Joint Application of Audio Spectral Envelope and Tonality Index in an E-Asthma Monitoring System

Joint Application of Audio Spectral Envelope and Tonality Index in an E-Asthma Monitoring System
Publishing date: 
May, 2015
Show in user profiles:: 
tzielin's picture
prof. dr hab. inż.
Tomasz P.
profesor zwyczajny
+48 12 6174814
wtorek 11:30- 12:30
by appoitment
Informacje dodatkowe: 

Tomasz P. Zieliński uzyskał stopień mgr inż. z elektroniki, dr habilitowanego z elektrotechniki i tytuł naukowy profesora z telekomunikacji odpowiednio w latach 1982, 1996 i 2003. Stopień doktora nauk technicznych otrzymał w 1989 roku w Instytucie Cybernetyki Technicznej i Robotów Bułgarskiej Akademii Nauk w Sofii. Od 1982 roku do 2006 roku pracował na AGH w Katedrze Metrologii, kolejno jako asystent (1982), adiunkt (1989) i profesor nadzwyczajny (2000). Od 2006 roku pracuje w Katedrze Telekomunikacji na stanowisku profesora zwyczajnego. Jest autorem lub współautorem ponad 150 prac naukowych (artykuły w czasopismach i referaty w materiałach konferencyjnych). Jest autorem trzech monografii: „Reprezentacje sygnałów niestacjonarnych typu czas-częstotliwość i czas-skala” (AGH, 1996), „Od teorii do cyfrowego przetwarzania sygnałów” (AGH, 2002, 2004) i „Cyfrowe przetwarzanie sygnałów: Od teorii do zastosowań” (WKŁ, 2005, 2007, 2009). Kierował ponad 10 polskimi projektami badawczymi oraz aktywnie uczestniczył w kilku programach międzynarodowych, „ECSON Engineering and Computational Science for Oncology Network” (Anglia), „VECTOR Versatile Endoscopic Capsule for gastrointestinal TumOr Recognition and therapy” (FP6 EC), „Efficacy of Laryngeal High-Speed Video-endoscopy” (NIH, USA). Jego zainteresowania naukowe obejmują zaawansowane zastosowania metod cyfrowego przetwarzania sygnałów w systemach telekomunikacyjnych i biomedycznych, w szczególności łączną czasowo-częstotliwościową analizę sygnałów. Jest członkiem IEEE.

Additional information: 

Tomasz P. Zielinski received the M.S. degree in electronics, the D.Sc. degree (habilitation) in electrical engineering and the the scientific Professor title in telecommunications from the AGH University of Science and Technology (AGH-UST), Kraków, Poland, in 1982, 1996 and 2003, respectively, and the Ph.D. degree in electrical engineering from the Institute of Engineering Cybernetics and Robotics of Bulgarian Academy of Sciences, Sofia, Bulgaria, in 1988. Since 1982 he has been working at the Department of Instrumentation & Measurement AGH-UST as a Research & Teaching Assistant (1982), Associate (1989), Assistant Professor (1996) and Associate Professor (2000). In 2006 he joined the Department of Telecommunications, AGH-UST as a Full Professor. He has authored and co-authored more than 150 scientific journal and conference papers. He is also the author of three monographs (all in Polish): Time-Frequency and Time-Scale Representations of Non-stationary Signals (1996), From Theory to Digital Signal Processing (2002, 2004) and Digital Signal Processing: From Theory to Applications (2005, 2007, 2009). He has been a supervisor of more than 10 Polish research projects and actively participated in a few international programs (EPSR Council UK, ECSON: Engineering and Computational Science for Oncology Network; VECTOR EC FP6: Versatile Endoscopic Capsule for gastrointestinal TumOr Recognition and therapy; NIH, USA: “Efficacy of Laryngeal High-Speed Video-endoscopy”). His research interests include advanced digital signal processing in telecommunication and biomedical systems, especially time-frequency signal analysis. He is an IEEE member.

Wiśniewski M., Zieliński T.P.
Publication type: 
IEEE Journal of Biomedical and Health Informatics
This paper presents in detail a recently introduced highly efficient method for automatic detection of asthmatic wheezing in breathing sounds. The fluctuation in the Audio Spectral Envelope (ASE) from the MPEG-7 standard and the value of the Tonality Index (TI) from the MPEG-2 Audio specification are jointly used as discriminative features for wheezy sounds, while the Support Vector Machine (SVM) with a polynomial kernel serves as a classifier. The advantages of the proposed approach are described in the paper (e.g. detecting weak wheezes, very good ROC characteristics, independence from noise color). Since the method is not computationally complex it is suitable for remote asthma monitoring using mobile devices (personal medical assistants). The main contribution of this paper consists of presenting all the implementation details concerning the proposed approach for the first time, i.e. the pseudo-code of the method, and adjusting the values of the ASE and TI parameters after which only one (not two) FFT is required for analysis of a next overlapping signal fragment. The efficiency of the method has also been additionally confirmed by the AdaBoost classifier with a built-in mechanism to feature ranking, as well as a previously performed minimal-redundancy-maximal-relevance (mRMR) test.
na wszystkich stronach