2026-09-24T10:57:21Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/24511 2023-07-10 col_2142_5131 col_2142_13836 col_2142_10761 com_2142_5130 com_2142_13835 com_2142_234 com_2142_10755

Han, Jiawei Yu, Xiao 2011-05-25T14:25:58Z 2011-05-25T14:25:58Z 2013-05-26T10:00:21Z 2011-05-25T14:25:58Z 2011-05 Anomaly detection is an important data mining task. Most existing methods treat anomalies as inconsistencies and spend the majority amount of time on modeling normal instances. A recently proposed, sampling-based approach may substantially boost the efficiency in anomaly detection but may lead to weaker accuracy and robustness. In this study, we propose a two-stage approach to find anomalies in complex datasets with high accuracy as well as low time complexity and space cost. Instead of analyzing normal instances, our algorithm first employs an efficient deterministic space partition algorithm to eliminate obvious normal instances and generates a small set of anomaly candidates with a single scan of the dataset. It then checks each candidate with density-based multiple criteria to determine the final results. This two-stage framework also detects anomalies of different notions. Our experiments show that this new approach finds anomalies successfully in different conditions and ensures a good balance of efficiency, accuracy, and robustness. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-04-26T13:15:20Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 thesis_anomaly_xiaoyu1.pdf: 349387 bytes, checksum: df8c74272271ae8db62384d07812dc6a (MD5) Made available in DSpace on 2011-05-25T14:25:58Z (GMT). No. of bitstreams: 2 Yu_Xiao.pdf: 349387 bytes, checksum: df8c74272271ae8db62384d07812dc6a (MD5) license.txt: 4056 bytes, checksum: 31a40d8ba642017fb42a3d0e5df6685e (MD5) Item marked as restricted to the 'Administrator' Group (id=1) by William Ingram (wingram2@illinois.edu) on 2011-05-25T14:30:11Z Item is restricted until 2013-05-25T14:29:35Z Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2013-05-26T10:00:21Z Item was in collections: University of Illinois Dissertations and Theses (ID: 204) Dissertations and Theses - Materials Science and Engineering (ID: 649) Dissertations and Theses - Computer Science (ID: 587) No. of bitstreams: 3 Yu_Xiao.pdf.txt: 44711 bytes, checksum: da101eb54d820ae09fe778992bf1f802 (MD5) Yu_Xiao.pdf: 349387 bytes, checksum: df8c74272271ae8db62384d07812dc6a (MD5) license.txt: 4056 bytes, checksum: 31a40d8ba642017fb42a3d0e5df6685e (MD5) Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2013-05-26T10:00:21Z http://hdl.handle.net/2142/24511 en Copyright 2011 Xiao Yu anomaly detection Filtering and refinement: a two-stage approach for efficient and effective anomaly detection Computer Science 1434 Computer Science 0112 University of Illinois at Urbana-Champaign Thesis M.S. PHD:Computer Science -UIUC 10KS0112PHD