This study reports on how velocity and force levels of caress-like haptic stimuli can elicit different emotional responses, which can be identified through the analysis of Autonomic Nervous System (ANS) dynamics. Affective stimuli were administered on the forearm of 32 healthy volunteers (16 women) through a haptic device with two levels of force, 2 N and 6 N, and two levels of velocity, 9.4 mm/s and 37 mm/s. ANS dynamics was estimated through Heart Rate Variability (HRV) linear and nonlinear analysis on recordings gathered before and after each stimulus. To this extent, we here propose and assess novel features from HRV symbolic analysis and Lagged Poincaré Plot. Classification was performed following a leave-one-subject-out procedure on nonlinear support vector machines. Pattern classification was split according to gender, significantly improving accuracies of recognition with respect to a "all-subjects" classification. Caressing force and velocity levels were recognized with up to 80% accuracy for men, and up to 84.38% for women. Our results demonstrate that changes in ANS control on cardiovascular dynamics, following emotional changes induced by caress-like haptic stimuli, can be effectively recognized by the proposed computational approach, considering that they occur in a gender-specific and nonlinear manner.

Classifying Affective Haptic Stimuli through Gender-specific Heart Rate Variability Nonlinear Analysis

Nardelli, Mimma;Greco, Alberto;Bianchi, Matteo;Scilingo, Enzo Pasquale;Valenza, Gaetano
2020-01-01

Abstract

This study reports on how velocity and force levels of caress-like haptic stimuli can elicit different emotional responses, which can be identified through the analysis of Autonomic Nervous System (ANS) dynamics. Affective stimuli were administered on the forearm of 32 healthy volunteers (16 women) through a haptic device with two levels of force, 2 N and 6 N, and two levels of velocity, 9.4 mm/s and 37 mm/s. ANS dynamics was estimated through Heart Rate Variability (HRV) linear and nonlinear analysis on recordings gathered before and after each stimulus. To this extent, we here propose and assess novel features from HRV symbolic analysis and Lagged Poincaré Plot. Classification was performed following a leave-one-subject-out procedure on nonlinear support vector machines. Pattern classification was split according to gender, significantly improving accuracies of recognition with respect to a "all-subjects" classification. Caressing force and velocity levels were recognized with up to 80% accuracy for men, and up to 84.38% for women. Our results demonstrate that changes in ANS control on cardiovascular dynamics, following emotional changes induced by caress-like haptic stimuli, can be effectively recognized by the proposed computational approach, considering that they occur in a gender-specific and nonlinear manner.
2020
Nardelli, Mimma; Greco, Alberto; Bianchi, Matteo; Scilingo, Enzo Pasquale; Valenza, Gaetano
File in questo prodotto:
File Dimensione Formato  
Classifying_Affective_Haptic_Stimuli.pdf

non disponibili

Tipologia: Versione finale editoriale
Licenza: NON PUBBLICO - accesso privato/ristretto
Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/915455
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 5
social impact