Multiclass-Classification of Algae Using Dc-GAN and Transfer Learning

EasyChair Preprint 7234

Abstract

The growth of algae is a natural process and highly increase in concentration having a bad impact on water bodies as well as other creatures. The monitoring and classification of algae by using the traditional method is a tedious and time-consuming task. The reliable and robust development of the alternative method is crucial to do these tasks, however, advanced machine learning and deep learning are excessively used to address this problem. In recent years the transfer learning method is getting more attention and extensively used by people for features extraction and classification purposes but due to high variation of environment, low-quality input images and different varieties of algae plants still create gaps for the researcher. To build a robust and reliable system all these factors should need to be considered. In this paper, we have used the transfer learning technique, in which various pre-train models are used to train on our custom dataset. We experiment to classify four genera of harmful algae bloom (HAB), furthermore, we compare each pre-train architecture performance on our unique dataset. The proposed model effectively classifies, and overall accuracy is 98.07 %. The transfer learning model approach would be an effective tool for rapid operational response to algae bloom events. The experimental results show that the proposed method is more effective and reliable to detect and classify the algae.

Keyphrases: Advanced Augmentation, DCGAN, Transfer Learning

@booklet{EasyChair:7234,
  author    = {Ziaullah Khan and Abdullah and Wajid Mumtaz and Hee-Cheol Kim and Abdul Samad Mumtaz},
  title     = {Multiclass-Classification of Algae Using Dc-GAN and Transfer Learning},
  howpublished = {EasyChair Preprint 7234},
  year      = {EasyChair, 2021}}