Reflections on first International Conference on Physiological Computing Systems

international-conference-on-physiological-computing-systems-phycs-logo

Last week I attended the first international conference on physiological computing held in Lisbon.  Before commenting on the conference, it should be noted that I was one of the program co-chairs, so I am not completely objective – but as this was something of a watershed event for research in this area, I didn’t want to let the conference pass without comment on the blog.

The conference lasted for two-and-a-half days and included four keynote speakers.  It was a relatively small meeting with respect to the number of delegates – but that is to be expected from a fledgling conference in an area that is somewhat niche with respect to methodology but very broad in terms of potential applications.

The conference began with a panel session on Tuesday afternoon headed up by Program Chair Hugo Placido da Silva on the future of physiological computing.  Each speaker (including myself) gave their take on this theme and several speakers had active interests in digital health, which tended to dominate the discussions.  A number of take-home messages came out of the panel discussion: (1) doctors need access to personal data in order to save lives, (2) the area needs to establish an interdisciplinary basis, and (3) physiological computing is for young researchers as it is an emerging technology.  The latter point made me smile (rather sadly) but it was noticeable that many attendees were young researchers, which is a healthy sign for the future.  The next session was the first of the two Methodology slots and encompassed a range of topics from gait analysis to the classification of intentionality within the context of BCI.

The next morning was started by Sandro Carrara’s keynote entitled “a tiny laboratory under the skin” about his work with implantable devices based upon nanotechnology.  It was a fascinating talk, though somewhat removed from what I normally do – it also demonstrated the range of the conference theme, encompassing detection of molecular processes that are embedded in the physiological system.   This session was followed by the poster session and a slot on applications/human factors that unfortunately I didn’t get to because of other commitments.

One unfortunate side-effect of trying to cram a lot into small amount of time was that some sessions ran in parallel hence a workshop on physiological monitoring and robotics ran at the same time as both human factors sessions.  I flitted between the two, alternating between work on emotion detection using thermal data from the face to work on neurofeedback and eye-controlled communication.  The second methodologies session ran on the late afternoon of the second day and the theme of psychophysiology and emotion detection was heavily featured.  There was some interesting work on stress detection (both inside and outside the laboratory) and research on reconciling measures with different temporal sensitivities that sparked some debate.  The second keynote speaker (Antonio Camara) was from industry and he presented some work on wireless sensors for professional people (fireman and footballers).  The technology on display was a nice example of wearables and he did very well to convey his work to the audience despite struggling with a severe sore throat and almost losing his voice.

The final day of the conference began with a keynote from Gernot Muller-Putz from Graz on BCIs or to be specific, hybrid BCI.  This was a very informative presentation of the state of the art in BCI research and I was interested to hear about how different types of measures were combined to achieve different kinds of control or simply to improve classification accuracy.  The next session on Devices covered a range of research, from EOG-monitoring of sleep stages to deep brain stimulation and the use of P300s during a teleoperation task.

The conference ran in parallel with three other meetings and I was doing one of the keynotes at the SensorNets conference and chairing another session at the same event.  Unfortunately I missed the next two sessions on Methods and Applications.  I returned to PhyCS for the final keynote from Thomas Falck of Philips Research who presented his work on camera-based ECG detection, especially in critical care environments.  He also presented work on the use of light to promote conventional 24h circadian rhythms and software to analyse sound in hospitals to promote a more restful environment.

Speaking personally, it was a real treat to see a broad range of material presented from researchers in both academia and industry.  Generally I am reconciled to seeking out one or two sessions on psychophysiology at the larger conferences, so I enjoyed the relative luxury of having many sessions with this kind of focus.  But having said that, an enormous range of material was presented with respect to different methods, themes, applications and devices – but because it all related to physiological computing in some way, the program retained a central coherence.

A second meeting is planned for 11-13th Feb 2015 to be held in Angers, France.  The first conference attracted 52 submissions, of which 25% were presented as full papers.  It would be nice to see more submissions to the second event and hopefully the meeting can become a regular fixture on the conference calendar.