Visual brain activity patterns classification with simultaneous EEG-fMRI: A multimodal approach

Rana Fayyaz Ahmad, Aamir Saeed Malik*, Nidal Kamel, Faruque Reza, Hafeez Ullah Amin, Muhammad Hussain

*Corresponding author for this work

Research output: Contribution to journalArticle (journal)peer-review

7 Citations (Scopus)

Abstract

BACKGROUND: Classification of the visual information from the brain activity data is a challenging task. Many studies reported in the literature are based on the brain activity patterns using either fMRI or EEG/MEG only. EEG and fMRI considered as two complementary neuroimaging modalities in terms of their temporal and spatial resolution to map the brain activity. For getting a high spatial and temporal resolution of the brain at the same time, simultaneous EEG-fMRI seems to be fruitful. METHODS: In this article, we propose a new method based on simultaneous EEG-fMRI data and machine learning approach to classify the visual brain activity patterns. We acquired EEG-fMRI data simultaneously on the ten healthy human participants by showing them visual stimuli. Data fusion approach is used to merge EEG and fMRI data. Machine learning classifier is used for the classification purposes. RESULTS: Results showed that superior classification performance has been achieved with simultaneous EEG-fMRI data as compared to the EEG and fMRI data standalone. This shows that multimodal approach improved the classification accuracy results as compared with other approaches reported in the literature. CONCLUSIONS: The proposed simultaneous EEG-fMRI approach for classifying the brain activity patterns can be helpful to predict or fully decode the brain activity patterns.

Original languageEnglish
Pages (from-to)471-485
Number of pages15
JournalTechnology and Health Care
Volume25
Issue number3
DOIs
Publication statusPublished - 28 Jun 2017

Keywords

  • classification
  • data fusion
  • EEG
  • fMRI
  • simultaneous EEG-fMRI

Fingerprint

Dive into the research topics of 'Visual brain activity patterns classification with simultaneous EEG-fMRI: A multimodal approach'. Together they form a unique fingerprint.

Cite this