Search Results (114)

Crop monitoring over large land extensions represents a central challenge in precision agriculture, especially in polyculture contexts where species with different nutritional needs are combined. This study presents a methodology to manage and analyze large volumes of multispectral images captured by unmanned aerial vehicles (UAVs) in order to identify and monitor crops at the plant level. The images are efficiently stored and retrieved using a Hilbert Curve, which reduces the complexity of the search process from $O\left(n^2\right)$ to $O(log(n\left)\right)$ where n represents the number of indexed data points). The system connects to a distributed Structured Query Language (SQL) database, allowing for fast image retrieval based on GPS coordinates and other metadata. Additionally, the Normalized Difference Vegetation Index (NDVI) is calculated using reflectance data from the red and near-infrared channels, adjusted by semantic segmentation masks generated with a U-Net model, which allows for species-specific evaluations. The methodology was evaluated on a 20,000 m² polyculture farm with coffee, avocado, and plantain crops, using a dataset of 270 aerial images partitioned into 70% for training and 30% for validation. The results show improvements in retrieval speed and precision with the Hilbert Space-Filling Curve (HSFC) approach, and an accuracy of 82.3% and an the Mean Intersection over Union (MIoU) of 68.4% in species detection with the U-Net model. Overall, this integrated framework demonstrates a scalable potential for precision agriculture in complex polyculture systems, facilitating efficient data management and targeted crop interventions. Full article

The geometric dimensional accuracy of large-scale prefabricated components is critical for the successful implementation of prefabricated construction. However, traditional manual contact-based inspection methods are inefficient and are often simplified or even neglected in practice due to operational difficulties. To address this challenge, this study proposes an automated non-contact dimensional inspection system based on UAV photogrammetry. The system consists of three core modules: First, the 3D Model Generation Module utilizes UAV-captured multi-view imagery to rapidly reconstruct high-fidelity 3D models of construction sites using improved 3D Gaussian Splatting technology, while recovering true physical scales by integrating GPS metadata. Second, the Segmentation Module extracts target components from complex backgrounds through flexible target selection and achieves automated planar segmentation using the Region Growing algorithm. Finally, the Dimensional Inspection Module accurately calculates geometric dimensions using a self-developed “Measurement Tree” algorithm. Engineering validation demonstrates that the system achieves an average relative error of only 0.35% in the inspection of prefabricated bent caps, exhibiting excellent measurement accuracy and robustness. This study provides an efficient, precise, and intelligent solution for the quality control of prefabricated components, effectively bridging the gaps inherent in traditional inspection methods. Full article

Source camera identification on smartphones constitutes a fundamental task in multimedia forensics, providing essential support for applications such as image copyright protection, illegal content tracking, and digital evidence verification. Numerous techniques have been developed for this task over the past decades. Among existing approaches, Photo-Response Non-Uniformity (PRNU) has been widely recognized as a reliable device-specific fingerprint and has demonstrated remarkable performance in real-world applications. Nevertheless, the rapid advancement of computational photography technologies has introduced significant challenges: modern devices often exhibit anomalous behaviors under PRNU-based analysis. For instance, images captured by different devices may exhibit unexpected correlations, while images captured by the same device can vary substantially in their PRNU patterns. Current approaches are incapable of automatically exploring the underlying causes of these anomalous behaviors. To address this limitation, we propose a simple yet effective forensic analysis framework leveraging Exchangeable Image File Format (EXIF) metadata. Specifically, we represent EXIF metadata as type-aware word embeddings to preserve contextual information across tags. This design enables visual interpretation of the model’s decision-making process and provides complementary insights for identifying the anomalous behaviors observed in modern devices. Extensive experiments conducted on three public benchmark datasets demonstrate that the proposed method not only achieves state-of-the-art performance for source camera identification but also provides valuable insights into anomalous device behaviors. Full article

Accurate and timely classification of skin lesions is critical for early cancer detection, yet current deep learning approaches suffer from high computational costs, limited interpretability, and poor transparency for clinical deployment. This study presents HCHS-Net, a lightweight and interpretable multimodal framework for six-class skin lesion classification on the PAD-UFES-20 dataset. The proposed framework extracts a 116-dimensional visual feature vector through three complementary handcrafted modules: a Color Module employing multi-channel histogram analysis to capture chromatic diagnostic patterns, a Haralick Module deriving texture descriptors from the gray-level co-occurrence matrix (GLCM) that quantify surface characteristics correlated with malignancy, and a Shape Module encoding morphological properties via Hu moment invariants aligned with the clinical ABCD rule. The architectural design of HCHS-Net adopts a biomimetic approach by emulating the hierarchical information processing of the human visual system and the cognitive diagnostic workflows of expert dermatologists. Unlike conventional black-box deep learning models, this framework employs parallel processing branches that simulate the selective attention mechanisms of the human eye by focusing on biologically significant visual cues such as chromatic variance, textural entropy, and morphological asymmetry. These visual features are concatenated with a 12-dimensional clinical metadata vector encompassing patient demographics and lesion characteristics, yielding a compact 128-dimensional multimodal representation. Classification is performed through an ensemble of three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) with majority voting. HCHS-Net achieves 97.76% classification accuracy with only 0.25 M parameters, outperforming deep learning baselines, including VGG-16 (94.60%), ResNet-50 (94.80%), and EfficientNet-B2 (95.16%), which require 60–97× more parameters. The framework delivers an inference time of 0.11 ms per image, enabling real-time classification on standard CPUs without GPU acceleration. Ablation analysis confirms the complementary contribution of each feature module, with metadata integration providing a 2.53% accuracy gain. The model achieves perfect melanoma and nevus recall (100%) with 99.55% specificity, maintaining reliable discrimination at safety-critical diagnostic boundaries. Comprehensive benchmarking against 13 published methods demonstrates that domain-informed handcrafted features combined with clinical metadata can match or exceed deep learning fusion approaches while offering superior interpretability and computational efficiency for point-of-care deployment. Full article

Medical image segmentation, particularly for pathological diagnosis, faces challenges in leveraging patient clinical metadata that could enhance diagnostic accuracy. This study presents MMY-Net (Multimodal Y-shaped Network), a novel deep learning framework that effectively fuses patient metadata with pathological images for improved tumor segmentation performance. The proposed architecture incorporates a Text Processing Block (TPB) utilizing BERT for metadata feature extraction and a Text Encoding Block (TEB) for multi-scale fusion of textual and visual information. The network employs an Interlaced Sparse Self-Attention (ISSA) mechanism to capture both local and global dependencies while maintaining computational efficiency. Experiments were conducted on two open/public eyelid tumor datasets (Dataset 1: 112 WSIs for training/validation; Dataset 2: 107 WSIs as an independent test set) and the public Dataset 3 gland segmentation benchmark. For Dataset 1, 7989 H&E-stained patches (1024 × 1024, resized to 224 × 224) were extracted and split 7:2:1 (train:val:test); Dataset 2 was used exclusively for external validation. All images underwent Vahadane stain normalization. Training employed SGD (lr = 0.001), 1000 epochs, and a hybrid loss (cross-entropy + MS-SSIM + Lovász). Results show that integrating metadata—such as age and gender—significantly improves segmentation accuracy, even when metadata does not directly describe tumor characteristics. Ablation studies confirm the superiority of the proposed text feature extraction and fusion strategy. MMY-Net achieves state-of-the-art performance across all datasets, establishing a generalizable framework for multimodal medical image analysis. Full article

This dataset presents a real-world lipidomics resource for developing and benchmarking quality control methods, batch effect detection algorithms, and data validation workflows. The data originates from a cross-sectional clinical study of psoriatic arthritis (PsA) patients (n = 81) and healthy controls (n = 26), matched for age, sex, and body mass index, which was collected at a tertiary university rheumatology center. Subtle laboratory irregularities were detected only through advanced unsupervised analysis, after passing conventional quality control and standard analytical methods. Blood samples were processed using standardized protocols and analyzed using high-resolution and tandem mass spectrometry platforms. Both targeted and untargeted lipid assays captured lipids of several classes (including carnitines, ceramides, glycerophospholipids, sphingolipids, glycerolipids, fatty acids, sterols and esters, endocannabinoids). The dataset is organized into four comma-separated value (CSV) files: (1) Box–Cox-transformed and imputed lipidomics values; (2) outlier-cleaned and imputed values on the original scale; (3) metadata including clinical classifications, biological sex, and batch information for all assay types and control sample processing dates; and (4) a variable-level description file (readme.csv). The 292 lipid variables are named according to LIPID MAPS classification and standardized nomenclature. Complete batch documentation and FAIR-compliant data structure make this dataset valuable for testing the robustness of analytical pipelines and quality control in lipidomics and related omics fields. This unique dataset does not compete with larger lipidomics quality control datasets for comparisons of results but provides a unique, real-life lipidomics dataset displaying traces of the laboratory sample processing schedule, which can be used to challenge quality control frameworks. Full article

Software maintenance and release management demand proper identification of bug dependencies since priority violations or unresolved dependent issues can often lead to a chain of failures. However, dependency annotations in bug reports are extremely sparse and imbalanced. These dependencies are often expressed implicitly through natural language descriptions rather than explicit metadata. This creates challenges for automated multilabel dependency classification systems. To tackle these drawbacks, we introduce a meta-contrastive optimization framework (MCOF). This framework integrates established learning paradigms to enhance transformer-based classification through two key mechanisms: (1) a meta-contrastive objective adapted for enhancing discriminative representation learning under few-shot supervision, particularly for rare dependency types, and (2) dependency-aware Laplacian regularization that captures relational structures among different dependency types, reducing confusion between semantically related labels. Experimental evaluation on a real-world dataset demonstrates that MCOF achieves significant improvement over strong baselines, including BM25-based clustering and standard BERT fine-tuning. The framework attains a micro-F1 score of 0.76 and macro-F1 score of 0.58, while reducing hamming loss to 0.14. Label-wise analysis shows significant performance gain on low-frequency dependency types, with improvements of up to 16% in F1 score. Runtime analysis exhibits only modest inference overhead at 15%, confirming that MCOF remains practical for deployment in CI/AT pipelines. These results demonstrate that integrating meta-contrastive learning and structural regularization is an effective approach for robust bug dependency discovery. The framework provides both practical and accurate solutions for supporting real-world software engineering workflows. Full article

This study presents DeepVisionAnalytics, an integrated framework that combines eye tracking, OpenCV-based computer vision (CV), and machine learning (ML) to support objective analysis of consumer behaviour in visually driven tasks. Unlike conventional self-reported surveys, which are prone to cognitive bias, recall errors, and social desirability effects, the proposed approach relies on direct behavioural measurements of visual attention. The system captures gaze distribution and fixation dynamics during interaction with products or interfaces. It uses AOI-level eye tracking metrics as the sole behavioural signal to infer candidate choice under constrained experimental conditions. In parallel, OpenCV and ML perform facial analysis to estimate demographic attributes (age, gender, and ethnicity). These attributes are collected independently and linked post hoc to gaze-derived outcomes. Demographics are not used as predictive features for choice inference. Instead, they are used as contextual metadata to support stratified, segment-level interpretation. Empirical results show that gaze-based inference closely reproduces observed choice distributions in short-horizon, visually driven tasks. Demographic estimates enable meaningful post hoc segmentation without affecting the decision mechanism. Together, these results show that multimodal integration can move beyond descriptive heatmaps. The platform produces reproducible decision-support artefacts, including AOI rankings, heatmaps, and segment-level summaries, grounded in objective behavioural data. By separating the decision signal (gaze) from contextual descriptors (demographics), this work contributes a reusable end-to-end platform for marketing and UX research. It supports choice inference under constrained conditions and segment-level interpretation without demographic priors in the decision mechanism. Full article

Digital identity operates as the connective infrastructure of the digital age, linking individuals, organisations, and devices into networks through which services, rights, and responsibilities are transacted. Despite this centrality, the field remains fragmented, with technical solutions, disciplinary perspectives, and regulatory approaches often developing in parallel without interoperability. This paper presents a systematic survey of digital identity research, drawing on a Scopus-indexed baseline corpus of 2551 publications spanning full years 2005–2024, complemented by a recent stratum of 1241 publications (2023–2025) used to surface contemporary thematic structure and inform the ontology-oriented synthesis. The survey contributes in three ways. First, it provides an integrated overview of the digital identity landscape, tracing influential and widely cited works, historical developments, and recent scholarship across technical, legal, organisational, and cultural domains. Second, it applies natural language processing and subject metadata to identify thematic patterns, disciplinary emphases, and influential authors, exposing trends and cross-field connections difficult to capture through manual review. Third, it consolidates recurring concepts and relationships into ontological fragments (illustrative concept maps and subgraphs) that surface candidate entities, processes, and contexts as signals for future formalisation and alignment of fragmented approaches. By clarifying how digital identity has been conceptualised and where gaps remain, the study provides a foundation for progress toward a universal digital identity that is coherent, interoperable, and socially inclusive. Full article

Voluntary carbon markets (VCMs) are growing rapidly but remain structurally fragmented due to verification delays, lifecycle opacity, inconsistent metadata, and capital mobilisation bottlenecks. While blockchain is often proposed as a digitalisation layer to improve transparency and traceability, this paper reframes tokenisation as a sector-aware financial infrastructure capturing the full lifecycle of carbon credits. Rather than treating it as a digital overlay, this study argues that tokenisation functions as a modular, automated architecture capable of absorbing sector-specific frictions within VCMs. Drawing on 1495 registry-compliant projects from the Berkeley Voluntary Offsets Database (BVOD v2025-06), the study develops the sector tokenisation opportunity matrix (STOM). This diagnostic framework maps registry-derived indicators—issuance volume, credit retirement ratio, and average credits per project—to three tokenisation functions: market expansion, retirement acceleration, and structuring for scale and fragmentation. STOM reveals how tokenisation can address VCM fragmentation by mobilising capital, reinforcing lifecycle integrity, and enabling assets to be packaged across diverse project types. By linking friction diagnostics to governance-sensitive infrastructure design, the research proposes a sector-aware blueprint for climate finance infrastructure and positions tokenisation as a strategic tool for scaling high-integrity climate action. Full article

Surface soil moisture (SSM) is essential for crop growth, irrigation management, and drought monitoring. However, conventional field-based measurements offer limited spatial and temporal coverage, making it difficult to capture environmental variability at scale. This study introduces a multimodal soil moisture estimation framework that combines synthetic aperture radar (SAR), optical imagery, vegetation indices, digital elevation models (DEM), meteorological data, and spatio-temporal metadata. To strengthen model performance and adaptability, an intermediate fine-tuning strategy is applied to two datasets comprising 10,571 images and 3772 samples. This approach improves generalization and transferability across regions. The framework is evaluated across diverse agro-ecological zones, including farmlands, alpine grasslands, and environmentally fragile areas, and benchmarked against single-modality methods. Results with RMSE 4.5834% and $R^2$ 0.8956 show consistently high accuracy and stability, enabling the production of reliable field-scale soil moisture maps. By addressing the spatial and temporal challenges of soil monitoring, this framework provides essential information for precision irrigation. It supports site-specific water management, promotes efficient water use, and enhances drought resilience at both farm and regional scales. Full article

Online chess platforms generate vast amounts of game data, presenting opportunities to analyze match outcomes using machine learning approaches. This study develops and compares four machine learning models to classify chess game results (White win, Black win, or Draw) by integrating player rating information with game dynamic metadata. We analyzed 11,510 complete games from the Lichess platform after preprocessing a dataset of 20,058 initial records. Seven key features were engineered to capture both pre-game skill parameters (player ratings, rating difference) and game complexity metrics (game duration, turn count). Four machine learning algorithms were implemented and optimized through grid search cross-validation: Multinomial Logistic Regression, Random Forest, K-Nearest Neighbors, and Histogram Gradient Boosting. The Gradient Boosting classifier achieved the highest performance with 83.19% accuracy on hold-out data and consistent 5-fold cross-validation scores (83.08% ± 0.009%). Feature importance analysis revealed that game complexity (number of turns) was the strongest correlate of the outcome across all models, followed by the rating difference between opponents. Draws represented only 5.11% of outcomes, creating class imbalance challenges that affected classification performance for this outcome category. The results demonstrate that ensemble methods, particularly gradient boosting, can effectively capture non-linear interactions between player skill and game length to classify chess outcomes. These findings have practical applications for chess platforms in automated content curation, post-game quality assessment, and engagement enhancement strategies. The study establishes a foundation for robust outcome analysis systems in online chess environments. Full article

Financial fraud detection is critical to modern economic security, yet remains challenging due to collusive group behavior, temporal drift, and severe class imbalance. Most existing graph neural network (GNN) detectors rely on pairwise edges and correlation-driven learning, which limits their ability to represent high-order group interactions and makes them vulnerable to spurious environmental cues (e.g., hubs or temporal bursts) that correlate with labels but are not necessarily causal. We propose Causal-DHG, a dynamic hypergraph framework that integrates hypergraph modeling, causal intervention, and multi-view contrastive learning. First, we construct label-agnostic hyperedges from publicly available metadata to capture high-order group structures. Second, a Multi-Head Spatio-Temporal Hypergraph Attention encoder models group-wise dependencies and their temporal evolution. Third, a Causal Disentanglement Module decomposes representations into causal and environment-related factors using HSIC regularization, and a dictionary-based backdoor adjustment approximates the interventional prediction $P(Y\mid do(C\left)\right)$ to suppress spurious correlations. Finally, we employ self-supervised multi-view contrastive learning with mild hypergraph augmentations to leverage unlabeled data and stabilize training. Experiments on YelpChi, Amazon, and DGraph-Fin show consistent gains in AUC/F1 over strong baselines such as CARE-GNN and PC-GNN, together with improved robustness under feature and structural perturbations. Full article

Traditional geoportals depend primarily on keyword-based search, which often fails to retrieve relevant datasets when metadata are heterogeneous, incomplete, or inconsistent with user terminology. This limitation reduces the efficiency of data discovery and selection, particularly in domains where metadata quality varies widely. This study aims to address this challenge by developing a semantic collaborative filtering recommendation system designed to enhance dataset discovery in geoportals through the analysis of implicit user interactions. The system captures users’ search queries, viewed datasets, downloads, and applied filters to infer feedback and organize it into a user–item matrix. Because interaction data are typically sparse, semantic user clustering is applied to mitigate this limitation by grouping users with semantically related interests through hierarchical relationships represented in the Simple Knowledge Organization System (SKOS). However, as users often need complementary datasets to complete specific tasks, association rule mining is employed to identify co-occurrence patterns in search histories and enhance task-related result diversity. The final recommendation scores are then computed by factorizing the user–item matrix with Alternating Least Squares (ALS), using cosine similarity on the latent user vectors to identify nearest neighbors, and applying a standard user-based neighborhood prediction model to rank unseen datasets. The system is implemented within an existing ontology-based geoportal as a standalone, configurable component, requiring only access to user interaction logs and dataset identifiers. Evaluation using precision, recall, and Precision@5 demonstrates that increasing user interactions improves recommendation performance by strengthening behavioral evidence used for ranking. The findings indicate that integrating semantic relationships and behavioral patterns can strengthen dataset discovery in geoportals and complement conventional metadata-based search mechanisms. Full article

Oropouche virus (OROV) is an emerging and underreported arbovirus with dengue-like symptoms confounding diagnosis. OROV is also neuroinvasive, with a small number of cases presenting severe neurological symptoms. There have been recently reported deaths from confirmed cases of OROV and reported instances of vertical transmission from mother to foetus, with confirmed cases in Brazil and a congenital anomaly, reportedly as a consequence of OROV infection in Cuba, with further cases under investigation. Whilst cases of OROV infection occur mainly in South America, many cases have been imported elsewhere, including the United States and Europe. Despite the emerging threat to public health, animal modelling to study OROV pathogenicity and immunity and to evaluate therapeutic candidates remains limited. For this review, we carried out a literature search through major research databases (PubMed and Scopus) up to September 2025 to capture the extent of in vivo model development for this pathogen. We identified only 17 relevant primary research articles within these criteria which detailed hamster, mouse and non-human primate (NHP) models. Here, we discuss the extent of in vivo model development for OROV. In summary, small and large animal models need to be assessed with recent clinical isolates and reassortants, asymptomatic disease presentation in the NHP model requires further study and the hamster model shows potential for use in pathogenicity and vaccine or antiviral efficacy studies. We also compile relevant metadata and discuss the need for an animal model that more closely resembles human disease. Full article