A Hybrid Complex-valued Neural Network Framework with Applications to Electroencephalogram (EEG)

TL;DR

This paper introduces a hybrid complex-valued neural network framework that effectively utilizes phase information from EEG signals, reducing parameters and improving classification accuracy on benchmark and simulated data.

Contribution

It presents a novel neural network architecture combining complex and real-valued CNNs with DFT for enhanced EEG signal classification.

Findings

Reduces model parameters significantly.

Improves accuracy over existing methods.

Enhances classification of simulated EEG signals.

Abstract

In this article, we present a new EEG signal classification framework by integrating the complex-valued and real-valued Convolutional Neural Network(CNN) with discrete Fourier transform (DFT). The proposed neural network architecture consists of one complex-valued convolutional layer, two real-valued convolutional layers, and three fully connected layers. Our method can efficiently utilize the phase information contained in the DFT. We validate our approach using two simulated EEG signals and a benchmark data set and compare it with two widely used frameworks. Our method drastically reduces the number of parameters used and improves accuracy when compared with the existing methods in classifying benchmark data sets, and significantly improves performance in classifying simulated EEG signals.