MISTic | Multi-source trend analytics for intelligent transportation systems

Better traffic management is essential if Brussels is to become a smart(er) city. The MISTic project focuses on mobility, intelligent transportation systems (ITS) and smart cities. The goal of this research project is to develop the technology underlying a trend analytics engine.

Context

MISTic focuses on research into the design and validation (in the ITS domain) of an advanced trend analytics engine to facilitate the development of dedicated solutions for acquiring an accurate and context-aware understanding (or situational picture) of a (traffic) situation and for providing insightful feedback to the stakeholders involved in that situation (e.g. traffic managers, road users), in order to facilitate their decision making.

In order to acquire a situational picture, data from multiple sources, including sensors at fixed locations (cameras, license plate readers, inductive loops, etc.), sensors moving with the traffic (such as data collected by probes and connected vehicles) and other sources, including historical and weather data, must be combined (fused) and exploited. This is known as multi-source data fusion. In addition, methods for profiling the traffic situation in a context-aware way, interpreting the situation and predicting the possible developments of that situation need to be developed in order to provide feedback on relevant trends detected, thus facilitating decision-making. Examples of possible trends to be considered are the number of vehicles of the same type (cars, motorcycles, trucks, trucks transporting hazardous substances, etc.) in a tunnel and how they interact, the different types of drivers in a given road segment based on their driving behaviour, the number of vulnerable users at crossroads, etc.

Objective

The goal of this research project is to develop the technology underlying a trend analytics engine. 

Approach

1. Investigate hierarchical and adaptive multi-source data and model integration techniques enabling the combination of information from heterogeneous sources.
2. Research knowledge propagation techniques within and across data sources.
3. Explore methods for estimating the quality of data fusion.
4. Research methods enabling context-aware situation profiling, interpretation and evolution prediction.
5. Develop and validate a proof-of-concept trend analytics engine and demonstrate its potential via realistic use cases.

Two such use cases were already identified together with the industrial partner, Macq, during the preparation of this proposal and will be further developed during the project. The first use case relates to tunnel (and infrastructure) safety. The second focuses on classifying and/or profiling road user behaviour. 

It must be noted that the use cases that we identified and potential new use cases that will be defined during the research are meant solely to demonstrate the potential of the trend analytics engine as a sort of toolkit of optimised and validated modules enabling the development of advanced mobility applications.

Reference

Doctoral theses in collaboration with university and industry, MISTic: Multi-source trend analytics for intelligent transportation systems

Project partners

The project involves Sirris (EluciDATA Lab) as the research organization and promotor, Macq as industrial partner, and VUB (ETRO and MOBI research labs) as academic partner and co-promotor.