Skip to main navigation Skip to search Skip to main content

Common Spatial Pattern Based Data Augmentation Technique for Decoding Imagined Speech

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Modern machine learning techniques require a huge amount of training data for satisfactory performance. This limits the application of these techniques in classifying EEG signals due to the non-availability of huge datasets. One way to mitigate this problem is by using data augmentation techniques to increase the number of training samples. In this paper, a novel common spatial pattern (CSP) based data augmentation technique is proposed. The efficiency of the proposed method is demonstrated by training a deep neural network (DNN) on the augmented dataset for decoding imagined speech from EEG. Using CSP, nine EEG channels that best represent the underlying cortical activity corresponding to the imagination of the words 'in' and 'cooperate' are identified, and discrete wavelet transform (DWT) features are extracted for each of these channels. Treating the selected EEG corresponding to each imagined word as an independent sample helps in providing enough samples to train the DNN. Maximum voting is applied to the results of individual feature vectors of each trial to obtain the predicted class label. We have obtained accuracies exceeding change level accuracies across subjects, which indicates that the network is able to generalize well.

Original languageEnglish
Title of host publicationProceedings of CONECCT 2021
Subtitle of host publication7th IEEE International Conference on Electronics, Computing and Communication Technologies
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665428491
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event7th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2021 - Bangalore, India
Duration: 9 Jul 2021 → 11 Jul 2021

Publication series

NameProceedings of CONECCT 2021: 7th IEEE International Conference on Electronics, Computing and Communication Technologies

Conference

Conference7th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2021
Country/TerritoryIndia
CityBangalore
Period9/07/21 → 11/07/21

Keywords

  • Brain-computer interface
  • Common spatial pattern
  • Deep learning
  • Imagined speech
  • Spatial filter

Fingerprint

Dive into the research topics of 'Common Spatial Pattern Based Data Augmentation Technique for Decoding Imagined Speech'. Together they form a unique fingerprint.

Cite this