Feasibility Study on Estimating Visual Attention using Electrodermal Activity

Abstract

Electrodermal Activity (EDA) refers to change in the electrical properties of skin during mental exertion caused by tension and agitation. In recent studies, it has been revealed that there is an overlap between the brain activation area where emotion occurs and the brain activation area responsible for attentiveness. Consequently, in this paper we test our hypothesis that, given these findings, visual attention can be estimated via EDA. The results of experiments conducted verify that EDA can be used as an attention index.

Estimating Orchestration Load in CSCL Situations Using EDA

“…Moreover, previous studies have shown that SCRs occur when a human changes their focus of attention [7]. Report 5.1 (See Table II) took place while the teacher was focused on the dashboard, reading students' answers and inspecting the activity of a particular group.…”

From the Laboratory into the Wild

“…Galvanic skin response (GSR), also known as skin conductance or electro-dermal activity EDA is one of the most sensitive psychophysical indicators [20]. The amounts of sweat secreted in times of arousal is responsible for the changes in skin conductance, and can easily be measured in regions with a high concentration of sweat glands, such as the hands and feet.…”

“…Especially reactions to startle stimuli that divert attention with a strong probability, such as a flash of light, create spikes in skin conductance. Even though we cannot conclude on the quality of the emotion (positive/negative), EDA can help to identify changes in attentional patterns [20]. Initial tests we conducted, have shown that the EOG electrodes on MEME glasses can also be used to measure EDA.…”

Driver Drowsiness Detection Using Gray Wolf Optimizer Based on Voice Recognition

“…The sympathetic nerve system includes the hippocampus, amygdala, and cingulate gyrus; these organs respond to attentiveness, showing a link with emotion. We can also employ sympathetic nervous system information from sweat glands to recognize emotions (Yoshida, et al, 2014). The present study aims to identify the emotion of drivers during speaking in two scenarios (drowsy and non-drowsy).…”