Close
Help





JOURNAL

Cancer Informatics

Flow Cytometry-Based Classification in Cancer Research: A View on Feature Selection

Submit a Paper


Cancer Informatics 2015:Suppl. 5 75-85

Original Research

Published on 10 Apr 2016

DOI: 10.4137/CIN.S30795


Further metadata provided in PDF



Sign up for email alerts to receive notifications of new articles published in Cancer Informatics

Abstract

In this paper, we study the problem of feature selection in cancer-related machine learning tasks. In particular, we study the accuracy and stability of different feature selection approaches within simplistic machine learning pipelines. Earlier studies have shown that for certain cases, the accuracy of detection can easily reach 100% given enough training data. Here, however, we concentrate on simplifying the classification models with and seek for feature selection approaches that are reliable even with extremely small sample sizes. We show that as much as 50% of features can be discarded without compromising the prediction accuracy. Moreover, we study the model selection problem among the ℓ₁ regularization path of logistic regression classifiers. To this aim, we compare a more traditional cross-validation approach with a recently proposed Bayesian error estimator.



Downloads

PDF  (973.68 KB PDF FORMAT)

RIS citation   (ENDNOTE, REFERENCE MANAGER, PROCITE, REFWORKS)

BibTex citation   (BIBDESK, LATEX)

XML





Quick Links


New article and journal news notification services