The research focuses on the application of site
selection for cage aquaculture in Taiwan by
developing the site evaluation DSS (Decision
Support System). The modeling aspect of the
system belongs to the domain of multi-criteria
decision theories, which AHP (Analytic Hierarchy
Process) and Fuzzy Set theory were used. Two case
studies based on real world and hypothetical data
were conducted to verify the integrity of the
system.
According to the literature review and the
interview with several domain experts, various
impact factors were identified first. The
corresponding weights of each factor were then
decided by analyzing the questionnaires designed
based on the concept of AHP. The following work
was to evaluate those impact factors based on the
experience of domain experts using some
appropriate approaches. To represent the domain
knowledge, it is appropriate to use rule based
inference system. Besides, fuzzy set theory was
chosen to describe the antecedent and consequence
of the rule base due to the considerations of
uncertainty from human experts and ocean field
data. Several related mythologies derived from
the fuzzy set theory were used, such as the
operation of fuzzy composition, determination of
suitable membership function, fuzzy relationship
matrix, fuzzy inference, defuzzification, and
fuzzy pattern classification.
All impact factors were categorized into three
different types of membership functions that were
designed specifically for the site selection of
cage aquaculture. The consequence in the rule
base, which is the site suitability, was also
represented as the unique membership function. To
calculate the fuzzy relationship matrix, the
current research found that the operation of
¡§algebraic product and bounder sum¡¨ would
produce better results than the commonly used
¡§max-min¡¨ operation. Each impact factor would
have the associated fuzzy relationship matrix
derived from the rule base. The site suitability
in term of a fuzzy set can then be inferred by
the fuzzy composition of current situation of the
factor and the relationship matrix. By
multiplying the AHP weight and the fuzzy
suitability, the final site suitability index,
taking all the impact factors into consideration,
can therefore be derived.
The real data in Feng-Gang, located in the
southern Taiwan, were collected and evaluated
using the site selection DSS. The results show
Feng-Gang is suitable for the development of cage
aquaculture, which is validated by the current
prosperous business locally in cage aquaculture.
As for the evaluation of multiple sites, 18
hypothetical sites near shore around Taiwan were
chosen to calculate the corresponding suitability
indexes, which were then be partitioned into
several groups using the fuzzy pattern
classification. Based on the results, the sites
that were classified in the same group have
similar cultivation conditions, which also proves
the applicability of the site evaluation DSS.
| Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0714100-010449 |
| Date | 14 July 2000 |
| Creators | Ma, Guo-Ding |
| Contributors | Jin-Yuan Wang, Chai-Cheng Huang, Yang-Chi Chang, Te-Min Chang, Shiahn-Wern Shyue |
| Publisher | NSYSU |
| Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
| Language | Cholon |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714100-010449 |
| Rights | unrestricted, Copyright information available at source archive |
Page generated in 0.0018 seconds