Biomedical Signal Processing

There are many signals produced by the human body which carry important information of its health and emotional, state, intentions, will and several other aspects. These signals are of nonlinear and nonstationary nature, and the information is hidden and coded in a complex way which is not clearly exposed in the raw signal. Those properties degrade the performance of automatic analysis and classification systems using those signals. We use recent advanced signal processing methods like sparse representation, nonnegative matrix factorization, blind source separation, independent component analysis, regularization and inverse problems to enhance the capabilities of information extraction and improve the behavior of systems for computational analysis of that information. The objective of this research line is to produce advanced signal processing and machine learning algorithms capable of extract that information, for a wide range of applications in speech signals, in respiratory, cardiac and electroencephalography signals, among others.

Team members

Leonardo Rufiner
Leandro Di Persia
Roman Rolon
Ivan Gareis
Jose Chelotti
Sebastian Vanrell

Web demos

fdICA: Algorithm for frequency-domain blind source separation based on the pseudoanechoic model.
multibinICA: Algorithm for frequency-domain blind source separation based on Multibin ICA for 2 by 2 mixtures.
blindder: Semi-supervised method for microRNA prediction with few labelled samples.
Beta Dereverberation: A blind, single channel dereverberation method in the time-frequency domain.

Selected publications

Classifying sleep–wake stages through recurrent neural networks using pulse oximetry signals    

R. Casal, L. Di Persia, G. Schlotthauer

Biomedical Signal Processing and Control, Volume 63 – 2021

Automatic scoring of apnea and hypopnea events using blood oxygen saturation signals    

Sleep-wake stages classification using heart rate signals from pulse oximetry 

R. Casal, L. Di Persia, G. Schlotthauer

Heliyon, Volume 5, Number 10, page e02529 – 2019

Switching divergences for spectral learning in blind speech dereverberation 

F. Ibarrola, R. Spies, L. Di Persia

IEEE/ACM Transactions on Audio, Speech, and Language Processing – 2019

Measuring complexity of biomedical signals (Editorial) 

G. Schlotthauer, A. Humeau-Heurtier, J. Escudero, H. L. Rufiner

Complexity, Volume 2018 – 2018

A Bayesian approach to convolutive nonnegative matrix factorization for blind speech dereverberation 

F. Ibarrola, L. Di Persia, R. Spies

Signal Processing, Volume 151, page 89–98 – 2018

Assessment of Homomorphic Analysis for Human Activity Recognition from Acceleration Signals    

S. R. Vanrell, D. H. Milone, H. L. Rufiner

IEEE Journal of Biomedical and Health Informatics, page 1001–1010 – 2018

Discriminative methods based on sparse representations of pulse oximetry signals for sleep apnea–hypopnea detection 

R.E. Rolon, L. Larrateguy, L. Di Persia, R. Spies, H. L. Rufiner

Biomedical Signal Processing and Control, Volume 33, page 358–367 – 2017

Empirical Mode Decomposition for adaptive AM-FM analysis of Speech: A Review    

R. Sharma, L. D. Vignolo, G. Schlotthauer, M. A. Colominas, H. L. Rufiner, S. R. M. Prasanna

Speech Communication, Volume 88, page 39–64 – 2017

On the use of convolutive nonnegative matrix factorization with mixed penalization for blind speech dereverberation    

F. Ibarrola, L. Di Persia, R. Spies

2017 XLIII Latin American Computer Conference (CLEI), page 1–4 – 2017

Denoising sound signals in a bioinspired non-negative spectro-temporal domain 

C. E. Martínez, J. Goddard, L. Di Persia, D. H. Milone, H. L. Rufiner

Digital Signal Processing, Volume 38, page 22–31 – jan 2015

Assessment of Homomorphic Analysis for Human Activity Recognition from Acceleration Signals    

S. R. Vanrell, D. H. Milone, H. L. Rufiner

IEEE Journal of Biomedical and Health Informatics, page 1001–1010 – 2018

3D acceleration for heat detection in dairy cows 

S. R. Vanrell, J. O. Chelotti, J. Galli, H. L. Rufiner, D. H. Milone

Congreso Argentino de Agroinformática (CAI 2014) – 43º JAIIO, page 121–134 – 2014

Wavelet Packet and Matched Filter inspired QRS Detector   

Carlos M. Pais, H. L. Rufiner

Anales del VI Congreso Latinoamericano de Ingeniería Biomédica (CLAIB 2014), page 403 – oct 2014

(Patent) Un procedimiento para la determinación del Índice de desaturación por Hora (IDH) y un dispositivo para llevar a cabo dicha determinación. 

D. H. Milone, L. Di Persia, G. Schlotthauer, Carlos M. Pais, L. Larrateguy

Technical Report , UNL, CONICET, Cardiocom. – sep 2013

Detector de QRS inspirado en Filtrado Óptimo y Paquetes de Onditas   

Carlos M. Pais, H. L. Rufiner

Proc. of the 13th Argentine Symposium on Computing Technology (AST 2012 y 41 JAIIO) – 2012

Denoising audio signals in the non-negative auditory cortical domain 

C. E. Martínez, J. Goddard, L. Di Persia, D. H. Milone, H. L. Rufiner

12th Argentine Symposium on Technology (40th JAIIO) – aug 2011