Rapid Identification of Cotton and Polyester Textiles Using Flow-through Dielectric Barrier Discharge Ionization Mass Spectrometry Combined with Random Forest Model

SHANG Yu-han; GE Yun-cheng; GAO Hai-yan; MENG Xian-shuang; MA Qiang

doi:10.12452/j.fxcsxb.24030803

您当前的位置：

首页 >

文章列表页 >

Rapid Identification of Cotton and Polyester Textiles Using Flow-through Dielectric Barrier Discharge Ionization Mass Spectrometry Combined with Random Forest Model

Scientific Papers | 更新时间：2024-06-11

- Rapid Identification of Cotton and Polyester Textiles Using Flow-through Dielectric Barrier Discharge Ionization Mass Spectrometry Combined with Random Forest Model
- Journal of Instrumental Analysis Vol. 43, Issue 6, Pages: 883-890(2024)
- 作者机构：
  
  1.中国检验检疫科学研究院，北京 100176
  2.大连理工大学化工海洋与生命学院，辽宁盘锦 124221
  3.内蒙古自治区市场监督管理审评查验中心，内蒙古呼和浩特 010090
- 作者简介：
- 基金信息：
- DOI：10.12452/j.fxcsxb.24030803
  CLC： O657.63;TS107
- Published：15 June 2024，
  
  Received：08 March 2024，
  
  Revised：02 April 2024，
- 稿件说明：
扫描看全文
尚宇瀚,葛运程,高海燕,孟宪双,马强.流过式介质阻挡放电电离质谱法结合随机森林模型快速鉴别棉、涤纶纺织品[J].分析测试学报,2024,43(06):883-890.

SHANG Yu-han,GE Yun-cheng,GAO Hai-yan,MENG Xian-shuang,MA Qiang.Rapid Identification of Cotton and Polyester Textiles Using Flow-through Dielectric Barrier Discharge Ionization Mass Spectrometry Combined with Random Forest Model[J].Journal of Instrumental Analysis,2024,43(06):883-890.
尚宇瀚,葛运程,高海燕,孟宪双,马强.流过式介质阻挡放电电离质谱法结合随机森林模型快速鉴别棉、涤纶纺织品[J].分析测试学报,2024,43(06):883-890. DOI： 10.12452/j.fxcsxb.24030803.

SHANG Yu-han,GE Yun-cheng,GAO Hai-yan,MENG Xian-shuang,MA Qiang.Rapid Identification of Cotton and Polyester Textiles Using Flow-through Dielectric Barrier Discharge Ionization Mass Spectrometry Combined with Random Forest Model[J].Journal of Instrumental Analysis,2024,43(06):883-890. DOI： 10.12452/j.fxcsxb.24030803.

摘要

为实现对棉、涤纶纺织品的快速准确鉴别，开发了电烙铁灼烧-流过式介质阻挡放电电离质谱法。结果表明，电烙铁灼烧-流过式介质阻挡放电电离质谱法无需样品前处理，操作简便，单次数据采集用时仅为4~5 s。使用棉、涤纶与棉涤混纺纺织品样品的质谱指纹图谱数据，建立了基于随机森林算法的预测模型。优化后的随机森林模型五折交叉验证与袋外验证的误判率分别为2.50%和2.52%。基于袋外验证混淆矩阵，求得该模型的预测准确率为97.5%，对棉与涤纶样品的精确率、召回率和F1分数均高于95%，满足快速鉴别要求。该方法可为棉、涤纶纺织品真伪鉴别与品质评价提供技术参考。

Abstract

To achieve the rapid and precise identification of cotton and polyester textiles，an analytical method utilizing an electric soldering iron for cauterization combined with soft ionization by chemical reaction in transfer-mass spectrometry（SICRIT-MS） was developed. The SICRIT ion source could ionize gaseous analytes by generating a plasma torch at the inlet of the mass spectrometer through dielectric barrier discharge ionization and maintaining the negative pressure inside the mass spectrometer. The results indicated that the SICRIT-MS method did not necessitate sample pretreatment，was easy to operate，and required only 4-5 s for a single data acquisition. Subsequently，a prediction model based on the random forest algorithm was established using the acquired mass spectrometry（MS） fingerprint data. The random forest model was optimized using the GridSearchCV function from the Scikit-learn library and underwent validation both through five-fold cross-validation and out-of-bag validation，yielding misclassification rates of 2.50% and 2.52%，respectively. According to the out-of-bag validation confusion matrix，the model achieved a prediction accuracy of 97.5%，with precision，recall，and F1 score for cotton and polyester samples all exceeding 95%，thereby meeting the requirements for rapid identification. This method can serve as a technical reference for the authentication and quality evaluation of cotton and polyester textiles.

关键词

流过式介质阻挡放电电离质谱随机森林模型棉涤纶快速鉴别

Keywords

flow-through dielectric barrier discharge ionization mass spectrometryrandom forest modelcottonpolyesterrapid identification

references

General Administration of Customs. China's trade in goods import and export grew 8.7% in the first 2 months（海关总署. 前2个月我国货物贸易进出口增长8.7%）. ［2024-03-07］. http：//www.customs.gov.cn/customs/xwfb34/302425/5715764/index.htmlhttp://www.customs.gov.cn/customs/xwfb34/302425/5715764/index.html.

Leader G M，Paola P D，Mina L，Hayda S，Moran K S，Beatrice J，Dhody A. Int. J. Hist. Archaeol.，2022，26：951-973.

Reffner J A，Kammrath B W，Kaplan S. J. Forensic Sci.，2019，65（3）：744-750.

Gu J J. Text. Test. Stand.（顾俊捷. 纺织检测与标准），2020，6（4）：8-12.

Xu X. Text. Test. Stand.（徐霞. 纺织检测与标准），2023，9（6）：5-7.

Zhang F. China Text. Leader. （章斐. 纺织导报），2023，5：80-84.

Chu X L，Shi Y Y，Chen P，Li J Y，Xu Y P. J. Instrum. Anal.（褚小立，史云颖，陈瀑，李敬岩，许育鹏. 分析测试学报），2019，38（5）：603-611.

Li H Y，Liu W，Cheng X Q，Han L P. Text. Test. Stand.（黎海洋，刘旺，程鑫桥，韩丽屏. 纺织检测与标准），2020，6（1）：13-16.

Lian Q Y，Qiu S R，Shi D W，Pei D J. Synth. Fiber China（连秋燕，邱尚仁，施点望，裴德君. 合成纤维），2017，46（6）：48-53.

Li S S，Zhang Y，Wang J H，Yang Y F，Miao C，Guo Y F，Zhang Z D，Cao Q C，Shui W Q. PLoS One，2016，11（1）：e0147044.

GB/T 42699.2-2023. Textiles-Qualitative and Quantitative Proteomic Analysis of Some Animal Hair Fibres-Part 2：Peptide Detection Using MALDI-TOF-MS. National Standards of the People's Republic of China

纺织品某些动物毛纤维蛋白质组定性和定量分析第二部分：还原蛋白质多肽分析基质辅助激光解吸电离飞行时间质谱（MALDI-TOF-MS）法. 中华人民共和国国家标准.

Mirabelli M F，Wolf J-C，Zenobi R. Anal. Chem.，2016，88（14）：7252-7258.

Mirabelli M F，Wolf J-C，Zenobi R. Analyst，2017，142（11）：1909-1915.

Mirabelli M F，Gionfriddo E，Pawliszyn J，Zenobi R. Analyst，2018，143（4）：891-899.

Ho T K. IEEE Trans. Pattern Anal. Mach. Intell.，1998，20（8）：832-844.

Pedregosa F，Varoquaux G，Gramfort A，Michel V，Thirion B，Grisel O，Blondel M，Prettenhofer P，Weiss R，Dubourg V，Vanderplas J，Passos A，Cournapeau D，Brucher M，Perrot M，Duchesnay É. J. Mach. Learn. Res.，2011，12（85）：2825-2830.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

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.

⁰