论文部分内容阅读
目的：对六味地黄丸缺味药进行Ｂａｙｅｓ 法和ＰＲＩＭＡ法定性识别研究。方法：采用反相ＨＰＬＣ法对六味地黄丸缺味药模拟方的浸出物进行分析，选取９ 个色谱峰的峰面积与内标峰面积之比值作为样本特征变量，通过１６９ 个训练集样本建立了其中３ 种缺味药的Ｂａｙｅｓ 法和ＰＲＩＭＡ法判别分析数学模型。结果：３ 种缺味药４ 种模式的平均正确识别率Ｂａｙｅｓ 法和ＰＲＩＭＡ 法均为１００％ ，对１６９ 个预示集样本的平均预示率Ｂａｙｅｓ 法为１００％ ，ＰＲＩＭＡ法为９９ ．６％ 。结论：Ｂａｙｅｓ 法和ＰＲＩＭＡ 法能对六味地黄丸３ 种缺味药进行准确识别。
OBJECTIVE: To study the Bayesian and PRIMA statutory identification of Liuweidihuang Pills. METHODS: Reversed-phase HPLC method was used to analyze the extracts from the simulated side of Liuweidihuang Pills. The ratio of the peak area of the 9 peaks to the peak area of the internal standard was selected as the sample feature variable. The sample was established with 169 training sets. Among them, Bayesian and PRIMA discriminant analysis mathematical models of 3 kinds of odor-reducing drugs. Results: The average correct recognition rates of the four modes of the three kinds of odor-absorption drugs were 100% for the Bayesian and PRIMA methods. The average predictive rate for the 169 predictive samples was 100% for the Bayes method and 99 for the PRIMA method. 6%. Conclusion: The Bayes method and PRIMA method can accurately identify the three kinds of odor-reducing drugs in Liuwei Dihuang Wan.