| 摘要 |
<p>The specification describes activity detection, such as training of an activity detector to detect activities represented in input time series data. One example of activities are swimming stokes, such as freestyle and breaststroke. Time series data representing an ordered sequence of activities (30) is provided as input. The method comprises repeatedly (60) generating a set of clusters of the time series data by iteratively (40) performing semi-Markov clustering on the data (30). A set of clusters that satisfy a criteria that is based on at least a list of activity types (32) is selected so that for each cluster of the selected set of clusters, associating an activity type based on the order of the activity types in the list. It is an advantage that the activity detector can be trained using minimal input, that is, only the time series data and the (received or known) list of ordered activity types. No annotated data is required. Aspects include methods, computer systems, activity detectors and software.</p> |
