WKLD-Based Feature Extraction for Diagnosis of Epilepsy Based on EEG

被引：4

作者：

Cai, Haoyang ^{[1
]}

Yan, Ying ^{[2
]}

Liu, Guanting ^{[1
]}

Cai, Jun ^{[2
,3
]}

David Cheok, Adrian ^{[2
]}

Liu, Na ^{[4
]}

Hua, Chengcheng ^{[2
]}

Lian, Jing ^{[2
]}

Fan, Zhiyong ^{[2
]}

Chen, Anqi ^{[2
]}

机构：

[1] Nanjing Univ Informat Sci & Technol, Reading Acad, Nanjing 210044, Peoples R China

[2] Nanjing Univ Informat Sci & Technol, Sch Automat, C MEIC, ICAEET, Nanjing 210044, Peoples R China

[3] Anhui Jianzhu Univ, Sch Mech & Elect Engn, Hefei 230009, Peoples R China

[4] Nanjing Med Univ, Nanjing Chest Hosp, Nanjing 210029, Peoples R China

来源：

IEEE ACCESS | 2024年 / 12卷

关键词：

Feature extraction; Electroencephalography; Epilepsy; Entropy; Complexity theory; Time series analysis; Brain modeling; electroencephalogram; discrete wavelet transform; Kullback-Leibler divergence; residual multidimensional Taylor network (ResMTN); SEIZURE DETECTION; APPROXIMATE ENTROPY; CLASSIFICATION; SIGNALS;

D O I：

10.1109/ACCESS.2024.3401568

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

High-performance automated detection methods for epilepsy play a crucial role in clinical diagnostic support. To address the challenge of effectively extracting features from epileptic EEG signals, characterized by strong spontaneity and complexity, a novel feature extraction approach based on Window Kullback-Leibler Divergence (WKLD) is proposed, coupled with discrete wavelet analysis for EEG signal feature extraction. Then, a Residual Multidimensional Taylor Network (ResMTN) classifier is applied for epilepsy state classification. Experimental results demonstrate an accuracy of 98% in classifying EEG signals during seizure and interictal periods, with both specificity and sensitivity reaching 98.18%, outperforming existing widely-used feature extraction and classification methods.

引用

页码：69276 / 69287

页数：12

共 32 条

[31] Model-Based Seizure Detection for Intracranial EEG Recordings [J].

Yadav, R. ;

Swamy, M. N. S. ;

Agarwal, R. .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (05) :1419-1428

[32]

Zheng Wei-Long, 2014, IEEE INT C MULTIMEDI

← 1 2 3 4 →