A neural network approach for feature extraction and discrimination between Parkinsonian tremor and essential tremor

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

BACKGROUND: Essential tremor (ET) and the tremor in Parkinson's disease (PD) are the two most common pathological tremor with a certain overlap in the clinical presentation. OBJECTIVE: The main purpose of this work is to use an artificial neural network to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometry and surface EMG signals. METHODS: The Soft-Decision wavelet-based technique is to be used in this work in order to obtain a 16 bands approximate spectral representation of both accelerometer and two EMG signals of two sets of data (training and test). The training set consists of 21 ET subjects and 19 PD subjects while the test set consists of 20 ET and 20 PD subjects. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. A neural network of the type feed forward back propagation has been used to find the frequency bands associated with the different signals that yield better discrimination efficiency on training data. The same designed network is used to discriminate the test set. RESULTS: Efficiency result of 87.5% was obtained using two different bands from each of the three signals under test. CONCLUSIONS: The artificial neural network has been used successfully in both feature extraction and in pattern matching tasks in a complete classification system.

Original languageEnglish
Pages (from-to)345-356
Number of pages12
JournalTechnology and Health Care
Volume21
Issue number4
DOIs
Publication statusPublished - 2013

Fingerprint

Essential Tremor
Tremor
Feature extraction
Neural networks
Parkinson Disease
Pattern matching
Neurology
Accelerometry
Backpropagation
Accelerometers
Spectrum analysis
Frequency bands
Time series
Germany

Keywords

  • Accelerometer
  • Artificial neural networks
  • EMG
  • ET
  • extraction
  • feature
  • pattern matching
  • PD
  • spectral analysis
  • wavelet-decomposition

ASJC Scopus subject areas

  • Biophysics
  • Biomaterials
  • Bioengineering
  • Biomedical Engineering
  • Information Systems
  • Health Informatics
  • Medicine(all)

Cite this

@article{54545889bd64495cbc3cb4e541b49a50,
title = "A neural network approach for feature extraction and discrimination between Parkinsonian tremor and essential tremor",
abstract = "BACKGROUND: Essential tremor (ET) and the tremor in Parkinson's disease (PD) are the two most common pathological tremor with a certain overlap in the clinical presentation. OBJECTIVE: The main purpose of this work is to use an artificial neural network to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometry and surface EMG signals. METHODS: The Soft-Decision wavelet-based technique is to be used in this work in order to obtain a 16 bands approximate spectral representation of both accelerometer and two EMG signals of two sets of data (training and test). The training set consists of 21 ET subjects and 19 PD subjects while the test set consists of 20 ET and 20 PD subjects. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. A neural network of the type feed forward back propagation has been used to find the frequency bands associated with the different signals that yield better discrimination efficiency on training data. The same designed network is used to discriminate the test set. RESULTS: Efficiency result of 87.5{\%} was obtained using two different bands from each of the three signals under test. CONCLUSIONS: The artificial neural network has been used successfully in both feature extraction and in pattern matching tasks in a complete classification system.",
keywords = "Accelerometer, Artificial neural networks, EMG, ET, extraction, feature, pattern matching, PD, spectral analysis, wavelet-decomposition",
author = "Abdulnasir Hossen",
year = "2013",
doi = "10.3233/THC-130735",
language = "English",
volume = "21",
pages = "345--356",
journal = "Technology and Health Care",
issn = "0928-7329",
publisher = "IOS Press",
number = "4",

}

TY - JOUR

T1 - A neural network approach for feature extraction and discrimination between Parkinsonian tremor and essential tremor

AU - Hossen, Abdulnasir

PY - 2013

Y1 - 2013

N2 - BACKGROUND: Essential tremor (ET) and the tremor in Parkinson's disease (PD) are the two most common pathological tremor with a certain overlap in the clinical presentation. OBJECTIVE: The main purpose of this work is to use an artificial neural network to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometry and surface EMG signals. METHODS: The Soft-Decision wavelet-based technique is to be used in this work in order to obtain a 16 bands approximate spectral representation of both accelerometer and two EMG signals of two sets of data (training and test). The training set consists of 21 ET subjects and 19 PD subjects while the test set consists of 20 ET and 20 PD subjects. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. A neural network of the type feed forward back propagation has been used to find the frequency bands associated with the different signals that yield better discrimination efficiency on training data. The same designed network is used to discriminate the test set. RESULTS: Efficiency result of 87.5% was obtained using two different bands from each of the three signals under test. CONCLUSIONS: The artificial neural network has been used successfully in both feature extraction and in pattern matching tasks in a complete classification system.

AB - BACKGROUND: Essential tremor (ET) and the tremor in Parkinson's disease (PD) are the two most common pathological tremor with a certain overlap in the clinical presentation. OBJECTIVE: The main purpose of this work is to use an artificial neural network to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometry and surface EMG signals. METHODS: The Soft-Decision wavelet-based technique is to be used in this work in order to obtain a 16 bands approximate spectral representation of both accelerometer and two EMG signals of two sets of data (training and test). The training set consists of 21 ET subjects and 19 PD subjects while the test set consists of 20 ET and 20 PD subjects. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. A neural network of the type feed forward back propagation has been used to find the frequency bands associated with the different signals that yield better discrimination efficiency on training data. The same designed network is used to discriminate the test set. RESULTS: Efficiency result of 87.5% was obtained using two different bands from each of the three signals under test. CONCLUSIONS: The artificial neural network has been used successfully in both feature extraction and in pattern matching tasks in a complete classification system.

KW - Accelerometer

KW - Artificial neural networks

KW - EMG

KW - ET

KW - extraction

KW - feature

KW - pattern matching

KW - PD

KW - spectral analysis

KW - wavelet-decomposition

UR - http://www.scopus.com/inward/record.url?scp=84884403504&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884403504&partnerID=8YFLogxK

U2 - 10.3233/THC-130735

DO - 10.3233/THC-130735

M3 - Article

C2 - 23949179

AN - SCOPUS:84884403504

VL - 21

SP - 345

EP - 356

JO - Technology and Health Care

JF - Technology and Health Care

SN - 0928-7329

IS - 4

ER -