Robust Multimodal Cognitive Load Measurement
Abstract
The objective of this project includes research of the fundamental issues related to the use of multiple input modalities and their fusion to enable robust and automatic cognitive load measurement (CLM) in the real world. Firstly, we carried out a further literature review on physiological measures of cognitive workload to include the recent advances of physiological measures of cognitive workload. In the meantime, we examined the use of various features (e.g. spectral and approximate entropies, wavelet-based complexity measures, correlation dimension, Hurst exponent) of electroencephalogram (EEG) signals to evaluate changes in working memory load during the performance of a cognitive task with varying difficulty/load levels. Eye based CLM was also studied. Eye activities such as pupillary response, blink, and eye movement (fixation and saccade) were investigated for CLM. We further investigated the linguistic and grammatical feature based CLM in this study and analyzed novel linguistic features as potential indices of cognitive load. Other modalities such as Galvanic skin response (GSR), face, and writing behavior were also extensively analyzed in indexing cognitive load levels. We also investigated the effect of stress on cognitive load. All together, we had carried out CLM study of multiple unobtrusive modalities, namely EEG, eye activity, linguistic and grammatical features, GSR, face, and writing behavior for CLM as well as emotion interference for CLM, in the past two-year
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 26, 2014
- Accession Number
- ADA606647
Entities
People
- Fang Chen