| Autor: |
Guo-jun MA, Shui-bo WANG, Qing-qi PEI, Yang ZHAN |
| Jazyk: |
English<br />Chinese |
| Rok vydání: |
2017 |
| Předmět: |
|
| Zdroj: |
网络与信息安全学报, Vol 3, Pp 18-27 (2017) |
| Druh dokumentu: |
article |
| ISSN: |
2096-109X |
| DOI: |
10.11959/j.issn.2096-109x.2017.00189 |
| Popis: |
In order to solve the problem that parallel coordinate visualization graphic lines are intensive,overlap and rules of data is not easy to be obtained which caused by high dimension and immense amount of multidimensional data.Parallel coordinate visualization method based on principal component analysis and K-means clustering was proposed.In this method,the principal component analysis method was used to reduce the dimensionality of the multidimensional data firstly.Secondly,the data of the dimension reduction was clustered by K-means.Finally,the data of the clustering were visualized by parallel coordinate visualization.The PCAKP visualization method is tested with the data published by the Bureau of Statistics as the test data,and compared with the traditional parallel coordinate visualization graph,the validity and effectiveness of the PCAKP visualization method are verified. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
