Repository logo
 

Statistical inference on recall, precision and average precision under random selection

Simple item page
dc.contributor.authorSu, Wanhua
dc.contributor.authorZhang, P.
dc.date.accessioned2020-10-02
dc.date.accessioned2022-05-31T01:15:21Z
dc.date.available2022-05-31T01:15:21Z
dc.date.issued2012
dc.description.abstractThe objective of a rare target detection problem is to identify the rare targets as early as possible. Recall, precision and average precision are three popular performance measures for evaluating different detection methods. However, there is little literature on the statistical properties of these three measures. We develop a framework for conducting statistical inference on recall, precision and average precision through establishing their asymptotic properties. Simulations are used to illustrate the idea. The proposed methods can also be applied in other areas where ranking systems need to be evaluated, such as information retrieval.
dc.description.urihttps://macewan.primo.exlibrisgroup.com/permalink/01MACEWAN_INST/d1nmsu/cdi_ieee_primary_6234049
dc.identifier.citationZhang, P. and Su, W. Statistical inference on recall, precision and average precision under random selection. International Conference on Fuzzy Systems and Knowledge Discovery IEEE, 2012:1348-1352.
dc.identifier.doihttps://doi.org/10.1109/FSKD.2012.6234049
dc.identifier.urihttps://hdl.handle.net/20.500.14078/1737
dc.languageEnglish
dc.language.isoen
dc.rightsAll Rights Reserved
dc.subjectobject detection
dc.subjectinformation retrieval
dc.subjectmathematical model
dc.subjectequations
dc.subjectvectors
dc.subjectjoints
dc.subjecteducational institutions
dc.titleStatistical inference on recall, precision and average precision under random selectionen
dc.typePresentation

Files

Collections

Department of Mathematics and Statistics