A New Automated Method for Evaluating Mental Workload Using Handwriting Features

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 twolevel handwriting features (i.e., sentenceand 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. key words: handwriting feature, mental workload, automated evaluation

[1]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[2]  C. M. Levy,et al.  Writing, Reading, and Speaking Memory Spans and the Importance of Resource Flexibility , 2005 .

[3]  M. Angela Sasse,et al.  From doing to being: getting closer to the user experience , 2004, Interact. Comput..

[4]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[5]  F. Paas,et al.  Cognitive Load Measurement as a Means to Advance Cognitive Load Theory , 2003 .

[6]  Sara Rosenblum,et al.  A computerized multidimensional measurement of mental workload via handwriting analysis , 2012, Behavior research methods.

[7]  G. Heath.  Writing , 1971, Veterinary Record.

[8]  F. T. Eggemeier,et al.  Recommendations for Mental Workload Measurement in a Test and Evaluation Environment , 1993 .

[9]  Mingtian Zhou,et al.  Feature selection and parameter optimization for support vector machines: A new approach based on genetic algorithm with feature chromosomes , 2011, Expert Syst. Appl..

[10]  Tao Lin,et al.  Using multiple data sources to get closer insights into user cost and task performance , 2008, Interact. Comput..

[11]  A. Kramer,et al.  Physiological metrics of mental workload: A review of recent progress , 1990, Multiple-task performance.

[12]  John P. Wann,et al.  Handwriting Disturbances: Developmental Trends , 1986 .

[13]  Fang Chen,et al.  Cognitive load evaluation of handwriting using stroke-level features , 2011, IUI '11.

[14]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[15]  G P Van Galen,et al.  Dysgraphia in children: lasting psychomotor deficiency or transient developmental delay? , 1997, Journal of experimental child psychology.

[16]  C. Mélan,et al.  What is the relationship between mental workload factors and cognitive load types? , 2012, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[17]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[18]  Roel Vertegaal,et al.  Using mental load for managing interruptions in physiologically attentive user interfaces , 2004, CHI EA '04.

[19]  Bernhard Schölkopf,et al.  Feature selection for support vector machines by means of genetic algorithm , 2003, Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence.

[20]  Yang Wang,et al.  Multimodal behavior and interaction as indicators of cognitive load , 2012, TIIS.

[21]  Regan L. Mandryk,et al.  A fuzzy physiological approach for continuously modeling emotion during interaction with play technologies , 2007, Int. J. Hum. Comput. Stud..

[22]  Yu Chen,et al.  Automatic cognitive load evaluation using writing features: An exploratory study , 2013 .

[23]  Kun Yu,et al.  Cognitive Load Evaluation with Pen Orientation and Pressure , 2011 .