Prediction of human error before it occurs is one of the most challenging topics in human factors engineering research.
Supported by NSF, this project led by professor Sean Wu studies the applications of data mining techniques in early detection of numerical typing errors by human operators through a quantitative analysis of multichannel electroencephalogram (EEG) recordings. Three feature extraction techniques were developed to capture temporal, morphological and time-frequency (wavelet) characteristics of EEG data. Based on the current results, it is possible to predict erroneous keystrokes a few hundred million seconds prior to error occurrence. This research transforms human error research work from traditional post-hoc analysis to real-time prediction of its occurrence with potential applications of intelligent human error prevention systems.