| dc.description.abstract | Mosquito is one of the animals that can transmit dangerous diseases in the world. Indonesia is recorded as the second country with the highest number of mosquito species in the world, with the Aedes and Culex genera being among the most commonly found. Several mosquitoes from the Aedes and Culex genera that transmit diseases such as dengue fever, malaria, and elephantiasis are found in Indonesia. Currently, the method used to identify and classify mosquitoes is still based on manual physical examination, which is time-consuming. Therefore, a system is needed to assist experts in classifying mosquitoes more efficiently. This research focuses on using images of mosquito bodies from the species aedes aegypti, aedes albopictus, and culex quinquefasciatus. The total image dataset used consists of 1,560 images, with 1,248 images used for training data and 312 images for testing data. The convolutional neural network (CNN) algorithm is employed in this study due to its ability to extract high-level features from images. The random forest algorithm is also utilized to minimize oveRFitting. After conducting testing, it can be concluded that the combination of the convolutional neural network and random forest algorithms can provide satisfactory results in classifying images of the three mosquito species with an accuracy of 90%. | en_US |
