Machine Vision Optimization using Nature-Inspired Algorithms to Model Sunagoke Moss Water Status

Abstract

Machine vision has been widely implemented to monitor water status of plants. The performance of machine vision affects the prediction process of plant water status. Therefore optimization is needed to improve the performance of machine vision. The objective of this study is to optimize the performance of machine vision to model Sunagoke moss water status. Back Propagation Neural Network was used to model the relationship of image features and Sunagoke moss water status. Multi Objective Optimization (MOO) was used to select 212 image features to get maximum prediction accuracy and minimum number of features subset. Nine nature-inspired algorithms for optimization i.e. Genetic Algorithms (GAs), Discrete Particle Swarm Optimization (DPSO), Honey Bees Mating Optimization (HBMO), Simulated Annealing (SA), Ant Colony Optimization (ACO), Intelligent Water Drops (IWD), Discrete Firefly Algorithm (DFA), Discrete Hungry Roach Infestation Optimization (DHRIO), and Fish Swarm Intelligent (FSI) were compared. The result shows generally that the prediction model using feature selection techniques achieved significant prediction accuracy, and the number of feature-subset, and was better than the model without feature selection to predict Sunagoke moss water status.