A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor

A. Hossen, M. Muthuraman, J. Raethjen, G. Deuschl, U. Heute

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A new technique for discrimination between Parkinsonian tremor and essential tremor is investigated in this paper. The method is based on spectral analysis of both accelerometer and surface EMG signals with neural networks. The discrimination system consists of two parts: feature extraction part and classification (distinguishing) part. The feature extraction part uses the method of approximate spectral density estimation of the data by implementing the wavelet-based soft decision technique. In the classification part, a machine learning approach is implemented using back-propagation supervised neural network. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. Two sets of data are used. The training set, which consists of 21 essential-tremor (ET) subjects and 19 Parkinson-disease (PD) subjects, is used to obtain the important features used for distinguishing between the two subjects. The test data set, which consists of 20 ET and 20 PD subjects, is used to test the technique and evaluate its performance.

Original languageEnglish
Title of host publicationAdvances in Intelligent and Soft Computing
Pages1051-1060
Number of pages10
Volume130 AISC
EditionVOL. 1
DOIs
Publication statusPublished - 2012
EventInternational Conference on Soft Computing for Problem Solving, SocProS 2011 - Roorkee, India
Duration: Dec 20 2011Dec 22 2011

Publication series

NameAdvances in Intelligent and Soft Computing
NumberVOL. 1
Volume130 AISC
ISSN (Print)18675662

Other

OtherInternational Conference on Soft Computing for Problem Solving, SocProS 2011
CountryIndia
CityRoorkee
Period12/20/1112/22/11

Fingerprint

Feature extraction
Neural networks
Spectral density
Neurology
Backpropagation
Accelerometers
Spectrum analysis
Learning systems

Keywords

  • Accelerometer
  • Artificial Neural Networks
  • EMG
  • Essential Tremor
  • Parkinsonian Tremor
  • Soft-Decision Technique
  • Wavelet-Decomposition

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Hossen, A., Muthuraman, M., Raethjen, J., Deuschl, G., & Heute, U. (2012). A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor. In Advances in Intelligent and Soft Computing (VOL. 1 ed., Vol. 130 AISC, pp. 1051-1060). (Advances in Intelligent and Soft Computing; Vol. 130 AISC, No. VOL. 1). https://doi.org/10.1007/978-81-322-0487-9_96

A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor. / Hossen, A.; Muthuraman, M.; Raethjen, J.; Deuschl, G.; Heute, U.

Advances in Intelligent and Soft Computing. Vol. 130 AISC VOL. 1. ed. 2012. p. 1051-1060 (Advances in Intelligent and Soft Computing; Vol. 130 AISC, No. VOL. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hossen, A, Muthuraman, M, Raethjen, J, Deuschl, G & Heute, U 2012, A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor. in Advances in Intelligent and Soft Computing. VOL. 1 edn, vol. 130 AISC, Advances in Intelligent and Soft Computing, no. VOL. 1, vol. 130 AISC, pp. 1051-1060, International Conference on Soft Computing for Problem Solving, SocProS 2011, Roorkee, India, 12/20/11. https://doi.org/10.1007/978-81-322-0487-9_96
Hossen A, Muthuraman M, Raethjen J, Deuschl G, Heute U. A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor. In Advances in Intelligent and Soft Computing. VOL. 1 ed. Vol. 130 AISC. 2012. p. 1051-1060. (Advances in Intelligent and Soft Computing; VOL. 1). https://doi.org/10.1007/978-81-322-0487-9_96
Hossen, A. ; Muthuraman, M. ; Raethjen, J. ; Deuschl, G. ; Heute, U. / A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor. Advances in Intelligent and Soft Computing. Vol. 130 AISC VOL. 1. ed. 2012. pp. 1051-1060 (Advances in Intelligent and Soft Computing; VOL. 1).
@inproceedings{9a2a674e2c6f4d469c878430feaae94e,
title = "A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor",
abstract = "A new technique for discrimination between Parkinsonian tremor and essential tremor is investigated in this paper. The method is based on spectral analysis of both accelerometer and surface EMG signals with neural networks. The discrimination system consists of two parts: feature extraction part and classification (distinguishing) part. The feature extraction part uses the method of approximate spectral density estimation of the data by implementing the wavelet-based soft decision technique. In the classification part, a machine learning approach is implemented using back-propagation supervised neural network. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. Two sets of data are used. The training set, which consists of 21 essential-tremor (ET) subjects and 19 Parkinson-disease (PD) subjects, is used to obtain the important features used for distinguishing between the two subjects. The test data set, which consists of 20 ET and 20 PD subjects, is used to test the technique and evaluate its performance.",
keywords = "Accelerometer, Artificial Neural Networks, EMG, Essential Tremor, Parkinsonian Tremor, Soft-Decision Technique, Wavelet-Decomposition",
author = "A. Hossen and M. Muthuraman and J. Raethjen and G. Deuschl and U. Heute",
year = "2012",
doi = "10.1007/978-81-322-0487-9_96",
language = "English",
isbn = "9788132204862",
volume = "130 AISC",
series = "Advances in Intelligent and Soft Computing",
number = "VOL. 1",
pages = "1051--1060",
booktitle = "Advances in Intelligent and Soft Computing",
edition = "VOL. 1",

}

TY - GEN

T1 - A neural network approach to distinguish Parkinsonian tremor from advanced essential tremor

AU - Hossen, A.

AU - Muthuraman, M.

AU - Raethjen, J.

AU - Deuschl, G.

AU - Heute, U.

PY - 2012

Y1 - 2012

N2 - A new technique for discrimination between Parkinsonian tremor and essential tremor is investigated in this paper. The method is based on spectral analysis of both accelerometer and surface EMG signals with neural networks. The discrimination system consists of two parts: feature extraction part and classification (distinguishing) part. The feature extraction part uses the method of approximate spectral density estimation of the data by implementing the wavelet-based soft decision technique. In the classification part, a machine learning approach is implemented using back-propagation supervised neural network. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. Two sets of data are used. The training set, which consists of 21 essential-tremor (ET) subjects and 19 Parkinson-disease (PD) subjects, is used to obtain the important features used for distinguishing between the two subjects. The test data set, which consists of 20 ET and 20 PD subjects, is used to test the technique and evaluate its performance.

AB - A new technique for discrimination between Parkinsonian tremor and essential tremor is investigated in this paper. The method is based on spectral analysis of both accelerometer and surface EMG signals with neural networks. The discrimination system consists of two parts: feature extraction part and classification (distinguishing) part. The feature extraction part uses the method of approximate spectral density estimation of the data by implementing the wavelet-based soft decision technique. In the classification part, a machine learning approach is implemented using back-propagation supervised neural network. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. Two sets of data are used. The training set, which consists of 21 essential-tremor (ET) subjects and 19 Parkinson-disease (PD) subjects, is used to obtain the important features used for distinguishing between the two subjects. The test data set, which consists of 20 ET and 20 PD subjects, is used to test the technique and evaluate its performance.

KW - Accelerometer

KW - Artificial Neural Networks

KW - EMG

KW - Essential Tremor

KW - Parkinsonian Tremor

KW - Soft-Decision Technique

KW - Wavelet-Decomposition

UR - http://www.scopus.com/inward/record.url?scp=84861148353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861148353&partnerID=8YFLogxK

U2 - 10.1007/978-81-322-0487-9_96

DO - 10.1007/978-81-322-0487-9_96

M3 - Conference contribution

SN - 9788132204862

VL - 130 AISC

T3 - Advances in Intelligent and Soft Computing

SP - 1051

EP - 1060

BT - Advances in Intelligent and Soft Computing

ER -