TY - JOUR
T1 - Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection
AU - Goodwin, Adam
AU - Padmanabhan, Sanket
AU - Hira, Sanchit
AU - Glancey, Margaret
AU - Slinowsky, Monet
AU - Immidisetti, Rakhil
AU - Scavo, Laura
AU - Brey, Jewell
AU - Sai Sudhakar, Bala Murali Manoghar
AU - Ford, Tristan
AU - Heier, Collyn
AU - Linton, Yvonne Marie
AU - Pecor, David B.
AU - Caicedo-Quiroga, Laura
AU - Acharya, Soumyadipta
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture methods. Convolutional neural networks (CNNs) are promising with limited sets of species, but image database requirements restrict practical implementation. Using an image database of 2696 specimens from 67 mosquito species, we address the practical open-set problem with a detection algorithm for novel species. Closed-set classification of 16 known species achieved 97.04 ± 0.87% accuracy independently, and 89.07 ± 5.58% when cascaded with novelty detection. Closed-set classification of 39 species produces a macro F1-score of 86.07 ± 1.81%. This demonstrates an accurate, scalable, and practical computer vision solution to identify wild-caught mosquitoes for implementation in biosurveillance and targeted vector control programs, without the need for extensive image database development for each new target region.
AB - With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture methods. Convolutional neural networks (CNNs) are promising with limited sets of species, but image database requirements restrict practical implementation. Using an image database of 2696 specimens from 67 mosquito species, we address the practical open-set problem with a detection algorithm for novel species. Closed-set classification of 16 known species achieved 97.04 ± 0.87% accuracy independently, and 89.07 ± 5.58% when cascaded with novelty detection. Closed-set classification of 39 species produces a macro F1-score of 86.07 ± 1.81%. This demonstrates an accurate, scalable, and practical computer vision solution to identify wild-caught mosquitoes for implementation in biosurveillance and targeted vector control programs, without the need for extensive image database development for each new target region.
UR - http://www.scopus.com/inward/record.url?scp=85109131398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85109131398&partnerID=8YFLogxK
U2 - 10.1038/s41598-021-92891-9
DO - 10.1038/s41598-021-92891-9
M3 - Article
C2 - 34211009
AN - SCOPUS:85109131398
SN - 2045-2322
VL - 11
JO - Scientific reports
JF - Scientific reports
IS - 1
M1 - 13656
ER -