In this paper we demonstrate a Markov model based technique for recognizing gestures from accelerometers that explicitly represents duration. We do this by embedding an Erlang-Cox state transition model, which has been shown to accurately represent the first three moments of a general distribution, within a Dynamic Bayesian Network (DBN). The transition probabilities in the DBN can be learned via Expectation-Maximization or by using closed-form solutions. We test this modeling technique on 10 hours of data collected from accelerometers worn by babies pre-categorized as high-risk in the Newborn Intensive Care Unit (NICU) at UCI. We show that by treating instantaneous machine learning classification values as observations and explicitly modeling duration, we improve the recognition of Cramped Synchronized General Movements, a motion highly correlated with an eventual diagnosis of Cerebral Palsy. ( local copy )
Published in Ubicomp 2012 .