A Novel Hybrid Model Based on Machine and Deep Learning Techniques for the Classification of Microalgae

Abstract

Classification and monitoring of microalgae species in aquatic ecosystems are important for understanding population dynamics. However, manual classification of algae is a time-consuming method and requires a lot of effort with expertise due to the large number of families and genera in its classification. The recognition of microalgae species has become an increasingly important research area in image recognition in recent years. In this study, machine learning and deep learning methods were proposed to classify images of 12 different microalgae species in order to successfully classify algae cells. 8 Different novel models (MobileNetV3Small-Lr, MobileNetV3Small-Rf, MobileNetV3Small-Xg, MobileNetV3Large-Lr, MobileNetV3Large-Rf, MobileNetV3Large-Xg, Mobile-NetV3Small-Improved and MobileNetV3Large-Improved) have been proposed to classify these microalgae species. Among these proposed model structures, the best classification accuracy rate was 92.22% and the loss rate was 0.72, obtained from the MobileNetV3Large-Improved model structure. In addition, as a result of the experimental results obtained, metrics such as the confusion matrix, which can meet the experts in the correct diagnosis of microalgae species, were also evaluated. This research may in the future open a new avenue for the development of a cost-effective, highly sensitive computer-based system for the use of image analysis and deep learning techniques for the identification and classification of different microalgae.