Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques
The quality control for fruit maturity inspection is a key issue in fruit packaging and international trade. The quantification of Soluble Solids (SS) in fruits gives a good approximation of the total sugar concentration at the ripe stage, and on the other hand, SS alone or in combination with acidi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/16/6081 |
| _version_ | 1797408028189786112 |
|---|---|
| author | Pedro Escárate Gonzalo Farias Paulina Naranjo Juan Pablo Zoffoli |
| author_facet | Pedro Escárate Gonzalo Farias Paulina Naranjo Juan Pablo Zoffoli |
| author_sort | Pedro Escárate |
| collection | DOAJ |
| description | The quality control for fruit maturity inspection is a key issue in fruit packaging and international trade. The quantification of Soluble Solids (SS) in fruits gives a good approximation of the total sugar concentration at the ripe stage, and on the other hand, SS alone or in combination with acidity is highly related to the acceptability of the fruit by consumers. The non-destructive analysis based on Visible (VIS) and Near-Infrared (NIR) spectroscopy has become a popular technique for the assessment of fruit quality. To improve the accuracy of fruit maturity inspection, VIS–NIR spectra models based on machine learning techniques are proposed for the non-destructive evaluation of soluble solids in considering a range of variations associated with varieties of stones fruit species (peach, nectarine, and plum). In this work, we propose a novel approach based on a Convolutional Neural Network (CNN) for the classification of the fruits into species and then a Feedforward Neural Network (FNN) to extract the information of VIS–NIR spectra to estimate the SS content of the fruit associated to several varieties. A classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> was obtained for the CNN classification model and a correlation coefficient of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>R</mi><mi>c</mi></msub><mo>></mo><mn>0.7109</mn></mrow></semantics></math></inline-formula> for the SS estimation of the FNN models was obtained. The results reported show the potential of this method for a fast and on-line classification of fruits and estimation of SS concentration. |
| first_indexed | 2024-03-09T03:51:22Z |
| format | Article |
| id | doaj.art-51be2501c48a4ee09063f0522ada6c90 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:51:22Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-51be2501c48a4ee09063f0522ada6c902023-12-03T14:26:16ZengMDPI AGSensors1424-82202022-08-012216608110.3390/s22166081Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning TechniquesPedro Escárate0Gonzalo Farias1Paulina Naranjo2Juan Pablo Zoffoli3Escuela de Ingeniería Eléctrica, Facultad de Ingeniería, Pontificia Universidad Católica de Valparaíso, Valparaiso 2374631, ChileEscuela de Ingeniería Eléctrica, Facultad de Ingeniería, Pontificia Universidad Católica de Valparaíso, Valparaiso 2374631, ChileDepartamento de Fruticultura y Enología, Facultad de Agronomía e Ingeniería Forestal, Pontificia Universidad Católica de Chile, Santiago 8331150, ChileDepartamento de Fruticultura y Enología, Facultad de Agronomía e Ingeniería Forestal, Pontificia Universidad Católica de Chile, Santiago 8331150, ChileThe quality control for fruit maturity inspection is a key issue in fruit packaging and international trade. The quantification of Soluble Solids (SS) in fruits gives a good approximation of the total sugar concentration at the ripe stage, and on the other hand, SS alone or in combination with acidity is highly related to the acceptability of the fruit by consumers. The non-destructive analysis based on Visible (VIS) and Near-Infrared (NIR) spectroscopy has become a popular technique for the assessment of fruit quality. To improve the accuracy of fruit maturity inspection, VIS–NIR spectra models based on machine learning techniques are proposed for the non-destructive evaluation of soluble solids in considering a range of variations associated with varieties of stones fruit species (peach, nectarine, and plum). In this work, we propose a novel approach based on a Convolutional Neural Network (CNN) for the classification of the fruits into species and then a Feedforward Neural Network (FNN) to extract the information of VIS–NIR spectra to estimate the SS content of the fruit associated to several varieties. A classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>98.9</mn><mo>%</mo></mrow></semantics></math></inline-formula> was obtained for the CNN classification model and a correlation coefficient of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>R</mi><mi>c</mi></msub><mo>></mo><mn>0.7109</mn></mrow></semantics></math></inline-formula> for the SS estimation of the FNN models was obtained. The results reported show the potential of this method for a fast and on-line classification of fruits and estimation of SS concentration.https://www.mdpi.com/1424-8220/22/16/6081stone fruitsfruit qualitysoluble solidsnear infrared spectravisible spectraconvolutional neural networks |
| spellingShingle | Pedro Escárate Gonzalo Farias Paulina Naranjo Juan Pablo Zoffoli Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques Sensors stone fruits fruit quality soluble solids near infrared spectra visible spectra convolutional neural networks |
| title | Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques |
| title_full | Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques |
| title_fullStr | Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques |
| title_full_unstemmed | Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques |
| title_short | Estimation of Soluble Solids for Stone Fruit Varieties Based on Near-Infrared Spectra Using Machine Learning Techniques |
| title_sort | estimation of soluble solids for stone fruit varieties based on near infrared spectra using machine learning techniques |
| topic | stone fruits fruit quality soluble solids near infrared spectra visible spectra convolutional neural networks |
| url | https://www.mdpi.com/1424-8220/22/16/6081 |
| work_keys_str_mv | AT pedroescarate estimationofsolublesolidsforstonefruitvarietiesbasedonnearinfraredspectrausingmachinelearningtechniques AT gonzalofarias estimationofsolublesolidsforstonefruitvarietiesbasedonnearinfraredspectrausingmachinelearningtechniques AT paulinanaranjo estimationofsolublesolidsforstonefruitvarietiesbasedonnearinfraredspectrausingmachinelearningtechniques AT juanpablozoffoli estimationofsolublesolidsforstonefruitvarietiesbasedonnearinfraredspectrausingmachinelearningtechniques |