In this project, we will look into how to make the physiological data of VR users visible to externals, e.g., a teacher watching a student learning in VR, or a supervisor watching a worker fulfil a task in VR.
Different studies have shown that fluctuations in cognitive load are expressed through changes in human physiology, such as temperature patterns on the face or pupil dilation. However, in users of VR headsets, the face and eyes are covered by the HMD.
To tackle this ambitious project, you will have to dive into the existing literature on physiological signals and human cognitive states. Then, you will be required to familiarize yourself with the HP G2 Omnicept HMD, which is equipped with a series of sensors. You will then develop an interface that allows visualising the cognitive load level of the HMD user on an external monitor, so it can be observed in real-time. Finally, we will design a user study and test the robustness of the approach with different users. (Very ambitious students, can develop an ML model to predict states of higher and lower cognitive load in the users.)
The results of this work have the potential to significantly impact our way of learning and teaching. It will introduce VR into more traditional education environments and enables teachers to oversee their students' efforts and identify students who struggle or thrive. In the follow-up, direct interaction with the content by the teacher will make the teaching and learning experience more targeted and effective.
The project scope includes:
- literature research to understand cognitive load
- VR development
- implementation of an interface for real-time physiological data presentation
Double Semester (including all of the above):
- design of a users study
- data analysis of physiological data
- optional: development of an ML model to predict different levels of cognitive load
- Kosch, T., Karolus, J., Zagermann, J., Reiterer, H., Schmidt, A., and Woźniak, P. W. (2023). A Survey on Measuring Cognitive Workload in Human-Computer Interaction. ACM Computing Surveys. https://doi.org/10.1145/3582272
- Sweller, J. (2010). Element interactivity and intrinsic, extraneous, and germane cognitive load. Educational Psychology Review, 22(2), 123–138. https://doi.org/10.1007/s10648-010-9128-5
- Development experience (ubicomp, sensors)
- Data visualisation (esp. of physiological data)
- Data analysis – Python/R
- optional: Machine Learning
- data analysis in Python or R (physiological data)
- Interest in VR and human cognition