Convex and Nonconvex Nonparametric Frontier-based Classification Methods for Anomaly Detection
Qianying Jin (qianying.jin@nuaa.edu.cn),
Kristiaan Kerstens and
Ignace van de Woestyne (ignace.vandewoestyne@kuleuven.be)
Additional contact information
Qianying Jin: College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China
Ignace van de Woestyne: KU Leuven, Research Centre for Operations Research and Statistics (ORSTAT), Brussels Campus, War- moesberg 26, B-1000 Brussels, Belgium
No 2023-EQM-01, Working Papers from IESEG School of Management
Abstract:
Effective methods for determining the boundary of the normal class are very useful for detecting anomalies in commercial or security applications - a problem known as anomaly detection. This contribution proposes a nonparametric frontier-based clas- sification (NPFC) method for anomaly detection. By relaxing the commonly used convexity assumption in the literature, a nonconvex NPFC method is constructed and the nonconvex nonparametric frontier turns out to provide a more conservative bound- ary enveloping the normal class. By reflecting on the monotonic relation between the characteristic variables and the membership, the proposed NPFC method is in a more general form since both input-type and output-type characteristic variables are incor- porated. A biomedical data set is used to test the performance of the proposed NPFC methods. The results show that the proposed NPFC methods have competitive clas- sification performance and have consistent advantages in detecting abnormal samples, especially the nonconvex NPFC method
Keywords: : Nonparametric Frontier; Convex; Nonconvex; Anomaly Detection (search for similar items in EconPapers)
Pages: 26 pages
Date: 2023-02
New Economics Papers: this item is included in nep-eff
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
https://www.ieseg.fr/wp-content/uploads/2023/02/2023-EQM-01.pdf (application/pdf)
Related works:
Journal Article: Convex and nonconvex nonparametric frontier-based classification methods for anomaly detection (2024) 
Working Paper: Convex and nonconvex nonparametric frontier-based classification methods for anomaly detection (2024)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:ies:wpaper:e202302
Access Statistics for this paper
More papers in Working Papers from IESEG School of Management Contact information at EDIRC.
Bibliographic data for series maintained by Lies BOUTEN (l.bouten@ieseg.fr).