Data-level hybrid strategy selection for disk fault prediction model based on multivariate GAN

TL;DR

This paper proposes a data-level hybrid strategy using multivariate GANs and genetic algorithms to address class imbalance in disk fault prediction, improving classification accuracy on SMART datasets.

Contribution

It introduces a novel combination of multivariate GANs and genetic algorithms for data balancing and fault prediction in disk health monitoring.

Findings

Enhanced dataset balance with GANs improved fault detection accuracy.

Genetic algorithms optimized the classification model performance.

Effective handling of class imbalance in SMART disk datasets.

Abstract

Data class imbalance is a common problem in classification problems, where minority class samples are often more important and more costly to misclassify in a classification task. Therefore, it is very important to solve the data class imbalance classification problem. The SMART dataset exhibits an evident class imbalance, comprising a substantial quantity of healthy samples and a comparatively limited number of defective samples. This dataset serves as a reliable indicator of the disc's health status. In this paper, we obtain the best balanced disk SMART dataset for a specific classification model by mixing and integrating the data synthesised by multivariate generative adversarial networks (GAN) to balance the disk SMART dataset at the data level; and combine it with genetic algorithms to obtain higher disk fault classification prediction accuracy on a specific classification model.