SVAD: Stacked Variational Autoencoder Deep Neural Network -Based Dimensionality Reduction and classification of Small Sample Size and High Dimensional Data

Abstract

Abstract The classification problem is a major concern in the field of computational biology, especially when there are many fewer samples than features. This is referred regarded as a "curse of dimensionality" problem caused by high-dimensional sample size problems. Many strategies for dimensionality reduction have been presented, however, they all have drawbacks when it comes to high-dimensional and small sample size (HDSSS) databases, such as large variance gradients and over-fitting issues. To address these issues, we suggested a variational autoencoder based deep neural network architecture that is dynamic and based on a mathematical foundation for unsupervised learning. The objective of this research is to propose a low-error classification algorithm for limited sample numbers and high-dimensional datasets. The study's innovation is that it guarantees the permissible dimension size regardless of reduction, in contrast to several previous approaches that typically reduce the dimension too heavily.The experimental findings reveal that the suggested method outperforms existing traditional methods such as RNN, CNN, and deep network architecture.