人工神经网络及其在卡马西平固体分散体优化中的应用

IF 0.4 4区医学 Q4 PHARMACOLOGY & PHARMACY

Acta poloniae pharmaceutica Pub Date : 2022-11-21 DOI:10.32383/appdr/154044

Tanja B Vojinovic, Zorica Potpara, M. Vukmirović, Nemanja Turkovic, S. Ibrić

{"title":"人工神经网络及其在卡马西平固体分散体优化中的应用","authors":"Tanja B Vojinovic, Zorica Potpara, M. Vukmirović, Nemanja Turkovic, S. Ibrić","doi":"10.32383/appdr/154044","DOIUrl":null,"url":null,"abstract":"The aim of this study was to examine the possibility of using artificial neural networks in the optimization of solid dispersions with carbamazepine. Artificial neural networks of the Generalized regression neural network type with four layers, gave models that describe the effect of components in solid dispersions carbamazepine-Neusilin ® UFL2 (magnesium aluminosilicate)-Collidon ® VA64 (vinylpyrrolidone-vinyl acetate) and dissolved carbamazepine value (%) after 10 (Q10) and 30(Q30) minutes of carbamazepine testing. After the learning process, root mean square error (RMS) values of 0.0029 were obtained for the training data set, and 0.1185 for the test training data, which is an excellent prediction of the neural network.","PeriodicalId":7147,"journal":{"name":"Acta poloniae pharmaceutica","volume":" ","pages":""},"PeriodicalIF":0.4000,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Artificial neural networks and their application in the optimization of carbamazepine solid dispersions\",\"authors\":\"Tanja B Vojinovic, Zorica Potpara, M. Vukmirović, Nemanja Turkovic, S. Ibrić\",\"doi\":\"10.32383/appdr/154044\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The aim of this study was to examine the possibility of using artificial neural networks in the optimization of solid dispersions with carbamazepine. Artificial neural networks of the Generalized regression neural network type with four layers, gave models that describe the effect of components in solid dispersions carbamazepine-Neusilin ® UFL2 (magnesium aluminosilicate)-Collidon ® VA64 (vinylpyrrolidone-vinyl acetate) and dissolved carbamazepine value (%) after 10 (Q10) and 30(Q30) minutes of carbamazepine testing. After the learning process, root mean square error (RMS) values of 0.0029 were obtained for the training data set, and 0.1185 for the test training data, which is an excellent prediction of the neural network.\",\"PeriodicalId\":7147,\"journal\":{\"name\":\"Acta poloniae pharmaceutica\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.4000,\"publicationDate\":\"2022-11-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Acta poloniae pharmaceutica\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.32383/appdr/154044\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"PHARMACOLOGY & PHARMACY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta poloniae pharmaceutica","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.32383/appdr/154044","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}

引用次数: 0

摘要

本研究的目的是研究利用人工神经网络优化卡马西平固体分散体的可能性。采用四层广义回归神经网络类型的人工神经网络，给出了描述卡马西平- neusilin®UFL2(硅酸铝镁)-Collidon®VA64(乙烯基吡罗烷酮-醋酸乙烯酯)固体分散体中各组分在卡马西平测试10 (Q10)和30(Q30)分钟后卡马西平溶解值(%)的影响的模型。经过学习过程，训练数据集的均方根误差(RMS)为0.0029，测试训练数据的均方根误差(RMS)为0.1185，是对神经网络很好的预测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Artificial neural networks and their application in the optimization of carbamazepine solid dispersions

The aim of this study was to examine the possibility of using artificial neural networks in the optimization of solid dispersions with carbamazepine. Artificial neural networks of the Generalized regression neural network type with four layers, gave models that describe the effect of components in solid dispersions carbamazepine-Neusilin ® UFL2 (magnesium aluminosilicate)-Collidon ® VA64 (vinylpyrrolidone-vinyl acetate) and dissolved carbamazepine value (%) after 10 (Q10) and 30(Q30) minutes of carbamazepine testing. After the learning process, root mean square error (RMS) values of 0.0029 were obtained for the training data set, and 0.1185 for the test training data, which is an excellent prediction of the neural network.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Acta poloniae pharmaceutica 医学-药学

CiteScore

0.80

自引率

0.00%

发文量

审稿时长

6-12 weeks

期刊介绍： The international journal of the Polish Pharmaceutical Society is published in 6 issues a year. The journal offers Open Access publication of original research papers, short communications and reviews written in English, in all areas of pharmaceutical sciences. The following areas of pharmaceutical sciences are covered: Analysis, Biopharmacy, Drug Biochemistry, Drug Synthesis, Natural Drugs, Pharmaceutical Technology, Pharmacology and General. A bimonthly appearing in English since 1994, which continues “Acta Poloniae Pharmaceutica”, whose first issue appeared in December 1937. The war halted the activity of the journal’s creators. Issuance of “Acta Poloniae Pharmaceutica” was resumed in 1947. From 1947 the journal appeared irregularly, initially as a quarterly, then a bimonthly. In the years 1963 – 1973 alongside the Polish version appeared the English edition of the journal. Starting from 1974 only works in English are published in the journal. Since 1995 the journal has been appearing very regularly in two-month intervals (six books a year). The journal publishes original works from all fields of pharmacy, summaries of postdoctoral dissertations and laboratory notes.