Thomas, OwenSunehag, PeterDror, GideonYun, SungrackKim, SRobards, MatthewSmola, AlexanderGreen, DanielSaunders, Philo U2015-12-101574-1192http://hdl.handle.net/1885/58689Detailed monitoring of training sessions of elite athletes is an important component of their training. In this paper we describe an application that performs a precise segmentation and labeling of swimming sessions. This allows a comprehensive breakdownKeywords: Activity analysis; Activity recognition; Discriminative hidden Markov models; Elite athlete; Human performance; Machine-learning; Margin setting; Semi Markov model; Sequential data; Training sessions; Wearable sensors; Accelerometers; Computational comple Accelerometer; Activity recognition; Human performance; Machine learning; Semi-Markov models201010.1016/j.pmcj.2010.01.0022016-02-24