Optimization of convolutional neural network hyperparameters for automatic classification of adult mosquitoes.

The economic and social impacts due to diseases transmitted by mosquitoes in the latest years have been significant. Currently, no specific treatment or commercial vaccine exists for the control and prevention of arboviruses, thereby making entomological characterization fundamental in combating diseases such as dengue, chikungunya, and Zika. The morphological identification of mosquitos includes a visual exam of the samples. It is time consuming and requires adequately trained professionals. Accordingly, the development of a new automated method for realizing mosquito-perception and -classification is becoming increasingly essential. Therefore, in this study, a computational model based on a convolutional neural network (CNN) was developed to extract features from the images of mosquitoes and then classify the species Aedes aegypti, Aedes albopictus, and Culex quinquefasciatus. In addition, the model was trained to detect the mosquitoes of the genus Aedes. To train CNNs to perform the automatic morphological classification of mosquitoes, a dataset, which included 7,561 images of the target mosquitoes and 1,187 images of other insects, was acquired. Various neural networks, such as Xception and DenseNet, were used for developing the automatic-classification model based on images. A structured optimization process of random search and grid search was developed to select the hyperparameters set and increase the accuracy of the model. In addition, strategies to eliminate overfitting were implemented to increase the generalization of the model. The optimized model, during the test phase, obtained the balanced accuracy (BA) of 93.5% in classifying the target mosquitoes and other insects and the BA of 97.3% in detecting the mosquitoes of the genus Aedes in comparison to Culex. The results provide fundamental information for performing the automatic morphological classification of mosquito species. Using a CNN-embedded entomological tool is a valuable and accessible resource for health workers and non-taxonomists for identifying insects that can transmit infectious diseases.

Application of convolutional neural networks for classification of adult mosquitoes in the field.

Dengue, chikungunya and Zika are arboviruses transmitted by mosquitos of the genus Aedes and have caused several outbreaks in world over the past ten years. Morphological identification of mosquitos is currently restricted due to the small number of adequately trained professionals. We implemented a computational model based on a convolutional neural network (CNN) to extract features from mosquito images to identify adult mosquitoes from the species Aedes aegypti, Aedes albopictus and Culex quinquefasciatus. To train the CNN to perform automatic morphological classification of mosquitoes, we used a dataset that included 4,056 mosquito images. Three neural networks, including LeNet, AlexNet and GoogleNet, were used. During the validation phase, the accuracy of the mosquito classification was 57.5% using LeNet, 74.7% using AlexNet and 83.9% using GoogleNet. During the testing phase, the best result (76.2%) was obtained using GoogleNet; results of 52.4% and 51.2% were obtained using LeNet and AlexNet, respectively. Significantly, accuracies of 100% and 90% were achieved for the classification of Aedes and Culex, respectively. A classification accuracy of 82% was achieved for Aedes females. Our results provide information that is fundamental for the automatic morphological classification of adult mosquito species in field. The use of CNN's is an important method for autonomous identification and is a valuable and accessible resource for health workers and taxonomists for the identification of some insects that can transmit infectious agents to humans.