Artūras Janušauskas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Artūras Janušauskas has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Arūnas Lukoševičius
Kaunas University of Technology
4 shared publications - Vaidotas Marozas
Biomedical Engineering Institute, Kaunas University of Technology, Kaunas, Lithuania
3 shared publications Leif Sörnmo
2 shared publicationsAlvydas Paunksnis
1 shared publicationRytis Jurkonis
1 shared publicationSkaidra Kurapkienė
1 shared publication
Latest Publications
- 3 November 2012
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 35 (8) , 1059-1069
Ensemble empirical mode decomposition based feature enhancement of cardio signals
This paper presents an application of ensemble empirical mode decomposition method for enhancement of specific biological signal features. The application for two types of cardiological signals is presented in this article. Detection of fiducial points is a routine task for analyzing these signals. In a clinical situation, cardiological signals are usually corrupted by artifacts and finding exact time instances of various fiducial points is a challenge. Filtering approach for signal to noise ratio enhancing is traditionally and widely used in clinical practice. Methods, based on filtering, however, have serious limitations when it is necessary to find compromise between noise suppression and preservation of signal features. The proposed method uses ensemble empirical mode decomposition in order to suppress noise or enhance specific waves in the signal. Performance of the method was estimated by using clinical electrocardiogram and impedance cardiogram signals with synthetic baseline-wander, power-line and added Gaussian noise. In electrocardiogram application, an average estimation error of QRS complex length was 2.06-4.47%, the smallest in comparison to the reference methods. In impedance cardiogram application, the proposed method provided the highest cross-correlation coefficient between original and de-noised signal in comparison to reference methods. When the signal to noise ratio of the input signal was -12 dB, the method provided signal to error ratio of 33 dB in this case. The proposed method is adaptive to template and signal itself and thus could be applied to other non-stationary biological signals.
- 3 November 2012
- Published by IOP Publishing in Medical Engineering & Physics
- Vol. 35 (8) , 1059-1069
Ensemble empirical mode decomposition based feature enhancement of cardio signals
This paper presents an application of ensemble empirical mode decomposition method for enhancement of specific biological signal features. The application for two types of cardiological signals is presented in this article. Detection of fiducial points is a routine task for analyzing these signals. In a clinical situation, cardiological signals are usually corrupted by artifacts and finding exact time instances of various fiducial points is a challenge. Filtering approach for signal to noise ratio enhancing is traditionally and widely used in clinical practice. Methods, based on filtering, however, have serious limitations when it is necessary to find compromise between noise suppression and preservation of signal features. The proposed method uses ensemble empirical mode decomposition in order to suppress noise or enhance specific waves in the signal. Performance of the method was estimated by using clinical electrocardiogram and impedance cardiogram signals with synthetic baseline-wander, power-line and added Gaussian noise. In electrocardiogram application, an average estimation error of QRS complex length was 2.06-4.47%, the smallest in comparison to the reference methods. In impedance cardiogram application, the proposed method provided the highest cross-correlation coefficient between original and de-noised signal in comparison to reference methods. When the signal to noise ratio of the input signal was -12 dB, the method provided signal to error ratio of 33 dB in this case. The proposed method is adaptive to template and signal itself and thus could be applied to other non-stationary biological signals.
- 1 January 2010
- Published by Vilnius University Press in Informatica
- Vol. 21 (2) , 191-204
Detection of Hearing Loss in Audiological Frequencies from Transient Evoked Otoacoustic Emissions
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: Detection of Hearing Loss in Audiological Frequencies from Transient Evoked Otoacoustic Emissions, Authors: Artūras Janušauskas, Vaidotas Marozas, Arūnas Lukoševičius, Leif Sörnmo , Transient evoked otoacoustic emissions (TEOAEs) have been analyzed for objective assessment of hearing function and monitoring of the influence of noise exposure and ototoxic drugs. This paper presents a novel application of the Hilbert–Huang transform (HHT) for detection and time-frequency mapping of TEOAEs. Since the HHT does not distinguish between signal and noise, it is combined with ensemble correlation in order to extract signal information in intervals with correlated activity. High resolution time-frequency mapping could predict 30 dBHL, or higher hearing loss, at different audiological frequencies in 63–90% of the cases and normal hearing in 75–90% of the cases. The proposed method offers TEOAE time-frequency mapping by constraining the analysis to regions with high signal-to-noise ratios. The results suggest that the HHT is suitable for hearing loss detection at individual frequencies and characterization of the fine structures of TEOAEs.
- 1 January 2010
- Published by Vilnius University Press in Informatica
- Vol. 21 (2) , 191-204
Detection of Hearing Loss in Audiological Frequencies from Transient Evoked Otoacoustic Emissions
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: Detection of Hearing Loss in Audiological Frequencies from Transient Evoked Otoacoustic Emissions, Authors: Artūras Janušauskas, Vaidotas Marozas, Arūnas Lukoševičius, Leif Sörnmo , Transient evoked otoacoustic emissions (TEOAEs) have been analyzed for objective assessment of hearing function and monitoring of the influence of noise exposure and ototoxic drugs. This paper presents a novel application of the Hilbert–Huang transform (HHT) for detection and time-frequency mapping of TEOAEs. Since the HHT does not distinguish between signal and noise, it is combined with ensemble correlation in order to extract signal information in intervals with correlated activity. High resolution time-frequency mapping could predict 30 dBHL, or higher hearing loss, at different audiological frequencies in 63–90% of the cases and normal hearing in 75–90% of the cases. The proposed method offers TEOAE time-frequency mapping by constraining the analysis to regions with high signal-to-noise ratios. The results suggest that the HHT is suitable for hearing loss detection at individual frequencies and characterization of the fine structures of TEOAEs.
- 1 January 2006
- Published by Vilnius University Press in Informatica
- Vol. 17 (1) , 25-38
The Hilbert–Huang Transform for Detection of Otoacoustic Emissions and Time–Frequency Mapping
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: The Hilbert–Huang Transform for Detection of Otoacoustic Emissions and Time–Frequency Mapping, Authors: Artūras Janušauskas, Vaidotas Marozas, Arūnas Lukoševičius, Leif Sörnmo , This paper presents an application of the Hilbert–Huang transform (HHT) and ensemble correlation for detection of the transient evoked otoacoustic emissions (TEOAEs), and high resolution time–frequency mapping. The HHT provides a powerful tool for nonlinear analysis of nonstationary signals such as TEOAEs. Since the HHT itself does not distinguish between signal and noise it was used with ensemble correlation to extract information about intervals with correlated activity. The combination of methods produced good results for both tasks TEOAE detection and time–frequency mapping. The resulting detection performance, using the mean hearing threshold as audiological separation criterion, was a specificity of 81% at a sensitivity of 90% to be compared to 65% with the traditional wave reproducibility detection criterion. High resolution time frequency mapping predicted in more than 70% of the cases hearing loss at a specific frequency in cases of ski-sloping audiograms. The present m ethod does not require a priori information on the signal and may, with minor changes, be successfully applied to analysis of other types of repetitive signals such as evoked potentials.
- 1 January 2006
- Published by Vilnius University Press in Informatica
- Vol. 17 (1) , 25-38
The Hilbert–Huang Transform for Detection of Otoacoustic Emissions and Time–Frequency Mapping
Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: The Hilbert–Huang Transform for Detection of Otoacoustic Emissions and Time–Frequency Mapping, Authors: Artūras Janušauskas, Vaidotas Marozas, Arūnas Lukoševičius, Leif Sörnmo , This paper presents an application of the Hilbert–Huang transform (HHT) and ensemble correlation for detection of the transient evoked otoacoustic emissions (TEOAEs), and high resolution time–frequency mapping. The HHT provides a powerful tool for nonlinear analysis of nonstationary signals such as TEOAEs. Since the HHT itself does not distinguish between signal and noise it was used with ensemble correlation to extract information about intervals with correlated activity. The combination of methods produced good results for both tasks TEOAE detection and time–frequency mapping. The resulting detection performance, using the mean hearing threshold as audiological separation criterion, was a specificity of 81% at a sensitivity of 90% to be compared to 65% with the traditional wave reproducibility detection criterion. High resolution time frequency mapping predicted in more than 70% of the cases hearing loss at a specific frequency in cases of ski-sloping audiograms. The present m ethod does not require a priori information on the signal and may, with minor changes, be successfully applied to analysis of other types of repetitive signals such as evoked potentials.
- 1 January 2005
- Published by Vilnius University Press in Informatica
- Vol. 16 (4) , 541-556
The Empirical Mode Decomposition and the Discrete Wavelet Transform for Detection of Human Cataract in Ultrasound Signals
This paper presents a new approach for human cataract automatical detection based on ultrasound signal processing. Two signal decomposition techniques, empirical mode decomposition and discrete wavelet transform are used in the presented method. Performance comparison of these two decomposition methods when applied to this specific ultrasound signal is given. Described method includes ultrasonic signal decomposition to enhance signal specific features and increase signal to noise ratio with the following decision rules based on adaptive thresholding. The resulting detection performance of the proposed method using empirical mode decomposition was better to compare to discrete wavelet transform and resulted in 70% correctly identified “healthy subject” cases and 82%, 97% and 100% correctly identified “cataract cases” in the incipience, immature and mature cataract subject groups, respectively. Discussion is given on the reasons of different results and the differences between the two used signal decomposition techniques.
- 1 January 2005
- Published by Vilnius University Press in Informatica
- Vol. 16 (4) , 541-556
The Empirical Mode Decomposition and the Discrete Wavelet Transform for Detection of Human Cataract in Ultrasound Signals
This paper presents a new approach for human cataract automatical detection based on ultrasound signal processing. Two signal decomposition techniques, empirical mode decomposition and discrete wavelet transform are used in the presented method. Performance comparison of these two decomposition methods when applied to this specific ultrasound signal is given. Described method includes ultrasonic signal decomposition to enhance signal specific features and increase signal to noise ratio with the following decision rules based on adaptive thresholding. The resulting detection performance of the proposed method using empirical mode decomposition was better to compare to discrete wavelet transform and resulted in 70% correctly identified “healthy subject” cases and 82%, 97% and 100% correctly identified “cataract cases” in the incipience, immature and mature cataract subject groups, respectively. Discussion is given on the reasons of different results and the differences between the two used signal decomposition techniques.