Algorithms for clustering data
Algorithms for clustering data
Reliability Estimation During Prototyping of Knowledge-Based Systems
IEEE Transactions on Knowledge and Data Engineering
| Hi-index | 0.10 |
The homogeneous clustering problem involves grouping data when neither the number of clusters nor the number of elements in a cluster are known, Instead, there is a threshold requirement on group or cluster homogeneity. The major existing approach to this problem is the leader algorithm. We present a new approach, called Clustering of Homogeneous Subsets (CHS). In tests on an important example of the homogeneous clustering problem, sensor fusion for military surveillance, CHS outperforms the leader algorithm.