Linear and Nonlinear Feature Extraction for Neural Seizure Detection

Mohamed A. Elgammal; Omar A. Elkhouly; Heba Elhosary; Mohamed Elsayed; Ahmed Nader Mohieldin; Khaled N. Salama; Hassan Mostafa

doi:10.1109/MWSCAS.2018.8624031

Linear and Nonlinear Feature Extraction for Neural Seizure Detection

Mohamed A. Elgammal, Omar A. Elkhouly, Heba Elhosary, Mohamed Elsayed, Ahmed Nader Mohieldin, Khaled N. Salama, Hassan Mostafa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Scopus citations

Abstract

In this paper, both linear and nonlinear features have been reviewed with linear support vector machine (SVM) classifier for neural seizure detection. The work introduced in the paper includes performance measurement through different metrics: accuracy, sensitivity, and specificity of multiple linear and nonlinear features with linear support vector machine (SVM). A comparison is performed between the performance of different combinations between 11 linear features and 9 nonlinear features to conclude the best set of features. It is found that some features enhance the detection performance greatly. Using a combination of 3 features of them, a linear SVM classifier detects seizures with sensitivity of 96.78%, specificity of 97.9%, and accuracy of 97.9%.

Original language	English (US)
Title of host publication	2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	795-798
Number of pages	4
ISBN (Print)	9781538673928
DOIs	https://doi.org/10.1109/MWSCAS.2018.8624031
State	Published - Feb 26 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research was partially funded by ONE Lab at Cairo University, Zewail City of Science and Technology, and KAUST.

Access to Document

10.1109/MWSCAS.2018.8624031

Cite this

Elgammal, M. A., Elkhouly, O. A., Elhosary, H., Elsayed, M., Mohieldin, A. N., Salama, K. N., & Mostafa, H. (2019). Linear and Nonlinear Feature Extraction for Neural Seizure Detection. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS) (pp. 795-798). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/MWSCAS.2018.8624031

@inproceedings{2954687a491f4140804e8ab770bc3985,

title = "Linear and Nonlinear Feature Extraction for Neural Seizure Detection",

abstract = "In this paper, both linear and nonlinear features have been reviewed with linear support vector machine (SVM) classifier for neural seizure detection. The work introduced in the paper includes performance measurement through different metrics: accuracy, sensitivity, and specificity of multiple linear and nonlinear features with linear support vector machine (SVM). A comparison is performed between the performance of different combinations between 11 linear features and 9 nonlinear features to conclude the best set of features. It is found that some features enhance the detection performance greatly. Using a combination of 3 features of them, a linear SVM classifier detects seizures with sensitivity of 96.78%, specificity of 97.9%, and accuracy of 97.9%.",

author = "Elgammal, {Mohamed A.} and Elkhouly, {Omar A.} and Heba Elhosary and Mohamed Elsayed and Mohieldin, {Ahmed Nader} and Salama, {Khaled N.} and Hassan Mostafa",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was partially funded by ONE Lab at Cairo University, Zewail City of Science and Technology, and KAUST.",

year = "2019",

month = feb,

day = "26",

doi = "10.1109/MWSCAS.2018.8624031",

language = "English (US)",

isbn = "9781538673928",

pages = "795--798",

booktitle = "2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

Linear and Nonlinear Feature Extraction for Neural Seizure Detection. / Elgammal, Mohamed A.; Elkhouly, Omar A.; Elhosary, Heba et al.
2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS). Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 795-798.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Linear and Nonlinear Feature Extraction for Neural Seizure Detection

AU - Elgammal, Mohamed A.

AU - Elkhouly, Omar A.

AU - Elhosary, Heba

AU - Elsayed, Mohamed

AU - Mohieldin, Ahmed Nader

AU - Salama, Khaled N.

AU - Mostafa, Hassan

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was partially funded by ONE Lab at Cairo University, Zewail City of Science and Technology, and KAUST.

PY - 2019/2/26

Y1 - 2019/2/26

N2 - In this paper, both linear and nonlinear features have been reviewed with linear support vector machine (SVM) classifier for neural seizure detection. The work introduced in the paper includes performance measurement through different metrics: accuracy, sensitivity, and specificity of multiple linear and nonlinear features with linear support vector machine (SVM). A comparison is performed between the performance of different combinations between 11 linear features and 9 nonlinear features to conclude the best set of features. It is found that some features enhance the detection performance greatly. Using a combination of 3 features of them, a linear SVM classifier detects seizures with sensitivity of 96.78%, specificity of 97.9%, and accuracy of 97.9%.

AB - In this paper, both linear and nonlinear features have been reviewed with linear support vector machine (SVM) classifier for neural seizure detection. The work introduced in the paper includes performance measurement through different metrics: accuracy, sensitivity, and specificity of multiple linear and nonlinear features with linear support vector machine (SVM). A comparison is performed between the performance of different combinations between 11 linear features and 9 nonlinear features to conclude the best set of features. It is found that some features enhance the detection performance greatly. Using a combination of 3 features of them, a linear SVM classifier detects seizures with sensitivity of 96.78%, specificity of 97.9%, and accuracy of 97.9%.

UR - http://hdl.handle.net/10754/652979

UR - https://ieeexplore.ieee.org/document/8624031

UR - http://www.scopus.com/inward/record.url?scp=85062213441&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2018.8624031

DO - 10.1109/MWSCAS.2018.8624031

M3 - Conference contribution

SN - 9781538673928

SP - 795

EP - 798

BT - 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Linear and Nonlinear Feature Extraction for Neural Seizure Detection

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this