Mind reading: An automated classification of thought processes from imagery FMRI data

Jong-Hwan Lee, Matthew Marzelli, Ferenc A. Jolesz, Seung Schik Yoo

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

2 Citations (Scopus)

Abstract

Automated interpretation and classification of functional MRI (fMRI) data is an emerging research field that enables the characterization of underlying cognitive processes with minimal human intervention. In this work, we present a method for automated classification of human thoughts reflected on an event-related paradigm using fMRI modality with significantly shortened data acquisition time (less than a minute). Six distinct thoughts (right-hand motor imagery, left-hand motor imagery, right-foot motor imagery, mental calculation, internal word/speech generation, and visual imagery) were chosen as target tasks. Five healthy volunteers performed the tasks. The regions-of-interest (ROIs) were delineated from the activated regions that were consistently and exclusively activated during the training phase. Extracted feature vectors of activations were recognized using a support vector machine (SVM) classifier. With a parameter optimization using a cross-validation scheme, the classifier successfully recognized the six different categories of the given thought tasks with above 80% average accuracy from four participants. The proposed automated processing method of short-time fMRI data can be utilized for the further investigation of monitoring/identifying of human minds and their possible link to the hardware and computer control.

Original languageEnglish
Title of host publication2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010
Pages3174-3179
Number of pages6
Volume6
DOIs
Publication statusPublished - 2010 Nov 15
Event2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010 - Qingdao, China
Duration: 2010 Jul 112010 Jul 14

Other

Other2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010
CountryChina
CityQingdao
Period10/7/1110/7/14

    Fingerprint

Keywords

  • FMRI classification
  • Functional MRI
  • Imagery task
  • Mind reading
  • Support vector machine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Human-Computer Interaction

Cite this

Lee, J-H., Marzelli, M., Jolesz, F. A., & Yoo, S. S. (2010). Mind reading: An automated classification of thought processes from imagery FMRI data. In 2010 International Conference on Machine Learning and Cybernetics, ICMLC 2010 (Vol. 6, pp. 3174-3179). [5580708] https://doi.org/10.1109/ICMLC.2010.5580708