Literature DB >> 32730917

CWT Based Transfer Learning for Motor Imagery Classification for Brain computer Interfaces.

Piyush Kant1, Shahedul Haque Laskar2, Jupitara Hazarika2, Rupesh Mahamune2.   

Abstract

BACKGROUND: The processing of brain signals for Motor imagery (MI) classification to have better accuracy is a key issue in the Brain-Computer Interface (BCI). While conventional methods like Artificial neural network (ANN), Linear discernment analysis (LDA), K-Nearest Neighbor (KNN), Support vector machine (SVM), etc. have made significant progress in terms of classification accuracy, deep transfer learning-based systems have shown the potential to outperform them. BCI can play a vital role in enabling communication with the external world for persons with motor disabilities. NEW
METHODS: Deep learning has been a success in many fields. However, for Electroencephalogram (EEG) signals, relatively minimal work has been carried out using deep learning. This paper proposes a combination of Continuous Wavelet Transform (CWT) along with deep learning-based transfer learning to solve the problem. CWT transforms one dimensional EEG signals into two-dimensional time-frequency-amplitude representation enabling us to exploit available deep networks through transfer learning.
RESULTS: The effectiveness of the proposed approach is evaluated in this study using an openly available BCI competition data-set. The results of the approach have been compared to earlier works on the same dataset, and a promising validation accuracy of 95.71% is achieved in our investigation. COMPARISON WITH EXISTING METHODS AND
CONCLUSION: Our approach has shown significant improvement over other studies, which is 5.71% improvement over earlier reported algorithm (Tabar and Halici, 2017) using the same dataset. Results show the validity of the proposed Deep Transfer-Learning based technique as a state of the art technique for MI classification in BCI.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  EEG signal processing; Transfer Learning; convolutional neural network; cwt filter-bank; deep learning; short-time Fourier transform

Mesh:

Year:  2020        PMID: 32730917     DOI: 10.1016/j.jneumeth.2020.108886

Source DB:  PubMed          Journal:  J Neurosci Methods        ISSN: 0165-0270            Impact factor:   2.390


  3 in total

1.  Multi-Hierarchical Fusion to Capture the Latent Invariance for Calibration-Free Brain-Computer Interfaces.

Authors:  Jun Yang; Lintao Liu; Huijuan Yu; Zhengmin Ma; Tao Shen
Journal:  Front Neurosci       Date:  2022-04-25       Impact factor: 5.152

2.  Arithmetic Optimization with RetinaNet Model for Motor Imagery Classification on Brain Computer Interface.

Authors:  Areej A Malibari; Fahd N Al-Wesabi; Marwa Obayya; Mimouna Abdullah Alkhonaini; Manar Ahmed Hamza; Abdelwahed Motwakel; Ishfaq Yaseen; Abu Sarwar Zamani
Journal:  J Healthc Eng       Date:  2022-03-24       Impact factor: 2.682

3.  Stockwell transform and semi-supervised feature selection from deep features for classification of BCI signals.

Authors:  Sahar Salimpour; Hashem Kalbkhani; Saeed Seyyedi; Vahid Solouk
Journal:  Sci Rep       Date:  2022-07-11       Impact factor: 4.996

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.