Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition

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

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

Abstract

The aim of the present study was to discriminate the electroencephalogram (EEG) of 5 patients with vascular dementia (VaD), 15 patients with stroke-related mild cognitive impairment (MCI), and 15 control normal subjects during a working memory (WM) task. We used independent component analysis (ICA) and wavelet transform (WT) as a hybrid preprocessing approach for EEG artifact removal. Three different features were extracted from the cleaned EEG signals: spectral entropy (SpecEn), permutation entropy (PerEn) and Tsallis entropy (TsEn). Two classification schemes were applied -support vector machine (SVM) and k-nearest neighbors (kNN) -with fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR) as a dimensionality reduction technique. The FNPAQR dimensionality reduction technique increased the SVM classification accuracy from 82.22% to 90.37% and from 82.6% to 86.67% for kNN. These results suggest that FNPAQR consistently improves the discrimination of VaD, MCI patients and control normal subjects and it could be a useful feature selection to help the identification of patients with VaD and MCI.

Original languageEnglish
Title of host publication2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publicationSmarter Technology for a Healthier World, EMBC 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3174-3177
Number of pages4
ISBN (Electronic)9781509028092
DOIs
Publication statusPublished - 13 Sep 2017
Event39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 - Jeju Island, Korea, Republic of
Duration: 11 Jul 201715 Jul 2017

Other

Other39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
CountryKorea, Republic of
CityJeju Island
Period11/7/1715/7/17

Fingerprint

Electroencephalography
Vascular Dementia
Dementia
Entropy
Stroke
Decomposition
Support vector machines
Independent component analysis
Wavelet Analysis
Wavelet transforms
Feature extraction
Short-Term Memory
Artifacts
Data storage equipment
Cognitive Dysfunction
Support Vector Machine

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Al-Qazzaz, N. K., Md Ali, S. H., Ahmad, S. A., & Escudero, J. (2017). Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings (pp. 3174-3177). [8037531] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2017.8037531

Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition. / Al-Qazzaz, Noor Kamal; Md Ali, Sawal Hamid; Ahmad, Siti Anom; Escudero, Javier.

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3174-3177 8037531.

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

Al-Qazzaz, NK, Md Ali, SH, Ahmad, SA & Escudero, J 2017, Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings., 8037531, Institute of Electrical and Electronics Engineers Inc., pp. 3174-3177, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017, Jeju Island, Korea, Republic of, 11/7/17. https://doi.org/10.1109/EMBC.2017.8037531
Al-Qazzaz NK, Md Ali SH, Ahmad SA, Escudero J. Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3174-3177. 8037531 https://doi.org/10.1109/EMBC.2017.8037531
Al-Qazzaz, Noor Kamal ; Md Ali, Sawal Hamid ; Ahmad, Siti Anom ; Escudero, Javier. / Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3174-3177
@inproceedings{bc84ef532fa6458d9c1db922ff86cdd7,
title = "Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition",
abstract = "The aim of the present study was to discriminate the electroencephalogram (EEG) of 5 patients with vascular dementia (VaD), 15 patients with stroke-related mild cognitive impairment (MCI), and 15 control normal subjects during a working memory (WM) task. We used independent component analysis (ICA) and wavelet transform (WT) as a hybrid preprocessing approach for EEG artifact removal. Three different features were extracted from the cleaned EEG signals: spectral entropy (SpecEn), permutation entropy (PerEn) and Tsallis entropy (TsEn). Two classification schemes were applied -support vector machine (SVM) and k-nearest neighbors (kNN) -with fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR) as a dimensionality reduction technique. The FNPAQR dimensionality reduction technique increased the SVM classification accuracy from 82.22{\%} to 90.37{\%} and from 82.6{\%} to 86.67{\%} for kNN. These results suggest that FNPAQR consistently improves the discrimination of VaD, MCI patients and control normal subjects and it could be a useful feature selection to help the identification of patients with VaD and MCI.",
author = "Al-Qazzaz, {Noor Kamal} and {Md Ali}, {Sawal Hamid} and Ahmad, {Siti Anom} and Javier Escudero",
year = "2017",
month = "9",
day = "13",
doi = "10.1109/EMBC.2017.8037531",
language = "English",
pages = "3174--3177",
booktitle = "2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Classification enhancement for post-stroke dementia using fuzzy neighborhood preserving analysis with QR-decomposition

AU - Al-Qazzaz, Noor Kamal

AU - Md Ali, Sawal Hamid

AU - Ahmad, Siti Anom

AU - Escudero, Javier

PY - 2017/9/13

Y1 - 2017/9/13

N2 - The aim of the present study was to discriminate the electroencephalogram (EEG) of 5 patients with vascular dementia (VaD), 15 patients with stroke-related mild cognitive impairment (MCI), and 15 control normal subjects during a working memory (WM) task. We used independent component analysis (ICA) and wavelet transform (WT) as a hybrid preprocessing approach for EEG artifact removal. Three different features were extracted from the cleaned EEG signals: spectral entropy (SpecEn), permutation entropy (PerEn) and Tsallis entropy (TsEn). Two classification schemes were applied -support vector machine (SVM) and k-nearest neighbors (kNN) -with fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR) as a dimensionality reduction technique. The FNPAQR dimensionality reduction technique increased the SVM classification accuracy from 82.22% to 90.37% and from 82.6% to 86.67% for kNN. These results suggest that FNPAQR consistently improves the discrimination of VaD, MCI patients and control normal subjects and it could be a useful feature selection to help the identification of patients with VaD and MCI.

AB - The aim of the present study was to discriminate the electroencephalogram (EEG) of 5 patients with vascular dementia (VaD), 15 patients with stroke-related mild cognitive impairment (MCI), and 15 control normal subjects during a working memory (WM) task. We used independent component analysis (ICA) and wavelet transform (WT) as a hybrid preprocessing approach for EEG artifact removal. Three different features were extracted from the cleaned EEG signals: spectral entropy (SpecEn), permutation entropy (PerEn) and Tsallis entropy (TsEn). Two classification schemes were applied -support vector machine (SVM) and k-nearest neighbors (kNN) -with fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR) as a dimensionality reduction technique. The FNPAQR dimensionality reduction technique increased the SVM classification accuracy from 82.22% to 90.37% and from 82.6% to 86.67% for kNN. These results suggest that FNPAQR consistently improves the discrimination of VaD, MCI patients and control normal subjects and it could be a useful feature selection to help the identification of patients with VaD and MCI.

UR - http://www.scopus.com/inward/record.url?scp=85032204343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032204343&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2017.8037531

DO - 10.1109/EMBC.2017.8037531

M3 - Conference contribution

SP - 3174

EP - 3177

BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - Institute of Electrical and Electronics Engineers Inc.

ER -