(please see the main page for schedule information)
One trillion dollars of US healthcare costs per year are directly attributable to people's lifestyle choices and our country spends less than 5% of that addressing this issue. What if there was an unobtrusive, accurate way to gather the physical and mental states of people in their natural environments, in real time and over long periods of time? If such information could be obtained, we could start to address the fundamental issue in health and wellness: behavior modification. This talk is a tour through five years of challenges and discoveries building a wearable body monitoring business using machine learning techniques. The talk will cover challenges of gathering data, building body state models, validating the models with the medical community, and will place AI within the larger context of the company, BodyMedia, and the healthcare, wellness, and fitness industries. The gap between the academic study of machine learning and its application in our industry will be addressed, as will areas where further academic research would be fruitful.
David is presently Director of Informatics at BodyMedia, where he directs the team responsible for collecting and analyzing clinical data, creating machine learning models of that data, and developing algorithms that provide high level metrics over that data (e.g. predicting energy expenditure or detecting sleep). David holds a Bachelor of Science in symbolic systems and a Bachelor of Arts in psychology from Stanford University. He earned his Ph.D in artificial intelligence from the University of California at Berkeley, where he was inducted as a Hertz fellow. His dissertation presented a computer programming language where the programmer only need specify portions of the computer's behavior -- the system completed the rest of the program by learning from experience. Back in 1996, David helped start Blue Pumpkin, a company that, like BodyMedia, utilizes AI technologies at the core of their business model, in this case for the task of managing and scheduling workforces at call centers. David is the author of more than 60 peer-reviewed articles, papers, and chapters in the areas of robotics, machine learning, reinforcement learning, evolutionary computation, and parallel processing. He is an inventor on numerous patents, seven of which are currently issued, as well as the author of a book on his work on automatic circuit design.