffic object detection. These findings can provide useful guidance for the development of robust and efficient perception modules in roadside monitoring, intelligent transportation systems, and vehicle-assisted driving applications under adverse weather conditions. Full article

Wheat is a major staple crop, and storage mold growth poses a severe threat to grain safety and quality stability. Natural mold development in stored wheat exhibits subtle, localized, and highly heterogeneous characteristics. Existing unimodal methods and global fusion approaches generally suffer from insufficient local feature sensitivity, hindering fine-grained mold severity grading. To address this limitation, we propose a Mask-Guided Fine-Grained Fusion Network, a weakly supervised framework based on local RGB–HSI fusion. This framework employs a dynamic parallel A/B experimental design to construct time-matched proxy labels via weakly supervised learning. A standardized preprocessing pipeline including single-kernel extraction, foreground segmentation, and cross-modal registration is established to resolve RGB–HSI spatial misalignment, ensuring physical-level spatial consistency of multimodal features. The model incorporates a Foreground-Aware Spectral Recalibration (FASR) module to suppress background noise, a Mask-Guided Dilated Cross-modal Local Attention (MDCLA) mechanism to establish fine-grained local mappings between RGB visual phenotypes and hyperspectral responses, and a sample-level adaptive fusion strategy to dynamically weight features by modal reliability, enhancing representation of complex samples across all mold stages. Experiments show that the Mask-Guided Fine-Grained Fusion Network achieves 0.9689 classification accuracy, 0.9698 Macro-F1 score, and 0.0593 Mean Absolute Error (MAE), significantly outperforming state-of-the-art unimodal deep models and global attention fusion baselines. This work provides a proof-of-principle framework for fine-grained non-destructive mold risk assessment in stored wheat. Full article

Traditional global localization systems frequently struggle with perceptual ambiguities in dynamic environments and structurally similar scenes, which severely compromises navigation robustness. Concurrently, conventional path planning methodologies rarely integrate proactive safety considerations regarding high-risk environmental features. To resolve these critical limitations, this paper introduces a comprehensive semantic-assisted framework for mobile robots to enhance both global localization and navigation. First, we develop a semantic-aware place representation derived from LiDAR point clouds. By explicitly filtering dynamic objects and assigning category-specific weights, this approach mitigates perceptual aliasing and ensures robust scene recognition. Furthermore, we implement a Hyper-Semantic Point Histogram (HyperSPH) to embed semantic encoding directly into local geometric features. A Semantic Geometric Consistency Filter is subsequently applied to eliminate matching outliers and maximize registration accuracy. For secure navigation, we propose the Semantic-guided Twin Delayed Deep Deterministic Policy Gradient with Long Short-Term Memory (S-TD3-LSTM) algorithm within a deep reinforcement learning architecture. This strategy extracts temporal correlations via Long Short-Term Memory networks and integrates a dedicated semantic cost function to optimize obstacle avoidance policies. Extensive experiments demonstrate that the proposed localization module achieves superior retrieval and pose estimation precision over conventional methods. In complex path planning scenarios, the S-TD3-LSTM algorithm ensures stable convergence and generates highly adaptive trajectories. By proactively identifying and bypassing semantic hazards, the integrated system drastically minimizes exposure to dangerous zones, successfully establishing a rigorous balance between path efficiency and execution safety. Full article

Accurate electricity price forecasting (EPF) is essential for market participants to optimize trading strategies and for power systems to accommodate the increasing penetration of volatile renewable energy sources. However, electricity price series are characterized by strong nonlinearity, high volatility, and significant structural breaks, which pose substantial challenges to conventional forecasting models. Although numerous hybrid deep learning models have been proposed for EPF, most existing approaches either overlook structural breaks or treat them as outliers rather than as signals of regime shifts, often resulting in systematic forecasting degradation when market conditions change abruptly. To address this issue, this study proposes COCAL-TTL, a novel multi-stage structural break-aware forecasting framework that integrates regime-adaptive data partitioning with a functionally differentiated hybrid deep learning architecture. First, a joint detection scheme combining the Iterated Cumulative Sum of Squares (ICSS) algorithm and the Chow test is employed to partition Spanish electricity market data from 2014 to 2023 into distinct regimes. Within each regime, CEEMDAN is applied to extract multi-scale features, which are subsequently reconstructed into trend, periodic, and random components based on an independent sample t-test and Fast Fourier Transform (FFT). The CNN-SE Attention-LSTM (CAL) model, with hyperparameters optimized by the Osprey Optimization Algorithm (OOA), serves as the primary forecasting engine. In addition, a dedicated heterogeneous error correction module, namely TTL, is introduced, in which Temporal Convolutional Network, Transformer, and LSTM are designed to capture local transients, long-range dependencies, and transitional dynamics in the residual series, respectively. Empirical results demonstrate that compared with the Naive benchmark, COCAL-TTL achieves percentage MAPE improvements of 58.48% and 48.97% in low- and high-volatility regimes, respectively. These findings indicate that the proposed structural break-aware framework provides a robust data-driven solution for EPF under heterogeneous market conditions and offers technical support for stable electricity market operation in the context of renewable energy integration. Full article

Event extraction is a core NLP task that aims to identify triggers and arguments in unstructured text. In the financial domain, dense events, overlapping arguments, and ambiguous semantics pose significant challenges. This paper proposes CADAEE, a joint extraction framework that integrates curriculum adversarial learning and an enhanced adaptive layer. Curriculum adversarial learning dynamically adjusts training difficulty, thereby improving robustness and generalization on complex samples. The enhanced adaptive layer introduces learnable role-bias embeddings to model semantic dependencies between triggers and arguments, while a multi-head attention mechanism captures diverse feature interactions. Extensive experiments on the FewFC and DuEE-Fin datasets demonstrate the superiority of CADAEE. The model achieves highly competitive F1-scores in both trigger and argument classification, reaching 80.1% and 73.5% on FewFC, and 88.8% and 71.8% on DuEE-Fin, respectively. Ablation studies validate the synergistic contributions of the proposed modules. These results demonstrate that CADAEE provides robust and accurate extraction in complex, overlapping event scenarios, highlighting the value of combining curriculum learning with adaptive, role-aware enhancements for financial event extraction. Full article

All-in-one weather-degraded image restoration aims to restore clean images from diverse weather-degraded observations (such as rain, haze, and snow) using a unified model. However, this topic remains challenging due to its ill-posed nature and the scarcity of large-scale paired training data. This article develops a novel semi-supervised learning framework, termed Semi-Supervised Degradation-Aware Learning (S²DAL), to adjust the feature space to align with the unified parameter space for all-in-one adverse weather removal. Specifically, the proposed S²DAL consists of two backbone networks: a Degradation-guided Histogram Transformer (DHformer) for weather-degraded image restoration and a Degradation-guided Convolutional Neural Network (DCNN) for degradation generation. A key component, the Degradation-guided Histogram Transformer (DHT) block, is designed to effectively capture intrinsic image features while suppressing diverse degradation interference through channel shuffling modulation, dynamic-range histogram self-attention, and dual-scale gated feed forward. Furthermore, a Monte Carlo-based Expectation-Maximization (EM) algorithm is introduced to jointly optimize latent variables and network parameters under both labeled and unlabeled data. Extensive quantitative and qualitative results on synthetic and real-world datasets consistently demonstrate that the proposed S²DAL achieves superior restoration performance compared to multiple state-of-the-art fully supervised and semi-supervised approaches. Full article

Accurate detection and reliable grasping of small bolts are essential for intelligent manufacturing and automated assembly. However, this remains a challenge due to the small size, slender geometry, and metallic reflective surfaces of bolts. In this paper, we propose a vision-guided robotic bolt handling framework that integrates lightweight object detection, optimization-oriented grasp execution, and collision-aware trajectory planning. The lightweight YOLOv8n-BoltLite detector, improved with E-C2f, LCA, SA-PAN, and WD-IoU loss, enhances localization accuracy and feature representation for small and slender bolts. A robotic grasping framework is designed to transform detection results into executable robotic actions through 3D pose estimation, mid-shank grasp point generation, and optimization-oriented execution formulation. Additionally, a five-segment trajectory planning strategy ensures safe and efficient robot motion. Experimental results show that YOLOv8n-BoltLite achieves a five-run average mAP of 99.64 ± 0.05% with 198 FPS, and 3.02 M parameters. On an additional challenging external test set involving illumination variation, clutter, partial occlusion, reflection, and clustered bolts, the proposed detector achieves 94.62 ± 0.18%, outperforming recent lightweight detectors under the same training protocol. Robotic experiments involving 1000 controlled grasping trials and 300 multi-target grasping attempts demonstrate a controlled-condition success rate of 97.0% and improved target-selection reliability in multi-bolt scenes. These results suggest that the proposed framework offers a practical and efficient solution for automated bolt handling in intelligent manufacturing environments. Full article

Aircraft targets in SAR imagery often exhibit discrete scattering characteristics, significant variations in pose and scale, strong speckle noise in background clutter, and complex background interference, which jointly hinder stable structural feature extraction and accurate target localization. Existing detectors for SAR aircraft recognition primarily rely on bounding-box regression and classification; they do not completely exploit target structural cues, spatial attention, and frequency-domain information. To address these limitations, we propose a collaborative detection framework that integrates an uncertainty-aware keypoint-driven module (UAKM) with a fractional Fourier convolution backbone (S-FRConv). UAKM introduces a center-keypoint regression branch that jointly predicts keypoint coordinates and Laplacian scale parameters and employs a 2D Laplace negative log-likelihood loss to estimate uncertainty. The derived dense uncertainty heatmap is then used as spatial attention weights to guide distribution-based regression and multi-scale feature re-weighting, without requiring any additional annotations. S-FRConv embeds the Fractional Fourier Transform into shallow backbone layers and C2f modules, enabling joint spatial–spectral feature modeling that suppresses speckle noise and enhances edge and orientation representations. Experiments on the public SAR-AIRcraft-1.0 dataset demonstrate that the proposed method systematically improves the detection performance. For the Nano model, the overall mAP50 increases from 0.810 to 0.867, and the mAP 50:95 improves from 0.637 to 0.655 compared with the baseline, corresponding to gains of 5.7 and 1.8 percentage points, respectively. These results validate the effectiveness and generalization potential of combining uncertainty-driven spatial attention with fractional spectral feature enhancement for SAR aircraft target detection. Full article

Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks. Full article

Background and Clinical Significance: Clear cell renal cell carcinoma (ccRCC) is notorious for its aggressiveness and great propensity to metastasize to virtually any organ, with a dismal five-year survival rate. While metastases from ccRCC typically occur in the lungs, lymph nodes, bones and liver, involvement of atypical locations such as the breast, pituitary gland and stomach is extremely rare. These unusual metastases can masquerade as primary tumours at their respective sites, posing significant diagnostic challenges. Case Presentation: Here, we describe three cases of metastatic ccRCC to unusual anatomical sites following nephrectomy: (1) a patient who presented with a suspicious left-sided breast mass and synchronous liver and lung metastases six months following the initial diagnosis of ccRCC; (2) a patient who presented with diplopia, found to have a pituitary lesion four months after nephrectomy; and (3) a patient with known pre-existing lung metastases who developed upper gastrointestinal bleeding one year post-nephrectomy, in whom oesophagogastroduodenoscopy (OGDS) revealed an 8 mm pedunculated gastric polyp. Histopathological examination following biopsies of these lesions showed compact nests and sheets of malignant cells with clear to eosinophilic cytoplasm and distinct membranes. Immunohistochemically, these malignant cells demonstrated CD10 immunopositivity, and were negative for CK7 and CK20, in keeping with the diagnosis of metastatic ccRCC. Conclusions: This case series illustrates the rare metastatic behaviour of ccRCC with its potential to spread to uncommon sites. Awareness of such presentations is crucial, particularly in patients with a known history of ccRCC, as these lesions may clinically and radiologically mimic primary tumours of the affected sites. Careful evaluation of its histomorphological features and judicious use of immunohistochemical panels, together with clinical and radiological correlations, is the key to arriving at an accurate diagnosis. Full article

Local feature matching plays a critical role in robotic SLAM and visual localization. However, in weakly textured indoor industrial environments, lightweight appearance-based methods often struggle to learn discriminative and stable local features. To address this challenge, this paper proposes GAEFeat, short for Geometry-Aware Efficient Feature, a lightweight vision–geometric feature learning network. To address the scarcity of specialized training data, we integrated robotic arm pose priors with depth information to automatically generate cross-view supervision signals and surface-normal labels. Based on this strategy, we constructed two complementary datasets, including a simulated dataset and a real-world dataset, to support feature learning and evaluation in weakly textured indoor industrial environments. For feature extraction, we design a dual enhancement mechanism consisting of a geometric auxiliary branch and a geometry-aware enhancement (GAE) module. The former guides the network to perceive local surface structures through surface normal supervision, while the latter utilizes a gating mechanism to achieve deep fusion between geometric priors and 2D texture descriptors. Experimental results demonstrate that GAEFeat achieves strong robustness and high inference efficiency in relative pose estimation, homography estimation, and visual localization tasks, with particularly notable advantages in near-field, weakly textured industrial scenes. The framework achieves an inference latency of only 3.9 ms on the NVIDIA Jetson AGX Orin edge platform, demonstrating its real-time capability and practical potential for deployment in edge computing environments. Full article

In underground mining environments, collisions between Load–Haul–Dump (LHD) machines and personnel pose serious safety risks. To address challenges such as uneven illumination, dust interference, occlusion, and limited computational resources, this paper proposes FP-DETR, an improved RT-DETR framework for underground personnel detection. The model integrates a CSP-FFCM module for efficient spatial–frequency feature extraction, a polarity-aware linear attention-based POTE module for enhanced global feature interaction, and a Matching-Aware Loss to improve confidence–quality alignment and reduce false alarms. Experiments on a self-constructed dataset show that FP-DETR achieves 88.5% mAP@0.5 and 58.6% mAP@0.5:0.95, improving RT-DETR-r18 by 1.5% and 3.5%, respectively, while reducing parameters from 20.0 M to 15.8 M and GFLOPs from 57.3 to 51.2. Field tests show a reduction in frame-level FPR from 4.1% to 3.4%. However, validation is limited to no-person scenarios, and full operational evaluation is required for comprehensive assessment. Full article

Small object detection in UAV aerial imagery poses significant challenges due to sparse pixel representation and ambiguous object boundaries. Through systematic analysis, we identify three critical degradation stages during forward propagation in deep detection networks: edge attenuation during feature extraction, semantic conflict during feature fusion, and detail loss during feature reconstruction. Existing methods address these stages in isolation or implicitly, lacking collaborative and stage-aware repair strategies. To address this issue, we propose EAGLE-DET, a novel detection framework based on sparse multi-scale attention and refined transformation. Specifically, the framework comprises three core modules: (1) the Cross-stage Multi-resolution Edge Enhancement Network (CMENet), which preserves small object edge representations via adaptive high-low frequency decomposition; (2) the Attention-guided Multi-scale Feature Fusion Network (AMFFN), which resolves cross-scale semantic conflicts through pyramidal sparse attention and multi-scale spatial decoupling; (3) the Enhanced Upsampling with Channel Bridging and Spatial Coordination module (EUCBSC), which recovers spatial detail fidelity via bidirectional channel shift mixing. Extensive experiments on three benchmark datasets—VisDrone-2019, UAVDT, and DOTA1.0—demonstrate the effectiveness of EAGLE-DET, which achieves improvements of 4.5% AP50 and 2.9% AP50:95 on VisDrone-2019 over the baseline, while maintaining inference at 71.7 FPS, achieving an optimal accuracy–efficiency trade-off. Full article

Breast cancer remains the leading cause of cancer-related deaths among women globally. Early detection through mammography is vital for improving survival rates; however, the large volume of medical images and subtle variations in lesion characteristics pose significant challenges to manual interpretation. Recent automated diagnostic models based on deep learning have shown strong potential for breast cancer classification, but challenges such as overfitting, high computational complexity, limited generalization, and insufficient interpretability remain unresolved. This paper proposes a computationally efficient and context-aware deep learning framework for breast cancer classification using transformer-based multi-scale attention mechanisms and explainable artificial intelligence (XAI). The proposed architecture integrates the Hierarchical Multi-Scale Transformer (HMT) and Edge-Aware Local Transformer (ELT) modules to jointly capture global contextual dependencies and boundary-sensitive local representations from mammographic images. ELT improves feature refinement in high-entropy regions, while HMT models global semantic interactions across multiple feature scales. In addition, an Adaptive Contextual Refinement (ACR) module is introduced to preserve semantically consistent feature representations across spatial resolutions. A Meta-Ensemble Classification (MEC) framework combining weighted SVM and K-Nearest Neighbors (KNN) classifiers is further employed using validation-guided class-adaptive weighting. The proposed framework is evaluated on four benchmark mammography datasets, namely CBIS-DDSM, DDSM, INBreast, and MIAS. The proposed model has demonstrated superior accuracy of over 99% across all breast cancer datasets. The model surpassed transformer-based baselines including Swin-T and ViT while maintaining lower parameter complexity and achieving approximately 7% higher accuracy on the CBIS-DDSM dataset. The proposed framework also demonstrated strong cross-dataset generalization and consistently achieved high precision, recall, and F1-score values across all benchmark datasets. To improve model interpretability, Grad-CAM, SHAP, Occlusion Sensitivity Analysis (OSA), and the proposed TIxAI consistency analysis framework are incorporated to provide preliminary explainability assessment for mammographic classification. The explainability analysis demonstrated spatially consistent saliency behavior across benchmark datasets; however, the current evaluation is based on internal saliency consistency rather than external clinical validation using expert lesion annotations. Overall, the proposed framework provides an effective and computationally efficient approach for automated breast cancer classification while improving model explainability and interpretability. Full article

Earthquakes pose a serious threat to urban areas located in seismically active regions, particularly in developing countries where rapid urbanization and weak enforcement of building regulations increase the vulnerability of the built environment. Pakistan is highly exposed to seismic hazards due to its tectonic setting, and many residential buildings are constructed without adequate seismic design considerations. Therefore, assessing building vulnerability and understanding community perception of earthquake risk are essential for effective disaster risk reduction. This study investigates the relationship between the structural vulnerability of residential buildings and earthquake risk perception among residents in Peshawar, Pakistan. Two contrasting urban settlements were selected as case studies: WAPDA Town, representing a planned residential area, and Hashtnagri, representing an older unplanned settlement. A total of 400 buildings were surveyed through field investigations. Seismic vulnerability was assessed using the Rapid Visual Screening (RVS) method based on structural characteristics such as building age, number of floors, construction materials, structural irregularities, construction quality, and presence of seismic reinforcement features. A Physical Vulnerability Index (PVI) was developed to categorize buildings into different vulnerability levels. In addition, a questionnaire survey was conducted to evaluate earthquake risk perception among residents, and a risk perception index (RPI) was calculated. The results indicate that buildings located in the unplanned settlement exhibit significantly higher seismic vulnerability compared to those in the planned residential area due to poor construction practices, irregular structural configurations, and the absence of seismic-resistant features. Statistical analysis further reveals a positive relationship between physical vulnerability and earthquake risk perception, suggesting that residents living in structurally vulnerable environments tend to perceive higher earthquake risk. The findings highlight the importance of integrating structural vulnerability assessment with community awareness and preparedness programs. Implementation of seismic design provisions and improved enforcement of construction regulations, such as those specified in the Building Code of Pakistan 2022, can significantly reduce earthquake risk in rapidly growing urban areas. However, the present study did not directly evaluate the level of enforcement or compliance with the Building Code of Pakistan 2022 in either WAPDA Town or Hashtnagri. Therefore, the policy recommendations are intended as general implications derived from the observed vulnerability patterns. Full article