APPLICATION OF ARTIFICIATION OF ARTIFICATION NETWORKS TO THE FEATURE EXTRACTION IN CHEMICAL PATTERN RECOGNITION OF THE TRADITIONAL CHINESE MELICINE VENENUM BUFONIS

A three-layer back propagation neural network was employed to extract featuresfrom HPLC data of the traditional Chinese medicine Venenum bufonis. method does not need torecalculate the data matrix after introducing a new sample.The result shows that the BP neuralnetwork can be used in the chemical pattern recognition directly.