To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Comparison between Radial Basis Function Network, Multi-Layer Perceptron and Cox Proportional Hazard Model in Survival Data |
|
Author |
Mohammad Salehi Veisi |
| Citation |
Vol. 26 No. 6 pp. 81-88 |
|
Abstract |
An interrelated group of artificial neurons using a mathematical model for information processing based on a connectionist approach to calculation is called an Artificial Neural Network (ANN). Performance of the Radial Basis Function (RBF) was also compared with the most commonly used Multi-Layer Perceptron (MLP) network model and the Cox Proportional Hazard (PH) model. Heart attack database was used for empirical comparisons and the outcomes show that RBF performs better than other models. The cox model is the most applicable method for finding the relationship between explanatory and the stable response variable or any other response variable. One of the limitations from this model is the hypothesis of proper dangers. This means that the amount of danger between two or more than two group of the explanatory variables must be constant over time. |
|
Keywords |
Radial Basis Function Network, Multi-Layer Perceptron, Hazard Model, Survival Data |
|
URL |
