Deep Learning for Electrocardiogram (ECG) Identification
| dc.contributor.author | Tian, Ziyi | |
| dc.contributor.supervisor | Lu, Wu-Sheng | |
| dc.date.accessioned | 2020-05-23T06:54:41Z | |
| dc.date.available | 2020-05-23T06:54:41Z | |
| dc.date.copyright | 2020 | en_US |
| dc.date.issued | 2020-05-22 | |
| dc.degree.department | Department of Electrical and Computer Engineering | en_US |
| dc.degree.level | Master of Engineering M.Eng. | en_US |
| dc.description.abstract | In this report, we describe three architectures based on deep learning for electrocardiogram (ECG) identification. Specially, a class of neural network-convolutional network-is used both to extract features from ECG signals and do classification. We provide necessary details in this report for implementation of these networks by using Keras and applying them on a publicly available dataset-MIT-BIH dataset, which contains 48 half-hour excerpts of two-channel ambulatory ECG recordings, obtained from 47 subjects studied by the BIH Arrhythmia Laboratory between 1975 and 1979. This report also shows the accuracy and computing time of our architectures on MIT-BIT datasets and comparison with other methods. The effect of several techniques specifically designed for CNNs are also discussed.. | en_US |
| dc.description.scholarlevel | Graduate | en_US |
| dc.identifier.uri | http://hdl.handle.net/1828/11765 | |
| dc.language.iso | en | en_US |
| dc.rights | Available to the World Wide Web | en_US |
| dc.subject | ECG | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Convolutional Neural Network | en_US |
| dc.title | Deep Learning for Electrocardiogram (ECG) Identification | en_US |
| dc.type | project | en_US |