Advanced Information Networking and Applications Workshops, International Conference on (2007)
Niagara Falls, Ontario, Canada
May 21, 2007 to May 23, 2007
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AINAW.2007.55
Jiawei Rong , University of Oregon, USA
Dejing Dou , University of Oregon, USA
Gwen Frishkoff , University of Pittsburgh, USA
Robert Frank , University of Oregon, USA
Allen Malony , University of Oregon, USA
Don Tucker , University of Oregon, USA
Event-related potentials (ERP) are brain electrophysiological patterns created by averaging electroencephalographic (EEG) data, time-locking to events of interest (e.g., stimulus or response onset). In this paper, we propose a semi-automatic framework for mining ERP data, which includes the following steps: PCA decomposition, extraction of summary metrics, unsupervised learning (clustering) of patterns, and supervised learning, i.e. discovery, of classification rules. Results show good correspondence between rules that emerge from decision tree classifiers and rules that were independently derived by domain experts. In addition, data mining results suggested ways in which expert-defined rules might be refined to improve pattern representation and classification results.
D. Dou, D. Tucker, R. Frank, J. Rong, G. Frishkoff and A. Malony, "A Semi-Automatic Framework for Mining ERP Patterns," Advanced Information Networking and Applications Workshops, International Conference on(AINAW), Niagara Falls, Ontario, Canada, 2007, pp. 329-334.