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

被引:4
|
作者
Zhu, Ting [1 ]
Feng, Yaoyao [2 ]
Dong, Xiaoxuan [2 ]
Yang, Ximeng [1 ]
Liu, Bin [1 ]
Yuan, Puying [3 ]
Song, Xingrong [3 ]
Chen, Shanxiong [2 ]
Sui, Shunzhao [1 ]
机构
[1] Southwest Univ, Coll Hort & Landscape Architecture, Chongqing Engn Res Ctr Floriculture, Minist Educ,Key Lab Agr Biosafety & Green Prod Upp, Chongqing, Peoples R China
[2] Southwest Univ, Coll Comp & Informat Sci, Chongqing, Peoples R China
[3] Sichuan Acad Agr Sci, Garden & Flower Res Ctr, Hort Res Inst, Chengdu, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
wintersweet; DUS test; feature selection; genetic algorithm; core feature; ANT COLONY OPTIMIZATION; PROTECTION; VARIETIES; MARKERS;
D O I
10.3389/fpls.2023.1328603
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
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.
引用
收藏
页数:15
相关论文
共 50 条
  • [21] Feature selection using genetic algorithm and cluster validation
    Wu, Yi-Leh
    Tang, Cheng-Yuan
    Hor, Maw-Kae
    Wu, Pei-Fen
    EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (03) : 2727 - 2732
  • [22] Feature selection using guided population based genetic algorithm with modified crossover and parent selection
    Naskar, Anurup
    Ghosh, Soumyajit
    Kundu, Mahantapas
    Sarkar, Ram
    APPLIED SOFT COMPUTING, 2025, 172
  • [23] Feature selection based-on genetic algorithm for CBIR
    Zhao, Tianzhong
    Lu, Jianjiang
    Zhang, Yafei
    Xiao, Qi
    CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 2, PROCEEDINGS, 2008, : 495 - 499
  • [24] Feature Selection for Image Retrieval based on Genetic Algorithm
    Kushwaha, Preeti
    Welekar, R. R.
    INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE, 2016, 4 (02): : 16 - 21
  • [25] GENETIC ALGORITHM BASED FEATURE SELECTION FOR PARAPHRASE RECOGNITION
    Chitra, A.
    Rajkumar, Anupriya
    INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2013, 22 (02)
  • [26] Hybrid feature selection based on improved genetic algorithm
    Hu, B. (hubin@njau.edu.cn), 1725, Universitas Ahmad Dahlan (11):
  • [27] Optimizing Sequential Forward Selection on Classification Using Genetic Algorithm
    Chotchantarakun K.
    Informatica (Slovenia), 2023, 47 (09): : 81 - 90
  • [28] RESEARCH ON FEATURE SELECTION ALGORITHM BASED ON MUTUAL INFORMATION AND GENETIC ALGORITHM
    Tang, Pan-Shi
    Tang, Xiao-Long
    Tao, Zhong-Yu
    Li, Jian-Ping
    2014 11TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICCWAMTIP), 2014, : 403 - 406
  • [29] Feature selection of Emg signal based on ReliefF algorithm and genetic algorithm
    He T.
    Hu J.
    Xia P.
    Gu C.
    Shanghai Jiaotong Daxue Xuebao, 2 (204-208): : 204 - 208
  • [30] Research on Mutual Information Feature Selection Algorithm Based on Genetic Algorithm
    College of Computer Science and Technology, Changchun University of Science and Technology, Jilin, Changchun
    130022, China
    不详
    J. Comput., 6 (131-141): : 131 - 141