Transfer Learning and SpecAugment applied to SSVEP Based BCI Classification

10/08/2020
by   Pedro R. A. S. Bassi, et al.
13

In this work, we used a deep convolutional neural network (DCNN) to classify electroencephalography (EEG) signals in a steady-state visually evoked potentials (SSVEP) based brain-computer interface (BCI). The raw EEG signals were converted to spectrograms and served as input to train a DCNN using the transfer learning technique. We applied a second technique, data augmentation, mostly SpecAugment, generally employed to speech recognition. The results, when excluding the evaluated user's data from the fine-tuning process, reached 99.3 mean test accuracy and 0.992 mean F1 score on 35 subjects from an open dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2018

An amplitudes-perturbation data augmentation method in convolutional neural networks for EEG decoding

Brain-Computer Interface (BCI) system provides a pathway between humans ...
research
04/13/2020

Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progresses Since 2016

A brain-computer interface (BCI) enables a user to communicate directly ...
research
12/15/2020

Deep Learning Based Classification of Unsegmented Phonocardiogram Spectrograms Leveraging Transfer Learning

Cardiovascular diseases (CVDs) are the main cause of deaths all over the...
research
09/05/2021

FBCNN: A Deep Neural Network Architecture for Portable and Fast Brain-Computer Interfaces

Objective: To propose a novel deep neural network (DNN) architecture – t...
research
06/11/2021

Efficient Deep Learning Architectures for Fast Identification of Bacterial Strains in Resource-Constrained Devices

This work presents twelve fine-tuned deep learning architectures to solv...
research
08/06/2018

Deep Transfer Learning for EEG-based Brain Computer Interface

The electroencephalography classifier is the most important component of...
research
04/10/2020

Deep transfer learning for improving single-EEG arousal detection

Datasets in sleep science present challenges for machine learning algori...

Please sign up or login with your details

Forgot password? Click here to reset