ANFIS modeling for predicting affective responses to tactile textures

Authors:
Diyar Akay;Xiaojuan Chen;Cathy Barnes;Brian Henson
Affiliations:
Department of Industrial Engineering, Gazi University, Ankara, Turkey;School of Mechanical Engineering, University of Leeds, Leeds, UK;School of Mechanical Engineering, University of Leeds, Leeds, UK;School of Mechanical Engineering, University of Leeds, Leeds, UK
Venue:
Human Factors in Ergonomics & Manufacturing
Year:
2012

Citing 9
Cited 0

Fuzzy logic, neural networks, and soft computing

Communications of the ACM
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Foundations of Neuro-Fuzzy Systems

Foundations of Neuro-Fuzzy Systems
An adaptive neuro-fuzzy inference system for bridge risk assessment

Expert Systems with Applications: An International Journal
A dominance-based rough set approach to Kansei Engineering in product development

Expert Systems with Applications: An International Journal
An investigation into affective design using sorting technique and Kohonen self-organising map

Advances in Engineering Software
A Kansei mining system for affective design

Expert Systems with Applications: An International Journal
A statistical model of relationship between affective responses and product design attributes for capturing user needs

UI-HCII'07 Proceedings of the 2nd international conference on Usability and internationalization
Kansei engineering and rough sets model

RSCTC'06 Proceedings of the 5th international conference on Rough Sets and Current Trends in Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Adaptive Neuro-Fuzzy Inference System (ANFIS) is proposed to simulate and analyze the mapping between the physical properties of tactile textures and people's affective responses. People were asked to rate the tactile feeling of 37 tactile textures against six pairs of adjectives on a semantic differential questionnaire. The friction coefficient, average roughness, compliance, and a thermal parameter of each tactile texture were measured. ANFIS models were built to predict the affective responses to tactile textures. The resulting ANFIS models demonstrated a good match between predicted and actual responses, and always yielded better performance when compared to linear and exponential regression models. The effects of physical properties of textures on affective responses were also analyzed by simulating the synthetic data with ANFIS. © 2011 Wiley Periodicals, Inc. © 2012 Wiley Periodicals, Inc.