Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning
Mango is a very popular climacteric fruit in America and Europe. Among the internal properties of the mango, total soluble solids (TSS) are an adequate indicator to estimate the quality of mango, however, the measurement of this indicator requires destructive tests. Several research have addressed s...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | inglés |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | Descargar el archivo Enlace permanente (DOI o Handle) Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1881508991575523328 |
|---|---|
| author | Ernesto Paiva-Peredo Diego Gonzales-Rodriguez W. T. Herrera Juan J. Soria Diana Quispe-Arpasi Christian Ovalle |
| author_browse | Christian Ovalle Diana Quispe-Arpasi Diego Gonzales-Rodriguez Ernesto Paiva-Peredo Juan J. Soria W. T. Herrera |
| author_facet | Ernesto Paiva-Peredo Diego Gonzales-Rodriguez W. T. Herrera Juan J. Soria Diana Quispe-Arpasi Christian Ovalle |
| author_sort | Ernesto Paiva-Peredo |
| collection | Producción científica |
| description | Mango is a very popular climacteric fruit in America and Europe. Among the internal properties of the mango, total soluble solids (TSS) are an adequate indicator to estimate the quality of mango, however, the measurement of this indicator requires destructive tests. Several research have addressed similar issues; they have made use of pre-processing transformations without making it clear which of them is statistically better. Here, we created a new spectral database to build machine learning (ML) models. We analyzed a total of 18 principal component regression (PCR) models and 18 partial least squared regression (PLSR) models, where 4 types of transformations, 3 different feature extractors, and 3 different pre-processing techniques are combined. The research proposes a double cross validation (CV) both to determine the optimal number of components and to obtain the final metrics. The best model had a root mean square error (RMSE) of 1.1382 °Brix and a RMSE on the transformed scale of 0.5140. The best model used 4 components, used y2 transformation, reflectance R as the independent variable and MSC as a pre-processing technique. |
| format | Article |
| id | oai:cris.upeu.edu.pe:20.500.15037/515 |
| institution | UPeU |
| language | English |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| record_format | dspace |
| spelling | oai:cris.upeu.edu.pe:20.500.15037/5152026-10-30T16:14:40ZTransformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learningErnesto Paiva-PeredoDiego Gonzales-RodriguezW. T. HerreraJuan J. SoriaDiana Quispe-ArpasiChristian OvalleMean squared errorPrincipal component analysisPartial least squares regressionMathematicsFeature (linguistics)Transformation (genetics)Artificial intelligenceClimactericRegression analysisRegressionPattern recognition (psychology)StatisticsLinear regressionMachine learningComputer scienceChemistryBiologyPhilosophyLinguisticsBiochemistryGeneticsMenopauseGeneMean squared errorPrincipal component analysisPartial least squares regressionMathematicsFeature (linguistics)Transformation (genetics)Artificial intelligenceClimactericRegression analysisRegressionPattern recognition (psychology)StatisticsLinear regressionMachine learningComputer scienceChemistryBiologyPhysical Sciences Chemistry Analytical Chemistry Spectroscopy and Chemometric AnalysesLife Sciences Agricultural and Biological Sciences Plant Science Postharvest Quality and Shelf Life ManagementHealth Sciences Medicine Biochemistry Phytochemicals and Antioxidant ActivitiesMango is a very popular climacteric fruit in America and Europe. Among the internal properties of the mango, total soluble solids (TSS) are an adequate indicator to estimate the quality of mango, however, the measurement of this indicator requires destructive tests. Several research have addressed similar issues; they have made use of pre-processing transformations without making it clear which of them is statistically better. Here, we created a new spectral database to build machine learning (ML) models. We analyzed a total of 18 principal component regression (PCR) models and 18 partial least squared regression (PLSR) models, where 4 types of transformations, 3 different feature extractors, and 3 different pre-processing techniques are combined. The research proposes a double cross validation (CV) both to determine the optimal number of components and to obtain the final metrics. The best model had a root mean square error (RMSE) of 1.1382 °Brix and a RMSE on the transformed scale of 0.5140. The best model used 4 components, used y2 transformation, reflectance R as the independent variable and MSC as a pre-processing technique.Articlehttps://ijece.iaescore.com/index.php/IJECE/article/download/32956/17112https://doi.org/10.11591/ijece.v14i1.pp532-54610.11591/ijece.v14i1.pp532-546https://hdl.handle.net/20.500.15037/515W4388656549enInternational Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering2722-256X2722-25782023-11-142026-06-13T08:15:51Z2026-06-13T08:15:51Z |
| spellingShingle | Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Philosophy Linguistics Biochemistry Genetics Menopause Gene Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Physical Sciences Chemistry Analytical Chemistry Spectroscopy and Chemometric Analyses Life Sciences Agricultural and Biological Sciences Plant Science Postharvest Quality and Shelf Life Management Health Sciences Medicine Biochemistry Phytochemicals and Antioxidant Activities Ernesto Paiva-Peredo Diego Gonzales-Rodriguez W. T. Herrera Juan J. Soria Diana Quispe-Arpasi Christian Ovalle Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title | Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title_full | Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title_fullStr | Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title_full_unstemmed | Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title_short | Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| title_sort | transformations for non destructive evaluation of brix in mango by reflectance spectroscopy and machine learning |
| topic | Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Philosophy Linguistics Biochemistry Genetics Menopause Gene Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Physical Sciences Chemistry Analytical Chemistry Spectroscopy and Chemometric Analyses Life Sciences Agricultural and Biological Sciences Plant Science Postharvest Quality and Shelf Life Management Health Sciences Medicine Biochemistry Phytochemicals and Antioxidant Activities |
| topic_facet | Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Philosophy Linguistics Biochemistry Genetics Menopause Gene Mean squared error Principal component analysis Partial least squares regression Mathematics Feature (linguistics) Transformation (genetics) Artificial intelligence Climacteric Regression analysis Regression Pattern recognition (psychology) Statistics Linear regression Machine learning Computer science Chemistry Biology Physical Sciences Chemistry Analytical Chemistry Spectroscopy and Chemometric Analyses Life Sciences Agricultural and Biological Sciences Plant Science Postharvest Quality and Shelf Life Management Health Sciences Medicine Biochemistry Phytochemicals and Antioxidant Activities |
| url | https://ijece.iaescore.com/index.php/IJECE/article/download/32956/17112 https://doi.org/10.11591/ijece.v14i1.pp532-546 https://hdl.handle.net/20.500.15037/515 |
| work_keys_str_mv | AT ernestopaivaperedo transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning AT diegogonzalesrodriguez transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning AT wtherrera transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning AT juanjsoria transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning AT dianaquispearpasi transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning AT christianovalle transformationsfornondestructiveevaluationofbrixinmangobyreflectancespectroscopyandmachinelearning |