A new method for classification of ECG arrhythmias using neural network with adaptive activation function

被引：71

作者：

Ozbay, Yueksel ^{[1
]}

Tezel, Guelay ^{[2
]}

机构：

[1] Selcuk Univ, Dept Elect & Elect Engn, TR-42075 Konya, Turkey

[2] Selcuk Univ, Dept Comp Engn, TR-42075 Konya, Turkey

来源：

DIGITAL SIGNAL PROCESSING | 2010年 / 20卷 / 04期

关键词：

Adaptive neural network; Adaptive activation function; MLP; Classification; ECG; Arrhythmia; SUPPORT VECTOR MACHINES; BEAT CLASSIFICATION; COMPONENT ANALYSIS;

D O I：

10.1016/j.dsp.2009.10.016

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this study, new neural network models with adaptive activation function (NNAAF) were implemented to classify ECG arrhythmias. Our NNAAF models included three types named as NNAAF-1, NNAAF-2 and NNAAf-3. Activation functions with adjustable free parameters were used in hidden neurons of these models to improve classical MLP network. In addition, these three NNAAF models were compared with the MLP model implemented in similar conditions. Ten different types of ECG arrhythmias were selected from MIT-BIH ECG Arrhythmias Database to train NNAAFs and MLP models. Moreover, all models tested by the ECG signals of 92 patients (40 males and 52 females, average age is 39.75 +/- 19.06). The average accuracy rate of all models in the training processing was found as 99.92%. The average accuracy rate of the all models in the test phases was obtained as 98.19. (C) 2009 Elsevier Inc. All rights reserved.

引用

页码：1040 / 1049

页数：10

共 50 条

[1] A new neural network with adaptive activation function for classification of ECG Arrhythmias
Tezel, Guelay
Oezbay, Yueksel
KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS: KES 2007 - WIRN 2007, PT I, PROCEEDINGS, 2007, 4692 : 1 - +
[2] Identifying arrhythmias based on ECG classification using an advanced neural network method
Philip, Akhil Mathew
Hemalatha, S.
SOFT COMPUTING, 2023, 28 (23) : 13831 - 13842
[3] A fuzzy clustering neural network architecture for classification of ECG arrhythmias
Özbay, Y
Ceylan, R
Karlik, B
COMPUTERS IN BIOLOGY AND MEDICINE, 2006, 36 (04) : 376 - 388
[4] ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network
Xiong, Zhaohan
Nash, Martyn P.
Cheng, Elizabeth
Fedorov, Vadim V.
Stiles, Martin K.
Zhao, Jichao
PHYSIOLOGICAL MEASUREMENT, 2018, 39 (09)
[5] PROPOSAL OF ADAPTIVE LAND CLASSIFICATION USING QUATERNION NEURAL NETWORK WITH ISOTROPIC ACTIVATION FUNCTION
Kinugawa, Kazutaka
Shang, Fang
Usami, Naoto
Hirose, Akira
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 7557 - 7560
[6] Classification of Cardiac Arrhythmias Using PNN Neural Network Based on ECG Feature Extraction
Darouei, A.
Ayatollahi, A.
WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING, VOL 25, PT 12, 2009, 25 (12): : 309 - +
[7] Classification of ECG Arrhythmias using Type-2 Fuzzy Clustering Neural Network
Ceylan, Rahime
Ozbay, Yueksel
Karlik, Bekir
BIYOMUT: 2009 14TH NATIONAL BIOMEDICAL ENGINEERING MEETING, 2009, : 5 - +
[8] Identifying arrhythmias based on ECG classification using an advanced neural network methodIdentifying arrhythmias based on ECG classification using an advanced neural network methodA. M. Philip and S. Hemalatha
Akhil Mathew Philip
S. Hemalatha
Soft Computing, 2024, 28 (23) : 13831 - 13842
[9] A new trained ECG signal Classification method using Modified Spline Activated Neural Network
Kumar, Ganesh R.
PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON COMPUTING METHODOLOGIES AND COMMUNICATION (ICCMC 2018), 2018, : 317 - 321
[10] Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network
Ceylan, Rahime
Ozbay, Yuksel
EXPERT SYSTEMS WITH APPLICATIONS, 2007, 33 (02) : 286 - 295

← 1 2 3 4 5 →