Physiological Fusion Net: Quantifying Individual VR Sickness with Content Stimulus and Physiological Response

Lee, Sangmin; Kim, Seongyeop; Kim, Hak Gu; Kim, Min Seob; Yun, Seok Hyun; Jeong, Bumseok; Ro, Yong Man

doi:10.1109/icip.2019.8802983

Cited by 14 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When classifying multiple subjects' cybersickness, the accuracy of the classifier was between 79 and 100% (Table 5). Several studies considered the temporal aspects of EEG features to detect cybersickness (Lee et al 2019a;Liao et al 2020;Kim et al 2019a). Kim et al (2019a) showed 80.57% of test accuracy when considering the longest duration of EEG data.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Brain activity during cybersickness: a scoping review

Chang

Billinghurst

2023

Virtual Reality

View full text Add to dashboard Cite

Virtual reality (VR) experiences can cause a range of negative symptoms such as nausea, disorientation, and oculomotor discomfort, which is collectively called cybersickness. Previous studies have attempted to develop a reliable measure for detecting cybersickness instead of using questionnaires, and electroencephalogram (EEG) has been regarded as one of the possible alternatives. However, despite the increasing interest, little is known about which brain activities are consistently associated with cybersickness and what types of methods should be adopted for measuring discomfort through brain activity. We conducted a scoping review of 33 experimental studies in cybersickness and EEG found through database searches and screening. To understand these studies, we organized the pipeline of EEG analysis into four steps (preprocessing, feature extraction, feature selection, classification) and surveyed the characteristics of each step. The results showed that most studies performed frequency or time-frequency analysis for EEG feature extraction. A part of the studies applied a classification model to predict cybersickness indicating an accuracy between 79 and 100%. These studies tended to use HMD-based VR with a portable EEG headset for measuring brain activity. Most VR content shown was scenic views such as driving or navigating a road, and the age of participants was limited to people in their 20 s. This scoping review contributes to presenting an overview of cybersickness-related EEG research and establishing directions for future work.

show abstract

Section: Discussionmentioning

confidence: 99%

“…8b). A limited number of studies used 360 videos (Lee et al 2019a;Lin et al 2018) and minimalist content (Wei et al 2019).…”

Section: Contentmentioning

confidence: 99%

Brain activity during cybersickness: a scoping review

Chang

Billinghurst

2023

Virtual Reality

View full text Add to dashboard Cite

show abstract

“…For model pre-training, original EEG data from KAIST IVY LAB were selected and processed [32]. The learner underwent 50 epochs of pre-training using the ADAM optimizer [33] with a batch size of 4, setting the initial learning rate at 0.00005 and incorporating β1 and β2 values of 0.9 and 0.999, respectively.…”

Section: Classification and Prediction Training Setmentioning

confidence: 99%

Feature extraction method of EEG based on wavelet packet reconstruction and deep learning model of VR motion sickness feature classification and prediction

Luo,

Ren,

et al. 2023

Preprint

View full text Add to dashboard Cite

The increased utilization of virtual reality (VR) technology has raised concerns regarding VR-induced motion sickness, an adverse condition linked to discomfort and nausea within simulated environments. Our approach commenced with an extensive analysis of EEG data and subjective feedback obtained from users immersed in VR environments. This data served to train a sophisticated deep learning model, employing an enhanced short-term memory network (GRU), aimed at identifying patterns and features associated with motion sickness. Following this, comprehensive data pre-processing and feature engineering were conducted to ensure the accuracy and suitability of the input data. Subsequently, a deep learning model was trained utilizing both supervised and unsupervised learning techniques, enabling the classification and prediction of motion sickness severity. Rigorous training and validation procedures were employed across multiple datasets to ascertain the model's robustness and performance under diverse scenarios. The research outcomes affirm the precision of our deep learning model in accurately classifying and forecasting the degree of motion sickness induced by virtual reality. The classification task achieved an accuracy rate of 84.9%, surpassing correlation and error indices of existing models. Consequently, this model exhibits superior capabilities in diagnosing and predicting motion sickness, thereby offering crucial support for enhancing the quality of the virtual reality experience and furthering advancements in VR technology.

show abstract

“…Recent research has started to utilize machine learning and user simulator sickness labels to predict simulator sickness from visual content [7,19,25,32,34,43]. In these approaches, identifying the right features that cause simulator sickness is critical since machine learning prediction highly depends on the features to learn.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Simulator Sickness Estimation from 3D Motion

Zhao,

Tran,

Chalmers

et al. 2023

2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

View full text Add to dashboard Cite

Physiological Fusion Net: Quantifying Individual VR Sickness with Content Stimulus and Physiological Response

Cited by 14 publications

References 19 publications

Brain activity during cybersickness: a scoping review

Brain activity during cybersickness: a scoping review

Feature extraction method of EEG based on wavelet packet reconstruction and deep learning model of VR motion sickness feature classification and prediction

Deep Learning-based Simulator Sickness Estimation from 3D Motion

Contact Info

Product

Resources

About