On the improvement of classifying EEG recordings using neural networks

Yiran Zhao, Raghu Ganti, Shuochao Yao, Mudhakar Srivatsa, Shaohan Hu, Shen Li, Shiyu Chang, Tarek Abdelzaher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents improved results on classifying electroencephalography (EEG) recordings using deep learning. The task is to classify movements that the subject is thinking about (motor imagery), using only the recorded electrical activities on the scalp. The challenges are: poor signal-to-noise ratio; interference from numerous sources such as electrical line noise, muscle activity, and eye movements; considerable variability between individuals and even recording sessions. Traditional signal processing techniques such as frequency band analysis, common spatial pattern (CSP) algorithm or independent component analysis (ICA) fall short due to their limited capacity. Thanks to the rise of big data in healthcare, medical recordings now come in abundance. Therefore deep learning which relies on large amounts of training data is becoming the new cutting edge tool. We present a significant improvement of classification accuracy on the Brain-Computer Interfaces Competition IV dataset (2a), and compare the results of various state of the art neural network structures.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Big Data, Big Data 2017
EditorsJian-Yun Nie, Zoran Obradovic, Toyotaro Suzumura, Rumi Ghosh, Raghunath Nambiar, Chonggang Wang, Hui Zang, Ricardo Baeza-Yates, Ricardo Baeza-Yates, Xiaohua Hu, Jeremy Kepner, Alfredo Cuzzocrea, Jian Tang, Masashi Toyoda
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1709-1711
Number of pages3
ISBN (Electronic)9781538627143
DOIs
StatePublished - Jul 1 2017
Event5th IEEE International Conference on Big Data, Big Data 2017 - Boston, United States
Duration: Dec 11 2017Dec 14 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Big Data, Big Data 2017

Other

Other5th IEEE International Conference on Big Data, Big Data 2017
Country/TerritoryUnited States
CityBoston
Period12/11/1712/14/17

Keywords

  • BCI Competition IV
  • Deep learning
  • EEG
  • Motor imagery

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems
  • Information Systems and Management
  • Control and Optimization

Fingerprint

Dive into the research topics of 'On the improvement of classifying EEG recordings using neural networks'. Together they form a unique fingerprint.

Cite this