Bayesian belief networks offer an alternative to conventional estimation methods in estimating user preference or utility functions. Because parameter estimates are updated sequentially, this approach seems very promising in user-centred design and data collection systems. The application of such networks however poses several questions, related to speed of learning, sample heterogeneity and discretionalisation of the parameter space. This paper reports the results of a series of numerical simulations which were conducted to gain more insights into these operational decisions.
AllenJDeanTLAloimononsJ, 1994Artificial Intelligence: Theory and Practice (Benjamin/Cummings, Redwood City, CA)
3.
DeanTLWellmanMP, 1991Planning and Control (Morgan Kaufmann, San Mateo, CA)
4.
FentonN, 2003, “SERENE (SafEty and Risk Evaluation Using Bayesian Nets) method tutorial”, Department of Computing, Queen Mary College, London, http://www.dcs.qmul.ac.uk/∼norman/serene.htm
5.
HaddawyP, 1999, “An overview of some recent developments in Bayesian problem solving techniques”AI Magazine20(2) 11–19
6.
JensenFV, 1996An Introduction to Bayesian Networks (Springer, New York)
7.
JohnsonW, 1999, “Natural interaction with pedagogical agents in virtual worlds”, in Proceedings of the Fifteenth Twente Workshop on Language TechnologyEnschede, The Netherlands, 19–21 May, pp 103–105, http://hmi.ewi.utwente.nl.Docs/oldwebpage/conferences/twlt15.html
8.
JosephAESmitBMcIllraveyGP, 1989, “Consumer preferences for rural residences: A conjoint analysis in Ontario, Canada”Environment and Planning A2147–65
9.
KozlovAVKollerD, 1997, “Nonuniform dynamic discretization in hybrid networks”, in Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence Eds GeigerDShenoyPP, pp 314–325, http://citeseen.ist.psu.edu/105549.html
10.
Norsys, 1997, “Netica application user's guide version 1.05”, Norsys Software Corporation, 3512 West 23rd Avenue, Vancouver, BC
11.
OrzechowskiMAde VriesBTimmermansHJP, 2003, “Virtual reality CAD system for non-designers”, in Proceedings of 7th Iberoamerican Congress of Digital Graphics Sigradi Eds CarmenaSUtgesR, pp 221–225, available from the author
12.
PearlJ, 1988Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference (Morgan Kaufmann, San Mateo, CA)
13.
RickelJJohnsonWL, 2000, “Task-oriented collaboration with embodied agents in virtual worlds”, in Embodied Conversational Agents Eds CassellJPrevostS (MIT Press, Cambridge, MA) pp 95–122
14.
TrainK, 2003Discrete Choice Methods with Simulation (Cambridge University Press, Cambridge)
15.
WangDLiJ, 2002, “Handling large numbers of attributes and/or large numbers of levels in conjoint experiments”Geographical Analysis34350–362
16.
WangDLiSM, 2004, “Housing preferences in a transitional housing system: The case of Beijing, China”Environment and Planning A3669–87
