【摘要】 目的:探讨反向传播(BP)人工神经网络在半夏泻心汤、生姜泻心汤、甘草泻心汤配比中的应用。方法:应用均匀设计对药味及剂量进行分组,测定不同组别对正常大鼠胃酸的影响。鉴于复方配比具有复杂性及大量非线性关系的特性,该研究应用MATLAB6 5进行编程,选用BP人工神经网络建立模型。结果:应用BP人工神经网络所建模型可以很好地拟合学习过的样本及未学习过的样本。结论:BP人工神经网络可以很好地拟合复方配比中复杂的非线性关系,可以应用于复方配比的研究。更多还原

【Abstract】 Objective:to observe the application of BP artificial neural network to study the compatible proportion of banxia xiexin decoction and its class prescriptions.Methods:to measure the influence on gastric acid of normal rats,which the groups of different flavor of a drug and dosage were divided according to homogeneous design.The study was programmed with MATLAB6.5,conformed the experimental data with BP artificial neural network,because of complexity and large numbers of non-linear relation of compound prescripitions.Results:it is a kind of good method of BP artificial neural network to uniform unstudied and studied knowledge.Conclusion:BP artificial neural network has the excellent ability of self-organization and self-acclimation,and it could conform the complicated non-linear relation during the proportioning of compound prescripitions.更多还原