Suggested Topics within your search.
Suggested Topics within your search.
-
3881
Assessing the Impacts of the Israeli–Palestinian Conflict on Global Sea Transportation: From the View of Mass Tanker Trajectories
Published 2025-02-01“…By using the global vessel trajectory data of tankers from the Automatic Identification System (AIS) and taking the global sea transportation of large tankers as an example, this paper quantifies and visualizes the changes in global sea transportation before and after conflicts from a data-driven perspective. …”
Get full text
Article -
3882
Field-level Comparison and Robustness Analysis of Cosmological N-body Simulations
Published 2025-01-01“…Our findings motivate the need for careful data filtering and the use of field-level OOD metrics, such as PQMass, to ensure robust inference.…”
Get full text
Article -
3883
SLIP-flood: Soft-combination of Swin Transformer and Lightweight Language-Image Pre-training for Flood Images Classification
Published 2025-05-01“…Flood monitoring is a complex task involving multimodal data mining and multitask collaboration. In order to leverage the role of multimodal data in flood management, conducting visual-language pretraining (VLP) in the field of flood disaster monitoring and obtaining foundational pretraining models that are suitable for multiple downstream flood-related tasks is an urgent problem that needs to be addressed. …”
Get full text
Article -
3884
Disaster in the Headlines: Quantifying Narrative Variation in Global News Using Topic Modeling and Statistical Inference
Published 2025-06-01“…The findings reveal that disaster narratives vary by event type and geopolitical context, supported by a mathematically robust, scalable, data-driven method for analyzing media framing of global crises.…”
Get full text
Article -
3885
Dataset Dependency in CNN-Based Copy-Move Forgery Detection: A Multi-Dataset Comparative Analysis
Published 2025-06-01“…Similarly, we observed that data augmentation was able to improve performance on large datasets but was ineffective on smaller ones. …”
Get full text
Article -
3886
Application of Enhanced Weighted Least Squares with Dark Background Image Fusion for Inhomogeneity Noise Removal in Brain Tumor Hyperspectral Images
Published 2024-12-01“…The inhomogeneity of spectral pixel response is an unavoidable phenomenon in hyperspectral imaging, which is mainly manifested by the existence of inhomogeneity banding noise in the acquired hyperspectral data. It must be carried out to get rid of this type of striped noise since it is frequently uneven and densely distributed, which negatively impacts data processing and application. …”
Get full text
Article -
3887
Quantifying winter forage resources for reindeer: Developing a method to estimate ground lichen cover and biomass at a local scale
Published 2025-03-01“…Following this, we collected field data on lichen cover and height in these plots. In addition, we compared methods for assessing lichen cover in the field and found that visual estimates resulted in lower values than a point-intercept method. …”
Get full text
Article -
3888
Support of individual educational trajectories based on the concept of explainable artificial intelligence
Published 2022-01-01“…A preliminary analysis of significant volumes of initial data made it possible to obtain objective information about the data quality, including the content and structure of documents presented in various university information systems. …”
Get full text
Article -
3889
Machine Learning-Driven Customer Segmentation: A Behavior-Based Approach for F&B Providers
Published 2025-12-01“…Using one year of invoice-level transactional data from a Romanian Food and Beverage (F&B) provider serving restaurants and coffee shops, the research aims to deliver actionable insights to enhance marketing and sales strategies. …”
Get full text
Article -
3890
Tracking Religious Freedom Violations with the Violent Incidents Database: A Methodological Approach and Comparative Analysis
Published 2025-05-01“…We offer a preliminary analysis of the data collected through the end of 2024 with selected figures for data visualization. …”
Get full text
Article -
3891
-
3892
Long term investigation of bonding characteristics between PVC based inhibitor and HTPB/IPDI based propellant
Published 2024-01-01“…Based on visual appearance of mentioned separated parts an assessment of way of separation was done. …”
Get full text
Article -
3893
Insurance claims estimation and fraud detection with optimized deep learning techniques
Published 2025-07-01Get full text
Article -
3894
Extraction of typical oyster pile columns in the Maowei Sea, Beibu Gulf, based on unmanned aerial vehicle laser point cloud orthophotos
Published 2025-03-01“…Consequently, obtaining data on oyster pile columns and oyster seedling culture areas presents certain limitations. …”
Get full text
Article -
3895
A Comprehensive Review on Light Field Occlusion Removal: Trends, Challenges, and Future Directions
Published 2025-01-01“…Overcoming occlusions in light field (LF) imaging is a challenging yet complex task crucial for scene understanding, image quality enhancement, and restoring visual details in obstructed scenes. This review examines contemporary occlusion removal methods, spanning from classical techniques to advanced deep learning approaches that leverage LF data’s spatial and angular dimensions. …”
Get full text
Article -
3896
BIM-GIS Integration for Interactive, Open and Low-Cost 3D Land Use Registration and Urban Neighbourhood Management
Published 2024-01-01“…The proposed platform is structured for registering, classifying and visualizing volumetric land use prisms, distributing conceptual and geometric information, conducting statistical analyses and data exchange aiming for optimal decision making, urban neighbourhood management and land use tracking. …”
Get full text
Article -
3897
-
3898
-
3899
A Catalog of Hα Emission-line Stars and 785 Newly Identified Young Stellar Object Candidates from LAMOST Based on a Deep Learning Method
Published 2025-01-01“…In this paper, we use bidirectional long short-term memory networks and convolutional neural networks to identify H α emission-line stars in medium-resolution spectra from the Large Area Multi-Target Fiber Optic Spectroscopic Telescope (LAMOST) survey, and further search for YSO candidates via the Li absorption line. We constructed a data set by crossmatching previously published data sets with LAMOST data and performing manual verification. …”
Get full text
Article -
3900
Digiral marketplaces and their effect to corporates’ business models and structures
Published 2025-04-01Get full text
Article