Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data
In this study, visible-near-infrared (VIS-NIR) hyperspectral imaging was combined with a data fusion strategy for the nondestructive assessment of the starch content in intact potatoes. Spectral and textural data were extracted from hyperspectral images and transformed principal component (PC) image...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/11/19/3133 |
| _version_ | 1797479329413726208 |
|---|---|
| author | Fuxiang Wang Chunguang Wang |
| author_facet | Fuxiang Wang Chunguang Wang |
| author_sort | Fuxiang Wang |
| collection | DOAJ |
| description | In this study, visible-near-infrared (VIS-NIR) hyperspectral imaging was combined with a data fusion strategy for the nondestructive assessment of the starch content in intact potatoes. Spectral and textural data were extracted from hyperspectral images and transformed principal component (PC) images, respectively, and a partial least squares regression (PLSR) prediction model was then established. The results revealed that low-level data fusion could not improve accuracy in predicting starch content. Therefore, to improve prediction accuracy, key variables were selected from the spectral and textural data through competitive adaptive reweighted sampling (CARS) and correlation analysis, respectively, and mid-level data fusion was performed. With a residual predictive deviation (RPD) value > 2, the established PLSR model achieved satisfactory prediction accuracy. Therefore, this study demonstrated that appropriate data fusion can effectively improve the prediction accuracy for starch content and thus aid the sorting of potato starch content in the production line. |
| first_indexed | 2024-03-09T21:44:18Z |
| format | Article |
| id | doaj.art-b34230a7a8af40849f49a3824d692e20 |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-09T21:44:18Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-b34230a7a8af40849f49a3824d692e202023-11-23T20:22:39ZengMDPI AGFoods2304-81582022-10-011119313310.3390/foods11193133Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural DataFuxiang Wang0Chunguang Wang1Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaMechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaIn this study, visible-near-infrared (VIS-NIR) hyperspectral imaging was combined with a data fusion strategy for the nondestructive assessment of the starch content in intact potatoes. Spectral and textural data were extracted from hyperspectral images and transformed principal component (PC) images, respectively, and a partial least squares regression (PLSR) prediction model was then established. The results revealed that low-level data fusion could not improve accuracy in predicting starch content. Therefore, to improve prediction accuracy, key variables were selected from the spectral and textural data through competitive adaptive reweighted sampling (CARS) and correlation analysis, respectively, and mid-level data fusion was performed. With a residual predictive deviation (RPD) value > 2, the established PLSR model achieved satisfactory prediction accuracy. Therefore, this study demonstrated that appropriate data fusion can effectively improve the prediction accuracy for starch content and thus aid the sorting of potato starch content in the production line.https://www.mdpi.com/2304-8158/11/19/3133hyperspectral imagingstarch contentpotatodata fusionpartial least squares regression |
| spellingShingle | Fuxiang Wang Chunguang Wang Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data Foods hyperspectral imaging starch content potato data fusion partial least squares regression |
| title | Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data |
| title_full | Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data |
| title_fullStr | Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data |
| title_full_unstemmed | Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data |
| title_short | Improved Model for Starch Prediction in Potato by the Fusion of Near-Infrared Spectral and Textural Data |
| title_sort | improved model for starch prediction in potato by the fusion of near infrared spectral and textural data |
| topic | hyperspectral imaging starch content potato data fusion partial least squares regression |
| url | https://www.mdpi.com/2304-8158/11/19/3133 |
| work_keys_str_mv | AT fuxiangwang improvedmodelforstarchpredictioninpotatobythefusionofnearinfraredspectralandtexturaldata AT chunguangwang improvedmodelforstarchpredictioninpotatobythefusionofnearinfraredspectralandtexturaldata |