Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE

Abstract: 

Information from different bio--signals such as speech, handwriting, and gait have been used to monitor the state of Parkinson's disease (PD) patients, however, all the multimodal bio--signals may not always be available. We propose a method based on multi-view representation learning via generalized canonical correlation analysis (GCCA) for learning a representation of features extracted from handwriting and gait that can be used as a complement to speech--based features. Three different problems are addressed: classification of PD patients vs. healthy controls, prediction of the neurological state of PD patients according to the UPDRS score, and the prediction of a modified version of the Frenchay dysarthria assessment (m-FDA). According to the results, the proposed approach is suitable to improve the results in the addressed problems, specially in the prediction of the UPDRS, and m-FDA scores.

up
0 users have voted:

Paper Details

Authors:
J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler
Submitted On:
28 February 2017 - 3:28pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Juan Camilo Vasquez-Correa
Paper Code:
3000
Document Year:
2017
Cite

Document Files

pendonVertical(1).pdf

(25)

Subscribe

[1] J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler, "MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1515. Accessed: May. 25, 2019.
@article{1515-17,
url = {http://sigport.org/1515},
author = {J. C. Vásquez-Correa; J. R. Orozco-Arroyave; R. Arora; E. Nöth; N. Dehak; H. Christensen; F. Rudzicz; T. Bocklet; M. Cernak; H. Chinaei; J. Hannink; Phani S. Nidadavolu; M. Yancheva; A. Vann; N. Vogler },
publisher = {IEEE SigPort},
title = {MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE},
year = {2017} }
TY - EJOUR
T1 - MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE
AU - J. C. Vásquez-Correa; J. R. Orozco-Arroyave; R. Arora; E. Nöth; N. Dehak; H. Christensen; F. Rudzicz; T. Bocklet; M. Cernak; H. Chinaei; J. Hannink; Phani S. Nidadavolu; M. Yancheva; A. Vann; N. Vogler
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1515
ER -
J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler. (2017). MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE. IEEE SigPort. http://sigport.org/1515
J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler, 2017. MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE. Available at: http://sigport.org/1515.
J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler. (2017). "MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE." Web.
1. J. C. Vásquez-Correa, J. R. Orozco-Arroyave, R. Arora, E. Nöth, N. Dehak, H. Christensen, F. Rudzicz, T. Bocklet, M. Cernak, H. Chinaei, J. Hannink, Phani S. Nidadavolu, M. Yancheva, A. Vann, N. Vogler. MULTI-VIEW REPRESENTATION LEARNING VIA GCCA FOR MULTIMODAL ANALYSIS OF PARKINSON'S DISEASE [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1515