scholarly journals An experimental methodology to capture user and gameplay data tied to cybersickness

2021 ◽  
Author(s):  
Thiago Porcino ◽  
Daniela Trevisan ◽  
Esteban Clua
Keyword(s):  
Machine Learning ◽  
Virtual Reality ◽  
Medical Informatics ◽  
Experimental Methodology ◽  
Head Mounted Displays ◽  
Recorded Data ◽  
Learning Analysis ◽  
High Sense

Virtual reality (VR) and head-mounted displays are constantly gaining popularity in various fields such as education, military, entertainment, and bio/medical informatics. Although such technologies provide a high sense of immersion, they can also trigger symptoms of discomfort. This condition is called cybersickness (CS) and is quite popular in recent publications in the virtual reality context. We created and conducted an iterative evaluating protocol methodology and proposed two VR games (a racing game and a flight game). The recorded data can be used for further machine learning analysis tied to cybersickness.

A cybersickness review: causes, strategies, and classification methods

2021 ◽  
Vol 12 (1) ◽  
pp. 269-282
Author(s):  
Thiago Porcino ◽  
Daniela Trevisan ◽  
Esteban Clua
Keyword(s):  
Machine Learning ◽  
Virtual Reality ◽  
Deep Learning ◽  
Learning Approaches ◽  
Classification Methods ◽  
Review Of The Literature ◽  
Profile Data ◽  
Head Mounted Displays ◽  
Decision Paths ◽  
High Sense

Virtual reality (VR) and head-­mounted displays are continually gaining popularity in various fields such as education, military, entertainment, and health. Although such technologies provide a high sense of immersion, they can also trigger symptoms of discomfort. This condition is called cybersickness (CS) and is quite popular in recent virtual reality research. In this work we first present a review of the literature on theories of discomfort manifestations usually attributed to virtual reality environments. Following, we reviewed existing strategies aimed at minimizing CS problems and discussed how the CS measurement has been conducted based on subjective, bio­signal (or objective), and users profile data. We also describe and discuss related works that are aiming to mitigate cybersickness problems using deep and symbolic machine learning approaches. Although some works used methods to make deep learning explainable, they are not strongly affirmed by literature. For this reason in this work we argue that symbolic classifiers can be a good way to identify CS causes, once they possibilities human-­readability which is crucial for analyze the machine learning decision paths. In summary, from a total of 157 observed studies, 24 were excluded. Moreover, we believe that this work facilitates researchers to identify the leading causes for most discomfort situations in virtual reality environments, associate the most recommended strategies to minimize such discomfort, and explore different ways to conduct experiments involving machine learning to overcome cybersickness.

scholarly journals Cybersickness in current-generation virtual reality head-mounted displays: systematic review and outlook

2021 ◽  
Author(s):  
Polona Caserman ◽  
Augusto Garcia-Agundez ◽  
Alvar Gámez Zerban ◽  
Stefan Göbel
Keyword(s):  
Systematic Review ◽  
Virtual Reality ◽  
Meta Analysis ◽  
Subjective Evaluation ◽  
Future Research ◽  
Current Generation ◽  
Research Areas ◽  
Head Mounted Displays ◽  
Skin Response ◽  
Golden Standard

AbstractCybersickness (CS) is a term used to refer to symptoms, such as nausea, headache, and dizziness that users experience during or after virtual reality immersion. Initially discovered in flight simulators, commercial virtual reality (VR) head-mounted displays (HMD) of the current generation also seem to cause CS, albeit in a different manner and severity. The goal of this work is to summarize recent literature on CS with modern HMDs, to determine the specificities and profile of immersive VR-caused CS, and to provide an outlook for future research areas. A systematic review was performed on the databases IEEE Xplore, PubMed, ACM, and Scopus from 2013 to 2019 and 49 publications were selected. A summarized text states how different VR HMDs impact CS, how the nature of movement in VR HMDs contributes to CS, and how we can use biosensors to detect CS. The results of the meta-analysis show that although current-generation VR HMDs cause significantly less CS ($$p<0.001$$ p < 0.001 ), some symptoms remain as intense. Further results show that the nature of movement and, in particular, sensory mismatch as well as perceived motion have been the leading cause of CS. We suggest an outlook on future research, including the use of galvanic skin response to evaluate CS in combination with the golden standard (Simulator Sickness Questionnaire, SSQ) as well as an update on the subjective evaluation scores of the SSQ.

scholarly journals Machine learning analysis using 77,044 genomic and transcriptomic profiles to accurately predict tumor type

2021 ◽  
Vol 14 (3) ◽  
pp. 101016 ◽  
Author(s):  
Jim Abraham ◽  
Amy B. Heimberger ◽  
John Marshall ◽  
Elisabeth Heath ◽  
Joseph Drabick ◽  
...  
Keyword(s):  
Machine Learning ◽  
Tumor Type ◽  
Learning Analysis

scholarly journals Gamification and Hazard Communication in Virtual Reality: A Qualitative Study

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4663
Author(s):  
Janaina Cavalcanti ◽  
Victor Valls ◽  
Manuel Contero ◽  
David Fonseca
Keyword(s):  
Virtual Reality ◽  
New Technologies ◽  
Training Environment ◽  
Hazard Communication ◽  
Head Mounted Display ◽  
Compliance Behavior ◽  
Before And After ◽  
Recorded Data ◽  
The Impact ◽  
Different Levels

An effective warning attracts attention, elicits knowledge, and enables compliance behavior. Game mechanics, which are directly linked to human desires, stand out as training, evaluation, and improvement tools. Immersive virtual reality (VR) facilitates training without risk to participants, evaluates the impact of an incorrect action/decision, and creates a smart training environment. The present study analyzes the user experience in a gamified virtual environment of risks using the HTC Vive head-mounted display. The game was developed in the Unreal game engine and consisted of a walk-through maze composed of evident dangers and different signaling variables while user action data were recorded. To demonstrate which aspects provide better interaction, experience, perception and memory, three different warning configurations (dynamic, static and smart) and two different levels of danger (low and high) were presented. To properly assess the impact of the experience, we conducted a survey about personality and knowledge before and after using the game. We proceeded with the qualitative approach by using questions in a bipolar laddering assessment that was compared with the recorded data during the game. The findings indicate that when users are engaged in VR, they tend to test the consequences of their actions rather than maintaining safety. The results also reveal that textual signal variables are not accessed when users are faced with the stress factor of time. Progress is needed in implementing new technologies for warnings and advance notifications to improve the evaluation of human behavior in virtual environments of high-risk surroundings.

scholarly journals Technical Note: A Guide to Annotation of Neurosurgical Intraoperative Video for Machine Learning Analysis and Computer Vision

2021 ◽  
Author(s):  
Dhiraj J. Pangal ◽  
Guillaume Kugener ◽  
Shane Shahrestani ◽  
Frank Attenello ◽  
Gabriel Zada ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Technical Note ◽  
Learning Analysis

scholarly journals Sustainable Virtual Reality Patient Rehabilitation Systems with IoT Sensors Using Virtual Smart Cities

2021 ◽  
Vol 13 (9) ◽  
pp. 4716
Author(s):  
Moustafa M. Nasralla
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Virtual Reality ◽  
Time Series Analysis ◽  
Smart City ◽  
Smart Cities ◽  
Rehabilitation Services ◽  
Simulation Scenario ◽  
Common Problems ◽  
Iot Devices

To develop sustainable rehabilitation systems, these should consider common problems on IoT devices such as low battery, connection issues and hardware damages. These should be able to rapidly detect any kind of problem incorporating the capacity of warning users about failures without interrupting rehabilitation services. A novel methodology is presented to guide the design and development of sustainable rehabilitation systems focusing on communication and networking among IoT devices in rehabilitation systems with virtual smart cities by using time series analysis for identifying malfunctioning IoT devices. This work is illustrated in a realistic rehabilitation simulation scenario in a virtual smart city using machine learning on time series for identifying and anticipating failures for supporting sustainability.

scholarly journals Dynamic prediction of energy and power usage cost using linear regression-machine learning analysis

2021 ◽  
Vol 1921 ◽  
pp. 012067
Author(s):  
Rani Fathima Kamal Basha ◽  
M.L Bharathi ◽  
Kanagaraj Venusamy
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Dynamic Prediction ◽  
Usage Cost ◽  
Learning Analysis
Sign in / Sign up

Export Citation Format

Share Document