Using fuzzy logic to generate conditional probabilities in Bayesian belief networks: a case study of ecological assessment

Abstract

The survival of rare animals is an important concern in an environmental impact assessment. However, it is very difficult to quantitatively predict the possible effect that a development project has on rare animals, and there is a heavy reliance on expert knowledge and judgment. In order to improve the credibility of expert judgment, this study uses Bayesian belief networks (BBN) to visually represent expert knowledge and to clearly explain the inference process. For the case study, the primary difficulty is in determining a large amount of conditional probabilities in the BBN, because there is a lack of sufficient data concerning rare animals. Therefore, a new method that uses fuzzy logic to systematically generate these probabilities is proposed. The combination of the BBN and the fuzzy logic system is used to assess the possible future population status of the Pheasant-tailed jacana and the associated probabilities, which have been affected by the construction of the Taiwan High-Speed Rail. The analysis shows that a restoration program would successfully preserve the species, because in the restoration area, the BBN model predicts that there is a 75.49 % probability that the species will flourish in the future.

Discussion of ‘Environmental decision‐making using bayesian networks: Creating an environmental report card’

“…CPT for the relationship between parent nodes ( X 1 , X 2 ) and the child node Y. scarce or incomplete, experts may provide input for all stages of the modelling and management process [3]. For instance, a method based on fuzzy logic for experts elicitation able to automatically infer conditional probabilities as in Liu et al [4] could be considered to enhance the stakeholders and experts engagement in the BN construction process. I would like to invite the authors to discuss this issue in slightly more detail in their rejoinder.…”

Old Tools, New Ways of Using Them: Harnessing Expert Opinions to Plan for Surprise in Marine Socio-Ecological Systems

“…This theory has limited application in tipping points, as it requires specification of all potential future states and their probabilities of occurrence, which are often unknown when dealing with multiple drivers of change (Polasky et al, 2011). In this context, it is more appropriate to qualitatively assign variables to linguistic categories using expert opinions (e.g., "low, " "moderate, " "high"), accompanied by a qualitative level of confidence (e.g., a "low" increase in a stressor will be "most likely" to have a "low impact" on biodiversity) (Liu et al, 2015). This qualitative use of expert opinions allows progress to be made in identifying the likelihood of various outcomes even when uncertainty is deep (see below).…”

Modeling customer satisfaction in microfinance sector: A fuzzy Bayesian networks approach

“…BNs have several other advantages that make them useful in many areas. According to Wu et al 32 and Liu et al, 34 BNs can provide a way to overcome data limitations through the integration of qualitative and quantitative data from various resources. These data can include results from previous experiments, experts' judgments, and published literature.…”

“…In this study, the fuzzy logic inference system is used to calculate the conditional possibilities (membership values) and then the conditional possibilities are assumed to be proportional to the CPs. 34 For instance, service quality is determined by the conditions of the staff competencies, incentive system, and the working conditions ( Figure 4) In this example, the evaluation rules for generating the associated conditional possibilities are seen in Table 4, where "staff competencies," "incentive system," and "working conditions" are linguistic variables. Good (G), Medium (M), Bad (B), Low (L), and High (H) are the possible fuzzy values defined by a Gaussian distribution.…”