Site visit in Oulu on 31 March 2003

The coordination unit made a site visit at the Intelligent Systems Group at the University of Oulu on 31 March 2003. Professors Jukka Riekki and Tapio Seppänen together with their research group presented their research in context-aware modelling and their PROACT project Behaviour modelling in context-aware systems.

The aim of the project is to develop methods for learning behaviour models. Both users and enabling devices are modelled. The results will be used for helping proactive systems adapt to environmental changes in real time. The research hypotheses are that behavioural modeling can be established based on user behaviour data and data from devices acting in the environment, and that these models can be used efficiently in proactive systems.

The group will validate the hypothesis by developing methods for learning, which can be off-line or on-line processes, and signal analysis methods for calculating parameters required by the learning methods from the data, and implementing prototypes applying the methods.

Some of the implications of this research include the increase of people's quality of life, decrease of society's expenses, as for example, elderly people can live at home, and benefit for service providers as people use their services more.

For practical implementations, the group has built a Smart Living Room in their laboratory. The room as a pressure-sensitive floor of about 100 square meters, which yields information about localized pressure events, like someone walking on the floor. The floor is constructed of a grid of strips of sensitive plastic material (EMFI sensors). Each strip out of 64 produces a continuous signal that must be analyzed in order to detect and recognize events.

The group has started to develop signal analysis methods and visualization tools for the floor's user interface. The group's aim is to use the floor as a basis to learn, monitor and predict users' movement behaviour. The goals include to detect, recognize and localize pressure events; to monitor and visualize pressure events in real-time; to model movement trajectories from measurement data; and to predict movement according to the learned models. The smart living room also includes other smart equipment such as mobile robots, different user terminals, wireless LAN, sensors and service machines. The ultimate goal is to have these components perceiving, reasoning, acting and communicating with each other and with the user in order to offer services to the users whenever and wherever they need them.

For example, a context-aware robot has been developed that is able to learn how to move around the room. The robot uses spatially encoded neural networks and an evolutionary algorithm for its neural control system.

More information
For more information, please contact Professor Röning at the University of Oulu or see the home page of the group at http://www.ee.oulu.fi/mvis/research/isg/.

Researchers involved in the project in the Intelligent Systems Group (University of Oulu, Department of Electrical and Information Engineering, Computing Engineering Laboratory) are Professors Juha Röning, Jukka Riekki, and Tapio Seppänen and reseachers Janne Haverinen, Kalle Koho, Antti Tikanmäki, and Susanna Pirttikangas.

See also the project's web page at this site.