Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm
Chimonanthus praecox is a famous traditional flower in China with high ornamental value. It has numerous varieties, yet its classification is highly disorganized. The distinctness, uniformity, and stability (DUS) test enables the classification and nomenclature of various species; thus, it can be us...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-01-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1328603/full |
_version_ | 1797352596444282880 |
---|---|
author | Ting Zhu Yaoyao Feng Xiaoxuan Dong Ximeng Yang Bin Liu Puying Yuan Xingrong Song Shanxiong Chen Shunzhao Sui |
author_facet | Ting Zhu Yaoyao Feng Xiaoxuan Dong Ximeng Yang Bin Liu Puying Yuan Xingrong Song Shanxiong Chen Shunzhao Sui |
author_sort | Ting Zhu |
collection | DOAJ |
description | Chimonanthus praecox is a famous traditional flower in China with high ornamental value. It has numerous varieties, yet its classification is highly disorganized. The distinctness, uniformity, and stability (DUS) test enables the classification and nomenclature of various species; thus, it can be used to classify the Chimonanthus varieties. In this study, flower traits were quantified using an automatic system based on pattern recognition instead of traditional manual measurement to improve the efficiency of DUS testing. A total of 42 features were quantified, including 28 features in the DUS guidelines and 14 new features proposed in this study. Eight algorithms were used to classify wintersweet, and the random forest (RF) algorithm performed the best when all features were used. The classification accuracy of the outer perianth was the highest when the features of the different parts were used for classification. A genetic algorithm was used as the feature selection algorithm to select a set of 22 reduced core features and improve the accuracy and efficiency of the classification. Using the core feature set, the classification accuracy of the RF model improved to 99.13%. Finally, K-means was used to construct a pedigree cluster tree of 23 varieties of wintersweet; evidently, wintersweet was clustered into a single class, which can be the basis for further study of genetic relationships among varieties. This study provides a novel method for DUS detection, variety identification, and pedigree analysis. |
first_indexed | 2024-03-08T13:19:10Z |
format | Article |
id | doaj.art-f46b8ac3978e4b06810cf9331a13b486 |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-03-08T13:19:10Z |
publishDate | 2024-01-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-f46b8ac3978e4b06810cf9331a13b4862024-01-18T04:29:48ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-01-011410.3389/fpls.2023.13286031328603Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithmTing Zhu0Yaoyao Feng1Xiaoxuan Dong2Ximeng Yang3Bin Liu4Puying Yuan5Xingrong Song6Shanxiong Chen7Shunzhao Sui8Chongqing Engineering Research Center for Floriculture, Key Laboratory of Agricultural Biosafety and Green Production of Upper Yangtze River (Ministry of Education), College of Horticulture and Landscape Architecture, Southwest University, Chongqing, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, ChinaChongqing Engineering Research Center for Floriculture, Key Laboratory of Agricultural Biosafety and Green Production of Upper Yangtze River (Ministry of Education), College of Horticulture and Landscape Architecture, Southwest University, Chongqing, ChinaChongqing Engineering Research Center for Floriculture, Key Laboratory of Agricultural Biosafety and Green Production of Upper Yangtze River (Ministry of Education), College of Horticulture and Landscape Architecture, Southwest University, Chongqing, ChinaGarden and Flower Research Center, Horticultural Research Institute of Sichuan Academy of Agricultural Science, Chengdu, ChinaGarden and Flower Research Center, Horticultural Research Institute of Sichuan Academy of Agricultural Science, Chengdu, ChinaCollege of Computer and Information Science, Southwest University, Chongqing, ChinaChongqing Engineering Research Center for Floriculture, Key Laboratory of Agricultural Biosafety and Green Production of Upper Yangtze River (Ministry of Education), College of Horticulture and Landscape Architecture, Southwest University, Chongqing, ChinaChimonanthus praecox is a famous traditional flower in China with high ornamental value. It has numerous varieties, yet its classification is highly disorganized. The distinctness, uniformity, and stability (DUS) test enables the classification and nomenclature of various species; thus, it can be used to classify the Chimonanthus varieties. In this study, flower traits were quantified using an automatic system based on pattern recognition instead of traditional manual measurement to improve the efficiency of DUS testing. A total of 42 features were quantified, including 28 features in the DUS guidelines and 14 new features proposed in this study. Eight algorithms were used to classify wintersweet, and the random forest (RF) algorithm performed the best when all features were used. The classification accuracy of the outer perianth was the highest when the features of the different parts were used for classification. A genetic algorithm was used as the feature selection algorithm to select a set of 22 reduced core features and improve the accuracy and efficiency of the classification. Using the core feature set, the classification accuracy of the RF model improved to 99.13%. Finally, K-means was used to construct a pedigree cluster tree of 23 varieties of wintersweet; evidently, wintersweet was clustered into a single class, which can be the basis for further study of genetic relationships among varieties. This study provides a novel method for DUS detection, variety identification, and pedigree analysis.https://www.frontiersin.org/articles/10.3389/fpls.2023.1328603/fullwintersweetDUS testfeature selectiongenetic algorithmcore feature |
spellingShingle | Ting Zhu Yaoyao Feng Xiaoxuan Dong Ximeng Yang Bin Liu Puying Yuan Xingrong Song Shanxiong Chen Shunzhao Sui Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm Frontiers in Plant Science wintersweet DUS test feature selection genetic algorithm core feature |
title | Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm |
title_full | Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm |
title_fullStr | Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm |
title_full_unstemmed | Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm |
title_short | Optimizing DUS testing for Chimonanthus praecox using feature selection based on a genetic algorithm |
title_sort | optimizing dus testing for chimonanthus praecox using feature selection based on a genetic algorithm |
topic | wintersweet DUS test feature selection genetic algorithm core feature |
url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1328603/full |
work_keys_str_mv | AT tingzhu optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT yaoyaofeng optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT xiaoxuandong optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT ximengyang optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT binliu optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT puyingyuan optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT xingrongsong optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT shanxiongchen optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm AT shunzhaosui optimizingdustestingforchimonanthuspraecoxusingfeatureselectionbasedonageneticalgorithm |