Microarray Gene Expression Cancer Diagnosis Using Modified Extreme Learning Machine Classification

Cancer classification is one of the major research areas in the medical fields. The primary objective is to propose efficient cancer classification techniques which provide reliable and significant classification accuracy. To achieve this primary research goal is to find the smallest set of genes that can ensure better performance in classification using machine learning algorithms. Gene expression of microarray data requires the selection of subsets of relevant genes in order to achieve good classification. Modified Extreme Learning Machine (MELM) is used for direct multicategory classification problems in the cancer diagnosis area. Modified ELM avoids problems like local minima, improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. Experimental result shows that the Modified Extreme Learning Machine (MELM) classifier is used for increasing the classification accuracy over ELM by using three benchmarks microarray datasets for cancer diagnosis namely, Leukemia, Lymphoma and SRBCT.