Bat detective - Deep learning tools for bat acoustic signal detection
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 128740499
- Type
- D - Journal article
- DOI
-
10.1371/journal.pcbi.1005995
- Title of journal
- PLoS Computational Biology
- Article number
- e1005995
- First page
- -
- Volume
- 14
- Issue
- 3
- ISSN
- 1553-734X
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
18
- Research group(s)
-
B - Data Science and Artificial Intelligence
- Citation count
- 35
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work introduced a compact deep neural network capable of detecting echolocating bats in ultrasonic audio recordings captured by citizen scientists. The developed model was later deployed, and is still online, on edge computing based devices across multiple locations in the Olympic Park in London enabling real-time monitoring of bat activity in the park (https://naturesmartcities.com/). The deployment received coverage on the BBC (https://www.bbc.co.uk/news/science-environment-40417936) and was awarded the NCETechFest Environmental Impact Award in 2018.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -