How can we explicitly represent, simulate and evaluate within-day behavioural (demand) and operational (supply) dynamics in emerging multi-actor passenger and freight transport systems?
Unlike purely data-driven methods, a simulation-based approach enables prediction of traffic states under recurrent conditions but also to predict the impact of incidents or changes to traffic control plans.
The phrase “digital twin” has become ubiquitous in the field of transportation, but it has been applied so undiscriminatingly to so many different concepts that it is hard to know what people mean by it.
Machine learning can assist traffic simulation systems and reduce computational effort by providing network-wide traffic state estimation under unseen conditions.
In the last post we discussed the current trends in Machine Learning (ML) and the need to go beyond big data. But how does this affect the fields of ITS and smart cities?
OK, big data is not dead, but the AI community is already moving beyond it and towards a new AI paradigm.
Supervised learning can help us to train our model to predict the right mobility patterns.
Unsupervised learning is a great tool for data analysis, particularly for understanding how mobility has changed due to COVID-19.
Classification problems with highly unbalanced datasets, such as incident detection, pose the trade-off between true positive rate and false negative rate.
Mobility patterns are a cornerstone of mobility demand modelling; clustering helps us extract usable daily patterns from huge sets of traffic data.
Aimsun Live is the ONLY predictive traffic management tool that combines AI techniques with simulation in real time – Paolo Rinelli explains why this is essential for accurate predictions and effective response plans under any conditions.
分享
