Evaluation Model of Cognitive Distraction State Based on Eye Tracking Data Using Neural Networks

Evaluation Model of Cognitive Distraction State Based on Eye Tracking Data Using Neural Networks

Taku Harada, Hirotoshi Iwasaki, Kazuaki Mori, Akira Yoshizawa, Fumio Mizoguchi
DOI: 10.4018/ijssci.2014010101
(Individual Articles)
No Current Special Offers


Eye tracking reveals a person's state of mind. Thus, representing personal cognitive states using eye tracking leads to objective evaluations of these states, and this representation can be applied to various application fields. In this paper, the authors focus on the cognitive distraction state as a cognitive state, and the authors propose a model that evaluates personal cognitive distraction. The model takes as input eye tracking data and outputs the degree of personal cognitive distraction. The authors use a simple recurrent neural network, which is a type of neural network, to build the proposed model. In addition, the authors apply the proposed model to eye tracking for a person driving a car.
Article Preview

3. Distraction Model

The input data and output value of the distraction model that we propose are shown in Figure 1. The input data are eye-tracking data, and the output value is a degree of distraction.

Figure 1.

Input and output for distraction model


A simple recurrent neural network (Jeffrey, 1990) is used as the basic structure in the proposed model, such as for a selective attention model or a short-term memory model in the study (T. Harada et al., 2012). A simple recurrent neural network is shown in Figure 2, which presents the basic structure with two units for simplicity.

Figure 2.

Simple recurrent neural network


Complete Article List

Search this Journal:
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing