Recognition of spikes of Schizonepeta tenuifolia from different area based on backpropagation neural network coupled with dimension reduction of principal component analysis

OBJECTIVE: The spikes of Schizonepeta tenuifolia from different habits were predicted by UV-Vis spectrum. METHOD: The dimensions of spectrum data obtained from ten habits were reduced by principal component analysis, and the first six new variables with 99.82% of cumulative reliability were put into the backpropagation neural network for model building. RESULT: The recognition rate of backpropagation neural network coupled with principal component analysis (PCA-BPNN) was 100%, and its mean square error was 0.001 0. CONCLUSION: PCA-BPNN can be used for the classifying of spikes of S. tenuifolia from different producing area, and this method is simple and fast.