Seamless door-to-door air travel
How the IMHOTEP research project is using simulation technology to improve airport management and ease the many pain points for customers traveling to and from busy airports.
Tag: AI Blog
Real-time simulation training for traffic managers
When Main Roads Western Australia installed a new traffic management system, their staff needed to learn how to use it in a realistic but risk-free environment – simulation training was the perfect solution.
Taking cost-benefit analysis to the next dimension
In this new article, Mark Brackstone takes a look at how this EU-funded research group has taken cost-benefit analysis to the next level.
Demand Responsive Transport: flexible tools for planning and operational solutions
The MultiDEPART team developed tools to plan, manage and monitor DRT solutions in Lisbon, Barcelona Metropolitan Area and Thessaloniki, targeting PTAs and facilitating the harmonization and scalability of DRT services across European cities.
Towards agent-based models: simulating multimodal transport systems
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?
Road safety for all: how transport simulation can help predict and prevent blackspots
Road safety is a major concern for public administrations worldwide: severe injuries and fatalities are not only a human tragedy but also have huge social costs
i4Driving: evaluating road safety in traffic simulation – a controversial topic and a paradox
Evaluating safety in a traffic simulation environment has always been a controversial research topic because vehicles in a simulation are programmed in such a way that they cannot potentially cause accidents.
Towards climate neutrality: integrating public transport with new mobility services
The EU-funded SPINE project employs simulation and data-driven models to virtually assess the impact of new solutions for increasing public transport’s modal share and user satisfaction.
Towards ML-assisted traffic simulation
Machine learning can assist traffic simulation systems and reduce computational effort by providing network-wide traffic state estimation under unseen conditions.
How will ITS contribute to machine learning?
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?
Is this the death of big data?
OK, big data is not dead, but the AI community is already moving beyond it and towards a new AI paradigm.
How to use random forests to predict mobility patterns
Supervised learning can help us to train our model to predict the right mobility patterns.
Understanding mobility using unsupervised learning
Unsupervised learning is a great tool for data analysis, particularly for understanding how mobility has changed due to COVID-19.
Metric selection for incident detection systems
Classification problems with highly unbalanced datasets, such as incident detection, pose the trade-off between true positive rate and false negative rate.
How to extract patterns from traffic data for better insights into mobility
Mobility patterns are a cornerstone of mobility demand modelling; clustering helps us extract usable daily patterns from huge sets of traffic data.
AI alone is not enough for real-time traffic management
The power of combining AI techniques with simulation in real time for accurate predictions and effective response plans under any conditions.
Mobility pattern prediction
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.
What is a digital twin?
The phrase “digital twin” has become ubiquitous in the field of transportation, but what does it really mean?
Deeper than Data
What is the value of data analytics in the mobility sector? The usual starting place is to look at historical data to find recurrences and trends but if you have real-time data feeds, then you can go deeper
