Cet évènement est passé.

Learning of Biosonars or Songs & other Models to Survey Marine Mammal

14 novembre 2018 @ 9 h 00 min - 17 h 00 min

Learning of Biosonars or Songs & other Models to Survey Marine Mammal
2nd Environmental Acoustic Big Data workshop
14 November – Univ Toulon La Garde

This workshop is a organized by MADICS GDR – EADM action.

It aims to demonstrate the needs and realisation of long term, big data monitoring of the biodiversity, by leveraging advances in IoT, versatil microcontrollers, advanced signal processing and machine learning. Continuous monitoring of ecosystems can be achieved by recording and analysing their acoustic environment (soundscape), which is the expression of the habitat quality, richness and biodiversity. Managing big acoustic data streams requires specialized tools to classify the scenes and detect / recognise the different components, e.g. biophony, geophony and anthropophony. This second edition will be devoted to model and applications on mammals.

Program

9h Welcome
9:15 Opening & objectives
« Data Science and bioacoustics of Biosonar & Songs of marine mammals »
Hervé Glotin, LIS CNRS U. Toulon
9:30 Case studies, overview« Marine soundscapes, to broaden the scope of underwater acoustic monitoring »
Gianni Pavan, CIBRA, univ Pavia, Italy

« ACCOBAMS addressing underwater noise issues »
Maÿlis Salivas, Accobams, Monaco
10:20 – 10:35 Coffee break

« Acoustic monitoring in Pelagos sanctuary »
Marion Peirache, Parc national de Port-Cros & Pelagos, France

« Caribbean survey of marine mammals »
Jeffrey Bernus, Scientific resp. of CARIMAM, AGOA & AFB, Martinique
11:05 Emb. PAM on Autonomous Surface Vehicle completed by satellite for large scale survey
« High Velocity acquisition : JASON sound card, 3D Tracking of Biosonar of pink Amazon River dolphins into the wild »
Valentin Barchasz et al., SMIoT

« Sphyrna : an oceanic big data scientific Autonomous Surface Vehicle »
Fabien de Varenne, Seaproven SA

« Passive acoustic 3D tracking of deep cetacean diver from the Sphyrna ASV »
Marion Poupard et al., Biosong SA
12:30 lunch – 14:00 Cont.

« Deep learning and satellite images, perspective on whale survey »
Adeline Paiement, LIS & Bristol univ.
14:20 Classification Multichannel Audio Autoencoder
« Deepnet & AutoEncoder : an overview from speech to bioacoustic event classification »
Ricard Marxer et al., LIS

« Towards Deepnet AutoEncoder, – application to Biosonar of Marine Mammal »
Maxence Ferrari et al., DGA LIS LAMFA
15:00 – 15:20 Coffee break
15:20 Detectop, Pattern analysis and inversion
« Scaled detection and browsing, big data strategies for marine mammal surveys »
Jan Schlüter et al., LIS CNRS & OFAI Austria

« Mathematical model for long term analysis of the frequency of songs of Blue or Humpback whales »
Julie Patris & Franck Malige, AMU, STIC AmSud BRILAM, Chili (visio)
16:00 Discussion
17:00 Closing

Détails

Date :: 14 novembre 2018
Heure :: 9 h 00 min - 17 h 00 min

Organisateur

: Hervé Glotin
E-mail: herve.glotin@lis-lab.fr
: Voir le site Organisateur

Lieu

: Université Toulon La Garde
: Campus de La Garde - Bt X
Toulon, 83041 + Google Map