Performance across difficulty levels. by Tarun Khajuria (12117309)

Classifying objects in constellation images. by Tarun Khajuria (12117309)

Final hyper-parameters for genetic search. by Tarun Khajuria (12117309)

“…This dataset serves as a testbed for exploring how inferred signals can guide the synthesis of suitable solutions in ambiguous conditions, framing visual inference as an instance of complex problem solving. Drawing on insights from human experiments, we develop a generative search algorithm and compare its performance to humans, examining factors such as accuracy, reaction time, and overlap in drawings. …”

Reproducing kernel-based semiparametric functional smoothed score estimation with binary responses by Meichen Liu (8168148)

“…Computationally, we tackle the nonconvex optimization by developing an efficient proximal gradient algorithm. Finally, the finite sample results in simulation studies as well as a real data analysis from the ADNI study demonstrate the favorable performance of the proposed method compared with some popular classifiers in terms of prediction and estimation.…”

Example display of the only tab, <i>Text-mining</i>, in the <i>Examine</i> section of the application for extraction and display of information from free-text wildlife necropsy dat... by Stefan Saverimuttu (20882325)

Image 7_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 2_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Table 1_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.docx by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 4_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 6_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 5_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 1_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Image 3_Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm.png by Yihang Wang (4731429)

“…This model combines the weighted cross-entropy loss function to enhance the classification effect, the cosine annealing algorithm to optimize the training process, and the improved k-nearest neighbors multi-scale grouping method to enhance the model’s ability to segment the point cloud with complex morphology. …”

Raw results. by Mahmood A. Jumaah (22272371)

General parameters setting. by Mahmood A. Jumaah (22272371)

“…To evaluate its performance, IFOX was tested on 20 classical benchmark functions, 61 benchmark test functions from the congress on evolutionary computation (CEC), and ten real-world problems. …”

Schematic representation of the coarse structure of serial interval data. by Oswaldo Gressani (13933254)

Data associated with "Functional specialisation of multisensory temporal integration in the mouse superior colliculus" by Gaia Bianchini (7570553)

“…<p dir="ltr">Dataset from Bianchini et al., "Functional specialisation of multisensory temporal integration in the mouse superior colliculus" available at https://www.biorxiv.org/content/10.1101/2025.02.11.637674v3.…”

Phase stability at interfaces (dataset) by J Pitfield (21962924)

IUTF Dataset(Enhanced): Enabling Cross-Border Resource for Analysing the Impact of Rainfall on Urban Transportation Systems by Xuhui Lin (19505503)

“…</p><h2>Data Structure</h2><p dir="ltr">The dataset is organized into four primary components:</p><ol><li><b>Road Network Data</b>: Topological representations including spatial geometry, functional classification, and connectivity information</li><li><b>Traffic Sensor Data</b>: Sensor metadata, locations, and measurements at both 5-minute and hourly resolutions</li><li><b>Precipitation Data</b>: Hourly meteorological information with spatial grid cell metadata</li><li><b>Derived Analytical Matrices</b>: Pre-computed structures for advanced spatial-temporal modelling and network analyses</li></ol><h2>File Formats</h2><ul><li><b>Tabular Data</b>: Apache Parquet format for optimal compression and fast query performance</li><li><b>Numerical Matrices</b>: NumPy NPZ format for efficient scientific computing</li><li><b>Total Size</b>: Approximately 2 GB uncompressed</li></ul><h2>Applications</h2><p dir="ltr">The IUTF dataset enables diverse analytical applications including:</p><ul><li><b>Traffic Flow Prediction</b>: Developing weather-aware traffic forecasting models</li><li><b>Infrastructure Planning</b>: Identifying vulnerable network components and prioritizing investments</li><li><b>Resilience Assessment</b>: Quantifying system recovery curves, robustness metrics, and adaptive capacity</li><li><b>Climate Adaptation</b>: Supporting evidence-based transportation planning under changing precipitation patterns</li><li><b>Emergency Management</b>: Improving response strategies for weather-related traffic disruptions</li></ul><h2>Methodology</h2><p dir="ltr">The dataset creation involved three main stages:</p><ol><li><b>Data Collection</b>: Sourcing traffic data from UTD19, road networks from OpenStreetMap, and precipitation data from ERA5 reanalysis</li><li><b>Spatio-Temporal Harmonization</b>: Comprehensive integration using novel algorithms for spatial alignment and temporal synchronization</li><li><b>Quality Assurance</b>: Rigorous validation and technical verification across all cities and data components</li></ol><h2>Code Availability</h2><p dir="ltr">Processing code is available at: https://github.com/viviRG2024/IUTDF_processing</p>…”

Validation of IDRAS on a model of bacterial growth and division. by Ron Teichner (21492434)