Bayesian-regularization BP Neural Network And The Application In Medical Fields

Artificial neural network(ANN) is a rising borderline science.It is an information-deal-with system invoked by biology neural network for its structure, function and some basic characters, but being abstracted and simplified. ANN has distributed storage form and parallel disposing form of information. Compared to the traditional statistics method, it doesn't need exact mathematical model and dose not have any consumption (such as distribution and independence) demanding the variables to meet. It can make up the deficiency of mathematical statistics methods and gives an idea and method to solving the problems.For medical researchers, particularly attention had been given to how to build a suitable ANN model to resolve the actual problems and model have excellent generalization capabilities. This study focuses on the back propagation network (BP network) which is a widely applied model in the medical filed. The fundamental of BP network and BP algorithm was introduced and the improved algorithm was given. To counter the over-fitting problem in BP algorithm and its improvements, we proposed method which was raising the generalization of the network of BP. Based on bayesian-regularization BP algorithm is put forward. The performance index includes a term interpreted as a log prior probability distribution over the network parameters and a sum-squared error term interpreted as the log likelihood for a noise model. The former is used for penalizing the network complexity. The optimal network parameters can be obtained with the maximum posterior probabilities of the models.On the basis of study on ANN theory and realization method, simulation study on theoretical data and application study on factual data have been done. Results of simulation study indicate: Based on bayesian-regularization BP neural network is superior to the general improved algorithm. Several simulative BP network architectures had been set up to discuss the designing, learning, optimizing on medical factual data. Based on bayesian-regularization BP neural network was used to predict systolic pressure about coal miners hypertension patient. Coefficient of determination is 0.97, for testing data, average fractional error is 2%. The models can not only exactly imitate training valuation but also make prediction accurately,the forecasting result was more precise and effective than traditional methods.Our results demonstrate that Bayesian regularization BP neural network can avoid effectively over-fitting in neural network training, the algorithm products networks which have excellent generalization capabilities and can be used as a conduct in application.