• 0

Continuous Trajectory Pattern Mining for Mobility Behaviour Change Detection

Category : research

Due to recent technological developments, it is now possible to track our movements at a high level of detail and with relatively low effort and cost, e.g., by using built-in GPS-receivers of our smartphones. This novel data source provides exciting new possibilities for increasing the sustainability of our mobility behaviour through monitoring as well as real-time regulation and management of our transport systems. For instance, there are now innovative systems which aim to monitor and directly influence our mobility decisions by providing eco-feedback (e.g., GoEco!). Such systems rely on identifying when and how their users change their behaviour, and e.g., form more sustainable travel habits. This time-consuming and cost-intensive task is currently mostly done manually. In general, however, methods to automatically detect and evaluate behaviour change are needed for understanding how people will react to new mobility options such as electric vehicles, the shared economy or mobility as a service (MAAS).

In this study, we propose a concept for a fully automated system which continuously monitors movement behaviour based on a stream of movement data, and uses data mining techniques to detect behavioural anomalies.

Proposed System

A particular problem here is data incompleteness caused by people not using the tracking application continuously. As these may trigger false alarms, we have to identify and filter these incomplete records in a separate step (Completeness Assessment). Another problem are behavioural changes which are not caused by changing travel habits, but a different contextual situation (e.g., a holiday trip). By additionally comparing the places which are visited by a person, our system is able to filter those temporary anomalies.

Detected Anomalies for One User

The figure shows the mobility behaviour anomalies (blue) and the place-related (yellow) anomalies for a user of our test sample. Behavioural anomalies are detected from calender week 2017-06 onwards. Since the visited places remain the same, we can conclude that this user indeed changed her mobility behaviour habits. In the future, a fully automated system could interpret and automatically react to this behaviour change, e.g., by sending out notifications to the users or analysts, triggering a response (e.g. encouraging or discouraging the observed behaviour change), logging the occurrence of the anomaly in a database, or providing information to an expert for decision support.

For more information, see

Jonietz, D., Bucher, D. (accepted): Continuous Trajectory Pattern Mining for Mobility Behaviour Change Detection. Accepted at: LBS 2018, Zurich, Switzerland.

  • 0

The MIE Lab is growing!

Category : news

We welcome Henry Martin as our new team member! With his focus on mobility data analysis, Henry will fit perfectly into the MIE Lab.

  • 0

News Article in NZZ about SBB Green Class

Category : news , research

On the 21st of October, the NZZ reported about the planned one-year extension of the project SBB Green Class, for which we provide the lead scientific support. In the article, Prof. Dr. Martin Raubal reports on selected preliminary findings.

  • 0

Best Paper Award Nominee at Energieinformatik 2017

Category : news , research

Our paper “Using Locally Produced Photovoltaic Energy to Charge Electric Vehicles” shared the second place for best paper with a contribution from the University of Bamberg / LAGRAR at D-A-CH+ Energieinformatik 2017.

You can find more information about the paper in our previous post and on our publications site.

  • 0

3 papers accepted at LBS 2018

Category : Uncategorized

Collaborating with colleagues from the GeoGazeLab and the University of Zurich, we have two full papers and one short paper accepted at next year’s LBS conference, which will take place in Zurich, Switzerland. For more information, visit our publications site.

  • 0

Best Poster Nomination at the 4th SCCER Mobility Conference

Category : news , research

The poster “Extracting Eco-Feedback from Movement Trajectories“, which we presented in collaboration with our colleagues from SUPSI, was nominated for the Best Poster Award at the 4th annual SCCER Mobility Conference in Zurich, Switzerland.

Over 120 participants from research and industry attended the conference and discussed relevant research topics and projects from the transport and mobility domain. Andreas Lischke (DLR Berlin) and Michael Frambourg (Volkswagen AG) held keynotes on the future of heavy-duty freight transport as well as future plans towards more sustainable passenger cars.

Both speakers emphasized the importance of an (economic and scientific) investement in alternative fuels next to pushing battery technologies forward. This point was later again highlighted, within the context of the rising shares of CO2 emissions from flight travels. With respect to Switzerland, three key topics were discussed in particular: 1) the logistics challenge, 2) passenger mobility in cities and regions, and 3) energy for transportation.

  • 0

2. Best Paper Award at COSIT 2017

Category : news

We are happy to announce that our paper “Timing of Pedestrian Navigation Instructions” was elected 2. Best Paper at COSIT 2017 conference in L’Aquila, Italy!

  • 0

Interview with Prof. Martin Raubal on the Project SBB Green Class

Category : news , research

Prof. Martin Raubal has answered questions regarding our data analyses in the course of the SBB Green Class Project. The full interview (in German) can be found here.

  • 0

Using Locally Produced Photovoltaic Energy to Charge Electric Vehicles

Category : news , research

As more and more countries announce their plans for banning combustion engines (e.g., [1, 2]), it becomes critical to find ecologically sustainable ways to power electric vehicles. While wind and water provide energy throughout the whole day, photovoltaic installations have production peaks around midday which need to captured either by smart appliances (such as washing machines) or by some form of energy storage, such as batteries or water reservoirs. A solution for both problems could be to use the car batteries to cap the solar production peaks – possibly even completely locally, i.e., without requiring transmission lines to transport energy over large distances.

Our paper Using Locally Produced Photovoltaic Energy to Charge Electric Vehicles [3] (to be published in Computer Science – Research and Development and presented at D-A-CH+ Energieinformatik 2017) discusses this potential of using solar energy to power electric cars of commuters in Switzerland. On the one hand, we compute the potentially available solar energy on rooftops in each municipality:

This is put in relation to the energy required by all work commuting travels, both within municipalities, as well as between different ones. The routes traveled are given as follows:

In a first scenario, we assume that people only charge their electric cars during the day at their workplace. We find that without shifting power from one municipality to another it is possible to cover up to 89% of the energy demand of commuter mobility. This also means that in larger cities (which have a high photovoltaic potential due to many rooftops), energy production peaks can be captured by electric cars, without the need to deploy additional batteries or storage capacity. The following figure shows the energy balance in July:

In a second scenario, where people only charge their cars at home (usually during the night), solar energy could cover 99.95% of the commuter energy demand. However, this requires installed storage capacity of around 9.32 GWh to shift the energy from day to night. Currently, 13.5 kWh batteries are targeted at homeowners, which means that around 690’000 households in Switzerland would need to be equipped with such a battery to let people charge their cars at home during the night.

The above presented analyses consider a full coverage of rooftops with solar panels, as well as a complete replacement of combustion engine cars with electric cars. This shift will not happen instantaneously, so the values should be taken solely as indications of potential future energy balances. It also needs to be noted that leisure travel and freight transport make up a substantial amount of mobility, which is not represented in above numbers. For more details, seasonal influence on solar energy production, and scenarios where people charge cars both at home and at work, please refer to the paper.

[1] https://www.theguardian.com/business/2017/jul/06/france-ban-petrol-diesel-cars-2040-emmanuel-macron-volvo
[2] http://www.independent.co.uk/environment/climate-change/norway-to-ban-the-sale-of-all-fossil-fuel-based-cars-by-2025-and-replace-with-electric-vehicles-a7065616.html
[3] https://www.research-collection.ethz.ch/handle/20.500.11850/173513

  • 0

Call for participation: Scientific study of location-based mobile learning

Dear geography teachers,

using mobile phones as an educational tool? Interacting with and augmenting local geographical phenomena via virtual assistants? With ETH’s learning platform OMLETH (Ortbezogenes Mobiles Lernen an der ETH / Location-based mobile learning at ETH), it is possible to go mobile and complete tasks in situ. The platform was developed as part of an Innovedum project at ETH Zurich:

With OMLETH, teachers can conveniently develop their program as a nature trail in the web browser and implement lessons out of school with the support of tablets and smartphones. This kind of teaching strategy allows the student to process learning content directly on the spot.

OMLETH was continuously evaluated and improved in cooperation with various partner institutes and learning experts within and outside of ETH. Numerous secondary school teachers in geography have already successfully implemented dozens of learning modules with OMLETH – not only for teaching, but also for high-school diploma theses. These studies have shown that this educational method is highly interactive and constructivist, and can have a positive effect on the learning objectives.

As a next step, we aim to evaluate the learning effectiveness of this new teaching strategy in an experimental setting. We are looking for individual teachers or groups of teachers who would like to use OMLETH and compare student’s learning achievements gained in regular classroom-based teaching versus location-mobile learning. These activities are planned for late summer / fall 2017.

In order to use the summer holidays as inspirational period, we recommend to organize an initial meeting right before or just after this time. It will contain an introductory trail around the school building, testing OMLETH on desktop computers and finally a presentation of the study design. Technical questions will be answered at any time during the study.

Further information about the platform and the study can be found at https://omleth.ch/workshop/ (in German).

If you have any questions or comments, please do not hesitate to contact us by phone. To plan your first meeting, please send us your registration by July 30 2017. Thank you!