Abstract
This paper reports the design and assessment of a neuro-fuzzy model to support clinicians during virtual reality therapy. The implemented model is able to automatically recognize the perceived stress levels of the patients by analyzing physiological and behavioral data during treatment. The model, consisting of a self-organizingmap and a fuzzy-rule-basedmodule, was trained unobtrusively recording electrocardiogram, breath rate and activity during stress inoculation provided by the exposure to virtual environments. Twenty nurses were exposed to sessions simulating typical stressful situations experienced at their workplace. Four levels of stress severity were evaluated for each subject by gold standard clinical scales administered by trained personnel. The model's performances were discussed and compared with the main machine learning algorithms. The neurofuzzy model shows better performances in terms of stress level classification with 83% of mean recognition rate.
| Original language | English |
|---|---|
| Pages (from-to) | 521-533 |
| Number of pages | 13 |
| Journal | Interacting with Computers |
| Volume | 27 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - 2015 |
Fingerprint
Keywords
- Artificial intelligence
- Empirical studies in HCI
- Human computer interaction
- Physiological computingt
- Stress recognition
- Virtual reality
ASJC Scopus subject areas
- Human-Computer Interaction
- Software
Cite this
Neuro-fuzzy physiological computing to assess stress levels in virtual reality therapy. / Tartarisco, G.; Carbonaro, N.; Tonacci, A.; Bernava, G. M.; Arnao, A.; Crifaci, G.; Cipresso, P.; Riva, G.; Gaggioli, A.; De Rossi, D.; Tognetti, A.; Pioggia, G.
In: Interacting with Computers, Vol. 27, No. 5, 2015, p. 521-533.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Neuro-fuzzy physiological computing to assess stress levels in virtual reality therapy
AU - Tartarisco, G.
AU - Carbonaro, N.
AU - Tonacci, A.
AU - Bernava, G. M.
AU - Arnao, A.
AU - Crifaci, G.
AU - Cipresso, P.
AU - Riva, G.
AU - Gaggioli, A.
AU - De Rossi, D.
AU - Tognetti, A.
AU - Pioggia, G.
PY - 2015
Y1 - 2015
N2 - This paper reports the design and assessment of a neuro-fuzzy model to support clinicians during virtual reality therapy. The implemented model is able to automatically recognize the perceived stress levels of the patients by analyzing physiological and behavioral data during treatment. The model, consisting of a self-organizingmap and a fuzzy-rule-basedmodule, was trained unobtrusively recording electrocardiogram, breath rate and activity during stress inoculation provided by the exposure to virtual environments. Twenty nurses were exposed to sessions simulating typical stressful situations experienced at their workplace. Four levels of stress severity were evaluated for each subject by gold standard clinical scales administered by trained personnel. The model's performances were discussed and compared with the main machine learning algorithms. The neurofuzzy model shows better performances in terms of stress level classification with 83% of mean recognition rate.
AB - This paper reports the design and assessment of a neuro-fuzzy model to support clinicians during virtual reality therapy. The implemented model is able to automatically recognize the perceived stress levels of the patients by analyzing physiological and behavioral data during treatment. The model, consisting of a self-organizingmap and a fuzzy-rule-basedmodule, was trained unobtrusively recording electrocardiogram, breath rate and activity during stress inoculation provided by the exposure to virtual environments. Twenty nurses were exposed to sessions simulating typical stressful situations experienced at their workplace. Four levels of stress severity were evaluated for each subject by gold standard clinical scales administered by trained personnel. The model's performances were discussed and compared with the main machine learning algorithms. The neurofuzzy model shows better performances in terms of stress level classification with 83% of mean recognition rate.
KW - Artificial intelligence
KW - Empirical studies in HCI
KW - Human computer interaction
KW - Physiological computingt
KW - Stress recognition
KW - Virtual reality
UR - http://www.scopus.com/inward/record.url?scp=84941911989&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84941911989&partnerID=8YFLogxK
U2 - 10.1093/iwc/iwv010
DO - 10.1093/iwc/iwv010
M3 - Article
AN - SCOPUS:84941911989
VL - 27
SP - 521
EP - 533
JO - Interacting with Computers
JF - Interacting with Computers
SN - 0953-5438
IS - 5
ER -