Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods
This paper develops a rapid method for discriminating the geographical origins and age of roasted Torreya grandis seeds by near infrared (NIR) spectroscopic analysis and pattern recognition. 337 samples were collected from three main producing areas and produced in the last two years. The objective...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Journal of Spectroscopy |
| Online Access: | http://dx.doi.org/10.1155/2013/468509 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559844402397184 |
|---|---|
| author | Lu Xu Si-Min Yan Chen-Bo Cai Wei Zhong Xiao-Ping Yu |
| author_facet | Lu Xu Si-Min Yan Chen-Bo Cai Wei Zhong Xiao-Ping Yu |
| author_sort | Lu Xu |
| collection | DOAJ |
| description | This paper develops a rapid method for discriminating the geographical origins and age of roasted Torreya grandis seeds by near infrared (NIR) spectroscopic analysis and pattern recognition. 337 samples were collected from three main producing areas and produced in the last two years. The objective of geographical origins analysis is to discriminate the seeds from Fengqiao with a protected geographical indication (PGI) from those of another two provinces. Age classification is aimed to detect the old seeds produced in the last year from the freshly produced ones. Partial least squares discriminant analysis (PLSDA) was used to develop classification models, and the influence of data preprocessing methods on classification performance was also investigated. Taking second-order derivatives of the raw spectra proves to be the most proper and effective preprocessing method, which can remove baselines and backgrounds and reduce model complexity. With second derivative spectra, the sensitivity and specificity were 0.939 and 0.871 for age discrimination, respectively. Perfect classification was obtained, and both sensitivity and specificity were 1 for discrimination of geographical origins. |
| format | Article |
| id | doaj-art-94fd98c8e0e3462181f8490349647285 |
| institution | Kabale University |
| issn | 2314-4920 2314-4939 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Spectroscopy |
| spelling | doaj-art-94fd98c8e0e3462181f84903496472852025-02-03T01:29:09ZengWileyJournal of Spectroscopy2314-49202314-49392013-01-01201310.1155/2013/468509468509Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition MethodsLu Xu0Si-Min Yan1Chen-Bo Cai2Wei Zhong3Xiao-Ping Yu4Zhejiang Provincial Key Laboratory of Biometrology and Inspection & Quarantine, College of Life Sciences, China Jiliang University, Hangzhou 310018, ChinaZhejiang Provincial Key Laboratory of Biometrology and Inspection & Quarantine, College of Life Sciences, China Jiliang University, Hangzhou 310018, ChinaDepartment of Chemistry and Life Science, Chuxiong Normal University, Chuxiong 675000, ChinaDepartment of Chemistry and Life Science, Chuxiong Normal University, Chuxiong 675000, ChinaZhejiang Provincial Key Laboratory of Biometrology and Inspection & Quarantine, College of Life Sciences, China Jiliang University, Hangzhou 310018, ChinaThis paper develops a rapid method for discriminating the geographical origins and age of roasted Torreya grandis seeds by near infrared (NIR) spectroscopic analysis and pattern recognition. 337 samples were collected from three main producing areas and produced in the last two years. The objective of geographical origins analysis is to discriminate the seeds from Fengqiao with a protected geographical indication (PGI) from those of another two provinces. Age classification is aimed to detect the old seeds produced in the last year from the freshly produced ones. Partial least squares discriminant analysis (PLSDA) was used to develop classification models, and the influence of data preprocessing methods on classification performance was also investigated. Taking second-order derivatives of the raw spectra proves to be the most proper and effective preprocessing method, which can remove baselines and backgrounds and reduce model complexity. With second derivative spectra, the sensitivity and specificity were 0.939 and 0.871 for age discrimination, respectively. Perfect classification was obtained, and both sensitivity and specificity were 1 for discrimination of geographical origins.http://dx.doi.org/10.1155/2013/468509 |
| spellingShingle | Lu Xu Si-Min Yan Chen-Bo Cai Wei Zhong Xiao-Ping Yu Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods Journal of Spectroscopy |
| title | Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods |
| title_full | Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods |
| title_fullStr | Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods |
| title_full_unstemmed | Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods |
| title_short | Rapid Analysis of Geographical Origins and Age of Torreya grandis Seeds by NIR Spectroscopy and Pattern Recognition Methods |
| title_sort | rapid analysis of geographical origins and age of torreya grandis seeds by nir spectroscopy and pattern recognition methods |
| url | http://dx.doi.org/10.1155/2013/468509 |
| work_keys_str_mv | AT luxu rapidanalysisofgeographicaloriginsandageoftorreyagrandisseedsbynirspectroscopyandpatternrecognitionmethods AT siminyan rapidanalysisofgeographicaloriginsandageoftorreyagrandisseedsbynirspectroscopyandpatternrecognitionmethods AT chenbocai rapidanalysisofgeographicaloriginsandageoftorreyagrandisseedsbynirspectroscopyandpatternrecognitionmethods AT weizhong rapidanalysisofgeographicaloriginsandageoftorreyagrandisseedsbynirspectroscopyandpatternrecognitionmethods AT xiaopingyu rapidanalysisofgeographicaloriginsandageoftorreyagrandisseedsbynirspectroscopyandpatternrecognitionmethods |