Accurate assessment of mosquito population density is crucial for the efficient management of mosquito-borne diseases such as malaria and dengue in areas affected by these vectors. Nevertheless, the traditional approach of manually counting and classifying mosquitoes through the use of traps is both laborious and expensive. This research paper presents a proposed pipeline for the identification and categorization of mosquitoes from photographs, specifically designed for low-cost Internet of Things (IoT) sensors. The pipeline aims to achieve a balance between accuracy and efficiency. Through the process of fine- tuning conventional machine learning models such as VGG16, RESNET50, and Convolutional Neural Network (CNN), a notable level of accuracy of 98% is attained. The present study highlights the potential of integrating a highly effective mosquito detection device with a convolutional neural network to offer a viable balance between precision and efficiency in the realm of mosquito identification, categorization, and quantification. Consequently, this approach has promise for improving the control and prevention of mosquito-borne illnesses.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2023 Iraqi Journal of Intelligent Computing and Informatics (IJICI)