Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features
IntroductionDue to its favorable traits-such as lower lignin content, higher oil concentration, and increased protein levels-the genetic improvement of yellow-seeded rapeseed has attracted more attention than other rapeseed color variations. Traditionally, yellow-seeded rapeseed has been identified...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2024.1518205/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527851444076544 |
|---|---|
| author | Fan Liu Fang Wang Zaiqi Zhang Liang Cao Jinran Wu You-Gan Wang |
| author_facet | Fan Liu Fang Wang Zaiqi Zhang Liang Cao Jinran Wu You-Gan Wang |
| author_sort | Fan Liu |
| collection | DOAJ |
| description | IntroductionDue to its favorable traits-such as lower lignin content, higher oil concentration, and increased protein levels-the genetic improvement of yellow-seeded rapeseed has attracted more attention than other rapeseed color variations. Traditionally, yellow-seeded rapeseed has been identified visually, but the complex variability in the seed coat color of Brassica napus has made manual identification challenging and often inaccurate. Another method, using the RGB color system, is frequently employed but is sensitive to photographic conditions, including lighting and camera settings.MethodsWe present four data-driven models to identify yellow-seeded B. napus using hyperspectral features combined with simple yet intelligent techniques. One model employs partial least squares regression (PLSR) to predict the R, G, and B color channels, effectively distinguishing yellow-seeded varieties from others according to globally accepted yellow-seed classification protocols. Another model uses logistic regression (Logit-R) to produce a probability-based assessment of yellow-seeded status. Additionally, we implement two intelligent models, random forest and support vector classifier to evaluate features selected through lasso-penalized logistic regression.Results and DiscussionOur findings indicate significant recognition accuracies of 96.55% and 98% for the PLSR and Logit-R models, respectively, aligning closely with the accuracy of previous methods. This approach represents a meaningful advancement in identifying yellow-seeded rapeseed, with high recognition accuracy demonstrating the practical applicability of these models. |
| format | Article |
| id | doaj-art-bb283b93cc3a4af2919ef261c75d89e4 |
| institution | Kabale University |
| issn | 1664-8021 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj-art-bb283b93cc3a4af2919ef261c75d89e42025-01-15T06:10:34ZengFrontiers Media S.A.Frontiers in Genetics1664-80212025-01-011510.3389/fgene.2024.15182051518205Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral featuresFan Liu0Fang Wang1Zaiqi Zhang2Liang Cao3Jinran Wu4You-Gan Wang5Hunan Provincial Key Laboratory of Dong Medicine, Hunan University of Medicine, Huaihua, ChinaKey Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering, Xiangtan University, Xiangtan, ChinaHunan Provincial Key Laboratory of Dong Medicine, Hunan University of Medicine, Huaihua, ChinaHunan Provincial Key Laboratory of Dong Medicine, Hunan University of Medicine, Huaihua, ChinaSchool of Mathematics and Physics, The University of Queensland, Brisbane, QLD, AustraliaSchool of Mathematics and Physics, The University of Queensland, Brisbane, QLD, AustraliaIntroductionDue to its favorable traits-such as lower lignin content, higher oil concentration, and increased protein levels-the genetic improvement of yellow-seeded rapeseed has attracted more attention than other rapeseed color variations. Traditionally, yellow-seeded rapeseed has been identified visually, but the complex variability in the seed coat color of Brassica napus has made manual identification challenging and often inaccurate. Another method, using the RGB color system, is frequently employed but is sensitive to photographic conditions, including lighting and camera settings.MethodsWe present four data-driven models to identify yellow-seeded B. napus using hyperspectral features combined with simple yet intelligent techniques. One model employs partial least squares regression (PLSR) to predict the R, G, and B color channels, effectively distinguishing yellow-seeded varieties from others according to globally accepted yellow-seed classification protocols. Another model uses logistic regression (Logit-R) to produce a probability-based assessment of yellow-seeded status. Additionally, we implement two intelligent models, random forest and support vector classifier to evaluate features selected through lasso-penalized logistic regression.Results and DiscussionOur findings indicate significant recognition accuracies of 96.55% and 98% for the PLSR and Logit-R models, respectively, aligning closely with the accuracy of previous methods. This approach represents a meaningful advancement in identifying yellow-seeded rapeseed, with high recognition accuracy demonstrating the practical applicability of these models.https://www.frontiersin.org/articles/10.3389/fgene.2024.1518205/fullrapeseed (Brassica napus)yellow-seededhyperspectral featurelogistic regressionpartial least squares regressionmachine learning |
| spellingShingle | Fan Liu Fang Wang Zaiqi Zhang Liang Cao Jinran Wu You-Gan Wang Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features Frontiers in Genetics rapeseed (Brassica napus) yellow-seeded hyperspectral feature logistic regression partial least squares regression machine learning |
| title | Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features |
| title_full | Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features |
| title_fullStr | Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features |
| title_full_unstemmed | Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features |
| title_short | Classical and machine learning tools for identifying yellow-seeded Brassica napus by fusion of hyperspectral features |
| title_sort | classical and machine learning tools for identifying yellow seeded brassica napus by fusion of hyperspectral features |
| topic | rapeseed (Brassica napus) yellow-seeded hyperspectral feature logistic regression partial least squares regression machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2024.1518205/full |
| work_keys_str_mv | AT fanliu classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures AT fangwang classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures AT zaiqizhang classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures AT liangcao classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures AT jinranwu classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures AT youganwang classicalandmachinelearningtoolsforidentifyingyellowseededbrassicanapusbyfusionofhyperspectralfeatures |