-
3941
Spatio-Temporal Travel Speed Estimation in Mixed Traffic Conditions: A Probe Vehicle-Based Approach With Autonomous Vehicle Sensor Integration
Published 2025-01-01“…Future research directions include integrating vehicle-to-everything (V2X) communication and machine learning models to further refine estimation accuracy and predictive capabilities in dynamic urban mobility environments.…”
Get full text
Article -
3942
Forensic of video object removal tamper based on 3D dual-stream network
Published 2021-12-01“…In order to solve the problems of inaccurate temporal detection and location of the object removal tampered video, a video tamper forensics method based on 3D dual-stream network was proposed.Firstly, the spatial rich model (SRM) layer was used to extract the high-frequency information from video frames.Secondly, the improved 3D convolution (C3D) network was used as the feature extractor of the dual-stream network to extract the high-frequency information and low-frequency information from the high-frequency frame and the original video frame respectively.Finally, through compact bilinear pooling (CBP) layer, two sets of different feature vectors were fused into one set of feature vectors for classification prediction.The experimental results demonstrate that the classification accuracy of the proposed method in all video frames has an advantage in SYSU-OBJFORG dataset, which makes the temporal detection and location of object removal tampered video more accurate.…”
Get full text
Article -
3943
Enhanced Pilot Attention Monitoring: A Time-Frequency EEG Analysis Using CNN–LSTM Networks for Aviation Safety
Published 2025-06-01“…Finally, our dual-architecture CNN–LSTM model processes spatial patterns via CNNs while capturing temporal degradation signals via LSTMs, enabling robust classification in noisy operational environments. …”
Get full text
Article -
3944
Detailed Numerical Simulation of Planar Liquid Sheet Atomization: Instability Dynamics, Ligament Formation, and Self-Destabilization Mechanisms
Published 2025-05-01“…This work provides critical insights for refining engineering atomization models through physics-based ligament diameter prediction criteria.…”
Get full text
Article -
3945
Spatiotemporal Characteristics and Influential Factors of Electronic Cigarette Web-Based Attention in Mainland China: Time Series Observational Study
Published 2025-02-01“…A variance inflation factor test was performed to avoid multicollinearity. A spatial panel econometric model was developed to assess the determinants of e-cigarette web-based attention. …”
Get full text
Article -
3946
International trade market forecasting and decision-making system: multimodal data fusion under meta-learning
Published 2025-08-01“…Experimental results demonstrate that the proposed multimodal data fusion model, ML-BiFPN under meta-learning, significantly outperforms existing methods in prediction performance. …”
Get full text
Article -
3947
Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation
Published 2025-06-01“…This fusion enhances the model’s prediction accuracy and robustness, particularly in challenging natural environments. …”
Get full text
Article -
3948
Integrating geostatistical methods and deep learning for enhanced 87Sr/86Sr isoscape Estimation: A case study in South Korea
Published 2025-08-01“…However, generating accurate and spatially continuous isoscape maps from sparse isotopic measurements remains a major challenge due to limited data availability and spatial heterogeneity. …”
Get full text
Article -
3949
Evaluation of the pharmacological potential of N-((5-phenyl-6,11-dihydro-[1,2,4]triazolo[1’,5’:1,6]pyrido[3,4-b]indol-2-yl)methyl)benzamides
Published 2025-07-01“…Advanced molecular docking techniques were employed to identify potential binding sites with model enzymes and to characterize the energetic and spatial features of ligand-target interactions. …”
Get full text
Article -
3950
Spatio-temporal mapping reveals changes in soil organic carbon stocks across the contiguous United States since 1955
Published 2025-08-01“…Then, multi-depth ST-DSM models are employed to generate spatial prediction of SOC in different layers (0–15 cm, 15–30 cm, 30–60 cm and 60–100 cm) from 1955 to 2014 at 250 m resolution and 5-year intervals (1955–1959, 1960–1964,…., 2010–2014). …”
Get full text
Article -
3951
Residual attention based multi-label learning for apple leaf disease identification
Published 2024-08-01“…Built upon an attention based multi-label learning framework, the channel and spatial attention mechanisms are investigated and embedded in residual network for multi-label disease prediction, which takes advantage of channel-wise and spatial-wise attention weights. …”
Get full text
Article -
3952
Multi-omics Analysis of Histone-related Genes in Osteosarcoma: A Multidimensional Integrated Study Revealing Drug Sensitivity and Immune Microenvironment Characteristics
Published 2025-04-01“…Based on nine histone modification-related genes, we constructed an efficient prognostic model (AUC values of 0.713, 0.845, and 0.888 for 1-, 3-, and 5-year predictions, respectively), which was validated in an external cohort (AUC = 0.808). …”
Get full text
Article -
3953
Location of capture sufficiently characterises lifetime growth trajectories in a highly mobile fish
Published 2025-03-01“…The predictive capacity of annual growth models slightly improved from the basin to the reach spatial scales (inclusive or exclusive of movement histories). …”
Get full text
Article -
3954
-
3955
Aboveground Carbon Estimation in a Mangrove Ecosystem Using UAV-Based Remote Sensing and Machine Learning
Published 2025-09-01“…Instead of plot-level metrics, which lack detailed spatial information about individual trees or areas smaller than the mapping unit, our model was developed based on tree-level metrics, using data on hundreds of trees from fewer forest inventory plots. …”
Get full text
Article -
3956
Human perception of self-motion and orientation during galvanic vestibular stimulation and physical motion.
Published 2024-11-01“…Subsequently, we develop a novel computational model that predicts 6DoF self-motion and self-orientation perceptions for any GVS waveform and motion by modeling the vestibular afferent neuron dynamics modulated by GVS in conjunction with an observer central processing model. …”
Get full text
Article -
3957
Combined simulation of fatigue crack nucleation and propagation based on a damage indicator
Published 2016-10-01“…Locations of fatigue crack emergence are predicted by these indicators and material degradation is utilized to model local material failure. …”
Get full text
Article -
3958
De impact van internationale instellingen in Brussel: een benadering vanuit een multicriteria‑analyse
Published 2008-12-01“…Possible distributive effects will be tracked across existing patterns of spatial diversity. The proposed model embeds identification, measurement and assessment in a fine-grained understanding of Belgian urban systems, thus allowing the disaggregation and localisation of impacts. …”
Get full text
Article -
3959
A spatiotemporal recurrent neural network for missing data imputation in tunnel monitoring
Published 2025-08-01“…ST-RNN consists of two moduli: a temporal module employing recurrent neural network (RNN) to capture temporal dependencies, and a spatial module employing multilayer perceptron (MLP) to capture spatial correlations. …”
Get full text
Article -
3960
The theoretical cognition and research paradigm of land system science
Published 2025-01-01“…The research paradigm of land system science has gradually transformed from knowledge and phenomenon description to the simulation and prediction of complex land systems, which emphasizes the integration of multidisciplinary theories and methods as well as understanding the local-distant coupled interactions of land systems based on the integrated multiscale analysis of expanding boundaries, and focuses on the construction of large-scale quantitative land system models to provide comprehensive and dynamic integrated analysis, prediction and simulation of its dynamic mechanisms, integrated effects and future scenarios and risks, and appeals for an opening scientific collaboration in the era of big data.…”
Get full text
Article