Mango varietal discrimination using hyperspectral imaging and machine learning
Mango is a highly diverse tropical fruit with numerous varieties that differ in flavor, texture, and chemical composition. Consequently, identifying fraudulent substitutions of mango varieties poses a significant challenge using traditional techniques. Therefore, there is an increasing need for new...
| Main Authors: | , , , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | Inglés |
| Published: |
Springer Nature
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/20.500.12955/2587 https://doi.org/10.1007/s00521-024-10218-x |
| _version_ | 1855028845656145920 |
|---|---|
| author | Castro, Wilson Tene, Baldemar Castro, Jorge Guivin, Alex Ruesta Campoverde, Nelson Asdrubal Avila George, Himer |
| author_browse | Avila George, Himer Castro, Jorge Castro, Wilson Guivin, Alex Ruesta Campoverde, Nelson Asdrubal Tene, Baldemar |
| author_facet | Castro, Wilson Tene, Baldemar Castro, Jorge Guivin, Alex Ruesta Campoverde, Nelson Asdrubal Avila George, Himer |
| author_sort | Castro, Wilson |
| collection | Repositorio INIA |
| description | Mango is a highly diverse tropical fruit with numerous varieties that differ in flavor, texture, and chemical composition. Consequently, identifying fraudulent substitutions of mango varieties poses a significant challenge using traditional techniques. Therefore, there is an increasing need for new methods to discriminate between mango varieties. Hyperspectral imaging coupled with machine learning techniques presents a promising approach for varietal discrimination. In this study, mango samples of eleven varieties were collected from a germplasm bank, with four slices obtained from each sample. Hyperspectral images were acquired in the Vis–NIR and NIR ranges for each slice, and spectral profiles were extracted and pretreated. Three discrimination models, linear discriminant analysis, K-nearest neighbor, and artificial neural networks, were implemented and validated using relevant wavelengths selected through a covering array feature selection algorithm. The performance of these models was evaluated using precision, accuracy, and F-score metrics. The average spectral profiles of the studied varieties exhibited a similar behavior with slight differences, which could be used for classification within the evaluated ranges. The optimal number of variables selected to refine the models was 17 for the UV–Vis–NIR range and 21 for the NIR range, with an accuracy ranging between 0.752 and 0.972. This study concludes that hyperspectral imaging combined with machine learning techniques can effectively discriminate between different varieties of mango. |
| format | info:eu-repo/semantics/article |
| id | INIA2587 |
| institution | Institucional Nacional de Innovación Agraria |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | Springer Nature |
| publisherStr | Springer Nature |
| record_format | dspace |
| spelling | INIA25872024-09-30T19:02:03Z Mango varietal discrimination using hyperspectral imaging and machine learning Castro, Wilson Tene, Baldemar Castro, Jorge Guivin, Alex Ruesta Campoverde, Nelson Asdrubal Avila George, Himer ANN Classification Hyperspectral imaging KNN LDA Machine learning Mango https://purl.org/pe-repo/ocde/ford#4.01.01 Espectroscopia Spectroscopy Machine learning Aprendizaje automático Mangifera indica Mango is a highly diverse tropical fruit with numerous varieties that differ in flavor, texture, and chemical composition. Consequently, identifying fraudulent substitutions of mango varieties poses a significant challenge using traditional techniques. Therefore, there is an increasing need for new methods to discriminate between mango varieties. Hyperspectral imaging coupled with machine learning techniques presents a promising approach for varietal discrimination. In this study, mango samples of eleven varieties were collected from a germplasm bank, with four slices obtained from each sample. Hyperspectral images were acquired in the Vis–NIR and NIR ranges for each slice, and spectral profiles were extracted and pretreated. Three discrimination models, linear discriminant analysis, K-nearest neighbor, and artificial neural networks, were implemented and validated using relevant wavelengths selected through a covering array feature selection algorithm. The performance of these models was evaluated using precision, accuracy, and F-score metrics. The average spectral profiles of the studied varieties exhibited a similar behavior with slight differences, which could be used for classification within the evaluated ranges. The optimal number of variables selected to refine the models was 17 for the UV–Vis–NIR range and 21 for the NIR range, with an accuracy ranging between 0.752 and 0.972. This study concludes that hyperspectral imaging combined with machine learning techniques can effectively discriminate between different varieties of mango. 2024-09-30T19:02:01Z 2024-09-30T19:02:01Z 2024-07-29 info:eu-repo/semantics/article Castro, W.; Tene, B.; Castro, J.; Guivin, A.; Ruesta-Campoverde, N.A.; Avila-George, H. (2024). Mango varietal discrimination using hyperspectral imaging and machine learning. Neural computing and applications, 36, 18693-18703. doi:10.1007/s00521-024-10218-x 1433-3058 https://hdl.handle.net/20.500.12955/2587 https://doi.org/10.1007/s00521-024-10218-x eng urn:issn:1433-3058 Neural computing and applications info:eu-repo/semantics/restrictedAccess application/pdf Springer Nature GB Instituto Nacional de Innovación Agraria Repositorio Institucional - INIA |
| spellingShingle | ANN Classification Hyperspectral imaging KNN LDA Machine learning Mango https://purl.org/pe-repo/ocde/ford#4.01.01 Espectroscopia Spectroscopy Machine learning Aprendizaje automático Mangifera indica Castro, Wilson Tene, Baldemar Castro, Jorge Guivin, Alex Ruesta Campoverde, Nelson Asdrubal Avila George, Himer Mango varietal discrimination using hyperspectral imaging and machine learning |
| title | Mango varietal discrimination using hyperspectral imaging and machine learning |
| title_full | Mango varietal discrimination using hyperspectral imaging and machine learning |
| title_fullStr | Mango varietal discrimination using hyperspectral imaging and machine learning |
| title_full_unstemmed | Mango varietal discrimination using hyperspectral imaging and machine learning |
| title_short | Mango varietal discrimination using hyperspectral imaging and machine learning |
| title_sort | mango varietal discrimination using hyperspectral imaging and machine learning |
| topic | ANN Classification Hyperspectral imaging KNN LDA Machine learning Mango https://purl.org/pe-repo/ocde/ford#4.01.01 Espectroscopia Spectroscopy Machine learning Aprendizaje automático Mangifera indica |
| url | https://hdl.handle.net/20.500.12955/2587 https://doi.org/10.1007/s00521-024-10218-x |
| work_keys_str_mv | AT castrowilson mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning AT tenebaldemar mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning AT castrojorge mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning AT guivinalex mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning AT ruestacampoverdenelsonasdrubal mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning AT avilageorgehimer mangovarietaldiscriminationusinghyperspectralimagingandmachinelearning |