Dual Denoising Autoencoder Feature Learning for Cancer Diagnosis

Abstract

Microarray data analysis has emerged as a strong tool for cancer diagnosis. Nevertheless, researches on it are significantly challenging as the microarray datasets are imbalanced and high-dimensional with relatively small sample size. In this paper, we utilized Dual Denoising Autoencoder Features (DDAF), which integrates two Denoising Auto-Encoders (DAE) with different activation function to map the features for both minority and majority classes into a better classification representation. The experimental results on four typical microarray datasets show that the DDAF outperforms the Dual Autoencoder Features (DAF) and the Cost-sensitive Oversampling Stacked Denoising Auto-Encoder (CO-SDAE), rendering the robust ability for dimensionality reduction and imbalanced classification.