本文選題：虛擬儀器 + 電子舌　； 參考：《電子測(cè)量與儀器學(xué)報(bào)》2017年07期

【摘要】：為了實(shí)現(xiàn)不同中成藥品的快速區(qū)分辨識(shí),采用基于虛擬儀器技術(shù)的伏安電子舌系統(tǒng)對(duì)治療感冒病癥的4種不同中成藥品進(jìn)行了檢測(cè)分析。分別采用特征點(diǎn)提取(FPE)法和離散小波變換(DWT)法對(duì)電子舌輸出信號(hào)進(jìn)行預(yù)處理,以樣本點(diǎn)的聚集性和分類效果為依據(jù),確定較佳的特征提取方法為以db4為母小波進(jìn)行的8層離散小波變換。在此基礎(chǔ)上,分別采用主成分分析法(PCA)、聚類分析法(CA)和BP神經(jīng)網(wǎng)絡(luò)(BPNN)對(duì)不同中成藥品進(jìn)行區(qū)分辨識(shí)。結(jié)果表明,PCA結(jié)果中PC1和PC2累計(jì)貢獻(xiàn)率為95.6%,除羚羊感冒片和銀翹解毒片有重疊趨勢(shì)外,其余各類得到有效區(qū)分;CA能夠有效地觀察出4種中成藥品之間的差異程度,但4種藥品最終被分成兩類,區(qū)分效果較差;非線性分類模型BPNN對(duì)不同中成藥品區(qū)分效果較好。通過優(yōu)化實(shí)驗(yàn),分別確定了模型的訓(xùn)練算法、激活函數(shù)和隱含層節(jié)點(diǎn)數(shù)目等參數(shù),測(cè)試集驗(yàn)證表明,BPNN模型對(duì)4種中成藥品的分類正確率達(dá)到100%。本研究結(jié)果可為中成藥品的非感官質(zhì)量評(píng)價(jià)和快速辨識(shí)研究提供技術(shù)參考。
[Abstract]:In order to realize the rapid identification of different proprietary Chinese medicines, four kinds of Chinese patent medicines for the treatment of colds were detected and analyzed by using the voltammetry electronic tongue system based on virtual instrument technology. The feature point extraction (FPE) method and discrete wavelet transform (DWT) method are used to preprocess the output signals of electronic tongue, which are based on the aggregation of sample points and the classification effect. The best feature extraction method is 8-layer discrete wavelet transform based on db4 wavelet. On this basis, the principal component analysis (PCA), cluster analysis (CAA) and BP neural network (BPNN) were used to distinguish and identify different Chinese patent medicines. The results showed that the cumulative contribution rate of PC1 and PC2 in PCA was 95.6. except for antelope Ganmao tablets and Yinqiao jiedu tablets, the differences between four kinds of proprietary medicines could be observed effectively. But the four drugs were divided into two categories, and the nonlinear classification model (BPNN) was better than BPNN in differentiating different Chinese patent medicines. Through optimization experiments, the training algorithm, activation function and number of hidden layer nodes are determined, respectively. The test results show that the classification accuracy of BPNN model for four kinds of Chinese patent medicines is 100%. The results of this study can provide technical reference for non-sensory quality evaluation and fast identification of Chinese patent medicine.
【作者單位】： 山東理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;山東淄博市中西醫(yī)結(jié)合醫(yī)院;山東淄博昌國醫(yī)院;
【基金】：山東省自然科學(xué)基金(2015CM016)資助項(xiàng)目
【分類號(hào)】：R286;TP212.9;TP391.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 杜瑞超;王優(yōu)杰;吳飛;馮怡;徐德生;洪燕龍;阮克鋒;;電子舌對(duì)中藥滋味的區(qū)分辨識(shí)[J];中國中藥雜志;2013年02期

2 劉瑞新;李慧玲;李學(xué)林;張杏芬;仇繼璽;;基于電子舌的穿心蓮水煎液的掩味效果評(píng)價(jià)研究[J];中草藥;2013年16期

相關(guān)會(huì)議論文 前1條

1 劉瑞新;吳子丹;李學(xué)林;;電子舌在藥學(xué)領(lǐng)域的應(yīng)用[A];第四屆全國臨床中藥學(xué)學(xué)術(shù)研討會(huì)論文摘要集[C];2011年

相關(guān)碩士學(xué)位論文 前1條

1 王素霞;花椒酰胺電子舌響應(yīng)規(guī)律及其應(yīng)用研究[D];西南交通大學(xué);2014年

，

本文編號(hào)：2010550