TY - GEN
T1 - Decoding semantic information from human electrocorticographic (ECoG) signals
AU - Wang, Wei
AU - Degenhart, Alan D.
AU - Sudre, Gustavo P.
AU - Pomerleau, Dean A.
AU - Tyler-Kabara, Elizabeth C.
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84864617645&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2011.6091553
DO - 10.1109/IEMBS.2011.6091553
M3 - Conference contribution
C2 - 22255777
AN - SCOPUS:84864617645
SN - 9781424441211
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 6294
EP - 6298
BT - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
T2 - 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Y2 - 30 August 2011 through 3 September 2011
ER -