Digital Commons Network^™

Prediction Of Strawberry Yield Based On Receptacle Detection And Bayesian Inference, Sunghyun Yoon, Jung Su Jo, Steven B. Kim, Ha Seon Sim, Sung Kyeom Kim, Dong Sub Kim

Mathematics and Statistics Faculty Publications and Presentations

The receptacle of strawberry is a more direct part than the flower for predicting yield as they eventually become fruits. Thus, we tried to predict the yield by combining an AI technique for receptacle detection in images and statistical analysis on the relationship between the number of receptacles detected and the strawberry yield over a period of time. Five major cultivars were cultivated to consider the cultivar characteristics and environmental factors for two years were collected to consider the climate difference. Faster R–CNN based object detector was used to estimate the number of receptacles per strawberry plant in given two-dimensional …

Shinycore: An R/Shiny Program For Establishing Core Collection Based On Single Nucleotide Polymorphism Data, Steven Kim, Dong Sub Kim, Hana Moyle, Seong Heo

Mathematics and Statistics Faculty Publications and Presentations

Background: Managing and investigating all available genetic resources are challenging. As an alternative, breeders and researchers use core collection—a representative subset of the entire collection. A good core is characterized by high genetic diversity and low repetitiveness. Among the several available software, GenoCore uses a coverage criterion that does not require computationally expensive distance-based metrics.

Results: ShinyCore is a new method to select a core collection through two phases. The first phase uses the coverage criterion to quickly attain a fixed coverage, and the second phase uses a newly devised score (referred to as the rarity score) to further enhance …

Estimating The Impact Of Environmental Management On Strawberry Yield Using Publicly Available Agricultural Data In South Korea, Steven Kim, Jung Su Jo, Vicky Luk, Sung Kyeom Kim, Dong Sub Kim

Mathematics and Statistics Faculty Publications and Presentations

Advanced information and communication technologies (ICTs) have made data collection more efficient for agricultural studies. Using publicly available database in South Korea, we estimated the relationship between the management of air temperature and relative humidity and the strawberry yield during two harvest seasons. Longitudinal data of multiple greenhouses were merged and processed, and mixed-effects models were applied to account both observed and unobserved factors across the greenhouses. The averages of air temperature and relative humidity inside each greenhouse do not take volatility of the time-varying variables into consideration, so we assessed the management of each greenhouse by the percent of …