원문정보
초록
영어
This paper presents an automatic system for detection of breast cancer using data preprocessing and Bayesian network. In this study, ReliefF algorithm is used for reducing the dimension of breast cancer database then a pre-processing is done on the data and ultimately Bayesian network classifier is used for classification. The system performance has been compared with model NN (neural network) and AR + NN (neural networks combined with association rules). The dimension of input feature space is reduced from nine to eight by using ReliefF. In test stage, 3-fold cross validation method was applied to the Wisconsin breast cancer database to evaluate the proposed system performance. The correct classification rate of proposed system is 98.1%.This research offered that the preprocessing is necessary on this data and combination of ReliefF and Bayesian network can be used to obtain fast automatic diagnostic systems for breast cancer.
목차
1. Introduction
2. Characteristics of Wisconsin Breast Cancer Database
3. Feature Reduction
4. Missing Data Handling and Data Balancing
5. Bayesian Network
6. Results
7. Conclusion
References