Digitalna obdelava signalov mobilnega uporabnika

Digitalna obdelava signalov mobilnega uporabnika Koordinatorja
Emil Plesnik, Univerza v Ljubljani, Fakulteta za elektrotehniko
dr. Matej Zajc, Univerza v Ljubljani, Fakulteta za elektrotehniko

Trajanje 2009 - 2012

Predavanja:

Emil Plesnik je predstavil delo: Mobile Users ECG Signal Processing na ICT INNOVATIONS 2012 konferenci (link), 13.9.2012 v Ohridu (predstavitev)  



Publikacije:

Emil Plesnik, Olga Malgina, Jurij F. Tasič and Matej Zajc. Detection of the electrocardiogram fiducial points in the phase space using the Euclidian distance measure. Medical engineering & physics, 1 May 2012, Vol. 34, No. 4,  pp. 524-529, http://www.sciencedirect.com/science/article/pii/S1350453312000082, DOI: 10.1016/j.medengphy.2012.01.005

Abstract The paper proposes a phase-space based algorithm applying the Euclidian distance measure enabling detection of heartbeats and characteristic (fiducial) points from a single-lead electrocardiogram (ECG) signal. It extends the QRS detection in the phase space by detecting the P and T fiducial points. The algorithm is derived by reconstructing the ECG signals in a two-dimensional (2D) phase space according to the delay method and utilizes geometrical properties of the reconstructed phase portrait of the signal in the phase space for the heartbeat and fiducial-point detection. It uses adaptive thresholding and the Euclidian distance measure between the signal points in the phase portrait as an alternative to the phase-portrait area calculation (Lee et al., 2002 [1]). It was verified with the QT Database (2011; [2]) and its performance was assessed using sensitivity (Se) and the positive predictive value (PPV). Results for the proposed algorithm are 99.06%, 99.75% and 99.66% for Se and 94.87%, 99.75% and 99.66% for PPV for the P points, heartbeats and T points, respectively.  

 

Emil Plesnik, Olga Malgina, Jurij F. Tasič and Matej Zajc. Detection of the electrocardiogram fiducial points in the phase space using area calculation. Electrotechnical review, english edition, 2011, Vol. 78, No. 5, pp. 257-262, http://ev.fe.uni-lj.si/5-2011/Plesnik.pdf.

Abstract The paper proposes an extension of a known method for heart-beat detection based on ECG reconstruction in a 2D phase space coherent to the delay method to detection of the P-Q-R-S-T characteristic (fiducial) points. The QT Database was used for evaluation and algorithm performance was assessed using sensitivity (Se) and positive predictive value (PPV). Results are 99.19 %, 99.67 % and 94.58 % for Se and 95.02 %, 99.67 % and 94.55 % for PPV for the P points, heartbeats and T points, respectively.  

 

Emil Plesnik, Olga Malgina, Jurij F. Tasič and Matej Zajc. ECG baseline drift correction through phase space for simple R-point detection. The 25th IEEE International Symposium on Computer-Based Medical System, CBMS 2012, June 20-22, Rome, Italy. CBMS 2012.. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=6266307

Abstract Baseline wandering interference causes inaccurate detection of electrocardiogram (ECG) characteristics such as the R point. In this paper an alternative approach for correction of the ECG baseline wandering for R-point detection is presented. The baseline wandering is corrected in the phase space where the ECG is reconstructed by using the first derivative of the signal. After correction in the phase space a simple thresholding can be used for the correct detection of R points. The method is evaluated on signals from the MIT-BIH Arrhythmia database. Results show that the method is effective in removing baseline wandering from the ECG and detecting the R points by a simple fixed threshold.


Pregled:
Zadnje raziskave evropskega statističnega urada Eurostat napovedujejo povečanje deleža prebivalstva v starostni skupini nad 65 let v celotni Evropski uniji. Poleg tega kar 86 % vseh smrti v EU povzročijo različne kronične bolezni, kot so kardiovaskularne bolezni, rak, diabetes, mišično skeletna obolenja, bolezni dihal, duševne bolezni, itd. Dodatno so vse višji tudi stroški zdravljenja in v zadnjih letih se količina sredstev, namenjenih zdravstvu nenehno povečuje. Vse to so resni motivi za raziskovanje alternativnih storitev, ki bi povečale učinkovitost zdravstva, olajšale življenja bolnikov in hkrati tudi znižale z zdravljenjem povezane stroške.

Skupina za telemedicinske storitve se posveča realizaciji algoritmov digitalne obdelave biosignalov, kot na primer algoritmom kompresije in algoritmom za določanje pomembnih značilnosti biosignalov. Pomembno področje raziskav skupine so arhitekture in sistemi za zajem biosignalov.

Pomembnejša znanstvena in aplikacijsko raziskovalna področja so:

1. Algoritmi za kompresijo signalov, določanje značilk in klasifikacijo signalov za različne namene uporabe, npr. v medicini, športu, zabavi, itd.
2. Uporabniški vmesniki: določanje informacije, ki potuje nazaj od sistema do uporabnika in način njenega prikaza.
3. Arhitekture za zajem biosignalov: senzorji in elektrode za zajem, ojačevalniki, izolacijska vezja, izenačevalniki, A/D pretvorniki, mikroprocesorji.
4. Brezžična senzorska omrežja (WSN, Wireless Sensor Networks): njihova uporaba v telemedicini, še posebej v smislu telesnih senzorskih omrežij (BSN, Body Sensor Networks).
5. Komunikacijske tehnologije in protokoli v brezžičnih senzorskih omrežjih.