CTIT University of Twente
Research Business & Innovation About CTIT Research Calls Looking for a job? Intranet

Sensor Content for Wellbeing

Project Number: P05
Project Manager: Prof. dr. Dirk Heylen
Faculty of Electrical Engineering, Mathematics and Computer Science
Tel.: +31-53-4893745
Email: d.k.j.heylen@utwente.nl


The general goal of this project is to enhance and sustain the wellbeing of people using an ecosystem of intelligent affective interfaces that give (real-time) feedback on people’s measured state of mind, helps them to connect to other people, and coaches them towards an improved state of wellbeing. Particular application areas are healthy aging, healthy living and learning & education.

Underlying needs of end-users in Lifestyle and Care show that there is a strong need for truly personalized applications. Technology needs to provide information on people’s state of well- being, in an unobtrusive way as well as a motivating, personalized coaching environment to improve the well-being. Key question is to make content, communication and entertainment seamlessly available to people, by starting with understanding the user thoroughly and using any (unobtrusively) measured data of people and their environments.

From a scientific point of view there are two major perspectives. The first is developing an insight in the relation between the needs of the population and the technology in their everyday use. For this we need a human-centric approach where we develop affective interactions and study their use in real-life situations. The second is developing the techniques to improve existing technologies in terms of unobtrusive sensing capabilities, understanding/interpretation and adequate (timely, situation-aware and personal) affective feedback that is both sensitive to the affective state of the user and the context and capable of producing the right kind of stimulus to elicit the desired affective state.

In more detail: Key research challenges addressed in this project include understanding how to measure wellbeing from bio-physiological signals, how to influence mental by multisensory signals such as voice, sound, light, tactile real-time and unobtrusive body signal measurement and interpretation, understanding people’s context (environment) from non-obtrusive sensors, and understanding content and seamlessly integrating body signals, environment data, and content into a single experience for the user. This is particularly hard in lifestyle settings, for consumers, including the elderly. Compared to the working situation in Healthcare, in Lifestyle the signals from biosensors will be much noisier, you cannot assume the exact situation a user is in when doing measurements, the link with content and content understanding is new and needs to be automatic. This is strongly linked with the way the application communicates with the consumer. Triggering new senses, for example touch & tactile, poses challenges in technology, e.g. how to automatically derive cues from audio-visual content using content analysis. On the other hand, we need to understand what is acceptable for people when their senses are triggered. Content and computer vision are essential for lifelike communication. Coaching and influencing of mood in a multi-modal way will be possible through light, music and video, to create personalized applications and has impact on the home domain, public spaces, hospitality.

In socio-economic terms, we have to make large steps to make the abundance of available technologies useful in the settings people live in today.

In more detail: the entertainment industry is a multi-billion industry and people are more and more extending the “professional” environment (e.g. cinemas) into their living room environment. This enables people to wind down after a long day of work, but it is important to offer the right content at the right time. Recommender technology using various sources of content (broadcast, internet) is essential to achieve this. This technology can also be applied in professional domains like healthcare clinical decision support systems.

Another target group is the elderly, who live longer independently and for whom care becomes more and more important. With the generation of baby-boomers retiring in the next decade there is a huge opportunity for keeping them active and living independently as long as possible. Further, this demographic has a huge economic potential. Our population is gradually aging and the traditional health care system cannot cope. In 2007 there were 2.4 million people over 65 years of age and this number will rise quickly after 20111. At the same time, the modern elderly are less prepared to be “taken care of” but want to stay in their homes and in control. However, they face the inevitable fate of becoming less physically able and less connected over time, which brings the risk of falling ill and severe loneliness. To help the elderly to stay in control, to stay connected and to increase their wellbeing, affective tangible Interfaces (ATIs) can help. This project will come up with design guidelines for building ATI’s, develop inspiring and effective examples, and demonstrate their use in real-life settings that the partners in this project have access to.

In conclusion, the project will research the basics of sensing & elicitation of people’s state of well-being, and the basics of coaching and interaction. The integrated demonstrations will apply the results of this basic research in applications for learning and education, sleep, and communication and care for families, including the elderly.

Project duration: 1-5-2011 / 1-5-2015
Project budget: 6.2 M-€ / 2.8 M-€ funding
Number of person/months: 583 person months 
Project Coordinator: Philips Research
Participants: Philips Research, UT, Waag Society, CWI, HVA, Serious Toys
Project budget CTIT: 633 k-€ / 285 k-€ funding
Number of person/years CTIT: 72 person/months
Involved groups: Human Media Interaction (HMI)