| Popis: |
Cervical cancer is one of the most common types of cancer in women. The way to reduce the number of deaths due to this type of cancer is early diagnosis. Machine learning and data mining techniques are used to assist doctors while early diagnosing the disease. In this study, a new method exploiting correlation-based feature selection (CFS), genetic algorithm (GA) and random forests (RF) techniques is proposed for the diagnosis of cervical cancer. The performance of the proposed method consisting of three stages: data preprocessing, feature selection and classification has been tested using classification accuracy, precision, recall, and F-measure metrics. In the sequel, the performance results are compared with the conventional machine learning techniques and the existing studies in the literature. It can be seen from the experimental results that the proposed method is effective and can be used as an auxiliary tool by doctors in diagnosing cervical cancer early. |
