General Information
The dataset (EyeVR) was created to support research on user behavior and performance in immersive industrial training environments, specifically in the operation of virtual cranes within virtual reality (VR).
Its main objective is to enable the identification of users and the analysis of their cognitive and emotional states (such as concentration, estress and level of experience) while performing simulated industrial tasks in VR.
The dataset includes:
-
- Anonimized user identifiers, corresponding to each participant interacting with the virtual system.
- Physiological and behavioral data collected through eye-tracking sensors integrated in a VR headset, capturing gaze position, fixation, and pupil dilation while participants performed the exercises.
A total of 11 exercises were designed, distributed across three sessions of increasing difficulty.
The activities simulate realistic crane operation scenarios, requiring users to demonstrate different levels of attention, precision, and coordination.
Detailed information about the exercises and participants can be found in the metadata folder, as well as in the data descriptor and related research publications.
The dataset includes records from 71 participants across all sessions.
Further methodological details and analyses based on this dataset can be found in the following research publications:
- Serrano-Mamolar, A., Miguel-Alonso, I., Checa, D., & Pardo-Aguilar, C. (2023).
Towards learner performance evaluation in iVR learning environments using eye-tracking and Machine-learning.
Comunicar, 31(76), 9–20.
https://www.revistacomunicar.com/ojs/index.php/comunicar/article/view/115335
- Ramírez-Sanz, J.M., Peña-Alonso, H.M., Serrano-Mamolar, A., Arnaiz-González, Á., Bustillo, A. (2023).
Detection of Stress Stimuli in Learning Contexts of iVR Environments.
In: De Paolis, L.T., Arpaia, P., Sacco, M. (eds) Extended Reality. XR Salento 2023. Lecture Notes in Computer Science, vol 14219. Springer, Cham.
https://doi.org/10.1007/978-3-031-43404-4_29
Structure of the Dataset
The root folder of the dataset includes two main subfolders:
- /data – Contains the raw data collected directly from the eye-tracking sensors. Each file corresponds to a single exercise performed by one participant.
- /metadata – Contains complementary information about the experiments, such as participant demographics, exercise descriptions, and experimental conditions.
Each of them also contain README files for more information.
Usage
Researchers are encouraged to start their analysis using the raw data, which can be processed with time-series feature extraction methods.
This approach is recommended due to the variability in duration and structure of the exercises across participants.
For convenience, the dataset also includes two pre-processed (feature-extracted) subsets, ready for further analysis using machine learning techniques.
This work is supported by the projects:
TED2021-129485B-C43 funded by MCIN/AEI/10.13039/501100011033 and by the European Union “NextGenerationEU”
PID2020-119894GB-I00/AEI/10.13039/501100011033 funded by Ministry of Science and Innovation of Spain
