Title :
TCM Pulse-Condition Classification Method Based on BP Neural Network
Author :
Wang Binghe ; Guo Hongxia ; Zheng Siyi ; Yang Xilin
Author_Institution :
Dept. of Commun. Eng., Chinese People´s Armed Police Force, Xi´an
Abstract :
In order to achieve the objective and exact classification of the traditional Chinese medicine pulse- conditions, a pulse-condition recognition method based on BP neural network has been successfully developed. The influence of concealed layer node number on convergent speed and recognition accuracy and the influence of learning rate on convergent speed are considered. The BP network-training algorithm is improved, which obtains satisfactory network convergent error and recognition effect. The recognition tests of many pulse-condition samples indicate that our method works well in classifying the traditional Chinese medicine pulse- conditions accurately and quickly.
Keywords :
backpropagation; medical computing; medicine; neural nets; patient treatment; back propagation network-training algorithm; convergent speed; learning rate; network convergent error; neural network; recognition effect; traditional Chinese medicine pulse-condition classification; Artificial neural networks; Biomedical imaging; Educational institutions; Feedforward neural networks; Medical diagnostic imaging; Neural networks; Neurons; Pattern recognition; Transfer functions; Vectors;
Conference_Titel :
Bioinformatics and Biomedical Engineering, 2007. ICBBE 2007. The 1st International Conference on
Conference_Location :
Wuhan
Print_ISBN :
1-4244-1120-3
DOI :
10.1109/ICBBE.2007.164
