Miguel Ángel Alonso Arévalo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Miguel Ángel Alonso Arévalo has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
David H. Covarrubias
3 shared publications- Rodrigo Méndez-Alonzo
Departamento de Biología de la Conservación Centro de Investigación Científica y de Educación Superior de Ensenada Ensenada Mexico
3 shared publications - David H. Covarrubias
Center for Scientific Research and Higher Education at Ensenada (CICESE), Carr. Tijuana-Ensenada 3918, Zona Playitas, Ensenada 22860, Mexico
2 shared publications - Eloísa García-Canseco
Facultad de Ciencias, Universidad Autonoma de Baja California, Baja California 22860, Mexico
2 shared publications - José Guadalupe Arceo Olague
Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juarez 147, Centro, Zacatecas 98000, Mexico
2 shared publications Leonardo F. Yepes
Department of Electronic and Telecommunications CICESE Research Center Carretera Ensenada‐Tijuana No. 3918, Zona Playitas Ensenada 22860 Baja California México
2 shared publications
Latest Publications
- Open Access
- 7 April 2025
- Published by MDPI AG in Technologies
- Vol. 13 (4) , 147
A Deep-Learning Approach to Heart Sound Classification Based on Combined Time-Frequency Representations
Worldwide, heart disease is the leading cause of mortality. Cardiac auscultation, when conducted by a trained professional, is a non-invasive, cost-effective, and readily available method for the initial assessment of cardiac health. Automated heart sound analysis offers a promising and accessible approach to supporting cardiac diagnosis. This work introduces a novel method for classifying heart sounds as normal or abnormal by leveraging time-frequency representations. Our approach combines three distinct time-frequency representations—short-time Fourier transform (STFT), mel-scale spectrogram, and wavelet synchrosqueezed transform (WSST)—to create images that enhance classification performance. These images are used to train five convolutional neural networks (CNNs): AlexNet, VGG-16, ResNet50, a CNN specialized in STFT images, and our proposed CNN model. The method was trained and tested using three public heart sound datasets: PhysioNet/CinC Challenge 2016, CirCor DigiScope Phonocardiogram Dataset 2022, and another open database. While individual representations achieve maximum accuracy of ≈85.9%, combining STFT, mel, and WSST boosts accuracy to ≈99%. By integrating complementary time-frequency features, our approach demonstrates robust heart sound analysis, achieving consistent classification performance across diverse CNN architectures, thus ensuring reliability and generalizability.
- 7 April 2025
- Published by MDPI AG in Technologies
- Vol. 13 (4) , 147
Open AccessA Deep-Learning Approach to Heart Sound Classification Based on Combined Time-Frequency Representations
Worldwide, heart disease is the leading cause of mortality. Cardiac auscultation, when conducted by a trained professional, is a non-invasive, cost-effective, and readily available method for the initial assessment of cardiac health. Automated heart sound analysis offers a promising and accessible approach to supporting cardiac diagnosis. This work introduces a novel method for classifying heart sounds as normal or abnormal by leveraging time-frequency representations. Our approach combines three distinct time-frequency representations—short-time Fourier transform (STFT), mel-scale spectrogram, and wavelet synchrosqueezed transform (WSST)—to create images that enhance classification performance. These images are used to train five convolutional neural networks (CNNs): AlexNet, VGG-16, ResNet50, a CNN specialized in STFT images, and our proposed CNN model. The method was trained and tested using three public heart sound datasets: PhysioNet/CinC Challenge 2016, CirCor DigiScope Phonocardiogram Dataset 2022, and another open database. While individual representations achieve maximum accuracy of ≈85.9%, combining STFT, mel, and WSST boosts accuracy to ≈99%. By integrating complementary time-frequency features, our approach demonstrates robust heart sound analysis, achieving consistent classification performance across diverse CNN architectures, thus ensuring reliability and generalizability.
- Open Access
- 31 March 2025
- Published by Wiley in Applications in Plant Sciences
- Vol. 13 (2) , e70004
A low‐cost protocol for the optical method of vulnerability curves to calculate P50
Premise: The quantification of plant drought resistance, particularly embolism formation, within and across species, is critical for ecosystem management and agriculture. We developed a cost‐effective protocol to measure the water potential at which 50% of hydraulic conductivity (P50) is lost in stems, using affordable and accessible materials in comparison to the traditional optical method.Methods and Results: Our protocol uses inexpensive USB microscopes, which are secured along with the plants to a pegboard base to avoid movement. A Python program automatized the image acquisition. This method was applied to quantify P50 in an exotic species (Nicotiana glauca) and native species (Rhus integrifolia) of the Mediterranean vegetation in Baja California, Mexico.Conclusions: The intra‐ and interspecific patterns of variation in stem P50 of N. glauca and R. integrifolia were obtained using the low‐cost optical method with widely available and affordable materials that can be easily replicated for other species.
- 31 March 2025
- Published by Wiley in Applications in Plant Sciences
- Vol. 13 (2) , e70004
Open AccessA low‐cost protocol for the optical method of vulnerability curves to calculate P50
Premise: The quantification of plant drought resistance, particularly embolism formation, within and across species, is critical for ecosystem management and agriculture. We developed a cost‐effective protocol to measure the water potential at which 50% of hydraulic conductivity (P50) is lost in stems, using affordable and accessible materials in comparison to the traditional optical method.Methods and Results: Our protocol uses inexpensive USB microscopes, which are secured along with the plants to a pegboard base to avoid movement. A Python program automatized the image acquisition. This method was applied to quantify P50 in an exotic species (Nicotiana glauca) and native species (Rhus integrifolia) of the Mediterranean vegetation in Baja California, Mexico.Conclusions: The intra‐ and interspecific patterns of variation in stem P50 of N. glauca and R. integrifolia were obtained using the low‐cost optical method with widely available and affordable materials that can be easily replicated for other species.
- Open Access
- 15 June 2024
- Published by Botanical Sciences, Sociedad Botanica de Mexico, AC in Botanical Sciences
- Vol. 102 (3) , 828-842
Intra and interspecific variation in foliage phenology and leaf spectroscopy in nine Baja Californian shrub species
Background: Canopy phenology, foliar biochemistry, and leaf lifespan vary according to season within and across species. Intrinsically, this variation should also determine changes in the spectral properties of foliar tissue. However, whether canopy phenology and leaf spectroscopy co-vary across species has seldom been tested in seasonal drylands. Questions and / or Hypotheses: We tested the covariation between growth rate, foliage phenology, and leaf spectral indices, expecting that species with high growth rates should have large variability in relative leaf number and foliar spectroscopy. Studied species / data description / Mathematical model: We partition the intra and interspecific variation in relative leaf number and spectroscopy within nine perennial chaparral shrub species. Study site and dates: Rancho El Mogor, Valle de Guadalupe, Baja California, during 2017 and 2018. Methods: Foliage phenology was quantified with an index of relative leaf number, foliar spectroscopy with three standard vegetation indices, and resource-use with stem growth and leaf functional traits. Results: Species with higher variability in foliage phenology (more deciduous species) had higher stem growth rates. The three vegetation indices varied significantly across species (ca. 20 % of explained variance), and across seasons within species (ca. 55 % of explained variance). The values of the three vegetation indices were correlated, and only NDVI was correlated with foliage phenology and stem growth. Conclusions: Our results show that variations in relative leaf number and spectroscopy in chaparral species are coupled with functional traits of species involved in resource exploitation strategies in a seasonally arid environment.
- 15 June 2024
- Published by Botanical Sciences, Sociedad Botanica de Mexico, AC in Botanical Sciences
- Vol. 102 (3) , 828-842
Open AccessIntra and interspecific variation in foliage phenology and leaf spectroscopy in nine Baja Californian shrub species
Background: Canopy phenology, foliar biochemistry, and leaf lifespan vary according to season within and across species. Intrinsically, this variation should also determine changes in the spectral properties of foliar tissue. However, whether canopy phenology and leaf spectroscopy co-vary across species has seldom been tested in seasonal drylands. Questions and / or Hypotheses: We tested the covariation between growth rate, foliage phenology, and leaf spectral indices, expecting that species with high growth rates should have large variability in relative leaf number and foliar spectroscopy. Studied species / data description / Mathematical model: We partition the intra and interspecific variation in relative leaf number and spectroscopy within nine perennial chaparral shrub species. Study site and dates: Rancho El Mogor, Valle de Guadalupe, Baja California, during 2017 and 2018. Methods: Foliage phenology was quantified with an index of relative leaf number, foliar spectroscopy with three standard vegetation indices, and resource-use with stem growth and leaf functional traits. Results: Species with higher variability in foliage phenology (more deciduous species) had higher stem growth rates. The three vegetation indices varied significantly across species (ca. 20 % of explained variance), and across seasons within species (ca. 55 % of explained variance). The values of the three vegetation indices were correlated, and only NDVI was correlated with foliage phenology and stem growth. Conclusions: Our results show that variations in relative leaf number and spectroscopy in chaparral species are coupled with functional traits of species involved in resource exploitation strategies in a seasonally arid environment.
- Open Access
- 7 November 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (7) , 531
Plant Foliar Geometry as a Biomimetic Template for Antenna Design
Plant diversity includes over 300,000 species, and leaf structure is one of the main targets of selection, being highly variable in shape and size. On the other hand, the optimization of antenna design has no unique solution to satisfy the current range of applications. We analyzed the foliar geometries of 100 plant species and applied them as a biomimetic design template for microstrip patch antenna systems. From this set, a subset of seven species were further analyzed, including species from tropical and temperate forests across the phylogeny of the Angiosperms. Foliar geometry per species was processed by image processing analyses, and the resultant geometries were used in simulations of the reflection coefficients and the radiation patterns via finite differences methods. A value below −10 dB is set for the reflection coefficient to determine the operation frequencies of all antenna elements. All species showed between 3 and 15 operational frequencies, and four species had operational frequencies that included the 2.4 and 5 GHz bands. The reflection coefficients and the radiation patterns in most of the designs were equal or superior to those of conventional antennas, with several species showing multiband effects and omnidirectional radiation. We demonstrate that plant structures can be used as a biomimetic tool in designing microstrip antenna for a wide range of applications.
- 7 November 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (7) , 531
Open AccessPlant Foliar Geometry as a Biomimetic Template for Antenna Design
Plant diversity includes over 300,000 species, and leaf structure is one of the main targets of selection, being highly variable in shape and size. On the other hand, the optimization of antenna design has no unique solution to satisfy the current range of applications. We analyzed the foliar geometries of 100 plant species and applied them as a biomimetic design template for microstrip patch antenna systems. From this set, a subset of seven species were further analyzed, including species from tropical and temperate forests across the phylogeny of the Angiosperms. Foliar geometry per species was processed by image processing analyses, and the resultant geometries were used in simulations of the reflection coefficients and the radiation patterns via finite differences methods. A value below −10 dB is set for the reflection coefficient to determine the operation frequencies of all antenna elements. All species showed between 3 and 15 operational frequencies, and four species had operational frequencies that included the 2.4 and 5 GHz bands. The reflection coefficients and the radiation patterns in most of the designs were equal or superior to those of conventional antennas, with several species showing multiband effects and omnidirectional radiation. We demonstrate that plant structures can be used as a biomimetic tool in designing microstrip antenna for a wide range of applications.
- Open Access
- 11 October 2023
- Published by Elsevier in Journal of Agriculture and Food Research
- Vol. 14
Developing a microscope image dataset for fungal spore classification in grapevine using deep learning
- 11 October 2023
- Published by Elsevier in Journal of Agriculture and Food Research
- Vol. 14
Open AccessDeveloping a microscope image dataset for fungal spore classification in grapevine using deep learning
- Open Access
- 11 October 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (10) , 335
Comparison of Supervised Learning Algorithms on a 5G Dataset Reduced via Principal Component Analysis (PCA)
Improving the quality of service (QoS) and meeting service level agreements (SLAs) are critical objectives in next-generation networks. This article presents a study on applying supervised learning (SL) algorithms in a 5G/B5G service dataset after being subjected to a principal component analysis (PCA). The study objective is to evaluate if the reduction of the dimensionality of the dataset via PCA affects the predictive capacity of the SL algorithms. A machine learning (ML) scheme proposed in a previous article used the same algorithms and parameters, which allows for a fair comparison with the results obtained in this work. We searched the best hyperparameters for each SL algorithm, and the simulation results indicate that the support vector machine (SVM) algorithm obtained a precision of 98% and a F1 score of 98.1%. We concluded that the findings of this study hold significance for research in the field of next-generation networks, which involve a wide range of input parameters and can benefit from the application of principal component analysis (PCA) on the performance of QoS and maintaining the SLA.
- 11 October 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (10) , 335
Open AccessComparison of Supervised Learning Algorithms on a 5G Dataset Reduced via Principal Component Analysis (PCA)
Improving the quality of service (QoS) and meeting service level agreements (SLAs) are critical objectives in next-generation networks. This article presents a study on applying supervised learning (SL) algorithms in a 5G/B5G service dataset after being subjected to a principal component analysis (PCA). The study objective is to evaluate if the reduction of the dimensionality of the dataset via PCA affects the predictive capacity of the SL algorithms. A machine learning (ML) scheme proposed in a previous article used the same algorithms and parameters, which allows for a fair comparison with the results obtained in this work. We searched the best hyperparameters for each SL algorithm, and the simulation results indicate that the support vector machine (SVM) algorithm obtained a precision of 98% and a F1 score of 98.1%. We concluded that the findings of this study hold significance for research in the field of next-generation networks, which involve a wide range of input parameters and can benefit from the application of principal component analysis (PCA) on the performance of QoS and maintaining the SLA.
- Open Access
Star-Identification System Based on Polygon Recognition
Accurate attitude determination is crucial for satellites and spacecraft. Among attitude determination devices, star sensors are the most accurate. Solving the lost-in-space problem is the most critical function of the star sensor. Our research introduces a novel star-identification system that utilizes a polygon-recognition algorithm to assign a unique complex number to polygons created by stars. This system aims to solve the lost-in-space problem. Our system includes a full solution with a lens, image sensor, processing unit, and algorithm implementation. To test the system’s performance, we analyzed 100 night sky images that resembled what a real star sensor in orbit would experience. We used a k-d tree algorithm to accelerate the search in the star catalog of complex numbers. We implemented various verification methods, including internal polygon verification and a voting mechanism, to ensure the system’s reliability. We obtained the star database used as a reference from the Gaia DR2 catalog, which we filtered, to eliminate irrelevant stars, and which we arranged by apparent magnitude. Despite manually introducing up to three false stars, the system successfully identified at least one star in 97% of the analyzed images.
Open AccessStar-Identification System Based on Polygon Recognition
Accurate attitude determination is crucial for satellites and spacecraft. Among attitude determination devices, star sensors are the most accurate. Solving the lost-in-space problem is the most critical function of the star sensor. Our research introduces a novel star-identification system that utilizes a polygon-recognition algorithm to assign a unique complex number to polygons created by stars. This system aims to solve the lost-in-space problem. Our system includes a full solution with a lens, image sensor, processing unit, and algorithm implementation. To test the system’s performance, we analyzed 100 night sky images that resembled what a real star sensor in orbit would experience. We used a k-d tree algorithm to accelerate the search in the star catalog of complex numbers. We implemented various verification methods, including internal polygon verification and a voting mechanism, to ensure the system’s reliability. We obtained the star database used as a reference from the Gaia DR2 catalog, which we filtered, to eliminate irrelevant stars, and which we arranged by apparent magnitude. Despite manually introducing up to three false stars, the system successfully identified at least one star in 97% of the analyzed images.
- 17 August 2023
- Published by Revista Mexicana de Ingenieria Biomedica in Revista Mexicana de Ingeniería Biomédica
- Vol. 44 (4) , 6-22
Comparison of Spectral and Sparse Feature Extraction Methods for Heart Sounds Classification
Cardiovascular diseases (CVDs) remain the leading cause of morbidity worldwide. The heart sound signal or phonocardiogram (PCG) is the most simple, low-cost, and effective tool to assist physicians in diagnosing CVDs. Advances in signal processing and machine learning have motivated the design of computer-aided systems for heart illness detection based only on the PCG. The objective of this work is to compare the effects of using spectral and sparse features for a classification scheme to detect the presence/absence of a pathological state in a heart sound signal, more specifically, sparse representations using Matching Pursuit with multiscale Gabor time-frequency dictionaries, linear prediction coding, and Mel-frequency cepstral coefficients. This work compares the performance of PCGs classification applying features as a result of averaging the samples or the features for each PCG sound event when feeding a random forest (RF) classifier. For data balancing, random under-sampling and synthetic minority oversampling (SMOTE) methods were applied. Furthermore, we compare the Correlation Feature Selection (CFS) and Information Gain (IG) for the dimensionality reduction. The findings show a SE=93.17 %, SP=84.32 % and ACC=85.9 % when joining MP+LPC+MFCC features set with an AUC=0.969 showing that these features are promising to be used in heart sounds anomaly detection schemes.
- 17 August 2023
- Published by Revista Mexicana de Ingenieria Biomedica in Revista Mexicana de Ingeniería Biomédica
- Vol. 44 (4) , 6-22
Comparison of Spectral and Sparse Feature Extraction Methods for Heart Sounds Classification
Cardiovascular diseases (CVDs) remain the leading cause of morbidity worldwide. The heart sound signal or phonocardiogram (PCG) is the most simple, low-cost, and effective tool to assist physicians in diagnosing CVDs. Advances in signal processing and machine learning have motivated the design of computer-aided systems for heart illness detection based only on the PCG. The objective of this work is to compare the effects of using spectral and sparse features for a classification scheme to detect the presence/absence of a pathological state in a heart sound signal, more specifically, sparse representations using Matching Pursuit with multiscale Gabor time-frequency dictionaries, linear prediction coding, and Mel-frequency cepstral coefficients. This work compares the performance of PCGs classification applying features as a result of averaging the samples or the features for each PCG sound event when feeding a random forest (RF) classifier. For data balancing, random under-sampling and synthetic minority oversampling (SMOTE) methods were applied. Furthermore, we compare the Correlation Feature Selection (CFS) and Information Gain (IG) for the dimensionality reduction. The findings show a SE=93.17 %, SP=84.32 % and ACC=85.9 % when joining MP+LPC+MFCC features set with an AUC=0.969 showing that these features are promising to be used in heart sounds anomaly detection schemes.
- Open Access
- 16 November 2017
- Published by SAGE Publications in International Journal of Distributed Sensor Networks
- Vol. 13 (11)
Multi-hop broadcast message dissemination in vehicular ad hoc networks: A security perspective review
Vehicular ad hoc networks have been identified as a key technology for enabling safety and infotainment applications in the context of smart and connected vehicles. In this sense, diverse approaches of multi-hop broadcast protocols have been proposed to collect and disseminate context information through the network. However, before vehicular ad hoc networks applications fulfill their expected potential to connect smart vehicles, several issues must be addressed. Among these issues, those related to security are of particular importance. In this article, the main security issues of broadcast message dissemination in vehicular ad hoc networks are discussed. Moreover, a review of the most relevant threats and proposed solutions to secure broadcast message dissemination in vehicular ad hoc networks is presented and discussed. As mentioned, security is an important topic which has not been fully addressed in vehicular ad hoc networks; therefore, the aim of this article is to introduce security issues and proposed solutions related to three main security concerns associated with the message dissemination process in vehicular ad hoc networks: network access, data consistency, and broadcast protocols.
- 16 November 2017
- Published by SAGE Publications in International Journal of Distributed Sensor Networks
- Vol. 13 (11)
Open AccessMulti-hop broadcast message dissemination in vehicular ad hoc networks: A security perspective review
Vehicular ad hoc networks have been identified as a key technology for enabling safety and infotainment applications in the context of smart and connected vehicles. In this sense, diverse approaches of multi-hop broadcast protocols have been proposed to collect and disseminate context information through the network. However, before vehicular ad hoc networks applications fulfill their expected potential to connect smart vehicles, several issues must be addressed. Among these issues, those related to security are of particular importance. In this article, the main security issues of broadcast message dissemination in vehicular ad hoc networks are discussed. Moreover, a review of the most relevant threats and proposed solutions to secure broadcast message dissemination in vehicular ad hoc networks is presented and discussed. As mentioned, security is an important topic which has not been fully addressed in vehicular ad hoc networks; therefore, the aim of this article is to introduce security issues and proposed solutions related to three main security concerns associated with the message dissemination process in vehicular ad hoc networks: network access, data consistency, and broadcast protocols.
- 1 October 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 89, 170-180
Design and evaluation of a parametric model for cardiac sounds
- 1 October 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 89, 170-180
Design and evaluation of a parametric model for cardiac sounds