Standard Article

Feature Extraction and Feature Selection: A Survey of Methods in Industrial Applications

  1. Michel J. Anzanello

Published Online: 14 JAN 2011

DOI: 10.1002/9780470400531.eorms0321

Wiley Encyclopedia of Operations Research and Management Science

Wiley Encyclopedia of Operations Research and Management Science

How to Cite

Anzanello, M. J. 2011. Feature Extraction and Feature Selection: A Survey of Methods in Industrial Applications. Wiley Encyclopedia of Operations Research and Management Science. .

Author Information

  1. Federal University of Rio Grande do Sul, Department of Industrial Engineering, Porto Alegre, Brazil

Publication History

  1. Published Online: 14 JAN 2011

Abstract

In industrial processes, the handling of large amounts of data collected by sensors and computers has challenged engineers and practitioners, making feature selection a subject of massive research in academy and industry. The use of redundant, irrelevant, and noisy features (also known as variables) tends to spoil the performance of many statistical tools, leading to unreliable inferences and costly data collection. In this article we present a survey on variable selection methods and applications in the manufacturing and chemometrics field. We deploy these methods in two major classes: variable selection for prediction and for classification. We then briefly suggest future developments on the topic.

Keywords:

  • variable selection;
  • PLS regression;
  • neural networks;
  • support vector machines;
  • data mining tools