@article{fdi:010088844,
  title = {{W}ing {I}nterferential {P}atterns ({WIP}s) and machine learning for the classification of some {A}edes species of medical interest},
  author = {{C}annet, {A}. and {S}imon-{C}hane, {C}. and {H}istace, {A}. and {A}khoundi, {M}. and {R}omain, {O}. and {S}ouchaud, {M}. and {J}acob, {P}. and {S}ereno, {D}. and {G}ouagna, {L}ouis-{C}l{\'e}ment and {B}ouss{\`e}s, {P}hilippe and {M}athieu-{D}aud{\'e}, {F}ran{\c{c}}oise and {S}ereno, {D}enis},
  editor = {},
  language = {{ENG}},
  abstract = {{H}ematophagous insects belonging to the {A}edes genus are proven vectors of viral and filarial pathogens of medical interest. {A}edes albopictus is an increasingly important vector because of its rapid worldwide expansion. {I}n the context of global climate change and the emergence of zoonotic infectious diseases, identification tools with field application are required to strengthen efforts in the entomological survey of arthropods with medical interest. {L}arge scales and proactive entomological surveys of {A}edes mosquitoes need skilled technicians and/or costly technical equipment, further puzzled by the vast amount of named species. {I}n this study, we developed an automatic classification system of {A}edes species by taking advantage of the species-specific marker displayed by {W}ing {I}nterferential {P}atterns. {A} database holding 494 photomicrographs of 24 {A}edes spp. from which those documented with more than ten pictures have undergone a deep learning methodology to train a convolutional neural network and test its accuracy to classify samples at the genus, subgenus, and species taxonomic levels. {W}e recorded an accuracy of 95% at the genus level and >85% for two ({O}chlerotatus and {S}tegomyia) out of three subgenera tested. {L}astly, eight were accurately classified among the 10 {A}edes sp. that have undergone a training process with an overall accuracy of >70%. {A}ltogether, these results demonstrate the potential of this methodology for {A}edes species identification and will represent a tool for the future implementation of large-scale entomological surveys.},
  keywords = {},
  booktitle = {},
  journal = {{S}cientific {R}eports - {N}ature},
  volume = {13},
  numero = {1},
  pages = {17628 [ p.]},
  ISSN = {2045-2322},
  year = {2023},
  DOI = {10.1038/s41598-023-44945-3},
  URL = {https://www.documentation.ird.fr/hor/fdi:010088844},
}