S. Cang and D. Partridge (UK)
Mixture Model, Probability Density Function, Bayes’ Rule, Multiplayer Perceptron Neural Network
This paper presents a new approach to finding the probability density function (PDF) for continuous and discrete variables together, a combined continuous and discrete (CCD) mixture model. Probability density functions play an important role in pattern recognition. If we obtain the probability density function for each class, then the classification rate for data set can be obtained by using Bayes’ rule, a combined continuous and discrete probability (CCDP) neural network. The PDF for continuous and discrete variables is very useful in many applications. It is demonstrated that the new algorithm can produce better results than Multilayer Perceptron (MLP) neural network does on a difficult real application, the Trauma data.
Important Links:
Go Back
