Multi-Instance Multi-Label Acoustic Classification of Plurality of Animals : birds, insects & amphibian
O. Dufour, H. Glotin, T. Artières, Y. Bas, and P. Giraudet. Proc. 1st workshop Neural Information Processing Scaled for Bioacoustics -from neurons to Big Data-NIPS4B, page 164-174. NIPS4B, (December 2013)
Abstract
Nowadays, consulting firms on environment propose to evaluate impacts of
transports and/or power production infrastructures on biodiversity using bioacoustic and adapted algorithms of signal processing. We present here our best algorithm (whose AUC score is 0.85\%). This is our contribution to the “Neural Information Processing Scaled for Bioacoustics ” (NIPS4B) workshop technical challenge 1 of NIPS 2013. Our objective was to obtain a bird-sound operational classification machine-learning model that environmental engineers (mostly or nithologists) could use to realise automatic inventories of acoustically active animals.
%0 Conference Paper
%1 dufour2013multiinstance
%A Dufour, Olivier
%A Glotin, Hervé
%A Artières, Thierry
%A Bas, Yves
%A Giraudet, Pascale
%B Proc. 1st workshop Neural Information Processing Scaled for Bioacoustics -from neurons to Big Data-NIPS4B
%D 2013
%E Hervé, Glotin
%E al,
%I NIPS4B
%K acoustic animals automatic birds classification instance label multi sounds
%P 164-174
%T Multi-Instance Multi-Label Acoustic Classification of Plurality of Animals : birds, insects & amphibian
%U http://sis.univ-tln.fr/~odufour/
%X Nowadays, consulting firms on environment propose to evaluate impacts of
transports and/or power production infrastructures on biodiversity using bioacoustic and adapted algorithms of signal processing. We present here our best algorithm (whose AUC score is 0.85\%). This is our contribution to the “Neural Information Processing Scaled for Bioacoustics ” (NIPS4B) workshop technical challenge 1 of NIPS 2013. Our objective was to obtain a bird-sound operational classification machine-learning model that environmental engineers (mostly or nithologists) could use to realise automatic inventories of acoustically active animals.
@inproceedings{dufour2013multiinstance,
abstract = {Nowadays, consulting firms on environment propose to evaluate impacts of
transports and/or power production infrastructures on biodiversity using bioacoustic and adapted algorithms of signal processing. We present here our best algorithm (whose AUC score is 0.85\%). This is our contribution to the “Neural Information Processing Scaled for Bioacoustics ” (NIPS4B) workshop technical challenge 1 of NIPS 2013. Our objective was to obtain a bird-sound operational classification machine-learning model that environmental engineers (mostly or nithologists) could use to realise automatic inventories of acoustically active animals.
},
added-at = {2014-01-16T15:07:16.000+0100},
author = {Dufour, Olivier and Glotin, Hervé and Artières, Thierry and Bas, Yves and Giraudet, Pascale},
biburl = {https://www.bibsonomy.org/bibtex/21ba0456f896d3c717a99a71f3d7d903a/olivierlouis},
booktitle = {Proc. 1st workshop Neural Information Processing Scaled for Bioacoustics -from neurons to Big Data-NIPS4B},
editor = {Hervé, Glotin and al},
interhash = {b1b898f242f6128014f3edf54b4f2e53},
intrahash = {1ba0456f896d3c717a99a71f3d7d903a},
keywords = {acoustic animals automatic birds classification instance label multi sounds},
month = {december},
pages = {164-174},
publisher = {NIPS4B},
timestamp = {2014-01-16T15:07:16.000+0100},
title = {Multi-Instance Multi-Label Acoustic Classification of Plurality of Animals : birds, insects \& amphibian},
url = {http://sis.univ-tln.fr/~odufour/},
year = 2013
}