An efficient approach for automatic removal of ocular artifacts from multichannel EEG data

Muhammad Tahir Akhtar, Wataru Mitsuhashi, Christopher J. James

Research output: Contribution to conferencePaper

Abstract

This paper proposes an efficient approach, based on independent component analysis (ICA) and wavelet denoising (WD), for automatic removal of ocular artifacts from EEG data. In the proposed approach, we employ the concept of spatially constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the EEG data, use WD to remove any cerebral activity from extracted ICs to obtain artifact-only components, and finally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as it is not necessary to identify all ICs. Computer experiments are carried out for long term EEG, which demonstrate the effectiveness of the proposed approach.

Original languageEnglish
Pages927-930
Number of pages4
Publication statusPublished - Dec 1 2010
Event2nd Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2010 - Biopolis, Singapore
Duration: Dec 14 2010Dec 17 2010

Conference

Conference2nd Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2010
CountrySingapore
CityBiopolis
Period12/14/1012/17/10

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Fingerprint Dive into the research topics of 'An efficient approach for automatic removal of ocular artifacts from multichannel EEG data'. Together they form a unique fingerprint.

  • Cite this

    Akhtar, M. T., Mitsuhashi, W., & James, C. J. (2010). An efficient approach for automatic removal of ocular artifacts from multichannel EEG data. 927-930. Paper presented at 2nd Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2010, Biopolis, Singapore.