UOW Malaysia KDU Penang University College, 32, Jalan Anson, 10400, George Town, Pulau Pinang, Malaysia.
School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia.
Sci Rep. 2021 May 10;11(1):9908. doi: 10.1038/s41598-021-89365-3.
Classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) by humans remains challenging. We proposed a highly accessible method to develop a deep learning (DL) model and implement the model for mosquito image classification by using hardware that could regulate the development process. In particular, we constructed a dataset with 4120 images of Aedes mosquitoes that were older than 12 days old and had common morphological features that disappeared, and we illustrated how to set up supervised deep convolutional neural networks (DCNNs) with hyperparameter adjustment. The model application was first conducted by deploying the model externally in real time on three different generations of mosquitoes, and the accuracy was compared with human expert performance. Our results showed that both the learning rate and epochs significantly affected the accuracy, and the best-performing hyperparameters achieved an accuracy of more than 98% at classifying mosquitoes, which showed no significant difference from human-level performance. We demonstrated the feasibility of the method to construct a model with the DCNN when deployed externally on mosquitoes in real time.
通过人类对埃及伊蚊（Linnaeus）和白纹伊蚊（Skuse）的分类仍然具有挑战性。我们提出了一种高度可访问的方法，通过使用可以调节发育过程的硬件来开发深度学习（DL）模型并实现模型，以用于蚊子图像分类。特别是，我们构建了一个包含 4120 张超过 12 天大的蚊子图像的数据集，这些图像具有常见的形态特征，这些特征已经消失，我们还说明了如何设置带有超参数调整的监督深度卷积神经网络（DCNN）。首先通过在三个不同代的蚊子上实时外部部署模型来进行模型应用，并将准确性与人类专家的性能进行比较。我们的结果表明，学习率和时期都显著影响准确性，最佳的超参数在对蚊子进行分类时的准确率超过 98%，与人类水平的性能没有显著差异。我们展示了在实时外部部署到蚊子上时，使用 DCNN 构建模型的方法的可行性。
