Demand-orientated planning of public transport services

Mobile Data Fusion: high-precision detection of passenger demand from multiple data sources

In order to fulfill its role as the backbone of sustainable mobility, public transport must respond to changes in mobility behaviour and growing demand. Whereas infrastructure investments and fleet expansions tend to have a long-term effect, increased demand must be considered in the short term by optimising the service without extending the existing transport networks. Improved data is urgently required in order to enhance the effectiveness of public transport planning and the Mobile Data Fusion research project has set itself the goal of providing this data basis.

In order to accurately determine demand, quantitative surveys using Automated Passenger Counting Systems (APC) or counting personnel are now commonly used. This research project is based on the idea of using additional data to determine the demand for public transport. For this purpose, WLAN and Bluetooth signals from mobile devices, queries to the connection information service as well as Mobilithek’s freely available database, formerly mCloud, from the Federal Ministry for Digital and Transport (Bundesministerium für Digitales und Verkehr), are all used.

The aim of the project is to merge these existing data sources for the first time. The focus is in particular on information on source-destination linkages and transfer flows. Furthermore, additional insights into the frequency and continuity of public transport use are gained.

Complex analysis and preparation of the data

For the data fusion, the input data is collected, processed and analysed in a Big Data pipeline (s. figure). The term “Big Data” in this project does not refer to the generated data volumes, but to the complex analysis, processing and utilisation of the data from different sources. In particular, the aim is to identify statistical correlations, patterns and relationships with regard to users’ route choices within the public transport network.

The back-end system developed by INIT is based on an Apache Kafka data infrastructure. As open source software for transferring and storing large data streams, Apache Kafka works as a data broker between the data producers (input data) and the data consumers (IT partner systems). Apache Flink is used to transform data streams and to link data sources. Apache Beam serves as a unified application programming interface (API) to enable algorithms to be used in various processes. A major advantage of these deployed technologies is their broad scalability as well as the possibility of real-time processing. This makes it possible to analyse a continuous stream of events in a traffic network and to take traffic control measures in real time as well as, for example, to provide occupancy levels in passenger information in the future.

COPILOTpc for recording Bluetooth and WiFi signals

To implement Bluetooth and WiFi sensing, various hardware solutions were developed as part of the Mobile Data Fusion project. In the first project phase, a prototype was deployed and tested in the NVV network. In the second development phase, an extension of the COPILOTpc on-board computer with additional Bluetooth and WiFi modules was developed. The system will be in operation in 21 NVV vehicles by 2024 – and for the first time with a Linux operating system.

In the back-end system, the Bluetooth and WiFi signals recorded in the vehicle are linked with the stored trips from MOBILEstatistics and merged with APC data to provide aggregated passenger data. The method developed by the project partner WVI to determine sourcedestination matrices was integrated into the INIT Big Data pipeline so that traffic flow data can be displayed accurately regarding lines and trips and can be updated on a daily basis. Particularly outstanding is the data protection approach that is anchored in the entire project. The WLAN MAC addresses and Bluetooth IDs are irreversibly encoded and therefore anonymised by a hash function before being stored; the original data is deleted immediately and not stored. Passengers who do not want to be detected can exclude their devices using a blacklist function.
 

In the future, precise knowledge of passenger flows will help transport companies to better tailor their services to passenger demand, without huge additional investment in existing transport networks. INIT is making a significant contribution in this area.

Mobile data fusion logo

Mobile Data Fusion is funded by the German Federal Ministry for Digital and Transport. The project consortium, led by the institute for transport research and structure planning WVI, Braunschweig, includes INIT, the consulting company for operations control, information and computer technology Blic, the University of Kassel, the Department of Transport Planning and Systems (VPVS), and the Nordhessischer Verkehrs Verbund (NVV), which, as part of the project is deploying over 40 vehicles for testing.

Contact

Dr. Roxana Hess

Product Manager MaaS
Team Manager Research
INIT GmbH
Germany

Get in touch

Subscribe now

This article was published in our customer magazine INITiative, issue 1/2023. If you want to receive the magazine regularly per e-mail, we kindly ask you to subscribe.

Proceed
Privacy settings
This site uses cookies to provide you with an optimal website experience. This includes cookies that are essential to the operation of the site and cookies that you need to agree to use. You can also reach this panel later via a text link in the data protection declaration and can further adjust your cookie settings on our website to your preferences at any time. You will find additional information in the detailed view below and in our data protection declaration.
Required
These cookies are necessary to enable the basic functions of our website. We store personal page settings and your language settings.
Statistics
To further improve our website, we collect anonymized data for statistics and analysis via Matomo. With the help of these cookies we can, for example, determine the number of visitors and the effect of certain pages of our website in order to optimize our content.
Video statistics
Third-party content – e.g. Vimeo or YouTube videos – can be embedded and displayed. To further improve our communication, we collect anonymous statistical data.
Settings saved
Accept selected
Accept all