Crab Molting Identification using Machine Learning Classifiers

Abstract

Soft-shell crab is an export product in which foreign demand is much higher than production. The production of soft-shell crabs done by selecting the crabs just prior to molting and placing them in a box until the molting occurs. Molting is a natural process of shedding the shell when crabs respond to the lack of growth space within its shell. Shortly after molting, the new crab shells are still very soft and will be hardened in a few hours after the crabs absorb calcium from water. Farmer must harvest the crab while the crabs’ shell is soft. This study investigates the initial identification of crab molting using machine learning classifier. We collected 1060 image datasets of crab molting and we divide data into 1000 training data and 60 testing data. We use three machine learning classifiers, namely K-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and the Random Forest Classifier (RFC). This study aims to compare and determine the best classification algorithm to be used for crab’s molting identification. The experimental results show that, KNN is the best classification algorithm for initial identification of crab’s molting.

Access to Document

Other files and links

• Link to publication in Scopus

Fingerprint