On the study of nearest neighbor algorithms for prevalence estimation in binary problems
This paper presents a new approach for solving binary quantification problems based on nearest neighbor (NN) algorithms. Our main objective is to study the behavior of these methods in the context of prevalence estimation. We seek for NN-based quantifiers able to provide competitive performance whil...
| Autores: | , , , |
|---|---|
| Tipo de documento: | artigo |
| Data de publicação: | 2013 |
| País: | España |
| Recursos: | Universidad de Oviedo (UNIOVI) |
| Repositório: | RUO. Repositorio Institucional de la Universidad de Oviedo |
| Idioma: | inglês |
| OAI Identifier: | oai:digibuo.uniovi.es:10651/28998 |
| Acesso em linha: | http://hdl.handle.net/10651/28998 https://dx.doi.org/10.1016/j.patcog.2012.07.022 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Quantification Prevalence estimation Nearest neighbor |
| Resumo: | This paper presents a new approach for solving binary quantification problems based on nearest neighbor (NN) algorithms. Our main objective is to study the behavior of these methods in the context of prevalence estimation. We seek for NN-based quantifiers able to provide competitive performance while balancing simplicity and effectiveness. We propose two simple weighting strategies, PWK and PWK , which stand out among state-of-the-art quantifiers. These proposed methods are the only ones that offer statistical differences with respect to less robust algorithms, like CC or AC. The second contribution of the paper is to introduce a new experiment methodology for quantification |
|---|