ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

EchoExplorer, a web application for automated bat and wildlife call classification

Gerlache, Anthony ; Sirjacobs, Noam
(2024)

Files

Gerlache_55961900_Sirjacobs_62501900_2024.pdf
  • Open access
  • Adobe PDF
  • 7.8 MB
Download

Details

Supervisors
Bonaventure, Olivier
Faculty
Ecole polytechnique de Louvain
Ecole polytechnique de Louvain
Degree label
Master [120] : ingénieur civil en informatique, à finalité spécialisée
Master [120] en sciences informatiques, à finalité spécialisée
Abstract
This master thesis presents the development of EchoExplorer, a web application aimed at facilitating automated bat call detection. Traditional methods and existing AI tools for classifying bat calls require technical expertise or advanced computer science skills, limiting their accessibility. EchoExplorer serves as an invaluable tool for bat enthusiasts. By creating a web application, we allow users to get rid of technical complexities and have access to sophisticated AI-driven analysis. Based on an existing AI model created during two previous master theses, the application offers and can support the integration of various AI models for different animal species, not limited to bats. The user interface provides multiple tools to give users a better experience while analysing their audio. Additionally, our application offers collective analysis by allowing users with expertise in bats identification to review and validate the results generated by the AI which enables labelled data collection, a key point in machine learning, often missing.