Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm

Ting Zhu, Yaoyao Feng, Xiaoxuan Dong, Ximeng Yang, Bin Liu, Puying Yuan, Xingrong Song, Shanxiong Chen, Shunzhao Sui · 2024

Read Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm by Ting Zhu, Yaoyao Feng, Xiaoxuan Dong, Ximeng Yang, Bin Liu, Puying Yuan, Xingrong Song, Shanxiong Chen, Shunzhao Sui (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10835806.txt.

Description

Ting Zhu, Yaoyao Feng, Xiaoxuan Dong, and a wider team wrote this research paper, published in 2024. It streamlines the official variety test for wintersweet, a beloved Chinese flower with a tangle of named varieties, using machine vision and a genetic algorithm to pick the traits that matter.

Variety certification checks distinctness, uniformity, and stability, normally by hand. The team measured forty-two flower traits automatically with pattern recognition, including fourteen new ones. Eight classifiers competed; random forest won, and the outer petals alone carried the strongest signal. A genetic search then trimmed the list to twenty-two core traits, lifting accuracy to just over ninety-nine percent. Clustering on those traits drew a family tree of twenty-three varieties. The authors say the trimmed test is faster and sharper for breeders registering new wintersweets.

Catalog record

CREATORTing Zhu, Yaoyao Feng, Xiaoxuan Dong, Ximeng Yang, Bin Liu, Puying Yuan, Xingrong Song, Shanxiong Chen, Shunzhao Sui
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE49 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10835806

Browse the full library · About the Tower of Babel