Home
Tags
No Tags
Using data mining to explore the regularity of genetic algorithms in job shop schedule problems
| Title: | Using data mining to explore the regularity of genetic algorithms in job shop schedule problems |
| Author: | Tsai, Shi-Chi |
| Description: | The purposes of this thesis are to apply data mining methodologies to explore the regularity of data generated by a genetic algorithm performing a scheduling operation and develop a rule set scheduler to approximate the genetic algorithms scheduler. Genetic algorithms are stochastic search algorithms based on the mechanics of genetics and natural selection. After evolution of each generation, the survivors are those best adapted to their environment. Because of genetic inheritance, these survivors are, to a certain degree, similar. For genetic algorithms in job shop scheduling problems, a solution presents an operation sequence for resource allocation. Among these optimal or near optimal solutions, similar relationships may exist between operations and sequential order, as well as characteristics of operations and sequential order. These relationships may be generalized to dispatching rules. Data mining, developed for extracting knowledge from data, employs machine learning and database management systems to extract useful information from data. This thesis uses an attribute-oriented induction methodology to explore the relationship between an operations' sequence and its attributes - operation order, processing time, remain processing time and machine load, and develop a rule set schedule with the discovered knowledge. |
| Permanent Link: |
http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1184347015
http://hdl.handle.net/2374.OX/13136 |
| Date: | 1997 |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||