Origin-destination matrix estimation by deep learning using maps with New York case study

@article{Koca2021OrigindestinationME,
  title={Origin-destination matrix estimation by deep learning using maps with New York case study},
  author={Danyel Koca and Jan-Dirk Schm{\"o}cker and Kouji Fukuda},
  journal={2021 7th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS)},
  year={2021},
  pages={1-6},
  url={https://api.semanticscholar.org/CorpusID:237446572}
}
The proposed learning approach is a hybrid model, combining a graph convolutional approach at the lower level with an upper level multilayer perceptron, and obtain promising results for expanding an OD matrix with limited observations.
View on IEEE
doi.org
5 Citations
Methods Citations
1

Figures from this paper

5 Citations

Uncertainty Quantification of Spatiotemporal Travel Demand With Probabilistic Graph Neural Networks

This study proposes a framework of probabilistic graph neural networks (Prob-GNN) to quantify the spatiotemporal uncertainty of travel demand, and highlights the importance of incorporating randomness into deep learning for spatiotsemporal ridership prediction.

Commuting Flow Prediction using 1 OpenStreetMap Data

This research broadens the applicability of state-of-the-art flow prediction models by employing features from freely accessible and globally available OpenStreetMap data and shows that the pre-18 diction accuracy of several state-of-the-art models using open data is comparable to location-specific and proprietary data.

An Interdisciplinary Survey on Origin-destination Flows Modeling: Theory and Techniques

Origin-destination (OD) flow modeling is an extensively researched subject across multiple disciplines, such as the investigation of travel demand in transportation and spatial interaction modeling…

Spatial econometrics to estimate traffic reduction by transforming office space into housing and other land uses: The case for Barcelona

Integration of dockless bike-sharing and metro: Prediction and explanation at origin-destination level

22 References

Cross-region traffic prediction for China on OpenStreetMap

An approach and a system to learn a prediction model from graphical traffic condition data provided by Baidu Map and apply the model on OSM so that one can predict the traffic conditions with nearly 90% accuracy in various parts of Shanghai, China, even though no traffic data is available for that area from BaidU Map.

Spatio-temporal analysis and prediction of cellular traffic in metropolis

This work proposes a novel decomposition of in-cell and inter-cell data traffic, and applies a graph-based deep learning approach to accurate cellular traffic prediction, and demonstrates that this method consistently outperforms the state-of-the-art time-series based approaches.

Development of origin–destination matrices using mobile phone call data

Fine-grained population estimation

It is shown how to estimate population numbers for arbitrary user-defined regions, down to the level of individual buildings, with good average accuracy for rural areas, metropolitan areas, and cities in countries other than that containing the training data.

Learning Mobility Flows from Urban Features with Spatial Interaction Models and Neural Networks**To appear in the Proceedings of 2020 IEEE International Conference on Smart Computing (SMARTCOMP 2020)

This paper proposes three neural network architectures, including graph neural networks (GNN), and conducts a systematic comparison between the proposed methods and state-of-the-art spatial interaction models, their modifications, and machine learning approaches.

Enhancing Trip Distribution Prediction with Twitter Data: Comparison of Neural Network and Gravity Models

The findings indicate that the traditional gravity models outperform neural networks in terms of having lower RMSE, but the R2 results show higher values for neural networks suggesting a better fit between the real and predicted outputs.

Estimation of a Long-Distance Travel Demand Model using Trip Surveys, Location-Based Big Data, and Trip Planning Services

A microscopic discrete choice model including trip generation, destination choice, and mode choice is developed for the province of Ontario, Canada, finding that the Foursquare data on number of check-ins at destinations was statistically significant, especially for leisure trips, and improved the goodness of fit.

Graph Neural Networks: A Review of Methods and Applications

Transportation Systems Analysis Models And Applications

Thank you very much for reading transportation systems analysis models and applications, maybe you have knowledge that, people have search numerous times for their chosen novels like this, but end up in malicious downloads.

Formulation and solution approach for calibrating activity-based travel demand model-system via microsimulation