基于代表率与投票机制的分类方法监测片剂包衣终点的研究

doi:10.6040/j.issn.1671-9352.4.2021.080

《山东大学学报(理学版)》 ›› 2022, Vol. 57 ›› Issue (11): 78-88.doi: 10.6040/j.issn.1671-9352.4.2021.080

• • 上一篇

基于代表率与投票机制的分类方法监测片剂包衣终点的研究

聂斌¹,陈裕凤¹,何雁^1*,罗晓健^1,2,饶小勇^1,2,李欢¹,金正吉¹

1.江西中医药大学计算机学院, 江西南昌 330004;2.江西中医药大学中药固体制剂制造技术国家工程研究中心, 江西南昌 330006

发布日期:2022-11-10
作者简介:聂斌(1972— ),男,博士研究生,教授,研究方向为数据挖掘、中医药信息学. E-mail:ncunb@163.com*通信作者简介:何雁(1963— ),女,教授,研究方向为中药数据分析. E-mail:274667818@qq.com
基金资助:
国家自然科学基金资助项目(81960715,61562045,62141202,61762051);国家“重大新药创制”科技重大专项基金资助项目(2018ZX09201010)

Study on monitoring the end points of tablet coating by classification method based on representative rate and voting mechanism

NIE Bin¹, CHEN Yu-feng¹, HE Yan^1*, LUO Xiao-jian^1,2, RAO Xiao-yong^1,2, LI Huan¹, JIN Zheng-ji¹

1. School of Computer Science, Jiangxi University of Chinese Medicine, Nanchang 330004, Jiangxi, China;
2. National Pharmaceutical Engineering Center for Solid Preparation in Chinese Herbal Medicine, Jiangxi University of Chinese Medicine, Nanchang 330006, Jiangxi, China

Published:2022-11-10

摘要/Abstract

摘要： 利用近红外技术,建立了一种基于代表率和投票机制的分类方法监测片剂包衣终点。首先,采用系统聚类对各包衣时间点样本均值进行聚类,建立分类模型;然后,用本文提出的代表率对各时间点样本进行模型验证,通过代表率验证均值聚类模型,明确模型的有效性和可行性;最后,用训练模型预测各时间点样本类别,通过投票机制获得各时间点最终投票结果,弥补了系统聚类无模型预测的不足,也可避免个别样本导致的错误判断。经实验数据验证:代表率最低的是T100M,为73.33%;最高的是T130M,为100.00%;平均代表率为86.77%。投票结果得出第一批测试数据和第二批测试数据的包衣终点分别为1T130M、2T132M,另外投票机制还能监测其他时间点的包衣过程。

关键词: 近红外技术, 包衣, 代表率, 投票机制

Abstract: A classification method based on representative rate and voting mechanism was established to monitor the end point of tablet coating by using near-infrared(NIR)technology. Firstly, the sample mean of each coating time point was clustered by hierarchical clustering, and establishing the classification model. Then, the representative rate proposed in this paper was used to verify the model at each time point. The method verified the mean clustering model through the representative rate to confirm the availability and feasibility of the model. Finally, the training model was used to predict the sample categories at each time point, and the final voting results at each time point were obtained through voting mechanism, which made up for the lack of model prediction in systematic clustering and avoided the wrong judgment caused by individual samples. The experimental data verified that the lowest representative rate was 73.33% for T100M, and the highest was 100.00% for T130M, with an average representative rate of 86.77%, The voting results show that the finishing points of the first batch of test data and the second batch of test data are 1T130M and 2T132M respectively. The voting mechanism can also monitor the process of coating at other time points.

Key words: near infrared technology, coating, representative rate, voting mechanism

中图分类号:

TP399

聂斌,陈裕凤,何雁,罗晓健,饶小勇,李欢,金正吉. 基于代表率与投票机制的分类方法监测片剂包衣终点的研究[J]. 《山东大学学报(理学版)》, 2022, 57(11): 78-88.

NIE Bin, CHEN Yu-feng, HE Yan, LUO Xiao-jian, RAO Xiao-yong, LI Huan, JIN Zheng-ji. Study on monitoring the end points of tablet coating by classification method based on representative rate and voting mechanism[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2022, 57(11): 78-88.

参考文献

[1] 李燕青,郭德慧,丁姗姗.近红外光谱法快速评估松花粉片薄膜包衣效果[J].现代食品科技,2020,36(3):288-295. LI Yanqing, GUO Dehui, DING Shanshan. Rapid evaluation on the film coating effect of pine pollen tablets by near infrared spectroscopy[J]. Modern Food Science & Technology, 2020, 36(3):288-295.
[2] 盛春梁,王洪香,刘俊国,等.薄膜包衣技术及应用[J].食品与药品,2007,9(8):36-38. SHENG Chunliang, WANG Hongxiang, LIU Junguo, et al. Film coating technique and its application[J]. Food and Drug, 2007, 9(8):36-38.
[3] 李超,罗万和,周凯翔,等.包衣技术提高药物药学性能的研究进展[J].中国畜牧兽医,2018,45(11):3271-3278. LI Chao, LUO Wanhe, ZHOU Kaixiang, et al. Research progress on coating technologies to improve pharmaceutical pharmacy performance[J]. China Animal Husbandry & Veterinary Medicine, 2018, 45(11):3271-3278.
[4] KNOP Klaus, KLEINEBUDDE Peter. PAT-tools for process control in pharmaceutical film coating applications[J]. International Journal of Pharmaceutics, 2013, 457(2):527-536.
[5] 潘卫三.药剂学[M].北京:化学工业出版社,2017:227-237. PAN Weisan. Pharmaceutics[M]. Beijing: Chemical Industry Press, 2017: 227-237.
[6] 李欣.薄膜包衣预混剂的应用[J].化工科技市场,2009,32(10):10-12. LI Xin. Application of pre-mixture coating film [J]. Chemical Technology Market, 2009, 32(10):10-12.
[7] LIU H, MEYER R, FLAMM M, et al. Optimization of critical quality attributes in tablet film coating and design space determination using pilot-scale experimental data[J]. AAPS Pharm Sci Tech, 2021, 22(1):17.
[8] WANG Jennifer, JEFFREY H, CHEN Wei, et al. An evaluation of process parameters to improve coating efficiency of an active tablet film-coating process[J]. International Journal of Pharmaceutics, 2012, 427(2):163-169.
[9] BENSAIDANE M R, TURGEON A F, LAUZIER F, et al. Neuromonitoring with near-infrared spectroscopy(NIRS)in aneurysmal subarachnoid haemorrhage: a systematic review protocol [J]. BMJ Open, 2020, 10(11):1-5.
[10] 张婉洁,刘蓉,徐可欣.基于平行因子分析法提高近红外无创血糖校正模型稳健性的研究[J].化学学报,2013,71(9):1281-1286. ZHANG Wanjie, LIU Rong, XU Kexin. Enhanced robustness of calibration models using parallel factor(PARAFAC)analysis with NIR spectral data for non-invasive blood glucose monitoring[J]. Acta Chimica Sinica, 2013, 71(9):1281-1286.
[11] 廉小亲,汤燊淼,吴静珠,等. 基于近红外的兰州百合品质定量建模方法研究[J].食品科技,2020,45(7):298-302. LIAN Xiaoqin, TANG Shenmiao, WU Jingzhu, et al. Research on quantitative model of lilium Lanzhou quality by near infrared spectroscopy[J]. Food Science and Technology, 2020, 45(7):298-302.
[12] WANG Hong, TANG Manlai, ZHAO Naifei, et al. Variable screening for near infrared(NIR)spectroscopy data based on ridge partial least squares regression[J]. Combinatorial Chemistry & High Throughput Screening, 2020, 23(8):740-756.
[13] ROSALBA Calvini, GIORGIA Orlandi, GIORGIA Foca, et al. Development of a classification algorithm for efficient handling of multiple classes in sorting systems based on hyperspectral imaging[J]. Journal of Spectral Imaging, 2018. doi: 10.1255/jsi.2018.a13.
[14] 夏春燕,徐芳芳,张欣,等.近红外光谱快速预测天舒片包衣终点研究[J].中草药,2019,50(21):5223-5230. XIA Chunyan, XU Fangfang, ZHANG Xin, et al. Study on fast prediction of film coating terminal point of Tianshu tablets by near-infrared spectroscopy[J]. Chinese Traditional and Herbal Drugs, 2019, 50(21):5223-5230.
[15] 邱素君,何雁,张国松,等.近红外光谱快速测定柴胡总皂苷肠溶片包衣膜厚度研究[J].中国药学杂志,2013,48(24):2128-2133. QIU Sujun, HE Yan, ZHANG Guosong, et al. Fast determination of coating thickness of the total saponin of radix bupleuri enteric coated tablets by NIRS[J]. Chinese Pharmaceutical Journal, 2013, 48(24):2128-2133.
[16] 陶青,金正吉,罗晓健,等.近红外光谱在片剂包衣终点判别与过程分析的研究[J].中国中药杂志,2020,45(19):4625-4632. TAO Qing, JIN Zhengji, LUO Xiaojian, et al. Study on endpoint determination and process analysis of tablet coating based on near infrared spectroscopy[J]. Chinese Pharmaceutical Journal, 2020, 45(19):4625-4632.
[17] HAN Jiawei, KAMBER Micheline, PEI Jian. 数据挖掘:概念与技术[M].范明,孟小峰译. 3版.北京:机械工业出版社,2012. HAN Jiawei, KAMBER Micheline, PEI Jian. Data mining: concepts and techniques[M]. Translated by FAN Ming, MENG Xiaofeng. 3rd ed. Beijing: China Machine Press, 2012.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于代表率与投票机制的分类方法监测片剂包衣终点的研究

Study on monitoring the end points of tablet coating by classification method based on representative rate and voting mechanism

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

多维度评价

本文评价

推荐阅读 0

[1]	解滨,李清扬,董新玉. 面向网络入侵检测数据的对抗样本生成方法[J]. 《山东大学学报(理学版)》, 2021, 56(3): 28-36.
[2]	岳园,田双亮,陈秀萍. 部分实现组合电路的等价验证优化算法[J]. 山东大学学报（理学版）, 2016, 51(3): 116-121.
[3]	刘井莲,王大玲,赵卫绩,冯时,张一飞. 一种基于核心节点扩展的社区挖掘算法[J]. 山东大学学报（理学版）, 2016, 51(1): 106-114.
[4]	黄崇争,吴元锡,陈红 . 数据流中一种有效的当前频繁序列挖掘方法[J]. J4, 2007, 42(11): 37-39 .
[5]	吴万青,周国龙,王巧,赵永新. 基于GSA搜索高非线性度的平衡布尔函数[J]. 《山东大学学报(理学版)》, 2022, 57(5): 74-84.