The winner of this year’s best paper award at ISWC (the first ISWC to have such an award) was a paper by Don Patterson from the University of Washington called Fine-Grained Activity Recognition by Aggregating Abstract Object Usage. All the authors got certificates and Don took home a new video iPod as the prize.

This was one of several papers presented that used an RFID reader in a glove, in this case to classify what kind of activity a person is conducting based on the sequence of objects she has touched. This would be useful, for example, for alerting a care worker if a resident of an assistive-living home had stopped eating.

From the abstract:

In this paper we present results related to achieving fine-grained activity recognition for context-aware computing applications. We examine the advantages and challenges of reasoning with globally unique object instances detected by an RFID glove. We present a sequence of increasingly powerful probabilistic graphical models for activity recognition. We show the advantages of adding additional complexity and conclude with a model that can reason tractably about aggregated object instances and gracefully generalizes from object instances to their classes by using abstraction smoothing. We apply these models to data collected from a morning household routine.

Here are all six nominees for best paper from ISWC’05, which were the top 10% of full papers based on reviewer-rating:

• Fine-Grained Activity Recognition by Aggregating Abstract Object Usage (author’s PDF), by Donald Patterson, Dieter Fox, Henry Kautz, Matthai Philipose (U. Washington and Intel Research, Seattle)

• ReachMedia: On-the-move interaction with everyday objects (author’s PDF), by Assaf Feldman, Emmanuel Munguia Tapia, Sajid Sadi, Pattie Maes and Chris Schmandt (MIT Media Lab)

• A Design Process for the Development of Innovative Smart Clothing that Addresses End-User Needs from Technical, Functional, Aesthetic and Cultural View Points by Jane McCann, Richard Hurford and Adam Martin (University of Wales)

• Pictorial Depth Cues for Outdoor Augmented Reality by Jason Wither and Tobias Höllerer (University of California, Santa Barbara)

• A Body-mounted Camera System for Capturing User-view Images without Head- mounted Camera by Hirotake Yamazoe, Akira Utsumi and Kenichi Hosaka (ATR)

• The Impacts of Limited Visual Feedback on Mobile Text Entry for the Twiddler and Mini-QWERTY Keyboard (author’s PDF) by James Clawson, Kent Lyons, Thad Starner and Edward Clarkson (Georgia Tech)

It’s decided: next year’s International Symposium on Wearable Computing will be in Montreux, Switzerland on October 11th-13th, with workshops and tutorials after the main conference on October 14th. This’ll be co-located with UIST, which has their doctorial symposium on the 15th and main conference October 16th – 18th.

The conference, by the way, will be held in Casino Montreux. I wonder if we can get back to our roots and try out some roulette-wheel predicting wearables? 😉

I’ve always pushed for more “artistic” papers at ISWC, but there’s often a culture and communications gap between the technical and artistic communities. Joanna Berzowska‘s presentation on her animated kinetic dresses was a wonderful exception. The goal of her project was entirely aestetic — the hemline of one dress rises and lowers as if betraying (or thwarting) the wearer’s secret desires, and broach flowers open and close of their own accord on the neckline of another dress. But her presentation was full of all the technical details and lessons necessary to accomplish these creations. A couple examples:

• They used Nitinol (memory wire) sewn into felt to cause the motion. After trying many configurations, they determined that a tight coil was the best configuration to “set” the Nitinol, as it created the largest motion.

• Felt was the perfect fabric for a number of reasons. It’s sturdy, so when the Nitinol relaxes back to its non-set shape the felt will pull the dress or flower back to the normal position. It’s thick, so circuitry and wires can be felted into the fabric itself. And it’s a good insulator of heat and electricity, so the wearer is protected if there’s a short. It’s even fairly fire-retardant.

Yesterday I took a tutorial on building a wearable computer from the Intel-based Stargate board. Both the Stargate and for that matter the iPaq have a good form-factor for a Tin-Lizzy-style wearable (small, low power and have USB-Host for a one-handed keyboard) except for the big problem that they don’t have VGA-out to drive a head-up display. Kent Lyons has developed a nice hack to get around this limitation. (Technical summary follows.)

The hardware Kent’s using is IO Data’s Compact-Flash XGA card. Compact Flash doesn’t have enough pins to memory-map, so the CFXGA card uses the BLT interface to send just the pixels that change. (The card is designed for giving PowerPoint presentations from your handheld so they’re not worried about fast-changing scenes.) Kent leverages this by using his own modified X server that can use the BLT interface. It’s only 640×480 at 16 bpp, but it’s enough for text and simple interfaces on a head-up display. There’s code and a brief how-to at Kent’s website, as well as an email address where you can bug him to add more detail :).

I picked up an iPod Nano as a birthday gift to myself, and love it. It’s small and light enough to fit in my shirt pocket, and I’m finding that even 2 Gig is enough for a wide range of my randomly-sampled music library (plus podcasts, which is really what I want to use it for).

The one big problem I have with it (besides still needing to buy some sort of sleeve to protect its screen) is what to do with the headphones when I’m not using it. The ones that come with it are always a tangled mess after sitting in my pocket, and the Javo Edge retractable kind seemed fine on my normal iPod but now actually takes up more room and is twice as thick as the iPod itself!

The problem of “what do you do with it when it’s not being used” is one that watches and belt-clip pagers have solved but iPods and cellphones headpieces really haven’t yet. Even wireless earpieces for cellphones don’t have a place when they’re not in use, though at least they don’t get tangled. It’s a harder industrial engineering problem than you might think, and one that I think often gets overlooked.

I’ll be blogging from the 2005 International Symposium on Wearable Computers in Osaka this week. Please enjoy!