Anomaly Detection in High Dimensional Data (Q74767): Difference between revisions

Revision as of 22:37, 24 November 2024 Tconrad (talk \| contribs) Bureaucrats, Interface administrators, private, Suppressors, Administrators 2,438 edits ‎Removed claim: summary (P1638): This article introduces a novel stray algorithm designed to detect anomalies in high-dimensional data, addressing limitations of the existing HDoutliers method by applying extreme value theory for precise threshold calculation and efficiency. The authors validate the new algorithm's efficacy with both synthetic and real datasets, showcasing its superiority over HDoutliers in accuracy and computational performance. The stray algorithm is encap... Tag: Reverted ← Older edit		Revision as of 22:37, 24 November 2024 Tconrad (talk \| contribs) Bureaucrats, Interface administrators, private, Suppressors, Administrators 2,438 edits ‎Removed claim: summary_simple (P1639): This article presents a new stray algorithm designed to detect anomalies in high-dimensional data effectively. The authors address limitations of the existing HDoutliers algorithm by incorporating extreme value theory, leading to more accurate anomaly detection thresholds and faster computational times. They validate the performance of their algorithm using both synthetic and real datasets, showcasing its superior accuracy and efficiency comp... Tag: Manual revert Newer edit →
Property / summary_simple
	This article presents a new stray algorithm designed to detect anomalies in high-dimensional data effectively. The authors address limitations of the existing HDoutliers algorithm by incorporating extreme value theory, leading to more accurate anomaly detection thresholds and faster computational times. They validate the performance of their algorithm using both synthetic and real datasets, showcasing its superior accuracy and efficiency compared to the HDoutliers algorithm. Notably, the stray algorithm is implemented as an open-source R package for versatile application in diverse data structures through feature engineering techniques. (English)
Property / summary_simple: This article presents a new stray algorithm designed to detect anomalies in high-dimensional data effectively. The authors address limitations of the existing HDoutliers algorithm by incorporating extreme value theory, leading to more accurate anomaly detection thresholds and faster computational times. They validate the performance of their algorithm using both synthetic and real datasets, showcasing its superior accuracy and efficiency compared to the HDoutliers algorithm. Notably, the stray algorithm is implemented as an open-source R package for versatile application in diverse data structures through feature engineering techniques. (English) / rank
	~~Normal rank~~