One step closer to automatic ID of bat echolocation

News from iBats is the development of iBatsID a tool for classifying bat calls using ensembles of artificial neural networks (eANN’s) to classify time-expanded recordings of bat echolocation calls from 34 European bat species.

The tool has been trained to identify echolocation calls of Barbastella barbastellus, Eptesicus bottae, E. nilssonii, E. serotinus, Hypsugo savii, Miniopterus schreibersii, Myotis alcathoe, M. bechsteinii, M. blythii, M. brandtii, M. capaccinii, M. dasycneme, M. daubentonii, M. emarginatus, M. myotis, M. mystacinus, M. punicus, Nyctalus lasiopterus, N. leisleri, N. noctula, Pipistrellus kuhlii, P. nathusii, P. pipistrellus, P. pygmaeus, Plecotus auritus, P. austriacus, Rhinolophus blasii, R. euryale, R. ferrumequinum, R. hipposideros, R. mehelyi, Tadarida teniotis, Vespertilio murinus. A fairly comprehensive list.

At present  ID of M. bechsteinii/M. brandtii/ M. daubentonii/ M. mystacinus is only to sub group rather than to species level ( M. myotis/M. blythii/M. punicus;  M. bechsteinii/M. brandtii/ M. daubentonii/ M. mystacinus;  M. emarginatus/M. alcathoe for European readers)

But it’s a great start. The only downside is the current need to process calls with Sonobat first to extract a text file of call parameters.

We can’t be too far now from integrating capturing, geolocating, analysing and identifying echolocation in a single app on a smartphone or tablet such as the Nexus 7.

Link to the paper:

Link to the iBatsID site: