Pathological voice assessment by recurrence quantification analysis

dc.contributor.authorDe A. Costa W.C.
dc.contributor.authorAssis F.M.
dc.contributor.authorNeto B.G.A.
dc.contributor.authorCosta S.C.
dc.contributor.authorVieira V.J.D.
dc.description.abstractIn this paper, the performance of quantification measures of recurrence plots is evaluated in the task of discriminating pathological voices from the healthy ones. In order to classify these signals as healthy, edema or paralysis, seven recurrence quantification measures are used: Determinism (DET), Maximum length of the diagonal structures (L max), Entropy (ENTR), Slope of line-of-best-fit (TREND), Laminarity (LAM), Length of longest vertical line segment (V max), and mean vertical line length or trapping time (TT). A discriminant analysis method is applied to each feature individually, using two discriminant functions: Linear and quadratic. The performance of individual classifiers are improved when combining the measures two by two. Results show that the method employed can be used as a highly reliable method for pathological voice assessment. © 2012 IEEE.
dc.relation.ispartof2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living, BRC 2012
dc.rightsAcesso Restrito
dc.subject.otherlanguagePathological voices
dc.subject.otherlanguagerecurrence plots
dc.subject.otherlanguagerecurrence quantification measures
dc.titlePathological voice assessment by recurrence quantification analysis
dc.typeArtigo de evento
local.scopus.subjectDiagonal structure
local.scopus.subjectDiscriminant functions
local.scopus.subjectIndividual classifiers
local.scopus.subjectPathological voice
local.scopus.subjectRecurrence plot
local.scopus.subjectRecurrence quantification analysis
local.scopus.subjectrecurrence quantification measures
local.scopus.subjectTrapping time
local.scopus.subjectVertical lines