A New Automated Method for Evaluating Mental Workload Using Handwriting Features

Zhiming WU  Hongyan XU  Tao LIN  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.9   pp.2147-2155
Publication Date: 2017/09/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDP7354
Type of Manuscript: PAPER
Category: Human-computer Interaction
handwriting feature,  mental workload,  automated evaluation,  

Full Text: PDF(494.3KB)>>
Buy this Article

Researchers have already attributed a certain amount of variability and “drift” in an individual's handwriting pattern to mental workload, but this phenomenon has not been explored adequately. Especially, there still lacks an automated method for accurately predicting mental workload using handwriting features. To solve the problem, we first conducted an experiment to collect handwriting data under different mental workload conditions. Then, a predictive model (called SVM-GA) on two-level handwriting features (i.e., sentence- and stroke-level) was created by combining support vector machines and genetic algorithms. The results show that (1) the SVM-GA model can differentiate three mental workload conditions with accuracy of 87.36% and 82.34% for the child and adult data sets, respectively and (2) children demonstrate different changes in handwriting features from adults when experiencing mental workload.