What is it about?
Taxonomy plays a vital role in identifying different mosquito species. This work solves this problem with a lightweight model built by compressing, duplicating, and fusing a Deep Convolutional Neural Network model (DCNN), adding a modified residual block, and training it through Knowledge Distillation (KD). Upon assessment, results yielded significant performance improvements, as the proposed model reached 99.22% overall accuracy that only requires 0.33 GFLOPs to operate and consumes only 437 KB of disk space.
Featured Image
Photo by Mike Norris on Unsplash
Why is it important?
Having an automated system for mosquito taxonomy can contribute in differentiating deadly vector mosquitoes to non-vector ones. This approach can also help eradicate or reduce the dangers they bring.
Read the Original
This page is a summary of: Machine-based mosquito taxonomy with a lightweight network-fused efficient dual ConvNet with residual learning and Knowledge Distillation, Applied Soft Computing, January 2023, Elsevier,
DOI: 10.1016/j.asoc.2022.109913.
You can read the full text:
Resources
Contributors
The following have contributed to this page
