Biosignal Generation and Latent Variable Analysis With Recurrent Generative Adversarial Networks

Shota Harada,Hideaki Hayashi,Seiichi Uchida

doi:10.1109/access.2019.2934928

Shota Harada, Hideaki Hayashi + Show 1 more

Open Access

https://doi.org/10.1109/access.2019.2934928

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2019
Citations: 22	License type: CC BY 4.0

Affiliation: Kyushu University

Abstract

The effectiveness of biosignal generation and data augmentation with biosignal generative models based on generative adversarial networks (GANs), which are a type of deep learning technique, was demonstrated in our previous paper. GAN-based generative models only learn the projection between a random distribution as input data and the distribution of training data.Therefore, the relationship between input and generated data is unclear, and the characteristics of the data generated from this model cannot be controlled. This study proposes a method for generating time-series data based on GANs and explores their ability to generate biosignals with certain classes and characteristics. Moreover, in the proposed method, latent variables are analyzed using canonical correlation analysis (CCA) to represent the relationship between input and generated data as canonical loadings. Using these loadings, we can control the characteristics of the data generated by the proposed method. The influence of class labels on generated data is analyzed by feeding the data interpolated between two class labels into the generator of the proposed GANs. The CCA of the latent variables is shown to be an effective method of controlling the generated data characteristics. We are able to model the distribution of the time-series data without requiring domain-dependent knowledge using the proposed method. Furthermore, it is possible to control the characteristics of these data by analyzing the model trained using the proposed method. To the best of our knowledge, this work is the first to generate biosignals using GANs while controlling the characteristics of the generated data.

Highlights

Biosignals, such as electrocardiogram (ECG) and electroencephalogram (EEG) signals, strongly reflect human internal states
This study proposes a generation method based on generative adversarial networks (GANs) that can select the class of generated data based on the class label
In this study, a conditional generation method for timeseries data based on GANs was proposed

Summary

INTRODUCTION

Biosignals, such as electrocardiogram (ECG) and electroencephalogram (EEG) signals, strongly reflect human internal states. The behavior of the GAN-based generative model is analyzed to control the characteristics of the data generated by the proposed method. This study proposes a generation method based on GANs that can select the class of generated data based on the class label. In this method, it is not required to learn models independently in each class. A unique property of the proposed method is that both G and D are LSTMs to generate time-series (i.e., sequences), whereas G and D are convolutional neural networks in most GANs. For generating sequences of length T , G and D are trained with a training set X , which comprises M training sequences.

BIOSIGNAL GENERATION EXPERIMENT

ANALYSIS OF LATENT VARIABLE SPACE AND CONTROL OF GENERATED DATA

DISCUSSION

CONCLUSION