Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier (2017-2018 à 2018-2019).

JASCO is a leading provider of passive acoustic monitoring solutions to the marine construction and petroleumx000D
exploration industries from our headquarters in Halifax, NS. JASCO regularly partners with government andx000D
academia on soundscape and marine mammal habitat research projects. As part of these projects JASCOx000D
collects continuous acoustic datasets that last from a day to year for multiple recorders over wide areas. To datex000D
JASCO accumulated 600,000 'truth-data' annotations from hundreds of types of marine mammal species andx000D
noise sources. JASCO has identified a need to improve their marine mammal detection and classificationx000D
algorithms. Current detector/classifiers are effective, but the expectation is that new machine learningx000D
techniques will both improve the probability of detection and will reduce false alarms. Being able to providex000D
reliable results quickly to universities, government and industry is a unique offering that JASCO believes itx000D
must continually improve to maintain it's market leader position. While JASCO has rich and extensive internalx000D
expertise in ocean acoustic data, it will benefit from a pilot study on the use of state-of-the-art Machinex000D
learning expertise in classifier development, contributed by Dalhousie University. We will apply severalx000D
Machine Learning classifiers on the labeled data. Moreover, we will experiment with data re-representationx000D
techniques known to perform well-from a Deep Learning perspective - when the representation is directlyx000D
learned from the data used for a given task (here, species classification). Convolutional Neural Networksx000D
(CNNs) are a promising approach. The hypothesis is that CNNs can produce a compact but at the same timex000D
highly performing representation to be used by one of the machine learning classifiers mentioned above.x000D
Finally, it is likely that due to the scale of the data, efficiency problems may arise wrt at least some of thex000D
methods (eg clustering). If that will be the case, we will look into the use of GPU-based solutions either thrux000D
the dedicated proprietary resources, or on Compute Canada's facilities with multiple GPU availability.