Dimension Reduction for time series with Variational AutoEncoders

Abstract

In this work, we explore dimensionality reduction techniques for univariate and multivariate time series data. We especially conduct a comparison between wavelet decomposition and convolutional variational autoencoders for dimension reduction. We show that variational autoencoders are a good option for reducing the dimension of high dimensional data like ECG. We make these comparisons on a real world, publicly available, ECG dataset that has lots of variability and use the reconstruction error as the metric. We then explore the robustness of these models with noisy data whether for training or inference. These tests are intended to reflect the problems that exist in real-world time series data and the VAE was robust to both tests.

Overview of Data Augmentation Techniques in Time Series Analysis

“…2) Variational Autoencoders (VAEs): Variational Autoencoders (VAEs) are deep generative models that learn latent representations of time series data, used to generate new time series samples by sampling from the learned latent space [49], [50]. In a VAE, the encoder network maps the input time series data to a latent space where each point represents a potential data point, and the decoder network generates time series samples from points in the latent space [51], [52].…”