My research deals essentially with the analysis of highly irregular data through the notions of scale invariance and
multifractal analysis.
Recently, I also started exploring applications of the scattering transform.
I am also interested in machine learning techniques for sparse learning.
Research Interests
Scale Invariance
Multifractal Analysis
Scattering Transform
Stochastic Processes
Biomedical Applications
Heart rate variability (adult and fetal)
Voice period
Tools and Methods
Wavelet transforms
Wavelet leader and p-leader multifractal formalism
Scattering transform
Machine learning: sparse classifiers
Applications
Intrapartum fetal heart rate
Acydosis detection during labor using multifractal analysis.
We analyze fetal heart rate during labor to detect fetal stress and, eventually, help obsetricians prescribe C-sections.
We advocate the use of multifractal features to measure irregularity.
We use sparse support vector machines to combine several types of features. We show that multifractal features are very relevant,
preferred over traditional descriptors of irregularity, and that they increase classification performance.
Characterization of ischemic strokes from heart rate under atrial fibrillation.
We used the scattering coefficients computed from the heart rate of patients suffering from atrial fibrilation as a tool to predict ischemic
stroke.
Scattering coefficients in the second layer were found to show significant differences between both groups of patients, and to improve
classification performance over state-of-the-art methods.
Scattering coefficients in the first layer (left), and in two nodes of the second layer (middle and right, different values of j2), for the RR
time series of patients that did (red crosses) and did not (blue crosses) develop ischemic strokes (median and 95% confidence intervals).
Artistic paintings
Author authentification of van Gogh's paintings and Raphael's drawings.
We used the scattering transform to discriminate between paintings by van Gogh and Raphael, and those from
forgers or contemporary painters.
We analyzed the performance of several classifiers, and we showed that scattering
coefficients are very sparse, and that sparse classifiers achieve an excelent classification performance.
Original image (a), first layer scattering coefficients (b), and second layer scattering coefficients (c-d) computed
from those in (b), for a painting by van Gogh (top tow) and a drawing by Raphael (bottom row).
Publication List
Last updated: 2018-03-27
Journal articles
R. Leonarduzzi, P. Abry, H. Wendt, S. Jaffard and H. Touchette
A Generalized Multifractal Formalism for the Estimation of Nonconcave Multifractal Spectra
IEEE Transactions on Signal Processing, vol XX, pp XX, 2018, submitted.
P. Abry, J. Spilka, R. Leonarduzzi, V. Chudáček, N. Pustelnik and M. Doret
Sparse learning for Intrapartum fetal heart rate analysis
Biomedical Physics and Engineering Express, vol XX, pp XX, 2018, submitted.
|||
R. Leonarduzzi, H. Liu and Y. Wang
Scattering Transform and Sparse Linear Classifiers for Art Authentication
Signal Processing, vol XX, pp XX, 2018, in press.
S. Jaffard, S. Seuret, H. Wendt, R. Leonarduzzi, S. Roux and P. Abry
Multivariate multifractal analysis
Applied and Computational Harmonic Analysis, vol XX, pp XX, 2018, in press.
R. Leonarduzzi, P. Abry, H. Wendt, K. Kiyono, Y. Yamamoto, E. Watanabe and J. Hayano
Scattering Transform of Heart Rate Variability for the Prediction of Ischemic Stroke in Patients with Atrial Fibrillation
Methods of Information in Medicine, vol XX, pp XX, 2017, in press.
R. Leonarduzzi, P. Abry, H. Wendt, S. Jaffard and C. Melot
Finite-Resolution Effect in p-leader Multifractal Analysis
IEEE Transactions on Signal Processing, vol 65, pp 3359–3368, 2017.
J. Spilka, J. Frecon, R. Leonarduzzi, N. Pustelnik, P. Abry and M. Doret
Sparse Support Vector Machine for Intrapartum Fetal Heart Rate Classification
IEEE Journal of Biomedical and Health Informatics, vol 21, pp 664-671, 2017.
S. Jaffard, C. Melot, R. Leonarduzzi, H. Wendt, P. Abry, S. G. Roux and M. Torres
p-exponent and p-leaders, Part I: Negative Pointwise Regularity.
Physica A, vol 448, pp 300–318, 2016.
R. Leonarduzzi, H. Wendt, P. Abry, S. Jaffard, C. Melot, S. G. Roux and M. Torres
p-exponent and p-leaders, Part II: Multifractal Analysis. Relations to Detrended Fluctuation Analysis.
Physica A, vol 448, pp 319–339, 2016.
R. Leonarduzzi, G. Alzamendi, G. Schlotthauer and M. Torres
Wavelet Leader Multifractal Analysis of Period and Amplitude Sequences from Sustained Vowels
Speech Communication, vol 72, pp 1–12, 2015.
R. Leonarduzzi, M. Torres and P. Abry
Scaling Range Automated Selection for Wavelet Leader Multifractal Analysis
Signal Processing, vol 105, pp 243–257, 2014.
P. Abry, S. Jaffard, R. Leonarduzzi, C. Melot and H. Wendt
New Exponents for Pointwise Singularities Classification
Proc. Fractals and Related Fields III, 19-26 September 2015, Porquerolles, France, Stéphane Seuret and Julien Barral, 2017, To appear.
|||
S. Jaffard, P. Abry, C. Melot, R. Leonarduzzi and H. Wendt
Multifractal Analysis Based on p-exponents and Lacunarity Exponents
Fractal Geometry and Stochastics V (Progress in probability), vol 70, C. Bandt, K. Falconer, M. Zähle, pp 279-313, 2015.
R. Leonarduzzi, P. Abry, S. Roux, H. Wendt, S. Jaffard and S. Seuret
On multifractal characterization for bivariate data
Proc. European Signal Proc. Conf. (EUSIPCO), 2018, Submitted.
|||
H. Wendt, R. Leonarduzzi, P. Abry, S. Roux, S. Jaffard and S. Seuret
Assessing cross-dependencies using bivariate multifractal analysis
Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc. (ICASSP), 2018, Accepted.
|||
R. Leonarduzzi, P. Abry, S. Jaffard, H. Wendt, L. Gournay, T. Kyriacopoulou, C. Martineau and C. Martinez
p-Leader Multifractal Analysis for Text Type Identification
Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc. (ICASSP), 2017.
|||
R. Leonarduzzi, P. Abry, H. Wendt, K. Kiyono, Y. Yamamoto, E. Watanabe and J. Hayano
Scattering Transform of Heart Rate Variability for the Prediction of Ischemic Stroke in Patients with Atrial Fibrillation
Proc. Int. Workshop Biosignal Interpretation (BSI), Osaka, Japan, 2016.
J. Spilka, R. Leonarduzzi, V. Chudáček, P. Abry and M. Doret
Fetal Heart Rate Classification: First vs Second Stage of Labor
Proc. Int. Workshop Biosignal Interpretation (BSI), Osaka, Japan, 2016.
R. Leonarduzzi, H. Touchette, H. Wendt, P. Abry and S. Jaffard
Generalized Legendre Transform Multifractal Formalism for Nonconcave Spectrum Estimation
2016 IEEE Statistical Signal Processing Workshop (SSP) (SSP 2016), pp 1-5, Palma de Mallorca, Spain, 2016.
J. Spilka, V. Chudáček, M. Huptych, R. Leonarduzzi, P. Abry and M. Doret
Intrapartum Fetal Heart Rate Classification: Cross-Database Evaluation
XIV Mediterranean Conference on Medical and Biological Engineering and Computing: MEDICON 2016, pp 1199–1204, 2016.
R. Leonarduzzi, H. Wendt, S. Jaffard and P. Abry
Pitfall in Multifractal Analysis of Negative Regularity
Proc. GRETSI Symposium Signal and Image Processing, Lyon, France, 2015.
J. Spilka, J. Frecon, R. Leonarduzzi, N. Pustelnik, P. Abry and M. Doret
Intrapartum Fetal Heart Rate Classification from Trajectory in Sparse SVM Feature Space
Proc. Ann. Int. Conf. IEEE Eng. Med. and Biol. Soc. (EMBC), pp 2335–2338, 2015.
R. Leonarduzzi, J. Spilka, J. Frecon, H. Wendt, N. Pustelnik, S. Jaffard, P. Abry and M. Doret
P-leader Multifractal Analysis and Sparse SVM for Intrapartum Fetal Acidosis Detection
Proc. Ann. Int. Conf. IEEE Eng. Med. and Biol. Soc. (EMBC), pp 1971–1974, 2015.
R. Leonarduzzi, J. Spilka, H. Wendt, S. Jaffard, M. Torres, P. Abry and M. Doret
p-leader Based Classification of First Stage Intrapartum Fetal HRV
Proc. Latin American Conference on Biomedical Engineering (CLAIB), Paraná, Argentina, 2014.
R. Leonarduzzi, H. Wendt, S. Jaffard, S. Roux, M. Torres and P. Abry
Extending Multifractal Analysis to Negative Regularity: p-exponents and p-leaders
Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc. (ICASSP), pp 305-309, Florence, Italy, 2014.
R. Leonarduzzi, G. Schlotthauer and M. Torres
Wavelet Leader Based Multifractal Analysis of Heart Rate Variability during Myocardial Ischaemia
Proc. Ann. Int. Conf. IEEE Eng. Med. and Biol. Soc. (EMBC), pp 110–113, 2010.
p-leader analysis and classification of oscillating singularities
CIMPA 2017 Research School: Harmonic Analysis, Geometric Measure Theory and Applications
Buenos Aires, Argentina. 2017. link
Multifractal analysis for text type identification
Séminaire Cristolien d'Analyse Multifractale, Université Paris-Est Créteil
Creteil, France. 2017. link
p-leader analysis and classification of oscillating singularities
Journées du GDR Multifractale
Avignon, France. 2016. link
p-leader multifractal analysis: advantages and applications
Fractals and Related Fields III
Porquerolles, France. link
% Indicate pseudo-fractional-integration order
mf_obj.gamint = 0;
% Indicate number of bootstrap resamples:
mf_obj.n_resamp_1 = 100;
% The input can be a 1d or 2d array.
mf_obj.analyze (data);
Which produces, among other, figures showing the data (top row),
structure functions (wavelet spectrum, bottom right), and multifractal spectrum (bottom left),
with their bootstrap-based confidence intervals.
This software is outdated. A new version is bundled in the p-leader based multifractal analysis toolbox
presented before.
Performs the bootstrap-based scaling range selection algorithm for wavelet leader multifractal analysis,
as described in this paper.
Works with legacy versions of the wavelet-leader multifractal analysis toolbox WLBMF.
2014: PhD in Engineering, National Univerity of Litoral, Argentina.
Specialty: Signals, Systems and Computational Inteligence
Thesis: Wavelet-leader-based multifractal analysis: automatic scaling range selection, p-leader-based multifractal formalism and application to biomedical signals.
2010: Biomedical Engineer, National Univerity of Entre Ríos, Argentina
Career
Current: Postdoctoral Fellow, Laboratoire de Physique, CNRS UMR 5672, ENS de Lyon, France
May 2017-October 2017: Visiting Scholar, Department of Mathematics, The Hong Kong University of Science and Technology.
2015-2017: Postdoctoral Fellow, Laboratoire de Physique, CNRS UMR 5672, ENS de Lyon, France
Awards
2010: first place, CORAL-EMBS Student Paper Competition. 32 IEEE Engineering in Medicine and Biology Conference Society
2010: Award to the Best Engineering Graduates, National Engineering Academy, Argentina