Related Experiment Video
Updated: Jun 16, 2025
06:02
Evaluating Usability Aspects of a Mixed Reality Solution for Immersive Analytics in Industry 4.0 Scenarios
Published on: October 6, 2020
2.2K
Optimized virtual reality design through user immersion level detection with novel feature fusion and explainable
Ali Raza1, Amjad Rehman2, Rukhshanda Sehar3
1Department of Software Engineering, University of Lahore, Lahore, Pakistan.
Peerj. Computer Science
|August 15, 2024
Summary
This study introduces a novel Polynomial Random Forest (PRF) model to accurately detect user immersion levels in virtual reality (VR). The PRF technique achieved a 98% detection rate, enhancing VR application design.
Area of Science:
- Computer Science
- Human-Computer Interaction
- Artificial Intelligence
Background:
- Virtual reality (VR) and immersive technologies offer realistic, interactive experiences across diverse fields like gaming, healthcare, and education.
- Optimizing VR application design necessitates accurate measurement of user immersion, defined as the user's sense of absorption in the virtual environment.
- Current methods for detecting user immersion in VR face challenges in efficiency and accuracy.
Purpose of the Study:
- To develop and evaluate an efficient machine learning model for detecting user immersion levels in virtual reality (VR).
- To introduce a novel feature generation technique, Polynomial Random Forest (PRF), for enhanced immersion detection.
- To compare the performance of the proposed PRF model against existing state-of-the-art machine learning approaches.
Main Methods:
- Utilized a benchmark dataset comprising user experiences within VR environments for model training and evaluation.
- Applied advanced deep and machine learning techniques, including a novel Polynomial Random Forest (PRF) for feature generation.
- Incorporated hyperparameter optimization, cross-validation, and explainable artificial intelligence (XAI) for model validation and interpretation.
Main Results:
- The proposed Polynomial Random Forest (PRF) technique significantly improved feature sets by extracting polynomial and class prediction probability features.
- Random Forest models, enhanced with PRF, outperformed other state-of-the-art methods in detecting user immersion levels.
- Achieved a high immersion level detection accuracy rate of 98% using the PRF technique.
Conclusions:
- The PRF technique offers an efficient and highly accurate method for detecting user immersion in virtual reality.
- The developed model demonstrates potential to significantly enhance the design process of VR applications by providing reliable immersion insights.
- Explainable AI (XAI) provides transparency into the model's decision-making, fostering trust and further development in VR immersion detection.
