Generation of explicit knowledge from temporal data
Expert decisions are usually based on experience knowledge regarding the decision environments. However due to the mobility or high turn-over of expert whether due to promotion, resignation or other reasons, there is a need to capture expert knowledge especially those involved critical decision.This...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://repo.uum.edu.my/3402/1/Ku.pdf http://repo.uum.edu.my/3402/ http://www.kmice.cms.net.my |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Expert decisions are usually based on experience knowledge regarding the decision environments. However due to the mobility or high turn-over of expert whether due to promotion, resignation or other reasons, there is a need to capture expert knowledge especially those involved critical decision.This paper will describe an approach of capturing expert knowledge through past operation data. An explicit knowledge extraction technique from temporal data representing reservoir operation will be presented.Rules regarding decision on the number of spillway gates to be open to release excess water from the dam will be discovered from the historical data. Temporal information related to a decision will be captured through sliding window method and classified into unique decision classes. This information can be transformed into decision rules for easy interpretation and understanding. These rules can be hrther use to guide future operation decisions. |
|---|