Introduction

Physiological data offers many challenges to the machine learning community including dealing with large amounts of data, sequential data, issues of sensor fusion, and a rich domain complete with noise, hidden variables, and significant effects of context. The Physiological Data Modeling Contest will use data collected using BodyMedia wearable body monitors. These collect and store continuous data from multiple sensors packaged in an unobtrusive armband. A dataset comprising several months of data from more than a dozen subjects exists and will be provided by BodyMedia for the contest. Competitors will receive the training data early in 2004 and will submit entries consisting of predictions for the test data shortly before ICML 2004. At the workshop, the performance of each entrant will be announced, a winner rewarded, and the various techniques discussed and analyzed in detail. A small prize will be awarded to the winning competitors, and honorable mentions given to the best competitor on each sub-part of the competition. Additionally, the organizers will help collect the best of the entrants' white papers into an article for a technical journal or magazine. A white paper is required of all participants as part of a complete entry.

Expected interested parties include graduate students, faculty, and industrial researchers interested in machine learning.  The organizers have established a mailing list for the Physiological Data Modeling contest and workshop. To subscribe to the list, send an email to pdmc_ml-subscribe@yahoogroups.com. Interested participants should join the mailing list and contact the organizers immediately.