Feature Selection with Complexity Measure in a Quadratic Programming Setting

• Type: Article in International Conference Proceedings Book
• Date: 2011

Authors

Ricardo Sousa (Author) Other; Helder P Oliveira (Author) FEUP; Jaime S Cardoso (Author) FEUP

Conference proceedings International

Title: PATTERN RECOGNITION AND IMAGE ANALYSIS: 5TH IBERIAN CONFERENCE, IBPRIA 2011

Pages: 524-531

5th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)

Las Palmas, SPAIN, JUN 08-10, 2011

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 1 Citation

Scientific classification

FOS: Engineering and technology > Electrical engineering, Electronic engineering, Information engineering

Other information

Authenticus ID: P-002-WW4

DOI: 10.1007/978-3-642-21257-4_65

Abstract (EN): Feature selection is a topic of growing interest mainly due to the increasing amount of information, being an essential task in many machine learning problems with high dimensional data. The selection of a subset of relevant features help to reduce the complexity of the problem and the building of robust learning models. This work presents an adaptation of a recent quadratic programming feature selection technique that identifies in one-fold the redundancy and relevance on data. Our approach introduces a non-probabilistic measure to capture the relevance based on Minimum Spanning Trees. Three different real datasets were used to assess the performance of the adaptation. The results are encouraging and reflect the utility of feature selection algorithms.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8