Identification of maize kernel varieties based on interpretable ensemble algorithms
IntroductionMaize kernel variety identification is crucial for reducing storage losses and ensuring food security. Traditional single models show limitations in processing large-scale multimodal data.MethodsThis study constructed an interpretable ensemble learning model for maize seed variety identi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2025.1511097/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856473427410944 |
|---|---|
| author | Chunguang Bi Chunguang Bi Xinhua Bi Jinjing Liu Hao Xie Shuo Zhang He Chen Mohan Wang Lei Shi Lei Shi Shaozhong Song |
| author_facet | Chunguang Bi Chunguang Bi Xinhua Bi Jinjing Liu Hao Xie Shuo Zhang He Chen Mohan Wang Lei Shi Lei Shi Shaozhong Song |
| author_sort | Chunguang Bi |
| collection | DOAJ |
| description | IntroductionMaize kernel variety identification is crucial for reducing storage losses and ensuring food security. Traditional single models show limitations in processing large-scale multimodal data.MethodsThis study constructed an interpretable ensemble learning model for maize seed variety identification through improved differential evolutionary algorithm and multimodal data fusion. Morphological and hyperspectral data of maize samples were extracted and preprocessed, and three methods were used to screen features, respectively. The base learner of the Stacking integration model was selected using diversity and performance indices, with parameters optimized through a differential evolution algorithm incorporating multiple mutation strategies and dynamic adjustment of mutation factors and recombination rates. Shapley Additive exPlanation was applied for interpretable ensemble learning.ResultsThe HDE-Stacking identification model achieved 97.78% accuracy. The spectral bands at 784 nm, 910 nm, 732 nm, 962 nm, and 666 nm showed positive impacts on identification results.DiscussionThis research provides a scientific basis for efficient identification of different corn kernel varieties, enhancing accuracy and traceability in germplasm resource management. The findings have significant practical value in agricultural production, improving quality management efficiency and contributing to food security assurance. |
| format | Article |
| id | doaj-art-07ab798067194832b368a91f1dd306e6 |
| institution | Kabale University |
| issn | 1664-462X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj-art-07ab798067194832b368a91f1dd306e62025-02-12T07:26:36ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-02-011610.3389/fpls.2025.15110971511097Identification of maize kernel varieties based on interpretable ensemble algorithmsChunguang Bi0Chunguang Bi1Xinhua Bi2Jinjing Liu3Hao Xie4Shuo Zhang5He Chen6Mohan Wang7Lei Shi8Lei Shi9Shaozhong Song10Institute for the Smart Agriculture, Jilin Agricultural University, ChangChun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaInstitute of Science and Technology, Changchun Humanities and Sciences College, Changchun, Jilin, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaJilin Zhongnong Sunshine Data Co., Changchun, ChinaInstitute for the Smart Agriculture, Jilin Agricultural University, ChangChun, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun, ChinaSchool of Data Science and Artificial Intelligence, Jilin Engineering Normal University, Changchun, ChinaIntroductionMaize kernel variety identification is crucial for reducing storage losses and ensuring food security. Traditional single models show limitations in processing large-scale multimodal data.MethodsThis study constructed an interpretable ensemble learning model for maize seed variety identification through improved differential evolutionary algorithm and multimodal data fusion. Morphological and hyperspectral data of maize samples were extracted and preprocessed, and three methods were used to screen features, respectively. The base learner of the Stacking integration model was selected using diversity and performance indices, with parameters optimized through a differential evolution algorithm incorporating multiple mutation strategies and dynamic adjustment of mutation factors and recombination rates. Shapley Additive exPlanation was applied for interpretable ensemble learning.ResultsThe HDE-Stacking identification model achieved 97.78% accuracy. The spectral bands at 784 nm, 910 nm, 732 nm, 962 nm, and 666 nm showed positive impacts on identification results.DiscussionThis research provides a scientific basis for efficient identification of different corn kernel varieties, enhancing accuracy and traceability in germplasm resource management. The findings have significant practical value in agricultural production, improving quality management efficiency and contributing to food security assurance.https://www.frontiersin.org/articles/10.3389/fpls.2025.1511097/fullmaize kernelvariety identificationstacking ensemble modelmultimodal datadifferential evolutionary algorithmSHAP value |
| spellingShingle | Chunguang Bi Chunguang Bi Xinhua Bi Jinjing Liu Hao Xie Shuo Zhang He Chen Mohan Wang Lei Shi Lei Shi Shaozhong Song Identification of maize kernel varieties based on interpretable ensemble algorithms Frontiers in Plant Science maize kernel variety identification stacking ensemble model multimodal data differential evolutionary algorithm SHAP value |
| title | Identification of maize kernel varieties based on interpretable ensemble algorithms |
| title_full | Identification of maize kernel varieties based on interpretable ensemble algorithms |
| title_fullStr | Identification of maize kernel varieties based on interpretable ensemble algorithms |
| title_full_unstemmed | Identification of maize kernel varieties based on interpretable ensemble algorithms |
| title_short | Identification of maize kernel varieties based on interpretable ensemble algorithms |
| title_sort | identification of maize kernel varieties based on interpretable ensemble algorithms |
| topic | maize kernel variety identification stacking ensemble model multimodal data differential evolutionary algorithm SHAP value |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2025.1511097/full |
| work_keys_str_mv | AT chunguangbi identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT chunguangbi identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT xinhuabi identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT jinjingliu identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT haoxie identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT shuozhang identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT hechen identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT mohanwang identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT leishi identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT leishi identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms AT shaozhongsong identificationofmaizekernelvarietiesbasedoninterpretableensemblealgorithms |