Loading...
Please wait, while we are loading the content...
Similar Documents
Cluster ensemble extraction for knowledge reuse framework
| Content Provider | Semantic Scholar |
|---|---|
| Author | Akbari, Ebrahim Dahlan, Halina Mohamed Ibrahim, Roliana |
| Copyright Year | 2015 |
| Abstract | Cluster ensemble framework attempts to find stable and robust results through composing calculated clusterings obtained from basic clustering algorithms without accessing the features or algorithms that determine these clusterings. Diversity of clusterings is a important factor for improving cluster ensemble performance, where an ensemble of small size of identical clusterings dose not improve the quality and robustness of solution. Concerning limited access to the raw data, how new clusterings with more diversity and size can be created using a few base clusterings. This paper proposes a new approach, cluster ensemble extraction, as a knowledge reuse framework to create a new diversity without accessing the raw data. This approach creates a new set of clusterings from the existing clusterings, which have more diversity and size compared to base clusterings. To evaluate the performance of the proposed approach, several experiments were conducted on several real data sets and the results were compered to the results obtained from executing of cluster ensemble on base clusterings. The comparison results showed the superiority of the proposed approach over the cluster ensemble approach in terms of quality. Key–Words: Clustering, Knowledge reuse, Diversity, Cluster ensemble extraction |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.wseas.org/multimedia/journals/information/2015/a445709-504.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
