Identificación de características de células de cáncer de mama por medio de testores típicos

One of the most significant concerns around the world has been human health, especially in diseases such as cancer. For this reason, this paper is focused on the application of Computer Science, specifically, Feature Subset Selection and Typical Testors to improve the diagnosis of cancer. In this case, a breast cancer cell database was processed. This database was published by the University of California for machine learning. The data describes features of the cell nuclei obtained from a digitized image of a fine needle aspirate of a breast mass classifying every cell as malignant or benign. Finally, the method will provide the informational weight of each feature. This information will let know if a feature actually describes a cell and then, classify new instances with the right data.