Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model
Hyperspectral technology is used to obtain spectral and spatial information of samples simultaneously and demonstrates significant potential for use in seed purity identification. However, it has certain limitations, such as high acquisition cost and massive redundant information. This study integra...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4384 |
| _version_ | 1797411921904795648 |
|---|---|
| author | Weihua Liu Shan Zeng Guiju Wu Hao Li Feifei Chen |
| author_facet | Weihua Liu Shan Zeng Guiju Wu Hao Li Feifei Chen |
| author_sort | Weihua Liu |
| collection | DOAJ |
| description | Hyperspectral technology is used to obtain spectral and spatial information of samples simultaneously and demonstrates significant potential for use in seed purity identification. However, it has certain limitations, such as high acquisition cost and massive redundant information. This study integrates the advantages of the sparse feature of the least absolute shrinkage and selection operator (LASSO) algorithm and the classification feature of the logistic regression model (LRM). We propose a hyperspectral rice seed purity identification method based on the LASSO logistic regression model (LLRM). The feasibility of using LLRM for the selection of feature wavelength bands and seed purity identification are discussed using four types of rice seeds as research objects. The results of 13 different adulteration cases revealed that the value of the regularisation parameter was different in each case. The recognition accuracy of LLRM and average recognition accuracy were 91.67–100% and 98.47%, respectively. Furthermore, the recognition accuracy of full-band LRM was 71.60–100%. However, the average recognition accuracy was merely 89.63%. These results indicate that LLRM can select the feature wavelength bands stably and improve the recognition accuracy of rice seeds, demonstrating the feasibility of developing a hyperspectral technology with LLRM for seed purity identification. |
| first_indexed | 2024-03-09T04:52:17Z |
| format | Article |
| id | doaj.art-bd4230d11e0943c48febfbe273007ea5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:52:17Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bd4230d11e0943c48febfbe273007ea52023-12-03T13:09:13ZengMDPI AGSensors1424-82202021-06-012113438410.3390/s21134384Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression ModelWeihua Liu0Shan Zeng1Guiju Wu2Hao Li3Feifei Chen4School of Electric & Electronic Engineering, Wuhan Polytechnic University, Wuhan 430023, ChinaSchool of Mathematics & Computer Science, Wuhan Polytechnic University, Wuhan 430023, ChinaThe Key Laboratory of Earthquake Geodesy, Institute of Seismology, China Earthquake Administration, Wuhan 430023, ChinaSchool of Mathematics & Computer Science, Wuhan Polytechnic University, Wuhan 430023, ChinaSchool of Mathematics & Computer Science, Wuhan Polytechnic University, Wuhan 430023, ChinaHyperspectral technology is used to obtain spectral and spatial information of samples simultaneously and demonstrates significant potential for use in seed purity identification. However, it has certain limitations, such as high acquisition cost and massive redundant information. This study integrates the advantages of the sparse feature of the least absolute shrinkage and selection operator (LASSO) algorithm and the classification feature of the logistic regression model (LRM). We propose a hyperspectral rice seed purity identification method based on the LASSO logistic regression model (LLRM). The feasibility of using LLRM for the selection of feature wavelength bands and seed purity identification are discussed using four types of rice seeds as research objects. The results of 13 different adulteration cases revealed that the value of the regularisation parameter was different in each case. The recognition accuracy of LLRM and average recognition accuracy were 91.67–100% and 98.47%, respectively. Furthermore, the recognition accuracy of full-band LRM was 71.60–100%. However, the average recognition accuracy was merely 89.63%. These results indicate that LLRM can select the feature wavelength bands stably and improve the recognition accuracy of rice seeds, demonstrating the feasibility of developing a hyperspectral technology with LLRM for seed purity identification.https://www.mdpi.com/1424-8220/21/13/4384hyperspectral imagingLASSO logistic regression modelwavelength band selectiongrey-scale imageseed purity identification |
| spellingShingle | Weihua Liu Shan Zeng Guiju Wu Hao Li Feifei Chen Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model Sensors hyperspectral imaging LASSO logistic regression model wavelength band selection grey-scale image seed purity identification |
| title | Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model |
| title_full | Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model |
| title_fullStr | Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model |
| title_full_unstemmed | Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model |
| title_short | Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model |
| title_sort | rice seed purity identification technology using hyperspectral image with lasso logistic regression model |
| topic | hyperspectral imaging LASSO logistic regression model wavelength band selection grey-scale image seed purity identification |
| url | https://www.mdpi.com/1424-8220/21/13/4384 |
| work_keys_str_mv | AT weihualiu riceseedpurityidentificationtechnologyusinghyperspectralimagewithlassologisticregressionmodel AT shanzeng riceseedpurityidentificationtechnologyusinghyperspectralimagewithlassologisticregressionmodel AT guijuwu riceseedpurityidentificationtechnologyusinghyperspectralimagewithlassologisticregressionmodel AT haoli riceseedpurityidentificationtechnologyusinghyperspectralimagewithlassologisticregressionmodel AT feifeichen riceseedpurityidentificationtechnologyusinghyperspectralimagewithlassologisticregressionmodel |