Search Results (220)

Accurate pedestrian trajectory prediction and intention estimation are crucial for autonomous systems and intelligent transportation applications. However, existing methods often address these two highly correlated tasks in isolation and rely on static or heuristic interaction modeling, leading to insufficient adaptability and limited generalization capability in dynamic traffic scenarios. To this end, this paper proposes MTG-TPNet, a Multi-task dynamic Graph Transformer network for joint Trajectory Prediction and intention estimation. The research framework integrates three key innovations: First, a dynamic graph neural network enhanced with motion features, whose graph topology can be adaptively learned end-to-end based on semantic and motion contexts to accurately capture evolving interactions. Second, a multi-granularity attention mechanism that collaboratively fuses geometric proximity, semantic similarity, and physical hard constraints to achieve fine-grained modeling of spatiotemporal dependencies. Third, a dynamic correlation loss based on Bayesian uncertainty, which balances multi-task learning in an adaptive manner and encourages beneficial interactions across tasks. Extensive experiments on the publicly available PIE and ETH/UCY datasets demonstrate that MTG-TPNet achieves state-of-the-art performance. On the PIE dataset, the proposed model significantly outperforms the best baseline model in trajectory prediction metrics, achieving an Average Displacement Error (ADE) of 0.21 and a Final Displacement Error (FDE) of 0.29. This represents a 27.6% reduction in ADE while maintaining stability in intention estimation. Systematic ablation studies validate the effectiveness of each proposed module, with the model retaining an average performance of 69.3%. Furthermore, cross-dataset evaluations confirm its superior generalization capability. This study provides a powerful unified framework for robust pedestrian behavior understanding in complex urban traffic scenarios. Full article

Accurate environmental perception is fundamental to safe autonomous driving; however, most existing multimodal systems rely on fixed or heuristic sensor fusion strategies that cannot adapt to scene-dependent variations in sensor reliability. This paper proposes Cross-Modal Adaptive Attention (CMAA), a unified end-to-end Bird’s-Eye-View (BEV) perception framework that dynamically fuses camera, LiDAR, and RADAR information through learnable, context-aware modality gating. Unlike static fusion approaches, CMAA adaptively reweights sensor contributions based on global scene descriptors, enabling the robust integration of semantic, geometric, and motion cues without manual tuning. The proposed architecture jointly performs 3D object detection, multi-object tracking, and motion forecasting within a shared BEV representation, preserving spatial alignment across tasks and supporting efficient real-time deployment. Experiments conducted on the official nuScenes validation split demonstrate that CMAA achieves 0.528 mAP and 0.691 NDS, outperforming fixed-weight fusion baselines while maintaining a compact model size and efficient inference. Additional tracking evaluation using the official nuScenes tracking devkit reports improved tracking performance, while motion forecasting experiments show reduced trajectory displacement errors (minADE and minFDE). Ablation studies further confirm the complementary contributions of adaptive modality gating and bidirectional cross-modal refinement, and a stratified dynamic analysis reveals consistent reductions in velocity estimation error across object classes, motion regimes, and environmental conditions. These results demonstrate that adaptive multimodal fusion improves robustness, motion reasoning, and perception reliability in complex traffic environments while remaining computationally efficient for deployment in safety-critical autonomous driving systems. Full article

Driven by advancements in artificial intelligence technology, pedestrian trajectory prediction is shifting from traditional machine learning methods toward autonomous decision-making frameworks based on neural networks. However, the spatiotemporal uncertainty of pedestrian movement results in low accuracy of existing prediction models. To address this issue, we propose a multi-source perception fusion system based on INS-GNSS wearable devices. By integrating high-precision inertial measurement units (IMUs) and multi-mode global navigation satellite systems (GNSS), we enhance localization and prediction accuracy. For localization, we introduce a Gait Adaptive UKF (Gait-AUKF) that identifies pedestrian gait patterns and motion states by fusing multi-sensor data. An adaptive algorithm effectively suppresses trajectory drift and improves tracking accuracy. For trajectory prediction, we propose a pedestrian trajectory prediction framework based on a multi-source fusion attention mechanism. A GRU encoder extracts pedestrian trajectory features from historical motion data. An attention mechanism assigns varying weights to trajectory features across different scales. An LSTM decoder and A* path planning algorithm constrain spatiotemporal paths to generate future pedestrian trajectories. Experimental results demonstrate that compared to UKF and AKF, the Gait-AUKF reduces eastward error by 30%, northward error by 26.27%, and vertical error by 49.08%. The complete prediction framework achieves a 68.54% reduction in average position error (APE) and a 70.42% reduction in direction error (DE) compared to LSTM and Transformer models. Ablation experiments demonstrate that the integrated Gait-AUKF algorithm and A* path planning algorithm enhance model decision performance. After incorporating these algorithms, the model’s ADE decreased by 68.49% and FDE by 71.86%. Full article

Accurate small object detection in unmanned aerial vehicle (UAV) imagery is fundamental to numerous safety-critical applications, including intelligent transportation, urban surveillance, and disaster assessment. However, extreme scale compression, dense object distributions, and complex backgrounds severely constrain the feature representation capability of existing detectors, leading to degraded reliability in real-world deployments. To overcome these limitations, we propose FDE-YOLO, a lightweight yet high-performance detection framework built upon YOLOv11 with three complementary architectural innovations. The Fine-Grained Detection Pyramid (FGDP) integrates space-to-depth convolution with a CSP-MFE module that fuses multi-granularity features through parallel local, context, and global branches, capturing comprehensive small target information while avoiding computational overhead from layer stacking. The Dynamic Detection Fusion Head (DDFHead) unifies scale-aware, spatial-aware, and task-aware attention mechanisms via sequential refinement with DCNv4 and FReLU activation, adaptively enhancing discriminative capability for densely clustered targets in complex scenes. The EdgeSpaceNet module explicitly fuses Sobel-extracted boundary features with spatial convolution outputs through residual connections, recovering edge details typically lost in standard operations while reducing parameter count via depthwise separable convolutions. Extensive experiments on the VisDrone2019 dataset demonstrate that FDE-YOLO achieves 53.6% precision, 42.5% recall, 43.3% mAP50, and 26.3% mAP50:95, surpassing YOLOv11s by 2.8%, 4.4%, 4.1%, and 2.8% respectively, with only 10.25 M parameters. The proposed approach outperforms UAV-specialized methods including Drone-YOLO and MASF-YOLO while using significantly fewer parameters (37.5% and 29.8% reductions respectively), demonstrating superior efficiency. Cross-dataset evaluations on UAV-DT and NWPU VHR-10 further confirm strong generalization capability with 1.6% and 1.5% mAP50 improvements respectively, validating FDE-YOLO as an effective and efficient solution for reliable UAV-based small object detection in real-world scenarios. Full article

Multi-agent trajectory prediction is essential for autonomous driving systems, as its performance heavily depends on the quality of feature representations. This paper proposes PFR-HiVT, a lightweight and effective approach for multi-agent trajectory prediction, and evaluates it on the Argoverse 1.1 motion forecasting dataset. Although existing methods such as the Hierarchical Vector Transformer (HiVT) have achieved strong performance, they still exhibit limitations in feature extraction and feature transition across different stages of the network. To address these limitations, a collaborative feature enhancement framework is introduced, consisting of two encoder-side modules and a Progressive Feature Refinement Global Interactor (PFR-Global Interactor). Specifically, the Feature Enhancement Module (FEM) and the Attention Enhancement Module (AEM) are employed to refine local spatiotemporal features before global interaction. In addition, the PFR-Global Interactor integrates three lightweight components—the Simple Feature Refinement Module (SFR), the Lightweight Gate Module (LG), and the Residual Connection Module (RC)—to progressively refine globally interacted features prior to trajectory decoding. All proposed modules adopt lightweight designs, introducing only 230.5 k additional parameters (approximately 8.7% of the total parameters of HiVT-128). Experiments on the Argoverse 1.1 dataset show that PFR-HiVT achieves a minADE of 0.703, a minFDE of 1.041, and an MR of 0.112, outperforming the baseline HiVT model. Ablation studies further validate the effectiveness and synergy of the proposed modules. Full article

X-ray imaging is the most widely used modality for fracture diagnosis in clinical practice due to its efficiency and accessibility. However, automated X-ray fracture detection faces two major challenges. First, fracture regions often contain subtle and low-contrast crack patterns, making it difficult for models to capture essential fine details. Second, fractures exhibit strong directional variability, while conventional detection frameworks have limited capacity to model rotation changes. To address these issues, we propose FDEA-Net, an enhanced detection framework tailored for fracture analysis. It integrates two lightweight improvement modules. The Fracture Detail Enhancer (FDE) strengthens high-frequency textures and fine-grained structural cues that are closely associated with fracture lines. The Rotation Aware Encoder (RAE) encodes rotation-sensitive representations, improving recognition under diverse fracture orientations. Experiments on a large-scale X-ray fracture dataset show clear performance gains, achieving an mAP50 of 0.742 and an F1-score of 0.738. These findings verify the effectiveness of combining detail enhancement with rotation-aware feature modeling. FDEA-Net provides an efficient and generalizable solution for reliable detection of subtle fractures in medical imaging. Full article

In this article, we propose an expanded mixed finite element method for variable-coefficient fractional dispersion equations (FDEs). By introducing two intermediate variables, $p=Du$ and $\sigma =-I_{\theta }^{\beta }p$, the FDEs are reformulated into a mixed system involving only lower-order derivatives. Based on this, we construct an expanded mixed variational framework and prove the weak coercivity in the sense of the LBB condition over appropriately chosen Sobolev spaces, thereby ensuring the well-posedness of the formulation. Then, we develop an expanded mixed finite element scheme and prove that the unique expanded finite element solution possesses optimal approximation accuracy to the fractional flux $\sigma ,$ the gradient p and the unknown u. Finally, numerical experiments are conducted to verify the efficiency and accuracy of the proposed method. Full article

Pedestrian trajectory prediction plays a vital role in autonomous driving and intelligent surveillance systems. Graph neural networks (GNNs) have shown remarkable effectiveness in this task by explicitly modeling social interactions among pedestrians. However, existing methods suffer from two key limitations. First, they face difficulty in balancing the reduction in redundant connections with the preservation of critical interaction relationships in spatial graph construction. Second, higher-order graph convolution methods lack adaptability to varying crowd densities. To address these limitations, we propose a pedestrian trajectory prediction method based on Delaunay triangulation and density-adaptive higher-order graph convolution. First, we leverage Delaunay triangulation to construct a sparse, geometrically principled adjacency structure for spatial interaction graphs, which effectively eliminates redundant connections while preserving essential proximity relationships. Second, we design a density-adaptive order selection mechanism that dynamically adjusts the graph convolution order according to pedestrian density. Experiments on the ETH/UCY datasets show that our method achieves 5.6% and 9.4% reductions in average displacement error (ADE) and final displacement error (FDE), respectively, compared with the recent graph convolution-based method DSTIGCN, demonstrating the effectiveness of the proposed approach. Full article

The development of sensor technology and deep learning has significantly improved the reliability and practicality of automatic driving technology. In an autonomous driving system, agent trajectory prediction is a complex challenge, which includes the understanding of different and unpredictable behavior patterns of various entities, including vehicles, pedestrians, and other traffic participants, among the data collected by sensors. In this paper, we deeply study two kinds of problems: Single-Agent Trajectory Prediction (SATP) and Multi-Agent Trajectory Prediction (MATP). We propose an innovative model, which combines the attention mechanism and integrates the Liquid Time-Constant (LTC) network with spatio-temporal features and the Mixture of Experts (MoE) framework, termed the Atten-LTC-MoE model. The model is general and extensible to support SATP and MATP problems in different autonomous driving environments. In order to improve computational efficiency and prediction accuracy, lane and agent vectorization, spatio-temporal features, agent data fusion, and trajectory endpoint generation technologies are studied. The effectiveness of our method is verified by comprehensive experiments on Argoverse and Interaction datasets. Our proposed model has been superior to the state-of-the-art models in terms of minADE₆ and minFDE₆ metrics and has shown significant advantages in the accuracy of agent trajectory prediction and computational performance. Full article

Face super-resolution (FSR) has made great progress thanks to deep learning and facial priors. However, many existing methods do not fully exploit landmark heatmaps and lack effective multi-scale texture modeling, which often leads to texture loss and artifacts under large upscaling factors. To address these problems, we propose a Multi-Scale Residual Stacking Network (MRSNet), which integrates multi-scale texture enhancement with multi-stage heatmap fusion. The MRSNet is built upon Residual Attention-Guided Units (RAGUs) and incorporates a Face Detail Enhancer (FDE), which applies edge, texture, and region branches to achieve differentiated enhancement across facial components. Furthermore, we design a Multi-Scale Texture Enhancement Module (MTEM) that employs progressive average pooling to construct hierarchical receptive fields and employs heatmap-guided attention for adaptive texture refinement. In addition, we introduce a multi-stage heatmap fusion strategy that injects landmark priors into multiple phases of the network, including feature extraction, texture enhancement, and detail reconstruction, enabling deep sharing and progressive integration of prior knowledge. Extensive experiments on CelebA and Helen demonstrate that the proposed method achieves superior detail recovery and generates perceptually realistic high-resolution face images. Both quantitative and qualitative evaluations confirm that our approach outperforms state-of-the-art methods. Full article

The growing demand for biodegradable and functional packaging has driven research toward polysaccharide-based materials with improved performance. In this study, sodium alginate films were modified using natural deep eutectic solvents (NADES) and acorn polyphenolic extract to enhance their antimicrobial, mechanical, and thermal properties. The films were acquired by solvent casting and characterized through mechanical, spectroscopic, thermal, and microbiological analyses. Both NADES and the polyphenolic extract enhanced tensile strength and flexibility through additional hydrogen bonding within the alginate network, while the extract also introduced antioxidant functionality. Among all tested formulations, the A4E2 film exhibited the most balanced performance. FTIR spectra revealed hydrogen bonding between the film components, and thermogravimetric analysis showed an approximately 15 °C (F-EXT) and 20 °C (F-DES) shift in the main DTG degradation peak, indicating enhanced thermal stability. Controlled-release experiments demonstrated the gradual diffusion of phenolic compounds in aqueous, acidic, and fatty simulants, with an initial release phase within the first 6 h followed by sustained release up to 48 h, confirming the films’ suitability for various food environments. The combined modification reduced the growth of Escherichia coli and Staphylococcus aureus by 30–35%, with inhibition zone diameters reaching 27.52 ± 2.87 mm and 25.68 ± 1.52 mm, respectively, evidencing synergistic antimicrobial activity. These results highlight the potential of NADES- and extract-modified alginate films as sustainable materials for active food packaging applications. Full article

This work develops and analyzes a novel fractional-order chemostat system (FOCS) with a Caputo fractional derivative (CFD) featuring a sliding memory window and periodic boundary conditions (PBCs), designed to model microbial pollutant degradation in sustainable water treatment. By incorporating the Caputo fractional derivative with sliding memory (CFDS), the model captures time-dependent behaviors and memory effects in biological systems more realistically than classical integer-order formulations. We reduce the two-dimensional fractional differential equations (FDEs) governing substrate and biomass concentrations to a one-dimensional FDE by utilizing the PBCs. The existence and uniqueness of non-trivial, periodic solutions are established using the Carathéodory framework and fixed-point theorems, ensuring the system’s well-posedness. We prove the positivity and boundedness of solutions, demonstrating that substrate concentrations remain within physically meaningful bounds and biomass concentrations stay strictly positive, with solution trajectories confined to a biologically feasible invariant set. Additionally, we analyze non-trivial equilibria under constant dilution rates and derive their stability properties. The rigorous mathematical results confirm the viability of FOCS models for representing memory-driven, periodic bioprocesses, offering a foundation for advanced water treatment strategies that align with Sustainable Development Goal 6 (Clean Water and Sanitation). This work establishes a comprehensive mathematical framework that bridges fractional calculus with sustainable water treatment applications, providing both theoretical foundations and practical implications for optimizing bioreactor performance in environmental biotechnology. Full article

Vehicle trajectory prediction is a pivotal technology in intelligent transportation systems. Existing methods encounter challenges in effectively modeling lane topology and dynamic interaction relationships in complex traffic scenarios, limiting prediction accuracy and reliability. This paper presents Lane Interaction Transformer (LITransformer), a lane-informed trajectory prediction framework that builds on spatio–temporal graph attention networks and Transformer-based global aggregation. Rather than introducing entirely new network primitives, LITransformer focuses on two design aspects: (i) a lane topology encoder that fuses geometric and semantic lane features via direction-sensitive, multi-scale dilated graph convolutions, converting vectorized lane data into rich topology-aware representations; and (ii) an Interaction-Aware Graph Attention mechanism (IAGAT) that explicitly models four types of interactions between vehicles and lane infrastructure (V2V, V2N, N2V, N2N), with gating-based fusion of structured road constraints and dynamic spatio–temporal features. The overall architecture employs a Transformer module to aggregate global scene context and a multi-modal decoding head to generate diverse trajectory hypotheses with confidence estimation. Extensive experiments on the Argoverse dataset show that LITransformer achieves a minADE of 0.76 and a minFDE of 1.20, and significantly outperforms representative baselines such as LaneGCN and HiVT. These results demonstrate that explicitly incorporating lane topology and interaction-aware spatio-temporal modeling can significantly improve the accuracy and reliability of vehicle trajectory prediction in complex real-world traffic scenarios. Full article

This study explored the efficacy of dietary Fagopyrum dibotrys extract (FDE) in mitigating Escherichia coli O157 (E. coli) infections in broilers. A total of 240 one-day-old male Shengze 901 broilers were randomly allocated to four groups (with 10 broilers per group): CON (basal diet), COLI (basal diet + E. coli challenge), FDE (basal diet + 500 mg/kg FDE), and FDEC (basal diet + 500 mg/kg FDE + E. coli challenge). The results showed that E. coli challenge reduced the average daily gain (ADG) and average daily feed intake (ADFI), increased the feed conversion ratio (FCR) and cecal E. coli load, impaired the intestinal mucosa, and induced intestinal inflammatory responses (p < 0.05). FDE supplementation improved growth performance, increased duodenal villus height and villus/crypt ratio; reduced serum interleukin (IL)-1β, tumor necrosis factor-α (TNF-α), diamine oxidase (DAO), and endotoxin levels; and lowered cecal E. coli counts (p < 0.05). Molecularly, FDE supplementation upregulated Occludin, Claudin-1, and ZO-1 gene expressions, and downregulated jejunal TLR4 and MyD88 mRNA levels. Microbiome analysis revealed that FDE increased the relative abundance of Faecalibacterium and alleviated the E. coli-induced reduction in Clostridia_UCG-014. In conclusion, dietary supplementation with 500 mg/kg FDE could mitigate colibacillosis-related intestinal damage and inflammatory responses. Full article

Background: Fixed drug eruption (FDE) is a non-immediate, CD8+ T cell–mediated hypersensitivity reaction characterized by well-demarcated erythematous–violaceous plaques that recur at the same site after re-exposure to the causative drug. Although NSAIDs and antibiotics are the most common triggers, various other medications may induce FDE, and genetic susceptibility has been linked to specific HLA alleles. Methods: We conducted a clinical evaluation supported by patch testing, oral drug provocation, and assessment of therapeutic alternatives to identify the causative agent and confirm delayed-type hypersensitivity. Results: We report the case of a 53-year-old woman with essential hypertension, autoimmune thyroiditis, and renal lithiasis who developed well-demarcated erythematous plaques with central vesiculation and moderate pruritus on the dorsal hand and posterior calf approximately 8 h after ingestion of a 60 mg etoricoxib tablet. Patch testing was negative, while oral challenge confirmed etoricoxib-induced FDE; celecoxib was subsequently evaluated as a potential safe alternative. Conclusions: This case underscores the importance of an integrated diagnostic approach—including careful history, clinical examination, and confirmatory testing—to accurately diagnose delayed cutaneous drug reactions and to identify safe therapeutic options for patients. Full article