Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy
Stone cells are a distinctive characteristic of pears and their formation negatively affects the quality of the fruit. To evaluate the stone cell content (SCC) of Korla fragrant pears, we developed a Vis/NIR spectroscopy system that allowed for the adjustment of the illuminating angle. The successiv...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/11/16/2391 |
| _version_ | 1797410249266692096 |
|---|---|
| author | Tongzhao Wang Yixiao Zhang Yuanyuan Liu Zhijuan Zhang Tongbin Yan |
| author_facet | Tongzhao Wang Yixiao Zhang Yuanyuan Liu Zhijuan Zhang Tongbin Yan |
| author_sort | Tongzhao Wang |
| collection | DOAJ |
| description | Stone cells are a distinctive characteristic of pears and their formation negatively affects the quality of the fruit. To evaluate the stone cell content (SCC) of Korla fragrant pears, we developed a Vis/NIR spectroscopy system that allowed for the adjustment of the illuminating angle. The successive projective algorithm (SPA) and the Monte Carlo uninformative variable elimination (MCUVE) based on the sampling algorithm were used to select characteristic wavelengths. The particle swarm optimization (PSO) algorithm was used to optimize the combination of penalty factor C and kernel function parameter g. Support vector regression (SVR) was used to construct the evaluation model of the SCC. The SCC of the calibration set ranged from 0.240% to 0.657% and that of the validation set ranged from 0.315% to 0.652%. The SPA and MCUVE were used to optimize 57 and 83 characteristic wavelengths, respectively. The combinations of C and g were (6.2561, 0.2643) and (2.5133, 0.1128), respectively, when different characteristic wavelengths were used as inputs of SVR, indicating that the first combination had good generalization ability. The correlation coefficients of the SPA-SVR model after pre-processing the standardized normal variate (SNV) for both sets were 0.966 and 0.951, respectively. These results show that the SNV-SPA-SVR model satisfied the requirements of intelligent evaluation of SCC in Korla fragrant pears. |
| first_indexed | 2024-03-09T04:27:11Z |
| format | Article |
| id | doaj.art-cd77dd40d76f46798723cccd1928112f |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-09T04:27:11Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-cd77dd40d76f46798723cccd1928112f2023-12-03T13:39:12ZengMDPI AGFoods2304-81582022-08-011116239110.3390/foods11162391Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection SpectroscopyTongzhao Wang0Yixiao Zhang1Yuanyuan Liu2Zhijuan Zhang3Tongbin Yan4Agricultural Engineering Key Laboratory, Department of Xinjiang Uygur Autonomous Region, University of Education, Alar 843300, ChinaAgricultural Engineering Key Laboratory, Department of Xinjiang Uygur Autonomous Region, University of Education, Alar 843300, ChinaAgricultural Engineering Key Laboratory, Department of Xinjiang Uygur Autonomous Region, University of Education, Alar 843300, ChinaAgricultural Engineering Key Laboratory, Department of Xinjiang Uygur Autonomous Region, University of Education, Alar 843300, ChinaAgricultural Engineering Key Laboratory, Department of Xinjiang Uygur Autonomous Region, University of Education, Alar 843300, ChinaStone cells are a distinctive characteristic of pears and their formation negatively affects the quality of the fruit. To evaluate the stone cell content (SCC) of Korla fragrant pears, we developed a Vis/NIR spectroscopy system that allowed for the adjustment of the illuminating angle. The successive projective algorithm (SPA) and the Monte Carlo uninformative variable elimination (MCUVE) based on the sampling algorithm were used to select characteristic wavelengths. The particle swarm optimization (PSO) algorithm was used to optimize the combination of penalty factor C and kernel function parameter g. Support vector regression (SVR) was used to construct the evaluation model of the SCC. The SCC of the calibration set ranged from 0.240% to 0.657% and that of the validation set ranged from 0.315% to 0.652%. The SPA and MCUVE were used to optimize 57 and 83 characteristic wavelengths, respectively. The combinations of C and g were (6.2561, 0.2643) and (2.5133, 0.1128), respectively, when different characteristic wavelengths were used as inputs of SVR, indicating that the first combination had good generalization ability. The correlation coefficients of the SPA-SVR model after pre-processing the standardized normal variate (SNV) for both sets were 0.966 and 0.951, respectively. These results show that the SNV-SPA-SVR model satisfied the requirements of intelligent evaluation of SCC in Korla fragrant pears.https://www.mdpi.com/2304-8158/11/16/2391successive projective algorithmuninformative variable eliminationsupport vector regressionKorla fragrant pearstone cell contentintelligent evaluation |
| spellingShingle | Tongzhao Wang Yixiao Zhang Yuanyuan Liu Zhijuan Zhang Tongbin Yan Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy Foods successive projective algorithm uninformative variable elimination support vector regression Korla fragrant pear stone cell content intelligent evaluation |
| title | Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy |
| title_full | Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy |
| title_fullStr | Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy |
| title_full_unstemmed | Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy |
| title_short | Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy |
| title_sort | intelligent evaluation of stone cell content of korla fragrant pears by vis nir reflection spectroscopy |
| topic | successive projective algorithm uninformative variable elimination support vector regression Korla fragrant pear stone cell content intelligent evaluation |
| url | https://www.mdpi.com/2304-8158/11/16/2391 |
| work_keys_str_mv | AT tongzhaowang intelligentevaluationofstonecellcontentofkorlafragrantpearsbyvisnirreflectionspectroscopy AT yixiaozhang intelligentevaluationofstonecellcontentofkorlafragrantpearsbyvisnirreflectionspectroscopy AT yuanyuanliu intelligentevaluationofstonecellcontentofkorlafragrantpearsbyvisnirreflectionspectroscopy AT zhijuanzhang intelligentevaluationofstonecellcontentofkorlafragrantpearsbyvisnirreflectionspectroscopy AT tongbinyan intelligentevaluationofstonecellcontentofkorlafragrantpearsbyvisnirreflectionspectroscopy |