VR-LENS: Super Learning-based Cybersickness Detection and Explainable AI-Guided Deployment in Virtual Reality
VR-LENS: Super Learning-based Cybersickness Detection and Explainable AI-Guided Deployment in Virtual Reality
复制标题
VR-LENS：基于超级学习的晕眩检测和虚拟现实中可解释的人工智能引导部署
DOI：
10.1145/3581641.3584044
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Hoque, Khaza Anuarul
中科院分区：
文献类型：
--
作者：
Kundu, Ripan Kumar;Elsaid, Osama Yahia;Calyam, Prasad;Hoque, Khaza Anuarul
虚拟现实（VR）系统因其对晕网病的敏感性而闻名，这会严重阻碍用户的体验。因此，最近的大量研究提出了几种基于机器学习（ML）和深度学习（DL）的自动化方法来检测晕网症。然而，这些检测方法被认为是计算密集型和黑箱方法。因此，这些技术对于部署在独立的VR头戴式显示器（HMD）上既不可信也不实用。这项工作提出了一个可解释的基于人工智能（XAI）的框架VR-LENS，用于开发网络病检测ML模型，解释它们，减小它们的大小，并将它们部署在基于高通Snapdragon 750 G处理器的三星A52设备中。具体来说，我们首先开发了一种新的基于超级学习的集成ML模型用于网络病检测。接下来，我们采用了事后解释方法，如SHapley加法解释（SHAP），莫里斯敏感性分析（MSA），局部可解释模型不可知解释（LIME）和部分依赖图（PDP）来解释预期的结果，并确定最主要的功能。然后，使用所识别的主导特征来重新训练超级学习者晕电病模型。我们提出的方法将眼动跟踪、玩家位置和皮肤电/心率响应确定为集成传感器、游戏和生物生理数据集的最主要特征。我们还表明，提出的XAI引导的特征约简将模型训练和推理时间显著减少了1.91倍和2.15倍，同时保持了基线精度。例如，使用集成的传感器数据集，我们的简化超级学习者模型通过将晕电病分类为4类（无，低，中和高），并以0.03的均方根误差（RMSE）进行回归（FMS 1-10），表现优于最先进的作品。我们提出的方法可以帮助研究人员真实的分析、检测和减轻晕网病，并在独立的VR头显中部署基于超级学习者的晕网病检测模型。
Virtual reality (VR) systems are known for their susceptibility to cybersickness, which can seriously hinder users’ experience. Therefore, a plethora of recent research has proposed several automated methods based on machine learning (ML) and deep learning (DL) to detect cybersickness. However, these detection methods are perceived as computationally intensive and black-box methods. Thus, those techniques are neither trustworthy nor practical for deploying on standalone VR head-mounted displays (HMDs). This work presents an explainable artificial intelligence (XAI)-based framework VR-LENS for developing cybersickness detection ML models, explaining them, reducing their size, and deploying them in a Qualcomm Snapdragon 750G processor-based Samsung A52 device. Specifically, we first develop a novel super learning-based ensemble ML model for cybersickness detection. Next, we employ a post-hoc explanation method, such as SHapley Additive exPlanations (SHAP), Morris Sensitivity Analysis (MSA), Local Interpretable Model-Agnostic Explanations (LIME), and Partial Dependence Plot (PDP) to explain the expected results and identify the most dominant features. The super learner cybersickness model is then retrained using the identified dominant features. Our proposed method identified eye tracking, player position, and galvanic skin/heart rate response as the most dominant features for the integrated sensor, gameplay, and bio-physiological datasets. We also show that the proposed XAI-guided feature reduction significantly reduces the model training and inference time by 1.91X and 2.15X while maintaining baseline accuracy. For instance, using the integrated sensor dataset, our reduced super learner model outperforms the state-of-the-art works by classifying cybersickness into 4 classes (none, low, medium, and high) with an accuracy of and regressing (FMS 1–10) with a Root Mean Square Error (RMSE) of 0.03. Our proposed method can help researchers analyze, detect, and mitigate cybersickness in real time and deploy the super learner-based cybersickness detection model in standalone VR headsets.
登录
查看更多内容
影响因子：
2.5
作者：
Melo, Miguel;Vasconcelos-Raposo, Jose;Bessa, Maximino
通讯作者：
Bessa, Maximino
用于非侵入式晕车检测的心率变异性
DOI：
--
发表时间：
2022
期刊：
IMX
影响因子：
--
作者：
P. Lobo;Pablo Pérez
通讯作者：
Pablo Pérez
健康受试者晕动病的易感性与视觉诱发的姿势不稳定和心脏自主反应相关
影响因子：
1.4
作者：
Yoichi Yokota;M. Aoki;K. Mizuta;Yatsuji Ito;N. Isu
通讯作者：
N. Isu
DOI：
10.1109/ccnc.2019.8651847
发表时间：
2018-11
期刊：
2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC)
影响因子：
--
作者：
Aniket Gulhane;Akhil Vyas;Reshmi Mitra;Roland Oruche;Gabriela Hoefer;Samaikya Valluripally;P. Calyam;K. A. Hoque
通讯作者：
Aniket Gulhane;Akhil Vyas;Reshmi Mitra;Roland Oruche;Gabriela Hoefer;Samaikya Valluripally;P. Calyam;K. A. Hoque
基于深度学习的框架，用于检测和减少网络病的发生
DOI：
--
发表时间：
2020
期刊：
2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
影响因子：
--
作者：
Rifatul Islam
通讯作者：
Rifatul Islam