eprintid: 2776
rev_number: 8
eprint_status: archive
userid: 69
dir: disk0/00/00/27/76
datestamp: 2015-10-19 09:40:53
lastmod: 2016-04-06 08:50:40
status_changed: 2015-10-19 09:40:53
type: book_section
metadata_visibility: show
creators_name: Morisi, Rita
creators_name: Gnecco, Giorgio
creators_name: Lanconelli, Nico
creators_name: Zanigni, Stefano
creators_name: Manners, David Neil
creators_name: Testa, Claudia
creators_name: Evangelisti, Stefania
creators_name: Gramegna, LauraLudovica
creators_name: Bianchini, Claudio
creators_name: Cortelli, Pietro
creators_name: Tonon, Caterina
creators_name: Lodi, Raffaele
creators_id: rita.morisi@imtlucca.it
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
title: Binary and Multi-class Parkinsonian Disorders Classification Using Support Vector Machines
ispublished: pub
subjects: QA75
subjects: RZ
subjects: T1
divisions: CSA
full_text_status: none
keywords: Support Vector Machines; Feature selection; Binary classification; Multi–class classification; Parkinsonian disorders classification
abstract: This paper presents a method for an automated Parkinsonian disorders classification using Support Vector Machines (SVMs). Magnetic Resonance quantitative markers are used as features to train SVMs with the aim of automatically diagnosing patients with different Parkinsonian disorders. Binary and multi–class classification problems are investigated and applied with the aim of automatically distinguishing the subjects with different forms of disorders. A ranking feature selection method is also used as a preprocessing step in order to asses the significance of the different features in diagnosing Parkinsonian disorders. In particular, it turns out that the features selected as the most meaningful ones reflect the opinions of the clinicians as the most important markers in the diagnosis of these disorders. Concerning the results achieved in the classification phase, they are promising; in the two multi–class classification problems investigated, an average accuracy of 81% and 90% is obtained, while in the binary scenarios taken in consideration, the accuracy is never less than 88%.
date: 2015
date_type: published
series: Lecture Notes in Computer Science
volume: 9117
publisher: Springer
pagerange: 379-386
refereed: TRUE
isbn: 978-3-319-19389-2
book_title: Pattern Recognition and Image Analysis
official_url: http://dx.doi.org/10.1007/978-3-319-19390-8_43
citation:   Morisi, Rita and Gnecco, Giorgio and Lanconelli, Nico and Zanigni, Stefano and Manners, David Neil and Testa, Claudia and Evangelisti, Stefania and Gramegna, LauraLudovica and Bianchini, Claudio and Cortelli, Pietro and Tonon, Caterina and Lodi, Raffaele  Binary and Multi-class Parkinsonian Disorders Classification Using Support Vector Machines.   In:  Pattern Recognition and Image Analysis.   Lecture Notes in Computer Science, 9117 .  Springer, pp. 379-386.  ISBN 978-3-319-19389-2      (2015)