A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats
An accurate electrocardiogram (ECG) beat classification can benefit the diagnosis of the cardiovascular disease. Deep convolutional neural networks (CNN) can automatically extract valid features from data, which is an effective way for the classification of the ECG beats. However, the fully-connecte...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/9/1590 |
| _version_ | 1819057942971809792 |
|---|---|
| author | Jia Li Yujuan Si Liuqi Lang Lixun Liu Tao Xu |
| author_facet | Jia Li Yujuan Si Liuqi Lang Lixun Liu Tao Xu |
| author_sort | Jia Li |
| collection | DOAJ |
| description | An accurate electrocardiogram (ECG) beat classification can benefit the diagnosis of the cardiovascular disease. Deep convolutional neural networks (CNN) can automatically extract valid features from data, which is an effective way for the classification of the ECG beats. However, the fully-connected layer in CNNs requires a fixed input dimension, which limits the CNNs to receive fixed-scale inputs. Signals of different scales are generally processed into the same size by segmentation and downsampling. If information loss occurs during a uniformly-sized process, the classification accuracy will ultimately be affected. To solve this problem, this paper constructs a new CNN framework spatial pyramid pooling (SPP) method, which solves the deficiency caused by the size of input data. The Massachusetts Institute of Technology-Biotechnology (MIT-BIH) arrhythmia database is employed as the training and testing data for the classification of heartbeat signals into six categories. Compared with the traditional method, which may lose a large amount of important information and easy to be over-fitted, the robustness of the proposed method can be guaranteed by extracting data features from different sizes. Experimental results show that the proposed architecture network can extract more high-quality features and exhibits higher classification accuracy (94%) than the traditional deep CNNs (90.4%). |
| first_indexed | 2024-12-21T13:47:20Z |
| format | Article |
| id | doaj.art-678569c93f1445b39f01417dc6139857 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T13:47:20Z |
| publishDate | 2018-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-678569c93f1445b39f01417dc61398572022-12-21T19:01:49ZengMDPI AGApplied Sciences2076-34172018-09-0189159010.3390/app8091590app8091590A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram BeatsJia Li0Yujuan Si1Liuqi Lang2Lixun Liu3Tao Xu4College of Instrument Science and Electrical Engineering, Jilin University, Changchun 130061, ChinaCollege of Instrument Science and Electrical Engineering, Jilin University, Changchun 130061, ChinaDepartment of Electronic Information Engineering, Zhuhai College of Jilin University, Zhuhai 519041, ChinaDepartment of Electronic Information Engineering, Zhuhai College of Jilin University, Zhuhai 519041, ChinaDepartment of Biomechanical Engineering, City University of Hong Kong, Hong Kong SAR 999077, ChinaAn accurate electrocardiogram (ECG) beat classification can benefit the diagnosis of the cardiovascular disease. Deep convolutional neural networks (CNN) can automatically extract valid features from data, which is an effective way for the classification of the ECG beats. However, the fully-connected layer in CNNs requires a fixed input dimension, which limits the CNNs to receive fixed-scale inputs. Signals of different scales are generally processed into the same size by segmentation and downsampling. If information loss occurs during a uniformly-sized process, the classification accuracy will ultimately be affected. To solve this problem, this paper constructs a new CNN framework spatial pyramid pooling (SPP) method, which solves the deficiency caused by the size of input data. The Massachusetts Institute of Technology-Biotechnology (MIT-BIH) arrhythmia database is employed as the training and testing data for the classification of heartbeat signals into six categories. Compared with the traditional method, which may lose a large amount of important information and easy to be over-fitted, the robustness of the proposed method can be guaranteed by extracting data features from different sizes. Experimental results show that the proposed architecture network can extract more high-quality features and exhibits higher classification accuracy (94%) than the traditional deep CNNs (90.4%).http://www.mdpi.com/2076-3417/8/9/1590ECG beatsclassificationfeature extractionconvolutional neural networksspatial pyramid pooling |
| spellingShingle | Jia Li Yujuan Si Liuqi Lang Lixun Liu Tao Xu A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats Applied Sciences ECG beats classification feature extraction convolutional neural networks spatial pyramid pooling |
| title | A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats |
| title_full | A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats |
| title_fullStr | A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats |
| title_full_unstemmed | A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats |
| title_short | A Spatial Pyramid Pooling-Based Deep Convolutional Neural Network for the Classification of Electrocardiogram Beats |
| title_sort | spatial pyramid pooling based deep convolutional neural network for the classification of electrocardiogram beats |
| topic | ECG beats classification feature extraction convolutional neural networks spatial pyramid pooling |
| url | http://www.mdpi.com/2076-3417/8/9/1590 |
| work_keys_str_mv | AT jiali aspatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT yujuansi aspatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT liuqilang aspatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT lixunliu aspatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT taoxu aspatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT jiali spatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT yujuansi spatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT liuqilang spatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT lixunliu spatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats AT taoxu spatialpyramidpoolingbaseddeepconvolutionalneuralnetworkfortheclassificationofelectrocardiogrambeats |