Máquinas de aprendizado extremo aplicadas à identificação de pessoas através de eletrocardiograma (ECG)

Abstract

This research studies the use of neural network Extreme Learning Machine (ELM) to identify individuals (biometrics) by electrocardiogram (ECG). Biometric data offer a high level of security for identifying people, and ECG is an emerging technique and increasing development. ELM was little used in pattern recognition systems that use the ECG signal. In this way, the signal processing techniques were studied: Wavelet Transform and Principal Component Analysis (PCA), with the objective of treating and reducing the dimensionality of the input data, as was as, to make a comparative study between the ELM and Multilayer Perceptron (MLP). The tests were performed with 90 people, the ECG signal used is related to the lead I containing 500 samples/s and 12- bit resolution within a nominal range of ±10 mV of variation, the number of records ranged from 2 to 20 for each people. The size of each ECG cycle to complete the process of forming the sample space defined in two ways: 167 samples containing the P+QRS waves and 280 samples containing the P+QRS+T waves, of which 10 cycles were used to had the highest level of similarity. With the Wavelet Transform, the ECG signal was decomposed into 3 levels, where for the P+QRS waves the reductions were 86, 45 and 25 samples, and for the P+QRS+T waves were 142, 73 and 39 samples. For PCA, the signal for reduced from 10 cardiac cycles to only 1. These were presented to network forming the joint training and testing. The Artificial Neural Networks ELM and MLP were used for ECG classification. The results obtained proved that the ELM may be used to identify individuals.