Orthogonal Features-based EEG Signal Denoising using Fractionally Compressed AutoEncoder

02/16/2021
by   Subham Nagar, et al.
0

A fractional-based compressed auto-encoder architecture has been introduced to solve the problem of denoising electroencephalogram (EEG) signals. The architecture makes use of fractional calculus to calculate the gradients during the backpropagation process, as a result of which a new hyper-parameter in the form of fractional order (α) has been introduced which can be tuned to get the best denoising performance. Additionally, to avoid substantial use of memory resources, the model makes use of orthogonal features in the form of Tchebichef moments as input. The orthogonal features have been used in achieving compression at the input stage. Considering the growing use of low energy devices, compression of neural networks becomes imperative. Here, the auto-encoder's weights are compressed using the randomized singular value decomposition (RSVD) algorithm during training while evaluation is performed using various compression ratios. The experimental results show that the proposed fractionally compressed architecture provides improved denoising results on the standard datasets when compared with the existing methods.

READ FULL TEXT
research
04/16/2021

Orthogonal Features Based EEG Signals Denoising Using Fractional and Compressed One-Dimensional CNN AutoEncoder

This paper presents a fractional one-dimensional convolutional neural ne...
research
08/17/2022

Deep Autoencoder Model Construction Based on Pytorch

This paper proposes a deep autoencoder model based on Pytorch. This algo...
research
05/28/2018

Block-optimized Variable Bit Rate Neural Image Compression

In this work, we propose an end-to-end block-based auto-encoder system f...
research
09/07/2018

Unsupervised Sentence Compression using Denoising Auto-Encoders

In sentence compression, the task of shortening sentences while retainin...
research
04/10/2021

Latent Code-Based Fusion: A Volterra Neural Network Approach

We propose a deep structure encoder using the recently introduced Volter...
research
03/06/2019

Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders

Denoising of time domain data is a crucial task for many applications su...

Please sign up or login with your details

Forgot password? Click here to reset