Variational Autoencoder Learns Better Feature Representations for EEG-based Obesity Classification

TL;DR

This paper introduces a variational autoencoder framework for extracting EEG features to classify obesity, demonstrating improved accuracy and interpretability over traditional methods.

Contribution

The study presents a novel VAE-based approach for EEG feature extraction that enhances classification performance in obesity detection.

Findings

VAE outperforms conventional methods in accuracy

Features show better visualization and lower impurity

Model reduces noise and captures invariant features

Abstract

Obesity is a common issue in modern societies today that can lead to various diseases and significantly reduced quality of life. Currently, research has been conducted to investigate resting state EEG (electroencephalogram) signals with an aim to identify possible neurological characteristics associated with obesity. In this study, we propose a deep learning-based framework to extract the resting state EEG features for obese and lean subject classification. Specifically, a novel variational autoencoder framework is employed to extract subject-invariant features from the raw EEG signals, which are then classified by a 1-D convolutional neural network. Comparing with conventional machine learning and deep learning methods, we demonstrate the superiority of using VAE for feature extraction, as reflected by the significantly improved classification accuracies, better visualizations and reduced impurity measures in the feature representations. Future work can be directed to gaining an in-depth understanding regarding the spatial patterns that have been learned by the proposed model from a neurological view, as well as improving the interpretability of the proposed model by allowing it to uncover any temporal-related information.