Expert and stakeholder perception: Extracting value from survey data using fuzzy logic
- QuantiSci Ltd., Thames (United Kingdom)
The assessment of stakeholder perception and quantitative understanding of respondent data concerning radiological risks is very important for the success of many radioactive waste management programmes. The traditional approach often relies on expert opinions and the use of standard statistical techniques to post process survey results. Such techniques require a number of underlying assumptions (e.g. independence, correlation) to ensure the application of the method is appropriate. The human perception process does not always allow attribute exchangeability, often permitted in statistical approaches. Hence, such snapshots are of limited use for predictive purposes. The most robust procedure is to assess the perceptions and attitudes from a range of respondents including: nuclear safety experts, scientists, public, public in close proximity to potential nuclear sites, and pressure groups. This should be done in a way that identifies whether any underlying logic (inferential rules, linking attributes to response) is exhibited, which could be anticipated or managed in the future. This will ensure all impacting views are incorporated and so lead to a focused information dissemination and communication strategy that will promote positive stakeholder response. The authors propose to analyse the process by which individuals formulate their response to perceived risks. Two sample data sets will be discussed to illustrate how inferential rules can be sought by applying AI techniques based on fuzzy logic. This framework is suited to the subjective, context-dependent, non-unique, classification of attributes and concepts involved in a cognitive approach to perception. Inferences are represented by memberships in hierarchical fuzzy sets. Such a hierarchy is inferred from the relative strengths of different attributes. The objective is to investigate individual evaluation and response to risks within and across different focus groups.
- OSTI ID:
- 474098
- Report Number(s):
- CONF-960804-Vol.2; TRN: 97:002181-0106
- Resource Relation:
- Conference: SPECTRUM `96: international conference on nuclear and hazardous waste management, Seattle, WA (United States), 18-23 Aug 1996; Other Information: PBD: 1996; Related Information: Is Part Of Proceedings of the international topical meeting on nuclear and hazardous waste management (SPECTRM `96): Volume 2; PB: 875 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
RISK REDUCTION WITH A FUZZY EXPERT EXPLORATION TOOL
Development of the on-line operator aid system OASYS using a rule-based expert system and fuzzy logic for nuclear power plants