Paper Title
Classifying Invasive Alien Frog Species in The Philippines Using Convolutional Neural Networks

Abstract
The proliferation of Invasive Alien Species (IAS) in the Philippines is a major threat to its biodiversity. Taxonomic information on IAS is crucial to preventing, controlling and eradicating it. Computer vision technology can be applied to assist in strategies and plans to fight IAS. Invasive alien species in the Philippines (IAS PH) include five alien frogs: the cane toad (Rhinella marina), Chinese bullfrog (Hoplobatrachusrugulosus), green paddy frog (Hylaranaerythraea), greenhouse frog (Eleutherodactylusplanirostris), and Asiatic painted toad (Kaloulapulchra). This study presents implementations of Resnet18 and MobileNetV2, two known convolutional neural network (CNN) models, previously used for other computer vision tasks, for classifying the five invasive alien frog species in the Philippines. In this interdisciplinary study, a dataset of 252 images of the five alien frogs collected by experts from the ASEAN Centre for Biodiversity was used. The images were pre-processed and used to train Resnet18 and MobileNetV2 to classify the five alien frogs in the Philippines. We used five-fold cross validation to evaluate the performance of our models. The validation accuracy of our models show that both CNNs can accurately classify the five invasive alien frog species in the Philippines. The top performing model, ResNet18, achieved a 92.92% average top-1 accuracy while MobileNetV2 achieved an average top-1 accuracy of 92.08%. While ResNet18 had slightly higher average accuracy than MobileNetV2, a paired t-test between accuracies from the corresponding validation folds of these two CNN models, however, showed no significant difference. Keywords - Invasive Alien Frog Species, Convolutional Neural Networks, Biodiversity