Graph-based clustering with DRepStream
© 2017 ACM. Finding and setting input parameters for clustering algorithms is a challenging thing due to the unsupervised nature of clustering. The accuracy of clustering algorithms can be affected greatly by setting parameters appropriately for the dataset, however without ground truth labels and e...
| Main Authors: | , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/58258 |
| _version_ | 1848760214726115328 |
|---|---|
| author | Callister, R. Lazarescu, Mihai Pham, DucSon |
| author_facet | Callister, R. Lazarescu, Mihai Pham, DucSon |
| author_sort | Callister, R. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | © 2017 ACM. Finding and setting input parameters for clustering algorithms is a challenging thing due to the unsupervised nature of clustering. The accuracy of clustering algorithms can be affected greatly by setting parameters appropriately for the dataset, however without ground truth labels and external validation it can be impossible to know when the parameters are set well. In this paper we propose the DRepStream algorithm, which extends the RepStream algorithm. DRepStream uses a graph-based approach, and unlike its predecessor does not require the primary K parameter used in K-nearest neighbour graphs. Our algorithm automatically computes the number of outgoing edges for each vertex in the graph using a computed metric known as the anomalous edge score. We evaluate the performance of our algorithm on other previous stream clustering algorithms on real world benchmark datasets. |
| first_indexed | 2025-11-14T10:12:13Z |
| format | Conference Paper |
| id | curtin-20.500.11937-58258 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:12:13Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-582582017-11-24T05:46:56Z Graph-based clustering with DRepStream Callister, R. Lazarescu, Mihai Pham, DucSon © 2017 ACM. Finding and setting input parameters for clustering algorithms is a challenging thing due to the unsupervised nature of clustering. The accuracy of clustering algorithms can be affected greatly by setting parameters appropriately for the dataset, however without ground truth labels and external validation it can be impossible to know when the parameters are set well. In this paper we propose the DRepStream algorithm, which extends the RepStream algorithm. DRepStream uses a graph-based approach, and unlike its predecessor does not require the primary K parameter used in K-nearest neighbour graphs. Our algorithm automatically computes the number of outgoing edges for each vertex in the graph using a computed metric known as the anomalous edge score. We evaluate the performance of our algorithm on other previous stream clustering algorithms on real world benchmark datasets. 2017 Conference Paper http://hdl.handle.net/20.500.11937/58258 10.1145/3019612.3019672 restricted |
| spellingShingle | Callister, R. Lazarescu, Mihai Pham, DucSon Graph-based clustering with DRepStream |
| title | Graph-based clustering with DRepStream |
| title_full | Graph-based clustering with DRepStream |
| title_fullStr | Graph-based clustering with DRepStream |
| title_full_unstemmed | Graph-based clustering with DRepStream |
| title_short | Graph-based clustering with DRepStream |
| title_sort | graph-based clustering with drepstream |
| url | http://hdl.handle.net/20.500.11937/58258 |