Detection of insect health with deep learning on near-infrared sensor data
Bick, E. N.; Edwards, S.; De Fine Licht, H. H.
Show abstract
Conventional monitoring methods for disease vectors, pollinators or agricultural pests require time-consuming trapping and identification of individual insects. Automated optical sensors that detect backscattered near-infrared modulations created by flying insects are increasingly used to identify and count live insects, but do not inform about the health status of individual insects. Here we show that deep learning in trained convolutional neural networks in conjunction with sensors is a promising emerging method to detect infected insects. Health status was correctly determined in 85.6% of cases as early as two days post infection with a fungal pathogen. The ability to monitor insect health in real-time potentially has wide-reaching implications for preserving pollinator biodiversity and the rapid assessment of disease carrying individuals in vector populations. One sentence summaryAutomated optical sensors distinguish between fungus-infected and healthy insects.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Adhesive and mechanical properties of the glue produced by 25 Drosophila species 92%
- A genetic toolkit for the analysis of metabolic changes in Drosophila provides new insights into metabolic responses to stress and malignant transformation 92%
- High-Throughput Tracking of Freely Moving Drosophila Reveals Variations in Aggression and Courtship Behaviors 91%
Similar papers in this journal
Similar papers in this journal
- Emergence of hyper insecticide-resistant dengue vectors in Indochina Peninsula: threats of concomitant knockdown resistance mutations 92%
- Multimodal social context modulates behavior in larval Drosophila 91%
- Gene drive mosquitoes can aid malaria elimination by retarding Plasmodium sporogonic development 91%
Similar papers in this journal
- Host range of naturally and artificially evolved symbiotic bacteria for a specific host insect 92%
- Step-specific adaptation and trade-off over the course of an infection by GASP-mutation small colony variants 92%
- Tornadic shear stress induces a transient, calcineurin-dependent hyper-virulent phenotype in Mucorales molds 91%
Similar papers in this journal
- The Dynamics of Cryptococcus neoformans infection in Galleria mellonella 94%
- Microbial composition in larval water enhances Aedes aegypti development but reduces transmissibility of Zika virus 91%
- Disentangling the relative roles of vertical transmission, subsequent colonizations and diet on cockroach microbiome assembly 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.