Body constitution in traditional Chinese medicine evaluation model based on back propagation artificial neural network

摘要

In this paper, artificial neural network architecture is introduced to predict the body constitution in traditional Chinese medicine (BCTCM) yin-yang index. According to the characteristics of BCTCM, the collected data is more consistent with the exact value of the characteristic parameters of BCTCM of the samples with pre-processing the inputting data by the median, and quasi-Newton algorithm is used to train the network model to accelerate the convergence speed of network training. Experiments show that, the average of absolute of relative error of predicted value of BCTCM yin-yang index compared with the observed value for 10 independent samples validating neural network model is 3.37%.Therefore, the prediction model of BCTCM yin-yang index with BP neural network is doable.