Dr. Marcelo Risk

Co-authors

Following

Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

16 February 2017 in Entropy

Journal Article

Classification of Normal and Pre-Ictal EEG Signals Using Permutation Entropies and a Generalized Linear Model as a Classifier

Francisco O Redelico

Francisco Traversaro Varela

María Del Carmen García

Walter Silva

Osvaldo Rosso

Marcelo Risk

In this contribution, a comparison between different permutation entropies as classifiers of electroencephalogram (EEG) records corresponding to normal and pre-ictal states is made. A discrete probability distribution function derived from symbolization techniques applied to the EEG signal is used to calculate the Tsallis entropy, Shannon Entropy, Renyi Entropy, and Min Entropy, and they are used separately as the only independent variable in a logistic regression model in order to evaluate its capacity as a classification variable in a inferential manner. The area under the Receiver Operating Characteristic (ROC) curve, along with the accuracy, sensitivity, and specificity are used to compare the models. All the permutation entropies are excellent classifiers, with an accuracy greater than 94.5% in every case, and a sensitivity greater than 97%. Accounting for the amplitude in the symbolization technique retains more information of the signal than its counterparts, and it could be a good candidate for automatic classification of EEG signals.

1 July 2018 in Chaos: An Interdisciplinary Journal of Nonlinear Science

Journal Article

Bandt-Pompe symbolization dynamics for time series with tied values: A data-driven approach

Francisco Traversaro Varela

In 2002, Bandt and Pompe [Phys. Rev. Lett. 88, 174102 (2002)] introduced a successfully symbolic encoding scheme based on the ordinal relation between the amplitude of neighboring values of a given data sequence, from which the permutation entropy can be evaluated. Equalities in the analyzed sequence, for example, repeated equal values, deserve special attention and treatment as was shown recently by Zunino and co-workers [Phys. Lett. A 381, 1883 (2017)]. A significant number of equal values can give rise to false conclusions regarding the underlying temporal structures in practical contexts. In the present contribution, we review the different existing methodologies for treating time series with tied values by classifying them according to their different strategies. In addition, a novel data-driven imputation is presented that proves to outperform the existing methodologies and avoid the false conclusions pointed by Zunino and co-workers.

25 September 2002 in Artificial Organs

Journal Article

A New Approach to Assist Postoperative Heart Failure in an Animal Model: Juxta‐Aortic Counterpulsation

Edmundo I. Cabrera Fischer

Alejandra Christen

Marcelo Risk

Franco M. Pessana

Eduardo De Forteza

23 December 2021 in IEEE Latin America Transactions

Journal Article

Ultra-short-term heart rate variability analysis: comparison between Poincare and frequency domain methods

Short-term (5 min) heart rate variability analysis (HRV) demand for monitoring people's health and well-being status is increasing due to portable sensors and mobile applications. Five minutes analysis is extensive compared to that used in measurements of glucose, blood pressure, temperature, etc. To reduce costs and achieve optimal performance in personal health assessment, ultra-short-term monitoring less than 5 min is suggested. The aim of this work is to establish the minimum ultra-short-term HRV analysis time required for LF/HF (LH) (frequency domain sympathy-vagal balance indicator) and SD21 (Poincare graphic domain sympathy-vagal balance indicator) to be equivalent to those obtained by 5 min HRV. From electrocardiograms (ECGs), processing of 23 subjects in the experiment and series of 60, 90, 120, 180, 240 and 300 s (5 min) were obtained. The HRV time series was calculated and each LH and SD21 indicator in each of the ultra-short series was compared with the 300 s (Gold Standard), using different concordance analysis methods, such us Pearson correlation, Bland Altman, Cohen Delta. The ultra-short-term HRV LH indicator is equivalent to short-term HRV (5 min) in series equal or greater than 180 s while SD21 was equivalent to series equal or greater than 120 s.

22 August 2024 in Electronics

Journal Article

Determining the Optimal Window Duration to Enhance Emotion Recognition Based on Galvanic Skin Response and Photoplethysmography Signals

Marcos F. Bamonte

Marcelo Risk

Victor Angel Herrero

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely, Lyapunov Exponent, Approximate Entropy, and Poincaré indices. We found an optimum window duration of 3 s with

50 %

overlap and achieved accuracies of 0.75 and 0.74 for both arousal and valence, respectively. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.94 for arousal. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

13 January 2021 in Journal of Medical and Biological Engineering

Journal Article

Heart Rate Variability: Influence of Pre-processing Methods in Identifying Single-Night Sleep-Deprived Subjects

About Me

I am a researcher and academic with an extensive background in bioengineering and medical sciences. I earned my Doctorate in Engineering Sciences from the National University of Córdoba in 2008 and a Doctorate in Physiological Sciences from the University of Buenos Aires in 2000, graduating with honors. I also hold an MBA with a focus on Information Systems from the University of Palermo and a degree in Electronics Engineering from the National Technological University. I was Visiting Professor and Lecturer at Harvard Medical School's Department of Neurology, from 1998 to 2010, following a predoctoral fellowship at both the Favaloro Foundation and Harvard Medical School's Children's Hospital from 1994 to 1998. Currently, I serve as the Director of the Institute of Translational Medicine and Biomedical Engineering (IMTIB), a tri-institutional entity affiliated with CONICET, the Italian Hospital University Institute, and the Italian Hospital of Buenos Aires. Since 2017, I have been the Director of the Biomedical Engineering program at the Italian Hospital University Institute and a member of its Superior Council since 2018. I also coordinate and teach in the Doctorate in Health Sciences and the Master's in Health Informatics programs at the same institution. I lead the Biomedical Engineering Group at IMTIB and direct the MAGenTA project, which focuses on genomic actionability mapping in Argentina.

Dr. Marcelo Risk

Dr. Marcelo Risk

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me