Affective State Classification in Virtual Reality Environments Using Electrocardiogram and Respiration Signals

2021 ◽  
Author(s):  
Apostolos Kalatzis ◽  
Laura Stanley ◽  
Vishnunarayan Girishan Prabhu
Keyword(s):  
Virtual Reality ◽  
Affective State ◽  
State Classification

scholarly journals Towards estimating affective states in Virtual Reality based on behavioral data

2021 ◽  
Author(s):  
Valentin Holzwarth ◽  
Johannes Schneider ◽  
Joshua Handali ◽  
Joy Gisler ◽  
Christian Hirt ◽  
...  
Keyword(s):  
Virtual Reality ◽  
Adaptive Systems ◽  
User Study ◽  
Affective State ◽  
Head Movements ◽  
Affective States ◽  
Physical Demand ◽  
Perceived Performance ◽  
Sequential Administration ◽  
Better Than

AbstractInferring users’ perceptions of Virtual Environments (VEs) is essential for Virtual Reality (VR) research. Traditionally, this is achieved through assessing users’ affective states before and after being exposed to a VE, based on standardized, self-assessment questionnaires. The main disadvantage of questionnaires is their sequential administration, i.e., a user’s affective state is measured asynchronously to its generation within the VE. A synchronous measurement of users’ affective states would be highly favorable, e.g., in the context of adaptive systems. Drawing from nonverbal behavior research, we argue that behavioral measures could be a powerful approach to assess users’ affective states in VR. In this paper, we contribute by providing methods and measures evaluated in a user study involving 42 participants to assess a users’ affective states by measuring head movements during VR exposure. We show that head yaw significantly correlates with presence, mental and physical demand, perceived performance, and system usability. We also exploit the identified relationships for two practical tasks that are based on head yaw: (1) predicting a user’s affective state, and (2) detecting manipulated questionnaire answers, i.e., answers that are possibly non-truthful. We found that affective states can be predicted significantly better than a naive estimate for mental demand, physical demand, perceived performance, and usability. Further, manipulated or non-truthful answers can also be estimated significantly better than by a naive approach. These findings mark an initial step in the development of novel methods to assess user perception of VEs.

scholarly journals An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy

Sensors ◽  
2020 ◽  
Vol 20 (2) ◽  
pp. 496 ◽  
Author(s):  
Oana Bălan ◽  
Gabriela Moise ◽  
Alin Moldoveanu ◽  
Marius Leordeanu ◽  
Florica Moldoveanu
Keyword(s):  
Virtual Reality ◽  
Deep Learning ◽  
Dominant Role ◽  
Affective State ◽  
Evaluation Procedure ◽  
In Vivo Evaluation ◽  
Exposure Scenario ◽  
Fear Level ◽  
Learning Classifiers

In this paper, we investigate various machine learning classifiers used in our Virtual Reality (VR) system for treating acrophobia. The system automatically estimates fear level based on multimodal sensory data and a self-reported emotion assessment. There are two modalities of expressing fear ratings: the 2-choice scale, where 0 represents relaxation and 1 stands for fear; and the 4-choice scale, with the following correspondence: 0—relaxation, 1—low fear, 2—medium fear and 3—high fear. A set of features was extracted from the sensory signals using various metrics that quantify brain (electroencephalogram—EEG) and physiological linear and non-linear dynamics (Heart Rate—HR and Galvanic Skin Response—GSR). The novelty consists in the automatic adaptation of exposure scenario according to the subject’s affective state. We acquired data from acrophobic subjects who had undergone an in vivo pre-therapy exposure session, followed by a Virtual Reality therapy and an in vivo evaluation procedure. Various machine and deep learning classifiers were implemented and tested, with and without feature selection, in both a user-dependent and user-independent fashion. The results showed a very high cross-validation accuracy on the training set and good test accuracies, ranging from 42.5% to 89.5%. The most important features of fear level classification were GSR, HR and the values of the EEG in the beta frequency range. For determining the next exposure scenario, a dominant role was played by the target fear level, a parameter computed by taking into account the patient’s estimated fear level.

A Portable Personality Recognizer Based on Affective State Classification Using Spectral Fusion of Features

2018 ◽  
Vol 9 (3) ◽  
pp. 330-342 ◽  
Author(s):  
Anushree Basu ◽  
Anirban Dasgupta ◽  
Anirud Thyagharajan ◽  
Aurobinda Routray ◽  
Rajlakshmi Guha ◽  
...  
Keyword(s):  
Affective State ◽  
State Classification

scholarly journals User Experience and usability of a new virtual reality set-up to treat eating disorders: a pilot study

2020 ◽  
Author(s):  
Marta Matamala-Gomez ◽  
Eleonora Brivio ◽  
Alice CHIRICO ◽  
Clelia Malighetti ◽  
Olivia Realdon ◽  
...  
Keyword(s):  
Virtual Reality ◽  
Body Size ◽  
Pilot Study ◽  
User Experience ◽  
Affective State ◽  
The Body ◽  
Long Term Memory ◽  
Italian Women ◽  
State Increase ◽  
Virtual Body

Virtual Reality (VR) has progressively emerged as an effective tool for wellbeing and health in clinical populations. VR effectiveness has been tested before in Anorexia Nervosa (AN) with full-body illusion. It consists in the embodiment of patients with AN into a different virtual body to modify their long-term memory of the body as a crucial factor for the onset and maintenance of this disorder. We extended this protocol using the autobiographical recall emotion-induction technique, in which patients recall an emotional episode of their life related to their body. In this pilot study, we aimed to test the usability and User Experience (UX) of this VR-based protocol. Five Italian women with AN were embodied in a virtual body resembling their perceived body size from an ego- and an allocentric perspective while remembering episodes of their life related to their body. High levels of embodiment were reported while embodied in a virtual body resembling their real perceived body size for ownership (p<0.0001), agency (p=0.04), and self-location (p=0.023). Negative affective state increase after session 2 (p=0.012), and positive affective state increase after session 4 (p=0.006) (PANAS). However, further iteration of the VR system is needed to improve the user experience and usability of the system.

Sign in / Sign up

Export Citation Format

Share Document