Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 2
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The aim of this paper is to compare the efficiency of various outlier correction methods for ECG signal processing in biometric applications. The main idea is to correct anomalies in various segments of ECG waveform rather than skipping a corrupted ECG heartbeat in order to achieve better statistics. Experiments were performed using a self-collected Lviv Biometric Dataset. This database contains over 1400 records for 95 unique persons. The baseline identification accuracy without any correction is around 86%. After applying the outlier correction the results were improved up to 98% for autoencoder based algorithms and up to 97.1% for sliding Euclidean window. Adding outlier correction stage in the biometric identification process results in increased processing time (up to 20%), however, it is not critical in the most use-cases.

Go to article

Authors and Affiliations

Su Jun
Miroslaw Szmajda
Volodymyr Khoma
Yuriy Khoma
Dmytro Sabodashko
Orest Kochan
Jinfei Wang
Download PDF Download RIS Download Bibtex

Abstract

Is this article simulation of statistical measurements is performed on the basis of which the analysis of the standard deviation of the obtained results is carried out. It is shown that the standard deviation is minimum and independent from measurement duration while an object is in the state of equilibrium. For objects in a stationary non-equilibrium state the standard deviation depends on the duration measurements and the parameters of the state. The influence of these factors on the standard deviation is assessed with equation which includes the relaxation time. The value of the relaxation time is determined by approximating the energy spectrum of the studied signals. The analysis of energy spectra showed that the spectrum of white noise is inherent in objects in equilibrium; the flicker component of the spectrum occurs when the state of the object deviates from equilibrium.
Go to article

Authors and Affiliations

Krzysztof Przystupa
1
Zenoviy Kolodiy
2
Svyatoslav Yatsyshyn
2
Jacek Majewski
3
Yuriy Khoma
2
Iryna Petrovska
2
Serhiy Lasarenko
2
Taras Hut
2

  1. Department Automation, Lublin University of Technology, ul. Nadbystrzycka 36, 20-618 Lublin, Poland
  2. Lviv Polytechnic National University, Institute of Computer Technologies, Automatics and Metrology, S. Bandera Str. 28a, 79013, Lviv, Ukraine
  3. Department of Automation and Metrology, Lublin University of Technology, ul. Nadbystrzycka 38D, 20-618 Lublin, Poland

This page uses 'cookies'. Learn more