Search Results for author:
Found 9 papers, 7 papers with code
Synthetic location trajectory generation using categorical diffusion models
Diffusion probabilistic models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data, for instance, for computer vision, audio, natural language processing, or biomolecule generation.
Revealing behavioral impact on mobility prediction networks through causal interventions
Deep neural networks are increasingly utilized in mobility prediction tasks, yet their intricate internal workings pose challenges for interpretability, especially in comprehending how various aspects of mobility behavior affect predictions.
Uncertainty quantification and out-of-distribution detection using surjective normalizing flows
Reliable quantification of epistemic and aleatoric uncertainty is of crucial importance in applications where models are trained in one environment but applied to multiple different environments, often seen in real-world applications for example, in climate science or mobility analysis.
Is A 15-minute City within Reach in the United States? An Investigation of Activity-Based Mobility Flows in the 12 Most Populous US Cities
Enhanced efforts in the transportation sector should be implemented to mitigate the adverse effects of CO2 emissions resulting from zoning-based planning paradigms.
Uncertainty Quantification for Image-based Traffic Prediction across Cities
We compare two epistemic and two aleatoric UQ methods on both temporal and spatio-temporal transfer tasks, and find that meaningful uncertainty estimates can be recovered.
Evaluating geospatial context information for travel mode detection
While studies have acknowledged the benefits of incorporating geospatial context information into travel mode detection models, few have summarized context modeling approaches and analyzed the significance of these context features, hindering the development of an efficient model.
Context-aware multi-head self-attentional neural network model for next location prediction
Accurate activity location prediction is a crucial component of many mobility applications and is particularly required to develop personalized, sustainable transportation systems.
How do you go where? Improving next location prediction by learning travel mode information using transformers
Predicting the next visited location of an individual is a key problem in human mobility analysis, as it is required for the personalization and optimization of sustainable transport options.
Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab
The goal of the IARAI competition traffic4cast was to predict the city-wide traffic status within a 15-minute time window, based on information from the previous hour.
