Microarray breast cancer data classification using machine learning methods
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Abstract
In this study We used microarray breast cancer data for classification of the patients using machine learning methods. First, 8 different machine learning algorithms are applied to the data, without applying any feature selection methods. Then two different feature selection methods are applied. The results of the classifications are compared with each other and with the results of the first case. The methods applied are SVM, KNN, MLP, Decision Trees, Random Forest, Logistic Regression, Adaboost and Gradient Boosting Machines. After applying the two different feature selection methods with the best 50 features are applied, SVM gave the best results. MLP is applied using different number of layers and neurons to examine the effect of the number of layers and neurons on the classification accuracy. It is determined that the increase in the number of layers sometimes decreased, sometimes didn't change the accuracy.Keywords
This publication has 6 references indexed in Scilit:
- A Cancer Gene Selection Algorithm Based on the K-S Test and CFSBioMed Research International, 2017
- An Ensemble of Filters and Wrappers for Microarray Data ClassificationMachine Learning and Applications: An International Journal, 2016
- Tumor MicroRNA Expression Profiling Identifies Circulating MicroRNAs for Early Breast Cancer DetectionClinical Chemistry, 2015
- A review of microarray datasets and applied feature selection methodsInformation Sciences, 2014
- Breast cancer statistics, 2011CA: A Cancer Journal for Clinicians, 2011
- Gene expression profiling predicts clinical outcome of breast cancerNature, 2002