Improving the Accuracy of Spectral Recognition of Expired Drug by an Ensemble Model and Virtual Sample Generation

TAN Chao; TAN Cheng; CHENG Bin; ZOU Qin; CHEN Hui; WU Tong; LIN Zan

doi:10.12452/j.fxcsxb.25020465

您当前的位置：

首页 >

文章列表页 >

Improving the Accuracy of Spectral Recognition of Expired Drug by an Ensemble Model and Virtual Sample Generation

Experimental Techniques and Methods | 更新时间：2025-06-09

- Improving the Accuracy of Spectral Recognition of Expired Drug by an Ensemble Model and Virtual Sample Generation
- Journal of Instrumental Analysis Vol. 44, Issue 6, Pages: 1131-1138(2025)
- 作者机构：
  
  1.宜宾学院过程分析与控制四川省高校重点实验室，四川宜宾 644007
  2.阿坝师范学院资源与环境学院，四川汶川 623002
  3.四川省骨科医院，四川成都 610041
- 作者简介：
- 基金信息：
- DOI：10.12452/j.fxcsxb.25020465
  CLC： O657.3;TB9
- Received：04 February 2025，
  
  Revised：24 March 2025，
  
  Accepted：26 March 2025，
  
  Published：15 June 2025
- 稿件说明：
移动端阅览
谭超,谭成,程斌,邹琴,陈慧,吴同,林瓒.基于虚拟样本生成的集成模型提升过期药物光谱识别精度[J].分析测试学报,2025,44(06):1131-1138.

TAN Chao,TAN Cheng,CHENG Bin,ZOU Qin,CHEN Hui,WU Tong,LIN Zan.Improving the Accuracy of Spectral Recognition of Expired Drug by an Ensemble Model and Virtual Sample Generation[J].Journal of Instrumental Analysis,2025,44(06):1131-1138.
谭超,谭成,程斌,邹琴,陈慧,吴同,林瓒.基于虚拟样本生成的集成模型提升过期药物光谱识别精度[J].分析测试学报,2025,44(06):1131-1138. DOI： 10.12452/j.fxcsxb.25020465.

TAN Chao,TAN Cheng,CHENG Bin,ZOU Qin,CHEN Hui,WU Tong,LIN Zan.Improving the Accuracy of Spectral Recognition of Expired Drug by an Ensemble Model and Virtual Sample Generation[J].Journal of Instrumental Analysis,2025,44(06):1131-1138. DOI： 10.12452/j.fxcsxb.25020465.

摘要

基于近红外光谱定性识别假药需借助计算机和化学计量学从复杂、重叠、变动的光谱中提取特征信息和建立预测模型。在该类任务中，可能遇到某类样本相对不足的类别不平衡问题。基于生成虚拟样和集成建模，有望提升基于不平衡训练集上所得模型的识别精度。该文以阿奇霉素为研究对象，设计了一组实验样本集，采用基于虚拟样本技术的集成偏最小二乘判别分析模型构建了分类器，用于识别药物过期与否。在10个不同光谱区间上比较了单个模型和集成模型的性能，并讨论了不平衡比率、样本组成和集成规模的影响，集成分类器的灵敏度平均提高了约9%。通过实验确认了该集成策略的优势，在少数类样本过少时，所提出的集成算法更能显示出优势，该方法对其他类型体具有应用潜力。

Abstract

The qualitative identification of fake drugs based on near-infrared（NIR） spectroscopy needs to extract characteristic information and establish prediction models from complex，overlapped and unstable spectra by using computers and chemometrics. In this kind of task，there may also be an imbalanced classification problem where there are relatively few samples of a certain class. Based on the generation of virtual samples and ensemble modeling，this approach has the potential to improve the recognition accuracy for imbalanced training set. In this paper，azithromycin was taken as the research object，a group of experimental samples were designed，and an ensemble algorithm of partial least squares discriminant analysis（PLS-DA） based on virtual samples was proposed to construct a classifier for identifying whether a drug sample had expired. The performance of single and ensemble models was compared in ten different spectral ranges，and the influence of different imbalance ratios，the composition of minority class samples and ensemble size were also discussed. The sensitivity of ensemble models was improved by about 9% on average. Finally，the overall effectiveness of the ensemble learning strategy was confirmed. The proposed ensemble algorithm shows more advantages when there are too few minority class samples，and the method can also be used for other types of systems.

关键词

Keywords

references

Shang H ， Shang L W ， Wu J J ， Xu Z B ， Zhou S W ， Wang Z H ， Wang H J ， Yin J H . Spectrochim. Acta A ， 2023 ， 287 ： 121990 .

Neto A J S ， Lopes D de C . J. Food Compos. Anal. ， 2024 ， 135 ： 106637 .

Tan C ， Chen H ， Chen M X ， Lin Z . Infrared Phys. Technol. ， 2024 ， 139 ： 105334 .

Liu L ， Wang B ， Xu X X ， Xu J . Infrared Phys. Technol. ， 2025 ， 145 ： 105713 .

Suarin N A S S ， Chia K S ， Fuzi S F Z M . Knowl.-Based Syst. ， 2024 ， 295 ： 111817 .

Leng H Y ， Zhang Z Y ， Chen C ， Chen C . Spectrochim. Acta A ， 2024 ， 320 ： 124581 .

Qi C C ， Zhou N N ， Hu T ， Wu M T ， Chen Q S ， Wang H ， Zhang K J ， Lin Z . Smart Agric. Technol. ， 2025 ， 10 ： 100728 .

Daud S N S S ， Sudirman R ， Shing T W . Biomed. Signal Proces. Control ， 2023 ， 83 ： 104649 .

Fonseca J ， Bacao F . Expert Syst. Appl. ， 2023 ， 234 ： 121053 .

Guan H J ， Zhao L ， Dong X J ， Chen C . Eng. Appl. Artif. Intel. ， 2023 ， 124 ： 106570 .

Chen H ， Tan C ， Lin Z . Spectrochim. Acta A ， 2024 ， 304 ： 123315 .

Yu S H ， Liu J . Spectrochim. Acta A ， 2022 ， 280 ： 121569 .

Bian X H ， LiuY X ， Zhang R L ， Sun H ， Liu P ， TanX Y . Spectrochim. Acta A ， 2024 ， 311 ： 124016 .

Yan Z L ， Xiao D ， Sun H ， Zhang L Z ， Yin L Y . Fuel ， 2024 ， 373 ： 132381 .

Liu S Y ， Fang L D ， Wang S T ， Hu C H ， Liu H T . Infrared Phys. Technol. ， 2024 ， 140 ： 105426 .

Chawla N V ， Bowyer K W ， Hall L O ， Kegelmeyer W P . J . Artif. Intel. Res. ， 2022 ， 16 ： 321 - 357 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Combining Near-infrared Spectroscopy and Model Updating for Nondestructive Testing of Apple Quality

Chemometrics in the Identification of Microplastics in Aquatic Ecosystems

Rapid Quantitative Detection of Multiple Additives in E-liquids Based on Near-infrared Spectroscopy Technology

Related Author

WU Qi

CHEN Xiao-jing

SHI Wen

XIE Zhong-hao

SU Lai-jin

HUANG Guang-zao

PENG Hao-ran

WAN Xi-zhe

Related Institution

College of Electrical and Electronic Engineering，Wenzhou University

College of Life and Environmental Science，Wenzhou University

School of Ecology and Environment，Tibet University，Lasa

School of Ecology，Hainan University

School of Environmental Science and Technology，Tianjin University

Address：100 Xianlie Middle Road, Guangzhou Postal code：510070
Tel：020-87684776,37656606 Fax：020-87684776 Email：fxcsxb@china.com
Technical support is provided by Beijing Founder electronics co., LTD 粤ICP备12017312号-3 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：514734 Visits Today：189

⁰