Effective pruning strategies for sequential pattern mining
In this paper, we systematically explore the search space of frequent sequence mining and present two novel pruning strategies, S E P (Sequence Extension Pruning) and I EP (Item Extension Pruning), which can be used in all Aption-like sequence mining algorithms or lattice-theoretic approaches. With...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE) Computer Society
2008
|
| Online Access: | http://hdl.handle.net/20.500.11937/34160 |
| _version_ | 1848754147516481536 |
|---|---|
| author | Xu, Y. Ma, Z. Li, L. Dillon, Tharam S. |
| author2 | Q. Luo |
| author_facet | Q. Luo Xu, Y. Ma, Z. Li, L. Dillon, Tharam S. |
| author_sort | Xu, Y. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In this paper, we systematically explore the search space of frequent sequence mining and present two novel pruning strategies, S E P (Sequence Extension Pruning) and I EP (Item Extension Pruning), which can be used in all Aption-like sequence mining algorithms or lattice-theoretic approaches. With a little more memory overhead, proposed pruning strategies can prune invalidated search space and decrease the total cost of frequency counting effectively. For effectiveness testing reason, we optimize SPAM [2) and present the improved algorithm, S P AMSEPIEP' which uses S E P and IEP to prune the search space by sharing the frequent 2sequences lists. A set of comprehensive performance experiments study shows that S P AMSEPIEP outperforms SPAM by a factor of 10 on small datasets and better than 30 % to 50 % on reasonably large dataset. |
| first_indexed | 2025-11-14T08:35:47Z |
| format | Conference Paper |
| id | curtin-20.500.11937-34160 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:35:47Z |
| publishDate | 2008 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) Computer Society |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-341602022-12-07T06:50:48Z Effective pruning strategies for sequential pattern mining Xu, Y. Ma, Z. Li, L. Dillon, Tharam S. Q. Luo M. Gong F. Xiong F. Yu In this paper, we systematically explore the search space of frequent sequence mining and present two novel pruning strategies, S E P (Sequence Extension Pruning) and I EP (Item Extension Pruning), which can be used in all Aption-like sequence mining algorithms or lattice-theoretic approaches. With a little more memory overhead, proposed pruning strategies can prune invalidated search space and decrease the total cost of frequency counting effectively. For effectiveness testing reason, we optimize SPAM [2) and present the improved algorithm, S P AMSEPIEP' which uses S E P and IEP to prune the search space by sharing the frequent 2sequences lists. A set of comprehensive performance experiments study shows that S P AMSEPIEP outperforms SPAM by a factor of 10 on small datasets and better than 30 % to 50 % on reasonably large dataset. 2008 Conference Paper http://hdl.handle.net/20.500.11937/34160 10.1109/WKDD.2008.22 Institute of Electrical and Electronics Engineers (IEEE) Computer Society fulltext |
| spellingShingle | Xu, Y. Ma, Z. Li, L. Dillon, Tharam S. Effective pruning strategies for sequential pattern mining |
| title | Effective pruning strategies for sequential pattern mining |
| title_full | Effective pruning strategies for sequential pattern mining |
| title_fullStr | Effective pruning strategies for sequential pattern mining |
| title_full_unstemmed | Effective pruning strategies for sequential pattern mining |
| title_short | Effective pruning strategies for sequential pattern mining |
| title_sort | effective pruning strategies for sequential pattern mining |
| url | http://hdl.handle.net/20.500.11937/34160 |