Search Results (189)

Rapid urbanization necessitates high-frequency monitoring of construction-ready bare land to timely detect and prevent illegal construction. However, the utility of optical imagery is often compromised in cloud-prone regions. While Synthetic Aperture Radar (SAR) offers all-weather capabilities, it struggles to distinguish construction-ready bare land from recently harvested agricultural land, leading to severe false alarms. To address the conflict between high-frequency monitoring and semantic identification, this study proposes the SAR-based Change Screening and Optical-Scene-Informed Identification (SCS-OI) framework. The first stage performs high-recall candidate screening based on SAR backscattering changes, while the second stage incorporates historical cloud-free optical imagery as semantic guidance, enabling refined identification without requiring synchronous optical data. Experiments in Guangzhou demonstrate that the framework achieves a False Alarm Rate of 13.31%, Recall of 90.63%, Precision of 74.81%, F1-score of 81.95%, and IoU of 69.43%. Compared with the SAR-only baseline (FR = 22.4%), the two-stage design reduces false alarms while maintaining high recall. Other deep learning baselines exhibit lower F1-scores (59–73%), highlighting the effectiveness of the overall framework. These results show that the proposed two-stage framework effectively integrates high-recall candidate screening and semantic-guided refinement, providing a robust solution for high-frequency monitoring of construction-ready bare land in cloud-prone regions of Guangzhou. Full article

Wireless capsule endoscopy (WCE) plays a vital role in non-invasive screening of small intestinal lesions. However, the automated detection of lesions remains challenging due to low contrast, uneven illumination, and severe visual variability across images. Existing convolutional detectors rely heavily on manually designed anchors and post-processing, while end-to-end detection transformers developed for natural images exhibit limited adaptability to the complex texture and spectral characteristics of WCE data. To overcome these limitations, this study proposes a deep learning-based detection transformer with enhanced relational-zone aggregation for WCE lesion detection, termed ERZA-DETR, specifically tailored for WCE lesion detection. The framework integrates three complementary modules: a Dual-Band Adaptive Fourier Spectral module (DBFS) that recalibrates frequency responses to suppress illumination artifacts and highlight lesion boundaries; a Fused Dual-scale Gated Convolutional module (FD-gConv) that selectively fuses multi-scale texture features; and a Graph-Linked Embedding at Semantic Scales module (GLES) that preserves local topological relationships through coordinate-gated aggregation. Experimental evaluations on the SEE-AI small intestine dataset demonstrate that ERZA-DETR achieves a 3.2% improvement in mAP@50 and a 12.4% reduction in parameters compared with RT-DETRv2, achieving a superior balance between detection accuracy, computational efficiency, and clinical applicability. Full article

This study addresses the challenge of the difficult identification of organ structures in the standard sections of fetal abdominal ultrasounds. A deep learning-based multi-task model named SEG-FAUSP was developed to segment the core anatomical structures of seven key fetal abdominal ultrasound sections. We collected fetal abdominal ultrasound images from pregnant women in the mid-pregnancy period (18–24 weeks) using various mainstream ultrasound devices, and professional physicians annotated key anatomical structures (e.g., umbilical veins, gastric bubbles, spine) in the images. Based on an improved deep learning framework, the model accurately segments and locates the target organ structures through a parallel dual-branch semantic segmentation network, which avoids the over-reliance on large-scale pre-trained data in traditional methods. Experimental results show that the model achieves excellent performance in anatomical structure segmentation, with the intersection over union of the bladder and gastric bubble both reaching above 0.84; its segmentation accuracy for complex structures such as the inferior vena cava is also significantly superior to the baseline model. As an end-to-end model, it simplifies the clinical interpretation process of fetal abdominal ultrasound, reduces the risk of missed diagnoses caused by unclear organ identification, provides an efficient auxiliary tool for prenatal screening in grassroots medical institutions, and is of great significance for improving the quality of newborns. Full article

Landslide hazards occur frequently in the Ya’an region; therefore, accurately identifying and delineating potential landslide areas is crucial for disaster prevention and mitigation. Although deep learning-based detection methods using optical remote sensing imagery are widely adopted, the complex terrain and diverse land cover in this area often result in blurred boundaries and weakened textural features, making it difficult to precisely define spatial extents. To overcome these challenges, this study proposes an improved YOLOv11 model for landslide detection. Building on the YOLOv11 baseline, we designed a novel Multi-Scale Detail Enhancement module and integrated it into the neck network to effectively aggregate shallow-level details with deep-level semantic information, thereby enhancing the model’s ability to represent ambiguous boundaries. Additionally, we incorporated the lightweight SimAM attention mechanism into the backbone network. This mechanism dynamically suppresses background noise based on an energy minimization principle, improving feature discriminability within landslide regions and enabling precise boundary boxes. We conducted validation experiments in the Ya’an region using a custom dataset constructed from high-resolution UAV orthoimagery, comparing our method against mainstream models such as YOLOv8 and YOLOv10. The results show that the proposed improved YOLOv11 model achieves a precision of 90.2%, a recall of 84.8%, and an mAP of 92.7%. This enhanced performance demonstrates the model’s effectiveness in detecting landslides under complex terrain conditions, providing a practical technical reference for efficient hazard screening and dynamic monitoring. Full article

To address the limited accuracy of speech-based Alzheimer’s Disease (AD) screening and the shortage of paired multimodal data, this paper proposes a detection framework based on feature alignment and Rectified Flow-driven latent representation generation. The EEG dataset consists of 36 AD patients and 29 Healthy Controls (HC). The speech dataset contains 399 samples, which include 114 AD cases, 132 Mild Cognitive Impairment (MCI) cases, and 153 HC cases. We extracted multidimensional features of EEG signals, such as time-domain and frequency-domain characteristics, alongside behavioral representations of speech. A heterogeneous alignment network was used to map these features into a common semantic subspace, where an adaptive interpolation strategy reconstructed the missing pathological trajectories of MCI within the latent space. On this basis, a conditional Rectified Flow model was introduced to learn the optimal transport mapping from speech to EEG. This model generated physiological-information-rich latent representations to compensate for semantic gaps. Experimental results showed that the fused features from speech and latent representations achieved a three-class classification accuracy of 89.08%, a precision of 88.77%, and a recall of 88.71%. This performance represented an accuracy improvement of 9.28% compared with the speech-based baseline system. Our method combines the convenience of speech screening with the high reliability of neurophysiological signals, and it provides a new approach for low-cost early detection of AD. Full article

Cross-view image geolocalization aims to achieve accurate localization of geo-tagged images without geo-tagging by matching ground-view images with satellite images. However, there are huge imaging differences between ground and satellite viewpoints, and existing methods usually rely on a large number of accurately labeled cross-view image pairs. Therefore, to address issues such as significant perspective differences, high annotation costs, and low utilization of unpaired data, this paper proposes a cross-view generation model that integrates multi-scale contrastive learning and dynamic optimization, designs a multi-scale contrast loss function to strengthen the semantic consistency between the generated images and the target domain, adaptively balances the quality and quantity of pseudo-labels according to a dynamic threshold screening mechanism, and introduces a hard-sample triplet loss to enhance the model discriminative ability. Ablation experiments on the CVUSA and CVACT datasets show that the BEV-CycleGAN+CL (Bird’s-Eye View Cycle-Consistent Generative Adversarial Network with Contrastive Learning) model proposed in this paper significantly outperforms the comparative models in PSNR, SSIM, and RMSE metrics. Specifically, on the CVACT dataset, compared with the BEV-CycleGAN, BEV, and CycleGAN baselines, PSNR increased by 2.83%, 16.02%, and 42.30%, SSIM increased by 6.12%, 8.00%, and 18.48%, and RMSE decreased by 9.28%, 15.51%, and 25.35%, respectively. Similar advantages are observed on the CVUSA dataset. Compared with current state-of-the-art models, the dynamic threshold pseudo-label localization method in this paper demonstrates overall superiority in recall metrics such as R@1, R@5, R@10, and R@1%, for example achieving an R@1 of 98.94% on CVUSA, outperforming the best comparative model, Sample4G^†, which reached 98.68%. This study provides innovative methodological support for disaster emergency response, high-precision map construction for autonomous driving, military reconnaissance, and other applications. Full article

Ligand-based virtual screening (LBVS) seeks strong early enrichment when searching ultra-large libraries, but practical screening often relies on 1D/2D descriptions while 3D information is expensive and uncertain due to conformer generation and alignment. We propose GNN-MA, a retrieval-style pairwise scoring model for query–candidate molecular pairs that uses molecular graphs as a unified representation. Built on intra-graph message passing, GNN-MA adds cross-graph attention to learn atom-level soft alignment that focuses on key substructures relevant to activity matching, and introduces a bond-to-atom semantic aggregation module to better exploit chemical bond cues for similarity scoring. The framework uses 2D molecular graphs derived from SMILES for retrieval-style matching and does not rely on explicit 3D conformational modeling or alignment. Experiments on DUD-E and LIT-PCBA show that GNN-MA achieves competitive overall discrimination (ROC-AUC) and, relative to its ablated variants, provides consistent gains in early-enrichment metrics (EF@1–5%) on DUD-E, while on LIT-PCBA the improvements are more target-dependent. The learned atom-level soft alignment also provides a qualitative interpretability cue in case studies. Throughput benchmarks suggest that GNN-MA is most suitable as a re-ranking/refinement model after a fast prefiltering stage. Full article

Knowledge Graphs (KGs) are increasingly adopted in cultural heritage research to address challenges of semantic heterogeneity, data fragmentation, and cross-institutional knowledge integration. Despite the rapid growth of KG-based heritage systems, a comprehensive and methodologically rigorous synthesis of existing applications remains limited. To address this gap, this study conducts a ROSES-based systematic review of KG applications in cultural heritage, aiming to examine prevailing application domains, methodological patterns, and emerging research trends. Following the Reporting Standards for Systematic Evidence Syntheses (ROSES), a structured search was conducted in Scopus, Web of Science, and IEEE Xplore. After duplicate removal, screening, eligibility assessment, and quality appraisal, 248 peer-reviewed studies published between 2015 and 2024 were retained for final synthesis. A mixed-method approach combining descriptive analysis and thematic synthesis was employed to analyze KG construction strategies, technological components, application contexts, and reported outcomes. The results indicate that KGs are primarily applied in five interconnected areas: digital recording and preservation, knowledge management and integration, protection and restoration support, cultural transmission and education, and research and innovation. Methodologically, the literature reveals a transition from ontology-driven and manually curated knowledge models toward hybrid approaches integrating artificial intelligence techniques such as natural language processing and machine learning. However, persistent challenges remain, including ontology alignment, scalability, evaluation inconsistency, and limited cross-project interoperability. This review contributes a consolidated and transparent evidence base for KG applications in cultural heritage and advances a conceptual understanding of KGs as socio-technical infrastructures that mediate cultural knowledge representation and interpretation. The findings offer methodological insights and practical implications for researchers, heritage professionals, and system designers, while highlighting directions for future interdisciplinary research. Full article

Social media has become a key venue where PhD graduates seek career information, compare experiences, and negotiate uncertainty. Drawing on information behavior and sense-making perspectives, this study examines how returnee PhDs from non-core study destinations discuss employment challenges in China’s academic labor market when credential signals are contested. Using Korean-trained PhDs as a theoretically motivated exemplary case, we collected 1149 publicly available posts from Xiaohongshu, a Chinese social media platform, and applied BERTopic to identify latent themes, followed by qualitative close reading of representative posts to interpret discourse functions. The model yielded ten topics, and semantic association analysis indicates substantial overlap among high-frequency topics, suggesting intertwined concerns rather than neatly separated issue domains. The four most prevalent topics account for 72.06% of the corpus, centering on credential recognition, job-search pathways, informal screening rules, and intersecting age- and gender-related pressures. Qualitative readings further reveal recurring discursive moves, including exposing tacit hiring heuristics, contesting stigmatizing labels (e.g., “water PhD,” a derogatory term implying low-quality credentials), and exchanging actionable strategies across regions and career tracks. Overall, the findings point to discursive convergence under evaluation uncertainty: when formal criteria are ambiguous and institutional signals are unreliable, participants turn to social media to stabilize expectations by triangulating cases and iteratively refining shared interpretations of the job market. This study contributes empirical evidence on uncertainty-driven information practices in highly educated labor markets and demonstrates the value of combining topic modeling with qualitative interpretation to capture online collective sense-making. Full article

Artificial intelligence (AI) has been increasingly applied to leukemia research, spanning diagnostic, prognostic, therapeutic, and translational domains. However, the rapid growth and methodological diversity of this literature present challenges for existing reviews, which are often constrained by limited scope, narrow clinical focus, or reliance on either manual or purely bibliometric approaches. As a result, cross-domain relationships, evolving methodological trends, and the interaction between data modalities and clinical objectives remain insufficiently understood. This paper presents a systematic, AI-assisted literature analysis of AI applications in leukemia, combining scalable machine-driven discovery with author-led qualitative interpretation. Using a PRISMA-guided screening process, a corpus of 2338 peer-reviewed publications retrieved from Scopus (1990–2024) is analyzed through semantic text representation and unsupervised clustering. An iterative human–machine process is employed to identify and refine 23 analytical parameters grouped into five macro-parameters, enabling structured organization of the research landscape across diagnostic, prognostic, therapeutic, genetic, and methodological dimensions. Building on this structured representation, in-depth qualitative analysis is conducted by the authors across parameters and macro-parameters, synthesizing methodological developments, data usage patterns, application domains, and commonly used datasets. The resulting analysis provides a coherent, interpretable mapping of AI-driven leukemia research, supporting cross-domain comparison and identification of research concentrations, fragmentation, and emerging directions. By integrating large-scale automation with domain-informed qualitative analysis in a reusable analytical pipeline, this work contributes a rigorous and transferable framework for structured literature analysis in leukemia and related biomedical domains. Full article

Background: The modernization of Traditional Chinese Medicine (TCM) is hindered by a “structure-blind” bottleneck: establishing molecular mechanisms for complex formulations with uncharacterized chemical constituents. Conventional computational screening fails in these scenarios due to a heavy reliance on pre-determined structures. We developed NovelHTI, an inductive graph-based framework designed to reverse-engineer protein targets directly from standardized clinical symptom profiles. Methods: NovelHTI implements a “Phenotype-to-Target” paradigm by integrating heterogeneous graph neural networks with systemic pathway constraints. Unlike traditional transductive models, NovelHTI leverages multi-view feature fusion of symptom semantics and biological pathways to enable de novo prediction for unseen herbs. The framework was evaluated across 698 herbs and 7854 targets, benchmarking against advanced GNNs (HAN) and non-graph classifiers (XGBoost) under strict cold-start and knowledge erosion simulations. Results: NovelHTI maintains high precision (>$84\%$) and balanced performance (F1-score $>77\%$), outperforming baselines by over 33% (ROC-AUC) in realistic imbalanced screening, where traditional models typically fail (AUC ≈ 0.51). Robustness analysis confirmed stable performance (>$0.83$ AUC) despite 30% structural data incompleteness. Notably, retrospective validation successfully “rediscovered” emerging mechanisms (e.g., the Artemisinin-GPX4 ferroptosis axis) elucidated in 2021–2024 literature, which were entirely latent in the training data. Conclusions: NovelHTI provides a robust computational prioritization filter that effectively bridges macroscopic phenotypes and microscopic pharmacology. By enabling mechanism-driven target de-risking, this framework optimizes resource allocation for downstream experimental validation and accelerates TCM-based drug discovery. Full article

This paper investigates the relationship between the typological organisation of residential interiors and the subjective experience of spatiality, formed through sequential, visually mediated movement. It examines whether perceived spatiality derives primarily from the mental integration of the dwelling as a whole through circular movement, or from immediately accessible visual relationships such as visual accessibility and perceptual depth. An experimental study was conducted in which participants with and without professional education in architecture and interior design evaluated four typologically distinct residential interior models (circular circulation, enfilade, branched structure, and open plan), presented through standardized screen-based animated walkthrough simulations designed to replicate continuous spatial movement under controlled visual conditions. Subjective evaluations were collected using eight bipolar semantic scales. Analysis of variance showed that typological structure had a statistically significant effect on all analysed dimensions of spatiality, while professional expertise did not produce significant differences. The results support the hypothesis that perceived spatiality is predominantly shaped by immediate visual accessibility and perceptual depth rather than by circular spatial connections requiring sequential cognitive integration. The findings clarify key perceptual mechanisms of spatiality and underscore the distinction between spatial flow as a structural property and spatiality as a perceptual category, with implications for residential design and further research. Full article

Large Language Models (LLMs) have acquired vast amounts of knowledge during pre-training. However, there are a lot of challenges when it is deployed in real-world applications, such as poor interpretability, hallucinations, and the inability to reference private data. To address these issues, Retrieval-Augmented Generation (RAG) has been proposed. Traditional RAG relying on text-based retrievers often converts documents using Optical Character Recognition (OCR) before retrieval. While testing has revealed that it tends to overlook tables and images contained within the documents. RAG, relying on vision-based retrievers, often loses information on text-dense pages. To address these limitations, we propose DRAG: Dual-channel Retrieval-Augmented Generation for Hybrid-Modal Document Understanding, a novel retrieval paradigm. The DRAG method proposed in this paper primarily comprises two core improvements: first, a parallel dual-channel processing architecture is adopted to separately extract and preserve the visual structural information and deep semantic information of documents, thereby effectively enhancing information integrity; second, a novel dynamic weighted fusion mechanism is proposed to integrate the retrieval results from both channels, enabling precise screening of the most relevant information segments. Empirical results demonstrate that our method achieves Competitive performance across multiple general benchmarks. Furthermore, performance on biomedical datasets (e.g., BioM) specifically highlights its potential in specialized, vertical domains such as elderly care and rehabilitation, where documents are characterized by dense hybrid-modal information. Full article

In response to the challenges of target recognition and misjudgment caused by varying target scales, diverse shapes, and interference such as lake surface reflections in river and lake scenarios, this paper proposes the YOLO v11n-DDH model for fast and detection of spatial targets in river and lake environments. The model builds upon YOLO v11n by introducing the Dynamic Snake Convolution (DySnakeConv) to enhance the ability to extract detailed features. It integrates the Deformable Attention Mechanism (DAttention) to strengthen key features and suppress noise, while combining the improved High-Level Screening Feature Pyramid Network (HSFPN) structure for multi-level feature fusion, thus improving the semantic representation of targets at different scales. Experiments on a self-constructed dataset show that the precision, recall, and mAP of the YOLO v11n-DDH model reached 88.4%, 78.9%, and 83.9%, respectively, with improvements of 3.4, 2.9, and 2.5 percentage points over the original model. Specifically, DySnakeConv increased mAP@50 by 0.6 percentage points, DAttention improved mAP@50 by 0.3 percentage points, and HSFPN contributed to a 0.9 percentage point rise in mAP@50. This patrol system can effectively identify and visualize various pollutants in river and lake areas, such as underwater waste, water quality pollution, illegal swimming and fishing, and the “Four Chaos” issues, providing technical support for intelligent river and lake management. Full article

Context: Code recommendation plays an important role in improving programming efficiency and software quality. Existing approaches mainly focus on method- or API-level recommendations, which limits their effectiveness to local code contexts. From a multi-stage recommendation perspective, class-level code recommendation aims to efficiently narrow a large candidate code space while preserving essential structural information. Objective: This paper proposes RioCC, a class-level code recommendation framework that leverages deep forest-based code clone detection to progressively reduce the candidate space and improve recommendation efficiency in large-scale code spaces. Method: RioCC models the recommendation process as a coarse-to-fine candidate reduction procedure. In the coarse-grained stage, a quick search-based filtering module performs rapid candidate screening and initial similarity estimation, effectively pruning irrelevant candidates and narrowing the search space. In the fine-grained stage, a deep forest-based analysis with cascade learning and multi-grained scanning captures context- and structure-aware representations of class-level code fragments, enabling accurate similarity assessment and recommendation. This two-stage design explicitly separates coarse candidate filtering from detailed semantic matching to balance efficiency and accuracy. Results: Experiments on a large-scale dataset containing 192,000 clone pairs from BigCloneBench and a collected code pool show that RioCC consistently outperforms state-of-the-art methods, including CCLearner, Oreo, and RSharer, across four types of code clones, while significantly accelerating the recommendation process with comparable detection accuracy. Conclusions: By explicitly formulating class-level code recommendation as a staged retrieval and refinement problem, RioCC provides an efficient and scalable solution for large-scale code recommendation and demonstrates the practical value of integrating lightweight filtering with deep forest-based learning. Full article