Abstract:The new pattern recognition method of traditional Chinese medicine based on High Performance Liquid Chromatogram(HPLC) is presented. While a new self-organizing fuzzy neural network is also proposed in order to recognize the traditional Chinese medicine. This network is composed of two levels neural network: the first level is a self-organizing fuzzy neural network which has the automatic clustering structure for sub-class; the second level is supervised sub-class classification neural network. The whole network has not only the learning ability to neural network, but also the logic ability to fuzzy system based on rules, especially the automatic clustering ability to sub-class. The automatic clustering ability for sub-class has great meaning to the pattern recognition of traditional Chinese medicine because the traditional Chinese medicine will be very different under the condition of different place come from, different time picked up and different method dealt with. In addition, the whole network can also adapt to the fuzzy pattern recognition problem when the feature dimensions are not equal. It is manifested after abundant of traditional Chinese medicine samples have been used to test the network’s abilities. The results show that the resistance to parallel removal, deformation and the adaptability to the medicines coming from new places are very strong, thus the goals expected are achieved.
李一波; 黄小原. 基于高效液相色谱的中药材模式识别新方法[J]. 电子与信息学报, 2004, 26(3): 382-388 .
Li Yi-bo①②; Huang Xiao-yuan①. The New Pattern Recognition Method of Traditional Chinese Medicine Based on HPLC. , 2004, 26(3): 382-388 .