الفهرس | Only 14 pages are availabe for public view |
Abstract Abstract Every year, more than one million patients suffer from breast cancer. It is one of the most common causes of death among women. A major threat to human life is cancer and deaths caused by cancer will cross around 12 million people in 2030 according to the World Health Organization (WHO) statistics. The early detection of breast anomalies helps doctor to quickly identify breast cancer. Doctors may rely on a number of precise factors that clarify and predict a person’s risk of developing breast cancer. DNA microarrays have the ability to assess the expression of thousands of genes simultaneously. Recent preliminary research suggests that genotyping of gene expression based on a DNA microarray could provide an independent potential prognostic information in patients with newly diagnosed breast cancer. We introduce new scaling techniques such as arithmetic mean, equilibration, geometric mean, Normalization [0,1], Normalization [-1,1]). By applying these scaling techniques with support vector machine, KNN, Naïve Byse, Random Forest and Decision Tree, we prove that new scaling techniques are efficient against the traditional scaling techniques. |