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.
Abstract:Monitoring the maturation process of Satsuma mandarin (Citrus unshiu Marc.) by determining the soluble solids (SS) and acid content non-destructively is needed. Fluorescence components potentially offer such means of accessing fruit maturity characteristics in the orchard. The aim of this study was to determine the potential of fluorescence spectroscopy for monitoring the stage of citrus maturity. Four major fluorescent components in peel and/or flesh were found including chlorophyll-a (excitation (Ex) 410 nm, emission (Em) 675 nm) and chlorophyll-b (Ex 460 nm, Em 650 nm),polymethoxyflavones (PMFs) (Ex 260 nm and 370 nm, Em 540 nm), coumarin (Ex 330 nm, Em 400 nm), and a tryptophan-like compound (Ex 260 nm, Em 330 nm). Our results indicated a significant (R 2 = 0.9554) logarithmic ratio between tryptophan-like compoundsExEm and chlorophyll-aExEm with the SS:acid ratio. Also, the log of the ratio of PMFs from the peel (ExExEm was significantly correlated with the SS:acid ratio (R 2 = 0.8207). While the latter correlation was not as strong as the former, it does demonstrate the opportunity to develop a non-destructive field measurement of fluorescent peel compounds as an indirect index of fruit maturity.
As a cost-effective and nondestructive detection method, the machine vision technology has been widely applied in the detection of potato defects. Recently, the depth camera which supports range sensing has been used for potato surface defect detection, such as bumps and hollows. In this study, we developed a potato automatic grading system that uses a depth imaging system as a data collector and applies a machine learning system for potato quality grading. The depth imaging system collects 3D potato surface thickness distribution data and stores depth images for the training and validation of the machine learning system. The machine learning system, which is composed of a softmax regression model and a convolutional neural network model, can grade a potato tube into six different quality levels based on tube appearance and size. The experimental results indicate that the softmax regression model has a high accuracy in sample size detection, with a 94.4% success rate, but a low success rate in appearance classification (only 14.5% for the lowest group). The convolutional neural network model, however, achieved a high success rate not only in size classification, at 94.5%, but also in appearance classification, at 91.6%, and the overall quality grading accuracy was 86.6%. The quality grading based on the depth imaging technology shows its potential and advantages in nondestructive postharvesting research, especially for 3D surface shape-related fields.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.