Abstract
Breast cancer affects millions of people annually, women being the most affected. This is a number that increases every year therefore, more tools are needed for an early detection to prevent cancer from spreading to other organs. In this article, we present a new method which is divided in 6 steps. First, data must be extracted, to subsequently remove all the noise from the dataset. Then, the data must be transformed and normalized. Next, an exploratory analysis is made to find the most correlated variables. After, the following supervised learning techniques are applied: Random Forest, Adaboost, and Artificial Neural Network. Finally, conclusions are presented. To be able to carry this method, a public dataset was used from University of California Irvine: Breast Cancer Coimbra Data Set. At last, this method can be applied for the detection of this disease and other diseases.
Translated title of the contribution | Breast Cancer Detection in the corpus “Breast Cancer Coimbra Data Set” Using Data Mining and Artificial Neural Networks |
---|---|
Original language | Spanish |
Pages (from-to) | 528-539 |
Number of pages | 12 |
Journal | RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao |
Volume | 2023 |
Issue number | E56 |
State | Published - 2023 |
Bibliographical note
Publisher Copyright:© 2023, Associacao Iberica de Sistemas e Tecnologias de Informacao. All rights reserved.