February 23, 2006
Wearables in 2005
An article I wrote for the Wearable Computing column of IEEE Pervasive Computing magazine just came out, and highlights some of the projects at last year's ISWC conference. Here's the intro:
Wearables in 2005
Bradley Rhodes and Kenji MaseIn July 1996, one year before the first International Symposium on Wearable Computers, DARPA sponsored a workshop entitled "Wearables in 2005" (www.darpa.mil/MTO/Displays/Wear2005). Attendees predicted how wearable computers might be used in 2005 and identified key technology gaps that needed to be filled to make their vision a reality. In October 2005, the 9th Annual International Symposium on Wearable Computing was held in Osaka, Japan, the first to be held in Asia. Participants presented a wide range of research from both industry and academia, spanning 13 countries and weaving together such diverse fields as interface design, hardware and systems, gesture and pattern recognition, textiles, augmented reality, and clothing design.1 Many of the themes would have sounded familiar in 1996, with continuing improvements in ergonomics and power management as well as gesture recognition and augmented reality.
As you would hope, the field has also developed in new directions in the past decade, with a much greater emphasis on large-scale recording and annotation of everyday activities, on the science and engineering of clothing design, and on performing thorough quantitative evaluations of potential input devices. We have also seen a large increase in the use of accelerometers, smart phones, and RFID readers as researchers leverage continuing drops in cost and size in the consumer electronics world.
As the largest primary conference for wearables researchers, ISWC provides a good snapshot of the state of the field. So, with the benefit of hindsight, here are some highlights of how wearables research actually looked in 2005.
The IEEE copy is here, and I've also got an HTML copy on my publications page.
Posted by bug to Wearable Computing at February 23, 2006 11:08 PM | TrackBackI'm surprised by the autism work. Even a decade ago, physical therapists were using sensors attached to the hands to measure range of motion, e.g., how far could you still lift your arms after stretching now that you've been through a windshield.
Given that the sensor technology is there, and we have a large amount of optimization per MEMS tiltometers and accelerometers, and we have better wireless shortrange communication, why isn't this just a semester project?
Is the problem boxing (make a box survive the environment with acceptable battery life, user interface, etc.), integration (the chip works in theory, in one lab, once), or analysis (the arms they move but fail to capture the essence of elan)?
There are really two problems. One is the pattern recognition: telling the difference between actual stimming behavior and running, eating, going up and down stairs, etc. Pattern rec is still something of a black art — we've got some basic tools in terms of sensors and algorithms, but a lot depends on details like where you place the sensors and what kind of preprocessing you do. The other big problem, which this work hasn't tackled yet, is that autistic people tend to hate having anything touching them or rubbing them the wrong way. That puts real limits on the size and location of sensors.
I like this particular paper not because of the pattern recognition itself but the way she frames the problem itself (namely how to help a therapist slog through tens of hours of video to find a few saliant moments, and what that implies for the recognition problem). That, plus the fact that she was trying to detect the start and end of activities in a continuous data stream, is I think its main contribution.
Posted by: Bug at February 24, 2006 9:14 PM