A Gaussian mixture model to detect suction events in rotary blood pumps

Alexandros T. Tzallas; George Rigas; Evaggelos C. Karvounis; Markos G. Tsipouras; Yorgos Goletsis; Krzysztof Zielinski; Libera Fresiello; Dimitrios I. Fotiadis; Maria G. Trivella

doi:10.1109/BIBE.2012.6399661

A Gaussian mixture model to detect suction events in rotary blood pumps

Alexandros T. Tzallas^*, George Rigas, Evaggelos C. Karvounis, Markos G. Tsipouras, Yorgos Goletsis, Krzysztof Zielinski, Libera Fresiello, Dimitrios I. Fotiadis, Maria G. Trivella

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

8 Citations (Scopus)

Abstract

In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.

Original language	English
Title of host publication	IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012
Pages	127-131
Number of pages	5
DOIs	https://doi.org/10.1109/BIBE.2012.6399661
Publication status	Published - 2012
Externally published	Yes
Event	12th IEEE International Conference on BioInformatics and BioEngineering, BIBE 2012 - Larnaca, Cyprus Duration: 11 Nov 2012 → 13 Nov 2012 Conference number: 12

Conference

Conference	12th IEEE International Conference on BioInformatics and BioEngineering, BIBE 2012
Abbreviated title	BIBE 2012
Country/Territory	Cyprus
City	Larnaca
Period	11/11/12 → 13/11/12

Keywords

Gaussian mixture model
Implantable rotary blood pump
Left ventricular assist device
Suction detection

Access to Document

10.1109/BIBE.2012.6399661

Cite this

Tzallas, A. T., Rigas, G., Karvounis, E. C., Tsipouras, M. G., Goletsis, Y., Zielinski, K., Fresiello, L., Fotiadis, D. I., & Trivella, M. G. (2012). A Gaussian mixture model to detect suction events in rotary blood pumps. In IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012 (pp. 127-131). Article 6399661 https://doi.org/10.1109/BIBE.2012.6399661

@inproceedings{3298b063e24d4ff7ab63729dd2eb471c,

title = "A Gaussian mixture model to detect suction events in rotary blood pumps",

abstract = "In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.",

keywords = "Gaussian mixture model, Implantable rotary blood pump, Left ventricular assist device, Suction detection",

author = "Tzallas, {Alexandros T.} and George Rigas and Karvounis, {Evaggelos C.} and Tsipouras, {Markos G.} and Yorgos Goletsis and Krzysztof Zielinski and Libera Fresiello and Fotiadis, {Dimitrios I.} and Trivella, {Maria G.}",

year = "2012",

doi = "10.1109/BIBE.2012.6399661",

language = "English",

isbn = "9781467343589",

pages = "127--131",

booktitle = "IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012",

note = "12th IEEE International Conference on BioInformatics and BioEngineering, BIBE 2012, BIBE 2012 ; Conference date: 11-11-2012 Through 13-11-2012",

}

Tzallas, AT, Rigas, G, Karvounis, EC, Tsipouras, MG, Goletsis, Y, Zielinski, K, Fresiello, L, Fotiadis, DI & Trivella, MG 2012, A Gaussian mixture model to detect suction events in rotary blood pumps. in IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012., 6399661, pp. 127-131, 12th IEEE International Conference on BioInformatics and BioEngineering, BIBE 2012, Larnaca, Cyprus, 11/11/12. https://doi.org/10.1109/BIBE.2012.6399661

A Gaussian mixture model to detect suction events in rotary blood pumps. / Tzallas, Alexandros T.; Rigas, George; Karvounis, Evaggelos C. et al.
IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012. 2012. p. 127-131 6399661.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A Gaussian mixture model to detect suction events in rotary blood pumps

AU - Tzallas, Alexandros T.

AU - Rigas, George

AU - Karvounis, Evaggelos C.

AU - Tsipouras, Markos G.

AU - Goletsis, Yorgos

AU - Zielinski, Krzysztof

AU - Fresiello, Libera

AU - Fotiadis, Dimitrios I.

AU - Trivella, Maria G.

N1 - Conference code: 12

PY - 2012

Y1 - 2012

N2 - In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.

AB - In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.

KW - Gaussian mixture model

KW - Implantable rotary blood pump

KW - Left ventricular assist device

KW - Suction detection

UR - http://www.scopus.com/inward/record.url?scp=84872858069&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2012.6399661

DO - 10.1109/BIBE.2012.6399661

M3 - Conference contribution

AN - SCOPUS:84872858069

SN - 9781467343589

SP - 127

EP - 131

BT - IEEE 12th International Conference on BioInformatics and BioEngineering, BIBE 2012

T2 - 12th IEEE International Conference on BioInformatics and BioEngineering, BIBE 2012

Y2 - 11 November 2012 through 13 November 2012

ER -

A Gaussian mixture model to detect suction events in rotary blood pumps

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this