Deep neural network model of haptic saliency

Abstract Haptic exploration usually involves stereotypical systematic movements that are adapted to the task. Here we tested whether exploration movements are also driven by physical stimulus features. We designed haptic stimuli, whose surface relief varied locally in spatial frequency, height, orie...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Anna Metzger, Matteo Toscani, Arash Akbarinia, Matteo Valsecchi, Knut Drewing
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/af5ad6883c504c7399a70eb95b324f76
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:af5ad6883c504c7399a70eb95b324f76
record_format	dspace
spelling	oai:doaj.org-article:af5ad6883c504c7399a70eb95b324f762021-12-02T14:01:24ZDeep neural network model of haptic saliency10.1038/s41598-020-80675-62045-2322https://doaj.org/article/af5ad6883c504c7399a70eb95b324f762021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80675-6https://doaj.org/toc/2045-2322Abstract Haptic exploration usually involves stereotypical systematic movements that are adapted to the task. Here we tested whether exploration movements are also driven by physical stimulus features. We designed haptic stimuli, whose surface relief varied locally in spatial frequency, height, orientation, and anisotropy. In Experiment 1, participants subsequently explored two stimuli in order to decide whether they were same or different. We trained a variational autoencoder to predict the spatial distribution of touch duration from the surface relief of the haptic stimuli. The model successfully predicted where participants touched the stimuli. It could also predict participants’ touch distribution from the stimulus’ surface relief when tested with two new groups of participants, who performed a different task (Exp. 2) or explored different stimuli (Exp. 3). We further generated a large number of virtual surface reliefs (uniformly expressing a certain combination of features) and correlated the model’s responses with stimulus properties to understand the model’s preferences in order to infer which stimulus features were preferentially touched by participants. Our results indicate that haptic exploratory behavior is to some extent driven by the physical features of the stimuli, with e.g. edge-like structures, vertical and horizontal patterns, and rough regions being explored in more detail.Anna MetzgerMatteo ToscaniArash AkbariniaMatteo ValsecchiKnut DrewingNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Anna Metzger Matteo Toscani Arash Akbarinia Matteo Valsecchi Knut Drewing Deep neural network model of haptic saliency
description	Abstract Haptic exploration usually involves stereotypical systematic movements that are adapted to the task. Here we tested whether exploration movements are also driven by physical stimulus features. We designed haptic stimuli, whose surface relief varied locally in spatial frequency, height, orientation, and anisotropy. In Experiment 1, participants subsequently explored two stimuli in order to decide whether they were same or different. We trained a variational autoencoder to predict the spatial distribution of touch duration from the surface relief of the haptic stimuli. The model successfully predicted where participants touched the stimuli. It could also predict participants’ touch distribution from the stimulus’ surface relief when tested with two new groups of participants, who performed a different task (Exp. 2) or explored different stimuli (Exp. 3). We further generated a large number of virtual surface reliefs (uniformly expressing a certain combination of features) and correlated the model’s responses with stimulus properties to understand the model’s preferences in order to infer which stimulus features were preferentially touched by participants. Our results indicate that haptic exploratory behavior is to some extent driven by the physical features of the stimuli, with e.g. edge-like structures, vertical and horizontal patterns, and rough regions being explored in more detail.
format	article
author	Anna Metzger Matteo Toscani Arash Akbarinia Matteo Valsecchi Knut Drewing
author_facet	Anna Metzger Matteo Toscani Arash Akbarinia Matteo Valsecchi Knut Drewing
author_sort	Anna Metzger
title	Deep neural network model of haptic saliency
title_short	Deep neural network model of haptic saliency
title_full	Deep neural network model of haptic saliency
title_fullStr	Deep neural network model of haptic saliency
title_full_unstemmed	Deep neural network model of haptic saliency
title_sort	deep neural network model of haptic saliency
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/af5ad6883c504c7399a70eb95b324f76
work_keys_str_mv	AT annametzger deepneuralnetworkmodelofhapticsaliency AT matteotoscani deepneuralnetworkmodelofhapticsaliency AT arashakbarinia deepneuralnetworkmodelofhapticsaliency AT matteovalsecchi deepneuralnetworkmodelofhapticsaliency AT knutdrewing deepneuralnetworkmodelofhapticsaliency
_version_	1718392162065842176

Deep neural network model of haptic saliency

Ejemplares similares