| Status |
Accepted |
| journal_subject |
Part A |
| Article Type |
Regular Paper (More than 4 pages) |
| Article Filed |
|
| Article Title |
A Selection Method of Vibration Signal Feature Based on Mutual Information and Distance Measurement |
| Keywords |
Vibration Signals, Mutual Information, Distance Measurement, Fault Diagnosis. |
| Abstract |
Feature selection is an important problem for fault diagnosis systems. This paper proposes a selection
method of characteristic parameters based on mutual information theory and distance measurement between
parameters. Its core goal is to search the parameter subset which has higher relevance between the selection and
state class, the lower redundancy and the longer distance measurement between the parameters. The experiment
compared the new algorithm with traditional methods by using Particle Swarm Optimization. The results prove
that the new method leads to improvement on feature selection and classification accuracy. |
| Authors |
| First Name
| Middle Name
| Last Name
| E-Mail
| Corresponding
|
| Huaqing |
|
Wang |
wanghq_buct@hotmail.com |
Yes |
| Hongfang |
|
Yuan |
|
No |
| Changdui |
|
Zhu |
|
No |
| Xi |
|
Cao |
|
No |
| Wenbin |
|
Liu |
|
No |
| Jianfeng |
|
Yang |
|
No |
|
| Upload Files |
Please Login to View Upload Files |
My Manuscript