GSR and Blink Features for Cognitive Load Classification

Abstract

Abstract.A system capable of monitoring its user's mental workload can evaluate the suitability of its interface and interactions for user's current cognitive status and properly change them when necessary. Galvanic skin response (GSR) and eye blinks are cognitive load measures which can be captured conveniently and at low cost. The present study has assessed multiple features of these two signals in classification of cognitive workload level. The experiment included arithmetic tasks with four difficulty levels and two types of machine learning algorithms have been applied for classification. Obtained results show that the studied features of blink and GSR can reasonably discriminate workload levels and combining features of the two modalities improves the accuracy of cognitive load classification. We have achieved around 75% for binary classification and more than 50% for four-class classification.

Medical students' cognitive load in volumetric image interpretation: Insights from human-computer interaction and eye movements

“…A wide variety of measures are utilised for measuring cognitive load, such as dualtask methodology (Brünken, Steinbacher, Schnotz, Plass, & Leutner, 2002), physiological measures (Antonenko, Paas, Grabner, & van Gog, 2010;DeLeeuw & Mayer, 2008;Nourbakhsh, Wang, & Chen, 2013), and self-report ratings (Kirschner, Paas, & Kirschner, 2009). However, these measures only provide a quantitative indication of cognitive load (Sweller, Ayres, & Kalyuga, 2011) but are uninformative of what causes this cognitive load.…”

“…The current research contributes to a growing body of research using indirect and direct objective measures to measure cognitive load such as EEG , skin response (Nourbakhsh et al, 2013), speech (Khawaja, Chen, & Marcus, 2014), eye movements (Chen & Epps, 2013) and human-computer interaction (Ruiz et al, 2011(Ruiz et al, , 2007.…”

Dynamic Workload Adjustments in Human-Machine Systems Based on GSR Features

“…A new task is followed with a particular CL level controlled by the adaptation model. CL levels are designed as in Table 1 based on [3], where the nu mber in each o f the co lu mns represents how many of the particular category of number (binary, 1-digit, 2-digit, 3-digit) are shown in the task.…”

“…Cognitive load measurement (CLM ) therefo re plays an important role in applications involving human-mach ine interface. Furthermo re, Galvanic Skin Response (GSR) is a measure of conductivity of hu man skin, and can provide an indication of changes in human sympathetic nervous system [3]. GSR has attracted researchers' attention as a prospective physiological indicator of cognitive load [3].…”

“…Furthermo re, Galvanic Skin Response (GSR) is a measure of conductivity of hu man skin, and can provide an indication of changes in human sympathetic nervous system [3]. GSR has attracted researchers' attention as a prospective physiological indicator of cognitive load [3]. In order to keep the user in an optimal state and improve user's engagement and performance, dynamic workload adjustment (DWA) systems automatically modulat e the difficu lty of tasks and other factors related to tasks in human -machine systems in real-t ime.…”