Exploring the role of fear in human decision making

Kelly, P, Adama, DA ORCID logoORCID: https://orcid.org/0000-0002-2650-857X, Ihianle, IK ORCID logoORCID: https://orcid.org/0000-0001-7445-8573, Machado, P ORCID logoORCID: https://orcid.org/0000-0003-1760-3871 and Otuka, RI ORCID logoORCID: https://orcid.org/0009-0006-0198-8999, 2023. Exploring the role of fear in human decision making. In: PETRA '23: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments. New York: Association for Computing Machinery (ACM), pp. 505-510. ISBN 9798400700699

[thumbnail of 1792119_Machado.pdf]
Preview
Text
1792119_Machado.pdf - Post-print

Download (1MB) | Preview

Abstract

This study explores the use of Convolutional Neural Networks (CNNs) to classify fear in the context of decision-making. The approach involves developing a CNN model that is trained using hyper-parameter tuning and K-fold cross-validation to accurately classify fear from video footage of participants’ facial expressions during an experiment. The videos are presented along with a map to show the location of the participants along the route. The study reports an overall accuracy of 95.05% for fear classification. The
results show that the model can successfully predict fear levels in different conditions. For example, the most desolate route with the lowest light levels recorded an overall fear detected at 49.15%, while the safest route with the highest light levels in a densely populated area saw an overall fear detected at 2.69%. These findings demonstrate the potential for using CNNs to classify fear and provide insight into how fear can be taken into consideration for decision-making in realistic scenarios.

Item Type: Chapter in book
Description: Paper presented at PETRA '23. 16th International Conference on PErvasive Technologies Related to Assistive Environments, Corfu, Greece, 5-7 July 2023
Creators: Kelly, P., Adama, D.A., Ihianle, I.K., Machado, P. and Otuka, R.I.
Publisher: Association for Computing Machinery (ACM)
Place of Publication: New York
Date: 5 July 2023
ISBN: 9798400700699
Identifiers:
Number
Type
10.1145/3594806.3596590
DOI
1792119
Other
Divisions: Schools > School of Science and Technology
Record created by: Linda Sullivan
Date Added: 26 Sep 2023 09:56
Last Modified: 26 Sep 2023 09:56
URI: https://irep.ntu.ac.uk/id/eprint/49812

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year