No abstract

No abstract

Ecophysiological stimulators directly affect root morphology, especially in the embryonic stage. To enhance crop germination, an understanding of the root traits under abiotic inducers is needed. In this study, the combined impacts of white and red-blue light spectrums, cold stratification, and seed fortification involving various concentrations of bioactive chemicals namely simple nutrient addition program solution, gibberellic acid, α-naphthaleneacetic acid with thiamine hydrochloride were evaluated on loose-leaf lettuce (Lactuca sativa var. Altima) seedling root architecture. The growth-promoting effects of these nutrients varied the growth rate and morphology of roots which are immediately shown during the radicle development. Integrated computer vision and computational intelligence were employed for phytomorphological signatures extraction of seedlings that were cultivated in a customized modulable spectrum experimental chamber (MSPEC). Root phenotype model was developed using graph-cut segmentation and region properties, and the ideal germination nutrient concentration was optimized using bioinspired models with firefly algorithm optimal result of 204.1 mg/L for nitrate, 238.15 mg/L for phosphate, and 158.08 mg/L for potassium. It was verified that lettuce seedlings can endure highly concentrated nutrients, however, it is more sensitive to phosphate as this macronutrient significantly promotes root growth with the increased whorl number on white light spectrum exposure with cold stratification.

No abstract

The arising problem on food scarcity drives the innovation of urban farming. One of the methods in urban farming is the smart aquaponics. However, for a smart aquaponics to yield crops successfully, it needs intensive monitoring, control, and automation. An efficient way of implementing this is the utilization of vision systems and machine learning algorithms to optimize the capabilities of the farming technique. To realize this, a comparative analysis of three machine learning estimators: Logistic Regression (LR), K-Nearest Neighbor (KNN), and Linear Support Vector Machine (L-SVM) was conducted. This was done by modeling each algorithm from the machine vision-feature extracted images of lettuce which were raised in a smart aquaponics setup. Each of the model was optimized to increase cross and hold-out validations. The results showed that KNN having the tuned hyperparameters of n_neighbors=24, weights='distance', algorithm='auto', leaf_size = 10 was the most effective model for the given dataset, yielding a cross-validation mean accuracy of 87.06% and a classification accuracy of 91.67%.

No abstract

No abstract

No abstract