Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor

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

1 Citation (Scopus)

Abstract

A novel discrimination method of Parkinsonian tremor from essential tremor is presented in this paper. The method uses the approximate power spectral density of specific sub-bands, which is estimated using a soft-decision wavelet-based decomposition of EMG and accelerometer signals. Selection of specific sub-bands of the spectrum of two EMG signals and accelerometer signal has been implemented to provide the neural network with its proper inputs. Two sets of data, training set and test set, which are recorded in the department of Neurology of the University of Kiel-Germany, are used in this work. The training set, which consists of 21 essential tremor subjects and 19 Parkinson disease subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists of 20 essential tremor subjects and 20 Parkinson disease subjects are used to test the performance of the discrimination system. A best discrimination efficiency of 87.5% has been obtained in this work.

Original languageEnglish
Title of host publication2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012
Pages37-40
Number of pages4
DOIs
Publication statusPublished - 2012
Event2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012 - Seville, Seville, Spain
Duration: Dec 9 2012Dec 12 2012

Other

Other2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012
CountrySpain
CitySeville, Seville
Period12/9/1212/12/12

Fingerprint

Accelerometers
Neural networks
Power spectral density
Neurology
Backpropagation
Decomposition

Keywords

  • Accelerometer
  • Artificial Neural networks
  • Discrimination
  • EMG
  • Essential Tremor
  • Parkinsonian Tremor
  • Power Spectral Density
  • Wavelet-Decomposition

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Hossen, A. (2012). Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor. In 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012 (pp. 37-40). [6463707] https://doi.org/10.1109/ICECS.2012.6463707

Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor. / Hossen, Abdulnasir.

2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012. 2012. p. 37-40 6463707.

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

Hossen, A 2012, Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor. in 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012., 6463707, pp. 37-40, 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012, Seville, Seville, Spain, 12/9/12. https://doi.org/10.1109/ICECS.2012.6463707
Hossen A. Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor. In 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012. 2012. p. 37-40. 6463707 https://doi.org/10.1109/ICECS.2012.6463707
Hossen, Abdulnasir. / Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor. 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012. 2012. pp. 37-40
@inproceedings{20cd273a15254ce290966b3ad037940f,
title = "Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor",
abstract = "A novel discrimination method of Parkinsonian tremor from essential tremor is presented in this paper. The method uses the approximate power spectral density of specific sub-bands, which is estimated using a soft-decision wavelet-based decomposition of EMG and accelerometer signals. Selection of specific sub-bands of the spectrum of two EMG signals and accelerometer signal has been implemented to provide the neural network with its proper inputs. Two sets of data, training set and test set, which are recorded in the department of Neurology of the University of Kiel-Germany, are used in this work. The training set, which consists of 21 essential tremor subjects and 19 Parkinson disease subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists of 20 essential tremor subjects and 20 Parkinson disease subjects are used to test the performance of the discrimination system. A best discrimination efficiency of 87.5{\%} has been obtained in this work.",
keywords = "Accelerometer, Artificial Neural networks, Discrimination, EMG, Essential Tremor, Parkinsonian Tremor, Power Spectral Density, Wavelet-Decomposition",
author = "Abdulnasir Hossen",
year = "2012",
doi = "10.1109/ICECS.2012.6463707",
language = "English",
isbn = "9781467312615",
pages = "37--40",
booktitle = "2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012",

}

TY - GEN

T1 - Selection of wavelet-bands for neural network discrimination of Parkinsonian tremor from essential tremor

AU - Hossen, Abdulnasir

PY - 2012

Y1 - 2012

N2 - A novel discrimination method of Parkinsonian tremor from essential tremor is presented in this paper. The method uses the approximate power spectral density of specific sub-bands, which is estimated using a soft-decision wavelet-based decomposition of EMG and accelerometer signals. Selection of specific sub-bands of the spectrum of two EMG signals and accelerometer signal has been implemented to provide the neural network with its proper inputs. Two sets of data, training set and test set, which are recorded in the department of Neurology of the University of Kiel-Germany, are used in this work. The training set, which consists of 21 essential tremor subjects and 19 Parkinson disease subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists of 20 essential tremor subjects and 20 Parkinson disease subjects are used to test the performance of the discrimination system. A best discrimination efficiency of 87.5% has been obtained in this work.

AB - A novel discrimination method of Parkinsonian tremor from essential tremor is presented in this paper. The method uses the approximate power spectral density of specific sub-bands, which is estimated using a soft-decision wavelet-based decomposition of EMG and accelerometer signals. Selection of specific sub-bands of the spectrum of two EMG signals and accelerometer signal has been implemented to provide the neural network with its proper inputs. Two sets of data, training set and test set, which are recorded in the department of Neurology of the University of Kiel-Germany, are used in this work. The training set, which consists of 21 essential tremor subjects and 19 Parkinson disease subjects, is used to train the neural network of type feed-forward back-propagation. The test set, which consists of 20 essential tremor subjects and 20 Parkinson disease subjects are used to test the performance of the discrimination system. A best discrimination efficiency of 87.5% has been obtained in this work.

KW - Accelerometer

KW - Artificial Neural networks

KW - Discrimination

KW - EMG

KW - Essential Tremor

KW - Parkinsonian Tremor

KW - Power Spectral Density

KW - Wavelet-Decomposition

UR - http://www.scopus.com/inward/record.url?scp=84874615634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874615634&partnerID=8YFLogxK

U2 - 10.1109/ICECS.2012.6463707

DO - 10.1109/ICECS.2012.6463707

M3 - Conference contribution

SN - 9781467312615

SP - 37

EP - 40

BT - 2012 19th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2012

ER -