Multivariate filter methods for feature selection with the $$\varvec{\gamma }$$-metric
Results highlighted a good combination of both the forward search direction and the <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>γ</mml:mi></mml:math> -metric as an evaluation function. However, using the backward search direction, the feature selection algorithm could fall into a local optima and can be improved.
Authors
- Nicolas Ngo
- Pierre Michel (ORCID: https://orcid.org/0000-0002-6442-2566)
- Roch Giorgi (ORCID: https://orcid.org/0000-0001-6135-3078)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Aix-Marseille Université (FR)
- Agropolis International (FR)
- Assistance Publique Hôpitaux de Marseille (FR)
- Economic & Social Sciences, Health Systems & Medical Informatics (FR)
- Hôpital de la Timone (FR)
- Institut de Recherche pour le Développement (FR)
Publication Details
- Journal
- BMC Medical Research Methodology
- Published
- 2024-12-19
- DOI
- https://doi.org/10.1186/s12874-024-02426-9
- Citations
- 1
- Primary Topic
- Anomaly Detection Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.35
Funders
- Agence Nationale de la Recherche