Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia

被引：30

作者：

Cui, Jianfeng ^{[1
]}

Wang, Lixin ^{[2
]}

He, Xiangmin ^{[2
]}

De Albuquerque, Victor Hugo C. ^{[3
]}

AlQahtani, Salman A. ^{[4
]}

Hassan, Mohammad Mehedi ^{[5
]}

机构：

[1] Xiamen Univ Technol, Sch Software Engn, Xiamen, Peoples R China

[2] Xiamen Univ Technol, Sch Comp & Informat Engn, Xiamen, Peoples R China

[3] Univ Porto FEUP, Fac Engn, Dept Mech Engn, Porto, Portugal

[4] King Saud Univ, Coll Comp & Informat Sci, Comp Engn Dept, Riyadh 11543, Saudi Arabia

[5] King Saud Univ, Coll Comp & Informat Sci, Informat Syst Dept, Riyadh 11543, Saudi Arabia

来源：

NEURAL COMPUTING & APPLICATIONS | 2023年 / 35卷 / 22期

基金：

中国博士后科学基金;

关键词：

ECG signals; Arrhythmia classification; Feature fusion; 1D-CNN4; NEURAL-NETWORK; INTERFERENCE; DIAGNOSIS; SYSTEM;

D O I：

10.1007/s00521-021-06487-5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Feature extraction plays an important role in arrhythmia classification, and successful arrhythmia classification generally depends on ECG feature extraction. This paper proposed a feature extraction method combining traditional approaches and 1D-CNN aiming to find the optimal feature set to improve the accuracy of arrhythmia classification. The proposed method is verified by using the MIT-BIH arrhythmia benchmark database. It is found that the features extracted by 1D-CNN and discrete wavelet transform form the optimal feature set with the average classification accuracy up to 98.35%, which is better than the latest methods.

引用

页码：16073 / 16087

页数：15

共 60 条

[1] A deep convolutional neural network model to classify heartbeats [J].

Acharya, U. Rajendra ;

Oh, Shu Lih ;

Hagiwara, Yuki ;

Tan, Jen Hong ;

Adam, Muhammad ;

Gertych, Arkadiusz ;

Tan, Ru San .

COMPUTERS IN BIOLOGY AND MEDICINE, 2017, 89 :389-396

[2]

Andreoli A., 2010, Wearable and Autonomous Biomedical Devices and Systems for Smart Environment, P369, DOI DOI 10.1007/978-3-642-15687-8

[3] Removing artifacts from electrocardiographic signals using independent components analysis [J].

Barros, AK ;

Mansour, A ;

Ohnishi, N .

NEUROCOMPUTING, 1998, 22 (1-3) :173-186

[4] Representation Learning: A Review and New Perspectives [J].

Bengio, Yoshua ;

Courville, Aaron ;

Vincent, Pascal .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1798-1828

[5] Medical Diagnosis Using Machine Learning: A Statistical Review [J].

Bhavsar, Kaustubh Arun ;

Singla, Jimmy ;

Al-Otaibi, Yasser D. ;

Song, Oh-Young ;

Bin Zikriya, Yousaf ;

Bashir, Ali Kashif .

CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 67 (01) :107-125

[6] Deep learning for intelligent IoT: Opportunities, challenges and solutions [J].

Bin Zikria, Yousaf ;

Afzal, Muhammad Khalil ;

Kim, Sung Won ;

Marin, Andrea ;

Guizani, Mohsen .

COMPUTER COMMUNICATIONS, 2020, 164 :50-53

[7] Review of Complementary and Alternative Medical Treatment of Arrhythmias [J].

Brenyo, Andrew ;

Aktas, Mehmet K. .

AMERICAN JOURNAL OF CARDIOLOGY, 2014, 113 (05) :897-903

[8]

Ciresan D.C., 2011, P 22 INT JOINT C ART, DOI DOI 10.5591/978-1-57735-516-8/IJCAI11-210

[9]

Das MK, 2013, 2013 IEEE 1ST INTERNATIONAL CONFERENCE ON CONDITION ASSESSMENT TECHNIQUES IN ELECTRICAL SYSTEMS (CATCON), P353, DOI 10.1109/CATCON.2013.6737526

[10] Automatic classification of heartbeats using ECG morphology and heartbeat interval features [J].

de Chazal, P ;

O'Dwyer, M ;

Reilly, RB .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2004, 51 (07) :1196-1206

← 1 2 3 4 5 6 →