© The Institution of Engineering and Technology
The Parkinson's disease (PD) detection based on dysphonia has been drawn significant attention. However, all dysphonia measurements differ in the uncontrolled acoustic environments. In order to gain as much reliability as possible, measurements should be assessed and the robust ones are chosen. In this study, motivated by statistical learning theory, the problem of PD detection is addressed to classify the participant as healthy or PD using support vector machine (SVM) with the dysphonia measurements as the input feature vector. Therefore an energy-based feature-ranking algorithm is adopted to assess the dysphonia measurements. Moreover, in order to improve the stability of the proposed algorithm, an ensemble version is also presented where multiple feature-ranking results are aggregated. The experimental results on PD data sets have shown the proposed algorithm outperforms other classic ones, and the ensemble version obtain the higher stability than single one.
References
-
-
1)
-
Kononerko, I.: `Estimating attributes: analysis and extension of RELIEF', Proc. Int. Conf. on Machine Learning, April 1994, Catania, Italy, p. 171–182.
-
2)
-
I. Guyon ,
A. Elisseeff
.
An introduction to variable and feature selection.
J. Mach. Learn. Res.
,
157 -
1182
-
3)
-
J.A. Logemann ,
H.B. Fisher ,
B. Boshes ,
E.R. Blonsky
.
Frequency and co-occurrence of vocal-tract dysfunctions in speech of a large sample of Parkinson patients.
J. Speech Hear. Disord.
,
47 -
57
-
4)
-
Kira, K., Rendell, L.: `A practical approach to feature selection', Proc. Int. Conf. on Machine Learning, 1992, Aberdeen, Scotland, UK, p. 249–256.
-
5)
-
K.Q. Weinberger ,
J. Blitzer ,
L.K. Saul
.
(2006)
Distance metric learning for large margin nearest neighbor classification.
-
6)
-
K. Crammer ,
R.G. Bachrach ,
A. Navot ,
N. Tishby
.
(2002)
Margin analysis of the lvq algorithm advances in neural information processing systems.
-
7)
-
Frank A., Asuncion A.: ‘UCI machine learning repository’. Available at http://archive.ics.uci.edu/ml, 2010.
-
8)
-
Y.J. Sun ,
S. Todorovic ,
S. Goodison
.
Local learning based feature selection for high dimensional data analysis.
IEEE Trans. Pattern Anal. Mach. Intell.
,
1610 -
1626
-
9)
-
Loscalzo, S., Yu, L., Ding, C.: `Consensus group based stable feature selection', Proc. 15th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD-09), 2009, Paris, France, p. 567–576.
-
10)
-
L. Cnockaert ,
J. Schoentgen ,
P. Auzou ,
C. Ozsancak ,
L. Defebvre ,
F. Grenez
.
Low-frequency vocal modulations in vowels produced by Parkinsonian subjects.
Speech Commun.
,
288 -
300
-
11)
-
S. Sapir ,
J.L. Spielman ,
L.O. Ramig ,
B.H. Story ,
C. Fox
.
Effects of intensive voice treatment (the Lee Silverman voice treatment [LSVT]) on vowel articulation in dysarthric individuals with idiopathic Parkinson disease: acoustic and perceptual findings.
J. Speech Lang. Hear. Res.
,
899 -
912
-
12)
-
J.R. Duffy
.
(2005)
Motor speech disorders: substrates, differential diagnosis, and management.
-
13)
-
Y. LeCun ,
S. Chopra ,
R. Hadsell ,
F.J. Huang ,
M.A. Ranzato ,
Bakir
.
(2006)
A tutorial on energy-based learning, predicting structured outputs.
-
14)
-
I. Guyon ,
S. Gunn ,
M. Nikravesh ,
L. Zadeh
.
(2006)
Feature extraction, foundations and applications.
-
15)
-
M.A. Little ,
P.E. McSharry ,
E.J. Hunter ,
J. Spielman ,
L.O. Ramig
.
Suitability of dysphonia measurements for telemonitoring of Parkinson's disease.
IEEE Trans. Biomed Eng.
,
4 ,
1015 -
1022
-
16)
-
C. Ruggiero ,
R. Sacile ,
M. Giacomini
.
Home telecare.
J. Telemed. Telecare
,
11 -
17
-
17)
-
Saeys, Y., Abel, T., Peer, Y.V.: `Robust feature selection using ensemble feature selection techniques', Proc. 25th European Conf. on Machine Learning and Knowledge Discovery in Databases, July 2008, Helsinki, Finland, p. 313–325.
-
18)
-
Y. Li ,
B.L. Lu
.
Feature selection based on loss margin of nearest neighbor classification.
Pattern Recognit.
,
1914 -
1921
-
19)
-
A.K. Ho ,
R. Iansek ,
C. Marigliani ,
J.L. Bradshaw ,
S. Gates
.
Speech impairment in a large sample of patients with Parkinson's disease.
Cogn. Behav. Neurol.
,
131 -
137
-
20)
-
H. Liu ,
L. Yu
.
Toward integrating feature selection algorithms for classification and clustering.
IEEE Trans. Knowl. Data Eng.
,
494 -
502
-
21)
-
A. Kalousis ,
J. Prados ,
M. Hilario
.
Stability of feature selection algorithms: a study on high dimensional spaces.
Knowl. Inf. Syst.
,
95 -
116
-
22)
-
Han, Y., Yu, L.: `A variance reduction framework for stable feature selection', Proc. Int. Conf. on Data Mining, 2010, Sydney, Australia, p. 206–215.
-
23)
-
Chang C.C., Lin C.J.: ‘LIBSVM: a library for support vector machines’. Available at http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.ps.gz, 2002.
-
24)
-
D.A. Rahn ,
M. Chou ,
J.J. Jiang ,
Y. Zhang
.
Phonatory impairment in Parkinson's disease: evidence from nonlinear dynamic analysis and perturbation analysis.
J. Voice
,
64 -
71
-
25)
-
K.Q. Weinberger ,
L.K. Saul
.
Distance metric learning for large margin nearest neighbor classification.
J. Mach. Learn. Res.
,
207 -
214
-
26)
-
Bachrach, R.G., Navot, A., Tishby, N.: `Margin based feature selection-theory and algorithm', Proc. Int. Conf. on Machine Learning, 2004, Banff, Canada.
-
27)
-
M.A. Little ,
P.E. McSharry ,
S.J. Roberts ,
D.A. Costello ,
I.M. Moroz
.
Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection.
Biomed. Eng. Online
,
1 -
19
-
28)
-
C. Cortes ,
V. Vapnik
.
Support vector networks.
Mach. Learn.
,
1 ,
273 -
297
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-spr.2011.0186
Related content
content/journals/10.1049/iet-spr.2011.0186
pub_keyword,iet_inspecKeyword,pub_concept
6
6