Interaction Design With Multi-objective Bayesian Optimization

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2023

Major/Subject

Mcode

Degree programme

Language

en

Pages

10

Series

IEEE Pervasive Computing, Volume 22, issue 1, pp. 29-38

Abstract

Interaction design typically involves challenging decision making that requires designers to consider multiple parameters and careful tradeoffs between various objectives. This article examines how AI can facilitate the process of interaction design by offloading some of the complex decision making required of designers. We study how multi-objective Bayesian optimization can be used to support designers when creating a tactile display for smart watches. We present the results of a study that explores how such human-AI collaboration afforded by multi-objective Bayesian optimization can be exploited by designers, and the advantages and disadvantages this solution offers over conventional design practice.

Description

Publisher Copyright: IEEE

Keywords

Bayes methods, Conferences, Haptic interfaces, Optimization, Prototypes, Task analysis, Vibrations

Other note

Citation

Liao, Y C, Dudley, J J, Mo, G B, Cheng, C L, Chan, L, Oulasvirta, A & Kristensson, P O 2023, ' Interaction Design With Multi-objective Bayesian Optimization ', IEEE Pervasive Computing, vol. 22, no. 1, pp. 29-38 . https://doi.org/10.1109/MPRV.2022.3230597