| Title |
Personal Identification Based on an Convolutional Neural Networks by Various Two-Dimensional Transform of Electrocardiogram Signals |
| Authors |
이진아(Jin-A, Lee) ; 곽근창(Keun-Chang Kwak) |
| DOI |
https://doi.org/10.5370/KIEEP.2022.71.1.54 |
| Keywords |
person identification; electrocardiogram; convolutional neural networks; time-frequency transform; Short-Time Fourier Transform; Fourier Synchrosqueezed Transform |
| Abstract |
In this paper, we propose personal identification method based on Convolutional Neural Networks (CNN) by various two-dimensional (2D) transform of Electrocardiogram (ECG) signals. For this purpose, various 2D time-frequency representation are peformed by Short-Time Fourier Transform (STFT), Fourier Synchrosqueezed Transform (FSST), and Wavelet Synchrosqueezed Transform (WSST) from one-dimensional ECG signals. The individual identification performance is achieved by transfer learning based on the pretrained GoogleNet and ResNet-101. The performance of experimental results are compared by the well-known PTB-ECG database. |