Bats Monitoring: A Classification Procedure of Bats Behaviors based on Hawkes Processes

We are interested in the problem of classifying commuting and foraging behavior of bats at a site. To this extent, we use echolocation calls data detected by acoustic sensors during a night at this site. As the temporal distribution of calls is a relevant indicator of behavior, it is natural to model the calls sequences by point processes. Given the self-exciting dynamics observed in foraging behavior, we propose to model the calls sequences of bats by Hawkes processes. Specifically, we consider that the start time of each call emitted on a site is a jump of a Hawkes process. For the classification task, we use a suitable procedure that relies on the empirical risk minimization principle. Then, we assess the performance of the procedure on synthetic data and also provide a comparison with the random forests algorithm. The overall methodology is evaluated with a goodness-of-fit test. Finally, we present the obtained results on a real data set, collected as part of Vigie-Chiro project. The classification results are convincing and show the relevance of our method.