Fish swarm intelligent to optimize real time monitoring of chips drying using machine vision

International Conference on Green Agro-industry and Bioeconomy 2017

农业科学;生物科学;经济学

Hendrawan, Y.^1 ; Hawa, L.C.^1 ; Damayanti, R.^1

Department of Agricultural Engineering, Faculty of Agricultural Technology, Universitas Brawijaya, Malang, Indonesia^1

关键词: Artificial neural network models;    Image features;    Monitoring system;    Optimization algorithms;    Prediction accuracy;    Real time monitoring;    Size minimization;    Swarm intelligent;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/131/1/012020/pdf
DOI  :  10.1088/1755-1315/131/1/012020

来源: IOP

【 摘 要 】

This study attempted to apply machine vision-based chips drying monitoring system which is able to optimise the drying process of cassava chips. The objective of this study is to propose fish swarm intelligent (FSI) optimization algorithms to find the most significant set of image features suitable for predicting water content of cassava chips during drying process using artificial neural network model (ANN). Feature selection entails choosing the feature subset that maximizes the prediction accuracy of ANN. Multi-Objective Optimization (MOO) was used in this study which consisted of prediction accuracy maximization and feature-subset size minimization. The results showed that the best feature subset i.e. grey mean, L(Lab)Mean, a(Lab)energy, red entropy, hue contrast, and grey homogeneity. The best feature subset has been tested successfully in ANN model to describe the relationship between image features and water content of cassava chips during drying process with R2of real and predicted data was equal to 0.9.