A framework to estimate cognitive load using physiological data
- PDF / 1,278,638 Bytes
- 15 Pages / 595.224 x 790.955 pts Page_size
- 59 Downloads / 217 Views
ORIGINAL ARTICLE
A framework to estimate cognitive load using physiological data Muneeb Imtiaz Ahmad1,2
· Ingo Keller1 · David A. Robb1 · Katrin S. Lohan3,4
Received: 27 November 2019 / Accepted: 5 September 2020 © The Author(s) 2020
Abstract Cognitive load has been widely studied to help understand human performance. It is desirable to monitor user cognitive load in applications such as automation, robotics, and aerospace to achieve operational safety and to improve user experience. This can allow efficient workload management and can help to avoid or to reduce human error. However, tracking cognitive load in real time with high accuracy remains a challenge. Hence, we propose a framework to detect cognitive load by non-intrusively measuring physiological data from the eyes and heart. We exemplify and evaluate the framework where participants engage in a task that induces different levels of cognitive load. The framework uses a set of classifiers to accurately predict low, medium and high levels of cognitive load. The classifiers achieve high predictive accuracy. In particular, Random Forest and Naive Bayes performed best with accuracies of 91.66% and 85.83% respectively. Furthermore, we found that, while mean pupil diameter change for both right and left eye were the most prominent features, blinking rate also made a moderately important contribution to this highly accurate prediction of low, medium and high cognitive load. The existing results on accuracy considerably outperform prior approaches and demonstrate the applicability of our framework to detect cognitive load. Keywords Cognitive load · Framework · Physiological data · Human-computer interaction
1 Introduction In the past few decades, cognitive load (CL) has been shown to negatively impact human performance in various tasks Muneeb Imtiaz Ahmad
[email protected] Ingo Keller [email protected] David A. Robb [email protected] Katrin Lohan [email protected] 1
Edinburgh Center for Robotics, Heriot-Watt University, Edinburgh, UK
2
Department of Computer Science, Swansea University, Swansea, UK
3
Department of Mathematical and Computer Science, Heriot-Watt University, Edinburgh, UK
4
EMS Institute for Development of Mechatronic Systems, NTB University of Applied Sciences in Technology, Buchs, Switzerland
demanding a high amount of mental effort [4]. In general, CL refers to the load placed on the user’s working memory, also viewed as short-term memory, during a task [53]. The significance of measuring CL has been well described in the past due to its application under various contexts such as problem-solving, instructional design, multimedia, aircraft, and automation [42]. CL can be monitored in real time as a method to capture the automation experience [15, 57]. Accurate measurement of CL can be used to apply mitigation strategies, such as the adaptation of the user interface in response to changes in CL [36]. One approach is to present information differently for a naive user vs. an expert user. This is needed because an expert user may view the
Data Loading...
