Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks
Drug detection and identification technology are of great significance in drug supervision and management. To determine the exact source of drugs, it is often necessary to directly identify multiple varieties of drugs produced by multiple manufacturers. Near-infrared spectroscopy (NIR) combined with...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1088 |
| _version_ | 1797414562026225664 |
|---|---|
| author | Anbing Zheng Huihua Yang Xipeng Pan Lihui Yin Yanchun Feng |
| author_facet | Anbing Zheng Huihua Yang Xipeng Pan Lihui Yin Yanchun Feng |
| author_sort | Anbing Zheng |
| collection | DOAJ |
| description | Drug detection and identification technology are of great significance in drug supervision and management. To determine the exact source of drugs, it is often necessary to directly identify multiple varieties of drugs produced by multiple manufacturers. Near-infrared spectroscopy (NIR) combined with chemometrics is generally used in these cases. However, existing NIR classification modeling methods have great limitations in dealing with a large number of categories and spectra, especially under the premise of insufficient samples, unbalanced samples, and sensitive identification error cost. Therefore, this paper proposes a NIR multi-classification modeling method based on a modified Bidirectional Generative Adversarial Networks (Bi-GAN). It makes full utilization of the powerful feature extraction ability and good sample generation quality of Bi-GAN and uses the generated samples with obvious features, an equal number between classes, and a sufficient number within classes to replace the unbalanced and insufficient real samples in the courses of spectral classification. 1721 samples of four kinds of drugs produced by 29 manufacturers were used as experimental materials, and the results demonstrate that this method is superior to other comparative methods in drug NIR classification scenarios, and the optimal accuracy rate is even more than 99% under ideal conditions. |
| first_indexed | 2024-03-09T05:35:10Z |
| format | Article |
| id | doaj.art-07f8aaf1bddb48bebef3ef4d84ac4184 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:35:10Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-07f8aaf1bddb48bebef3ef4d84ac41842023-12-03T12:29:27ZengMDPI AGSensors1424-82202021-02-01214108810.3390/s21041088Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial NetworksAnbing Zheng0Huihua Yang1Xipeng Pan2Lihui Yin3Yanchun Feng4School of Automation, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Haidian District, Beijing 100086, ChinaSchool of Automation, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Haidian District, Beijing 100086, ChinaSchool of Computer Science and Information Security, Guilin University of Electronic Technology, No.1 Jinji Road, Qixing District, Guilin 541004, ChinaChina Institute for Food and Drug Control, 2 Tiantan Xili, Dongcheng District, Beijing 100086, ChinaChina Institute for Food and Drug Control, 2 Tiantan Xili, Dongcheng District, Beijing 100086, ChinaDrug detection and identification technology are of great significance in drug supervision and management. To determine the exact source of drugs, it is often necessary to directly identify multiple varieties of drugs produced by multiple manufacturers. Near-infrared spectroscopy (NIR) combined with chemometrics is generally used in these cases. However, existing NIR classification modeling methods have great limitations in dealing with a large number of categories and spectra, especially under the premise of insufficient samples, unbalanced samples, and sensitive identification error cost. Therefore, this paper proposes a NIR multi-classification modeling method based on a modified Bidirectional Generative Adversarial Networks (Bi-GAN). It makes full utilization of the powerful feature extraction ability and good sample generation quality of Bi-GAN and uses the generated samples with obvious features, an equal number between classes, and a sufficient number within classes to replace the unbalanced and insufficient real samples in the courses of spectral classification. 1721 samples of four kinds of drugs produced by 29 manufacturers were used as experimental materials, and the results demonstrate that this method is superior to other comparative methods in drug NIR classification scenarios, and the optimal accuracy rate is even more than 99% under ideal conditions.https://www.mdpi.com/1424-8220/21/4/1088near-infrared spectroscopydrug identificationmulti-class classificationdeep learninggenerative adversarial networks |
| spellingShingle | Anbing Zheng Huihua Yang Xipeng Pan Lihui Yin Yanchun Feng Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks Sensors near-infrared spectroscopy drug identification multi-class classification deep learning generative adversarial networks |
| title | Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks |
| title_full | Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks |
| title_fullStr | Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks |
| title_full_unstemmed | Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks |
| title_short | Identification of Multi-Class Drugs Based on Near Infrared Spectroscopy and Bidirectional Generative Adversarial Networks |
| title_sort | identification of multi class drugs based on near infrared spectroscopy and bidirectional generative adversarial networks |
| topic | near-infrared spectroscopy drug identification multi-class classification deep learning generative adversarial networks |
| url | https://www.mdpi.com/1424-8220/21/4/1088 |
| work_keys_str_mv | AT anbingzheng identificationofmulticlassdrugsbasedonnearinfraredspectroscopyandbidirectionalgenerativeadversarialnetworks AT huihuayang identificationofmulticlassdrugsbasedonnearinfraredspectroscopyandbidirectionalgenerativeadversarialnetworks AT xipengpan identificationofmulticlassdrugsbasedonnearinfraredspectroscopyandbidirectionalgenerativeadversarialnetworks AT lihuiyin identificationofmulticlassdrugsbasedonnearinfraredspectroscopyandbidirectionalgenerativeadversarialnetworks AT yanchunfeng identificationofmulticlassdrugsbasedonnearinfraredspectroscopyandbidirectionalgenerativeadversarialnetworks |