| Autor: |
Rajput, Pushpendra Kumar, Nagpal, Geeta, Aarti |
| Zdroj: |
International Journal of Computational Intelligence Studies; January 2014, Vol. 3 Issue: 1 p74-93, 20p |
| Abstrakt: |
Multi–attribute data, needed to be clustered may have different consequences of attributes on clustering criteria. In this paper, a new soft clustering technique is proposed in which similarity measures between data points and impact of each attribute is calculated using grey relational analysis. Algorithm provides the flexibility to choose significant number of attributes for classification purpose using feature subset selection. An iterative approach is adopted to find desired number of clusters having more appropriate and unique centroid. In addition, the use of proposed technique is instanced on software cost estimation because inherent uncertainty in software attributes due to the measurement by expert judgment has a significant impact on estimation accuracy. Combination of clustering and regression technique reduces the potential problem in efficacy of predictive assays due to heterogeneity of the data. Clustered approach creates the subsets of data having a degree of homogeneity that elaborate more accurate prediction. |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
