Integrating Behavior Modeling with Data Mining to Improve Human Error Prediction in Numerical Data Entry

Abstract

Human errors in numerical data entry can lead to serious consequence but it is difficult to predict those errors because mechanisms of human errors vary and no contextual clues are available. This study suggests integrating human behavior modeling and data mining as an advanced method to predict human errors. Human behavior modeling utilized top-down inference to transform interactions between task characteristics and conditions into general inclination of an average operator to make errors, while data mining parsed psychophysiological measurements into individual’s likeliness of making errors on a trial-by-trial basis through bottom-up analysis. Specifically, an enhanced Queuing Network-Model Human Processor (QN-MHP) generated modeling features to be combined with real-time EEG features that were collected in a realistic numerical typing experiment, and potential errors were predicted by detecting error-associated features by linear discriminant analysis (LDA) classifiers before responses. The detection could be made as early as 300 milliseconds beforehand, and the results showed that integration improved the LDA classifiers’ performance by 31.7% in keenness (d') and by 12.5 % in area under ROC curve (AUC) from that of using EEG only. The integration may help implement future adaptive augmented system to prevent cognitive breakdown by determining appropriate automation/augmentation levels.