Description
Conventional manual counting methods for the monitoring of mosquito species and populations can hinder the accurate determination of the optimal timing for pest control in the field. In this exercise is required to train a deep learning-based automated image analysis algorithm, for a two-fold task: the classification of different species and order of mosquito, based on a professionally made dataset of mosquitos photographs from multiple species.
Machine learning methods
CNN
Project proposal: general context
Deep Neural Network base don CNN architectures, multi-classification taks, application on medical physics
Input dataset
input data in image format
Goal and FOM
confusion matrix, accuracy, precision, recall, F1 score
Project proposal: description of the problem
Analysis and preprocessing of the dataset (highly unbalanced among species), identification of the correct deep learning architecture, two tasks - two loss training, analysis of performances
