Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning
With the rising demand of saffron, it is essential to standardize the confirmation of its origin and identify any adulteration to maintain a good quality led market product. However, a rapid and reliable strategy for identifying the adulteration saffron is still lacks. Herein, a combination of heads...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Food Chemistry: X |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590157524008691 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846125281077624832 |
|---|---|
| author | Yingjie Lu Chi Zhang Kunmiao Feng Jie Luan Yuqi Cao Khalid Rahman Jianbo Ba Ting Han Juan Su |
| author_facet | Yingjie Lu Chi Zhang Kunmiao Feng Jie Luan Yuqi Cao Khalid Rahman Jianbo Ba Ting Han Juan Su |
| author_sort | Yingjie Lu |
| collection | DOAJ |
| description | With the rising demand of saffron, it is essential to standardize the confirmation of its origin and identify any adulteration to maintain a good quality led market product. However, a rapid and reliable strategy for identifying the adulteration saffron is still lacks. Herein, a combination of headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS) and convolutional neural network (CNN) was developed. Sixty-nine volatile compounds (VOCs) including 7 groups of isomers were detected rapidly and directly. A CNN prediction model based on GC-IMS data was proposed. With the merit of minimal data prepossessing and automatic feature extraction capability, GC-IMS images were directly input to the CNN model. The origin prediction results were output with the average accuracy about 90 %, which was higher than traditional methods like PCA (61 %) and SVM (71 %). This established CNN also showed ability in identifying counterfeit saffron with a high accuracy of 98 %, which can be used to authenticate saffron. |
| format | Article |
| id | doaj-art-d13e5e1636b0444c93f85a9dd7b63999 |
| institution | Kabale University |
| issn | 2590-1575 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Food Chemistry: X |
| spelling | doaj-art-d13e5e1636b0444c93f85a9dd7b639992024-12-13T11:02:06ZengElsevierFood Chemistry: X2590-15752024-12-0124101981Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learningYingjie Lu0Chi Zhang1Kunmiao Feng2Jie Luan3Yuqi Cao4Khalid Rahman5Jianbo Ba6Ting Han7Juan Su8School of Pharmacy, Naval Medical University, Shanghai 200433, ChinaSchool of Pharmacy, Naval Medical University, Shanghai 200433, China; National Demonstration Center for Experimental Military Pharmacy Education, Naval Medical University, Shanghai 200433, ChinaSchool of Pharmacy, Naval Medical University, Shanghai 200433, ChinaNaval Medicine Center of PLA, Naval Medical University, Shanghai 200433, ChinaTechnical Centre, Shanghai Tobacco (Group) Corp., Shanghai 200082, ChinaFaculty of Science, School of Pharmacy and Biomolecular Sciences, Liverpool John Moores University, Liverpool, United KingdomNaval Medicine Center of PLA, Naval Medical University, Shanghai 200433, China; Corresponding authors.School of Pharmacy, Naval Medical University, Shanghai 200433, China; Corresponding authors.School of Pharmacy, Naval Medical University, Shanghai 200433, China; National Demonstration Center for Experimental Military Pharmacy Education, Naval Medical University, Shanghai 200433, China; Corresponding author at: School of Pharmacy, Naval Medical University, Shanghai 200433, China.With the rising demand of saffron, it is essential to standardize the confirmation of its origin and identify any adulteration to maintain a good quality led market product. However, a rapid and reliable strategy for identifying the adulteration saffron is still lacks. Herein, a combination of headspace-gas chromatography-ion mobility spectrometry (HS-GC-IMS) and convolutional neural network (CNN) was developed. Sixty-nine volatile compounds (VOCs) including 7 groups of isomers were detected rapidly and directly. A CNN prediction model based on GC-IMS data was proposed. With the merit of minimal data prepossessing and automatic feature extraction capability, GC-IMS images were directly input to the CNN model. The origin prediction results were output with the average accuracy about 90 %, which was higher than traditional methods like PCA (61 %) and SVM (71 %). This established CNN also showed ability in identifying counterfeit saffron with a high accuracy of 98 %, which can be used to authenticate saffron.http://www.sciencedirect.com/science/article/pii/S2590157524008691SaffronVolatile componentsConvolutional neural networksHS-GC-IMSOrigins |
| spellingShingle | Yingjie Lu Chi Zhang Kunmiao Feng Jie Luan Yuqi Cao Khalid Rahman Jianbo Ba Ting Han Juan Su Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning Food Chemistry: X Saffron Volatile components Convolutional neural networks HS-GC-IMS Origins |
| title | Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning |
| title_full | Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning |
| title_fullStr | Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning |
| title_full_unstemmed | Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning |
| title_short | Characterization of saffron from different origins by HS-GC-IMS and authenticity identification combined with deep learning |
| title_sort | characterization of saffron from different origins by hs gc ims and authenticity identification combined with deep learning |
| topic | Saffron Volatile components Convolutional neural networks HS-GC-IMS Origins |
| url | http://www.sciencedirect.com/science/article/pii/S2590157524008691 |
| work_keys_str_mv | AT yingjielu characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT chizhang characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT kunmiaofeng characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT jieluan characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT yuqicao characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT khalidrahman characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT jianboba characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT tinghan characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning AT juansu characterizationofsaffronfromdifferentoriginsbyhsgcimsandauthenticityidentificationcombinedwithdeeplearning |