Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs

Noor Kamal Al-Qazzaz, Sawal Hamid Md Ali, Siti Anom Ahmad

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

Abstract

The aim of the present study was to select the optimal denoising technique that helps in discriminating dementia in the early stages and illustrating its degree of severity. In this paper, a comparative analysis of three denoising techniques, which are wavelet (WT), automatic independent component analysis (AICA) rejection, and automatic hybrid technique using independent component analysis and wavelet (AICA-WT), has been conducted to select the optimal denoising technique. Two approaches have been used to extract meaningful features these are Permutation entropy (PEn) and Higuchi's fractal dimension (FD) from Electroencephalography (EEG) dataset of 5 vascular dementia (VD) patients, 15 stroke-related patients with mild cognitive impairment (MCI) and 15 healthy subjects during working memory task (WMT). k-nearest neighbors (kNN) classifier has been used. The results show that the AICA-WT denoising technique improved the kNN classification accuracy from 88.15% for WT and 89.26% for AICA rejection to 90.37%for AICA-WT denoising technique. These results suggest AICA-WT consistently improves the discrimination of VD, MCI patients and control normal subjects which are useful for dementia early detection.

Original languageEnglish
Title of host publication2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages109-112
Number of pages4
ISBN (Electronic)9781538612774
DOIs
Publication statusPublished - 7 Nov 2018
Event2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018 - Kuching, Sarawak, Malaysia
Duration: 24 Jul 201826 Jul 2018

Other

Other2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018
CountryMalaysia
CityKuching, Sarawak
Period24/7/1826/7/18

Fingerprint

Wavelet Analysis
Vascular Dementia
Independent component analysis
Electroencephalography
Dementia
Fractals
Entropy
Short-Term Memory
Healthy Volunteers
Fractal dimension
Stroke
Classifiers
Data storage equipment

Keywords

  • fractal dimension
  • independent components analysis permutation entropy
  • k-nearest neighbors
  • wavelet

ASJC Scopus subject areas

  • Health Informatics
  • Signal Processing
  • Biomedical Engineering

Cite this

Al-Qazzaz, N. K., Md Ali, S. H., & Ahmad, S. A. (2018). Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs. In 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018 (pp. 109-112). [8527412] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICBAPS.2018.8527412

Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs. / Al-Qazzaz, Noor Kamal; Md Ali, Sawal Hamid; Ahmad, Siti Anom.

2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 109-112 8527412.

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

Al-Qazzaz, NK, Md Ali, SH & Ahmad, SA 2018, Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs. in 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018., 8527412, Institute of Electrical and Electronics Engineers Inc., pp. 109-112, 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018, Kuching, Sarawak, Malaysia, 24/7/18. https://doi.org/10.1109/ICBAPS.2018.8527412
Al-Qazzaz NK, Md Ali SH, Ahmad SA. Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs. In 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 109-112. 8527412 https://doi.org/10.1109/ICBAPS.2018.8527412
Al-Qazzaz, Noor Kamal ; Md Ali, Sawal Hamid ; Ahmad, Siti Anom. / Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs. 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 109-112
@inproceedings{3d1cf2040a554a9aad43bba118ec22d3,
title = "Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs",
abstract = "The aim of the present study was to select the optimal denoising technique that helps in discriminating dementia in the early stages and illustrating its degree of severity. In this paper, a comparative analysis of three denoising techniques, which are wavelet (WT), automatic independent component analysis (AICA) rejection, and automatic hybrid technique using independent component analysis and wavelet (AICA-WT), has been conducted to select the optimal denoising technique. Two approaches have been used to extract meaningful features these are Permutation entropy (PEn) and Higuchi's fractal dimension (FD) from Electroencephalography (EEG) dataset of 5 vascular dementia (VD) patients, 15 stroke-related patients with mild cognitive impairment (MCI) and 15 healthy subjects during working memory task (WMT). k-nearest neighbors (kNN) classifier has been used. The results show that the AICA-WT denoising technique improved the kNN classification accuracy from 88.15{\%} for WT and 89.26{\%} for AICA rejection to 90.37{\%}for AICA-WT denoising technique. These results suggest AICA-WT consistently improves the discrimination of VD, MCI patients and control normal subjects which are useful for dementia early detection.",
keywords = "fractal dimension, independent components analysis permutation entropy, k-nearest neighbors, wavelet",
author = "Al-Qazzaz, {Noor Kamal} and {Md Ali}, {Sawal Hamid} and Ahmad, {Siti Anom}",
year = "2018",
month = "11",
day = "7",
doi = "10.1109/ICBAPS.2018.8527412",
language = "English",
pages = "109--112",
booktitle = "2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Comparison of the effectiveness of AICA-WT technique in discriminating vascular dementia EEGs

AU - Al-Qazzaz, Noor Kamal

AU - Md Ali, Sawal Hamid

AU - Ahmad, Siti Anom

PY - 2018/11/7

Y1 - 2018/11/7

N2 - The aim of the present study was to select the optimal denoising technique that helps in discriminating dementia in the early stages and illustrating its degree of severity. In this paper, a comparative analysis of three denoising techniques, which are wavelet (WT), automatic independent component analysis (AICA) rejection, and automatic hybrid technique using independent component analysis and wavelet (AICA-WT), has been conducted to select the optimal denoising technique. Two approaches have been used to extract meaningful features these are Permutation entropy (PEn) and Higuchi's fractal dimension (FD) from Electroencephalography (EEG) dataset of 5 vascular dementia (VD) patients, 15 stroke-related patients with mild cognitive impairment (MCI) and 15 healthy subjects during working memory task (WMT). k-nearest neighbors (kNN) classifier has been used. The results show that the AICA-WT denoising technique improved the kNN classification accuracy from 88.15% for WT and 89.26% for AICA rejection to 90.37%for AICA-WT denoising technique. These results suggest AICA-WT consistently improves the discrimination of VD, MCI patients and control normal subjects which are useful for dementia early detection.

AB - The aim of the present study was to select the optimal denoising technique that helps in discriminating dementia in the early stages and illustrating its degree of severity. In this paper, a comparative analysis of three denoising techniques, which are wavelet (WT), automatic independent component analysis (AICA) rejection, and automatic hybrid technique using independent component analysis and wavelet (AICA-WT), has been conducted to select the optimal denoising technique. Two approaches have been used to extract meaningful features these are Permutation entropy (PEn) and Higuchi's fractal dimension (FD) from Electroencephalography (EEG) dataset of 5 vascular dementia (VD) patients, 15 stroke-related patients with mild cognitive impairment (MCI) and 15 healthy subjects during working memory task (WMT). k-nearest neighbors (kNN) classifier has been used. The results show that the AICA-WT denoising technique improved the kNN classification accuracy from 88.15% for WT and 89.26% for AICA rejection to 90.37%for AICA-WT denoising technique. These results suggest AICA-WT consistently improves the discrimination of VD, MCI patients and control normal subjects which are useful for dementia early detection.

KW - fractal dimension

KW - independent components analysis permutation entropy

KW - k-nearest neighbors

KW - wavelet

UR - http://www.scopus.com/inward/record.url?scp=85058041481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058041481&partnerID=8YFLogxK

U2 - 10.1109/ICBAPS.2018.8527412

DO - 10.1109/ICBAPS.2018.8527412

M3 - Conference contribution

SP - 109

EP - 112

BT - 2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -