Decoding semantic information from human electrocorticographic (ECoG) signals

Wei Wang, Alan D. Degenhart, Gustavo P. Sudre, Dean A. Pomerleau, Elizabeth C. Tyler-Kabara

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

34 Scopus citations

Abstract

This study examined the feasibility of decoding semantic information from human cortical activity. Four human subjects undergoing presurgical brain mapping and seizure foci localization participated in this study. Electrocorticographic (ECoG) signals were recorded while the subjects performed simple language tasks involving semantic information processing, such as a picture naming task where subjects named pictures of objects belonging to different semantic categories. Robust high-gamma band (60-120Hz) activation was observed at the left inferior frontal gyrus (LIFG) and the posterior portion of the superior temporal gyrus (pSTG) with a temporal sequence corresponding to speech production and perception. Furthermore, Gaussian Nave Bayes and Support Vector Machine classifiers, two commonly used machine learning algorithms for pattern recognition, were able to predict the semantic category of an object using cortical activity captured by ECoG electrodes covering the frontal, temporal and parietal cortices. These findings have implications for both basic neuroscience research and development of semantic-based brain-computer interface systems (BCI) that can help individuals with severe motor or communication disorders to express their intention and thoughts.

Original languageEnglish
Title of host publication33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Pages6294-6298
Number of pages5
DOIs
StatePublished - 2011
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States
Duration: Aug 30 2011Sep 3 2011

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Country/TerritoryUnited States
CityBoston, MA
Period08/30/1109/3/11

Fingerprint

Dive into the research topics of 'Decoding semantic information from human electrocorticographic (ECoG) signals'. Together they form a unique fingerprint.

Cite this