SACA Net: Cybersickness Assessment of Individual Viewers for VR Content via Graph-Based Symptom Relation Embedding

Deep Learning-based Simulator Sickness Estimation from 3D Motion

“…Recently, more and more machine learning-based methods have emerged due to the advancement of artificial intelligence. Some methods focused on visually-induced simulator sickness predictions [25-27, 34, 43] while others investigate physiological signals, including postural sway, gait motion, heart rate, breathing rate, galvanic skin response, and electroencephalogram (EEG) data [10,16,18,30,32,35,51], or the combination of visual content information and physiological signals [28,31,33]. For visual-based machine learning methods, gameplay video will always be analyzed first to extract the raw features of depth and optical flow, and then input them into the deployed machine learning method to regress simulator sickness level or classify simulator sickness arousal.…”

“…Jin et al [19] used long-short term memory recurrent neural networks (LSTM-RNN) models with many visual-based features and head movement. Instead of predicting a general simulator sickness score, some works [26,31] have tried to advance the machine learning model to assess more specific symptoms (such as nausea, disorientation, and oculomotor), using either visual content [26] or a combination of visual content and physiological information [31].…”

Towards a Better Understanding of VR Sickness: Physical Symptom Prediction for VR Contents

“…VRSA using content information and physiological signals Most recently, objective assessment methods considering both content information and physiological signals have been proposed Kim et al 2019;Lee et al 2020). In (Lee et al , 2020, the authors proposed a deep learning-based individual VR sickness assessment method considering content stimulus and physiological responses of each subject. Experimental results showed that this approach was effective to predict the level of individual VR sickness based on individual physiological signals.…”