Development of Micro Precision Irrigation System in Plant Factory

Abstract

AbstractComputer integrated systems and Artificial Intelligence (AI) have become an apparent need for control in a plant factory. Sunagoke moss Rachomitrium japonicum is one of the plant products which are cultivated in plant factory. One of the primary determinants of moss growth is water availability. The present work attempted to apply machine vision-based micro-precision irrigation system which is able to optimize water use in plant factory and maintain the water content of moss constantly in optimum growth condition. The objective of this study is to propose nature-inspired algorithms to find the most significant set of image features suitable for predicting water content of cultured Sunagoke moss. Multi-Objective Optimization (MOO) was used in this study which consisted of prediction accuracy maximization and feature-subset size minimization. Feature Selection (FS) methods included Neural-Intelligent Water Drops (N-IWD), Neural-Simulated Annealing (N-SA), Neural-Genetic Algorithms (N-GAs), Neural-Ant Colony Optimization (N-ACO), Neural-Honey Bee Mating Optimization (N-HBMO), and Neural-Fish Swarm Intelligent (N-FSI). Image features consist of colour features and textural features with the total of 212 features extracted from grey, RGB, HSV, HSL, L*a*b* XYZ, LCH and Luv colour spaces. Back-Propagation Neural Network (BPNN) model performance was tested successfully to describe the relationship between water content of Sunagoke moss and image features. FS methods improve the prediction performance of BPNN.