Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 5 (2022) > Article

DOI: 10.14704/nq.2022.20.5.NQ22227

An Improvised Random Forest Model for Breast Cancer Classification

Dr. Tina Elizabeth Mathew

Abstract

Breast Cancer is considered as the most common cancer in females with high incidence rate. The evolution of modern facilities has helped in reducing the mortality rate, yet the incidence is still the highest among all cancers affecting women. Early diagnosis is a predominant factor for survival. Hence techniques to assist the current modalities are essential. Machine learning techniques have been used so as to produce better prediction and classification models which will aid in better and earlier disease diagnosis and classification. Random Forest is a supervised machine learning classifier that helps in better classification. Random Forests are applied to the Wisconsin breast cancer dataset and the performance of the classifier is evaluated for breast cancer classification. Here in this study an improvised random forest model which uses a cost sensitive learning approach for classification is proposed and it is found to have a better performance than the traditional random forest approach. The model gave an accuracy of 97.51%.

Keywords

Cost Matrix, Decision Trees, Breast Cancer, Classification, Improved Random Forest Classifier Approach (IRFC)

Full Text

PDF

References

?>