Feature Selection Study on Separate Multi-modal Datasets: Application on Cutaneous MelanomaReportar como inadecuado




Feature Selection Study on Separate Multi-modal Datasets: Application on Cutaneous Melanoma - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 UCG - University of Central Greece 2 Institute of Biological Research and Biotechnology

Abstract : In this work, we study the behavior of a feature selection algorithm backwards selection using random forests, by fusing multi-modal data from different subjects. Two separate datasets related to cutaneous melanoma, obtained from image dermoscopy and non-image microarray sources are used. Imputations are applied in order to acquire a unified dataset, prior the effect of machine learning algorithms. The results suggest that application of the normal random imputation method acts as an additional variation factor, helping towards stability of potential recommended biomarkers. In addition, microarray-derived features were favorably selected as best predictors compared to image-derived features.

Keywords : feature selection random forest biomarkers cutaneous melanoma





Autor: Konstantinos Moutselos - Aristotelis Chatziioannou - Ilias Maglogiannis -

Fuente: https://hal.archives-ouvertes.fr/



DESCARGAR PDF




Documentos relacionados