High Accuracy Optical Character Recognition Using Neural Networks with Centroid Dithering
IEEE Transactions on Pattern Analysis and Machine Intelligence
A study of cross-validation and bootstrap for accuracy estimation and model selection
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Integrated feature architecture selection
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
The paper demonstrates an artificial neural networks (ANN) model for prediction survival of colorectal cancer. Data model is collected from SEER which is one of the largest and most comprehensive sources of information on cancer incidence and survival in the USA. Data set consists of over 100000 of colorectal cancer patients. Experimental results are carried out to get the minimum number of extracted features with an optimum ANN architecture without decreasing the prediction accuracy rate. Two models of prediction survival are described. In the first model, the experimental results show that the maximum prediction rate is 84.73%. In the second model, the main objective is to discover the minimum subset of input features that yields the highest accuracy. The experiment results reveal that 73.68% of selected features are sufficient for discrimination and the maximum prediction rate achieves 86.51%. Moreover, 72.72% of hidden neurons are sufficient to get optimum ANN architecture.