Paula Martiskainen

Jerk-based feature extraction for robust activity recognition from acceleration data

A current trend in activity recognition is to use just one easily carried accelerometer, either integrated into a mobile phone, carried in a pocket, or attached to an animals collar. The main disadvantage of this approach is that the orientation of the accelerometer is generally unknown. Therefore, one cannot separate body-related accelerations from the gravitational acceleration or determine the real directions of the observed accelerations accurately. As a solution, we introduce a new technique where jerk (changes of accelerations) is analyzed instead of the original acceleration signal. The total jerk magnitude is completely orientation-independent and it reflects only body-related accelerations. If the direction of the gravitation can be approximated even loosely, then the jerk signal can be further enriched with valuable information on jerk angles (direction changes). According to our experiments this kind of jerk-filtered signal produces robust features and can improve the recognition accuracy remarkably.

Training dairy bull calves to stay within light-built electric fences

Training cattle to avoid electric fences before turnout to grazing reduces the risk of the animals breaking out from their paddock. We investigated the time needed for dairy bull calves to learn to avoid a light-built electric fence. Nineteen dairy bull calves were trained to an electric fence in a training yard during seven days. The number of electric shocks the animals received from the training fence was recorded continuously. After the training period, the calves were turned to pasture. Nine of the animals were also grazed the following summer as yearlings, and observed before turnout in a smaller enclosure. The calves got more shocks from the fence during training hour 1 than during any of the following seven hours. The number of shocks the calves received from the fence also declined from training day 1 to 2 and from training day 3 to 4. The results indicate that the dairy bull calves learned to avoid an electric fence quickly, even within an hour from release into the training yard. A simple training procedure was sufficient to ensure that the animals could be grazed in and would avoid a light-built electric fencing system as calves and, even after a winter-housing period, as bulls.