Úrsula Samantha Morales-Rodríguez

Dr. Úrsula Samantha Morales-Rodríguez

Instituto Politécnico Nacional, Mexico City, Ciudad de México, Mexico
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
17 November 2025 in Computers
Verified
Journal Article
Open access
PDF file
MDMaryjose Devora
Maryjose Devora
Benjamín Luna BenosoBenjamín Luna Benoso
Benjamín Luna Benoso
AAAntonio Alarcón-Paredes
Antonio Alarcón-Paredes
JPJosé Cruz Martínez Perales
José Cruz Martínez Perales
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
Early detection of plant diseases is key to ensuring food production, reducing economic losses, minimizing the use of agrochemicals, and maintaining the sustainability of the agricultural sector. Citrus plants, an important source of vitamin C, fiber, and antioxidants, are among the world’s most significant fruit crops but face threats such as canker and Huanglongbing (HLB), incurable diseases that require management strategies to mitigate their impact. Manual diagnosis, although common, I s imprecise, slow, and costly; therefore, efficient alternatives are emerging to identify diseases from early stages using Artificial Intelligence techniques. This study evaluated four deep learning models, specifically convolutional neural networks. In this study, we evaluated four convolutional neural network models (DenseNet121, ResNet50, EfficientNetB0, and MobileNetV2) to detect canker and HLB in citrus leaf images. We applied preprocessing and data-augmentation techniques; transfer learning via selective fine-tuning; stratified k-fold cross-validation; regularization methods such as dropout and weight decay; and hyperparameter-optimization techniques. The models were evaluated by the loss value and by metrics derived from the confusion matrix, including accuracy, recall, and F1-score. The best-performing model was EfficientNetB0, which achieved an average accuracy of 99.88% and the lowest loss value of 0.0058 using cross-entropy as the loss function. Since EfficientNetB0 is a lightweight model, the results show that lightweight models can achieve favorable performance compared to robust models, models that can be useful for disease detection in the agricultural sector using portable devices or drones for field monitoring. The high accuracy obtained is mainly because only two diseases were considered; consequently, it is possible that these results do not hold in a database that includes a larger number of diseases.

22 June 2022 in Tecnología y ciencias del agua
Verified
Journal Article
Closed access
CNCiudad de México Centro de Investigación En Computación – Instituto Politécnico Nacional
Ciudad de México Centro de Investigación En Computación – Instituto Politécnico Nacional
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
JCJosé Juan Carbajal-Hernández
José Juan Carbajal-Hernández
HMHerón Molina-Lozano
Herón Molina-Lozano
JTJuan A. Tello-Balinas
Juan A. Tello-Balinas
MPMichoacán de Ocampo Centro Regional de Investigación Pesquera – Instituto Nacional de Pesca
Michoacán de Ocampo Centro Regional de Investigación Pesquera – Instituto Nacional de Pesca

1 July 2025 in Journal of Animal Behaviour and Biometeorology
Verified
Journal Article
Open access
PDF file
CVChristian Axel Vera-Cortes
Christian Axel Vera-Cortes
JCJosé Juan Carbajal-Hernández
José Juan Carbajal-Hernández
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
DHDaniel Hernández-Montaño
Daniel Hernández-Montaño
IHIgnacio Hernández-Bautista
Ignacio Hernández-Bautista
Mexico is home to 17 species of the genus Ambystoma. Among them, 15 have some risk category, and the Ambystoma mexicanum is endangered. Different projects are focused on breeding them in aquaculture, where the growth rates of organisms are highly important. In this research, five parameters were selected as input variables: water temperature, pH, ammonia, nitrite, and nitrate nitrogen. These parameters were selected because they affect the growth of the species through their negative effects on the metabolism of the species. A computer model for growth forecasting is subsequently proposed. A backpropagation artificial neural network (ANN) was used to estimate weights via water quality parameters. The model has a hyperbolic-sigmoid transfer function for the hidden layer and a linear transfer function for the output layer. The data from the samples were generated over 90 days, divided into groups, and subjected to different diets. A trial-and-error approach optimized the number of hidden layer nodes and identified seven optimal neuron nodes. Then, autoregressive models were used to forecast individual parameters as the ANN input. The model obtained was able to predict weight within seven days with an error of less than three grams. The simulation results reveal that the ANN model efficiently forecasts the weight in Ambystoma intensive culture.

1 May 2023 in Tecnología y ciencias del agua
Verified
Journal Article
Open access
PDF file
ICInstituto Politécnico Nacional Centro de Investigación En Computación
Instituto Politécnico Nacional Centro de Investigación En Computación
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
JCJosé Juan Carbajal-Hernández
José Juan Carbajal-Hernández
HMHerón Molina-Lozano
Herón Molina-Lozano
JTJuan A. Tello-Balinas
Juan A. Tello-Balinas
IPInstituto Nacional de Pesca Centro Regional de Investigación Pesquera
Instituto Nacional de Pesca Centro Regional de Investigación Pesquera
México cuenta con una gran variedad de lagos de diferentes características y de gran importancia tanto para aspectos biológicos como sociales. El presente trabajo muestra el desarrollo de un sistema computacional para el análisis de la calidad del agua en cuerpos lacustres mediante la medición de parámetros fisicoquímicos de relevancia, como son temperatura, turbiedad y niveles de oxígeno disuelto. A través del diseño y construcción de un sistema de medición sumergible se automatiza el proceso de análisis de calidad del agua. El desarrollo de un software especializado para la gestión y medición de los datos obtenidos permite agilizar el proceso de evaluaciones de calidad del agua. Asimismo, se definen modelos matemáticos para la estimación de los parámetros de la calidad del agua a diferentes profundidades. Las mediciones experimentales realizadas se llevaron a cabo en el Lago de Zirahuén, localizado en el estado de Michoacán de Ocampo, México, debido a la importancia para el ecosistema de la localidad y a la diversidad de especies endémicas que habitan en él. Como resultado se obtiene una herramienta para facilitar la toma de decisiones con el propósito de conservar los cuerpos de agua, permitiendo realizar análisis más avanzados.

23 January 2025 in Edelweiss Applied Science and Technology
Verified
Journal Article
Open access
PDF file
Benjamín Luna BenosoBenjamín Luna Benoso
Benjamín Luna Benoso
JPJosé Cruz Martínez Perales
José Cruz Martínez Perales
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
JCJORGE CORTÉS-GALICIA
JORGE CORTÉS-GALICIA
At the end of 2019, a type of pneumonia of unknown origin was detected in Wuhan, China. It was later determined that the illness was caused by the SARS-CoV-2 virus, and in 2020, the World Health Organization designated this disease as COVID-19. Various efforts have been made to enable timely detection of COVID-19 within the field of computational systems. This study proposes detecting COVID-19 based on the symptoms experienced by patients, utilizing data provided by the National Epidemiological Surveillance System (SINAVE) of Mexico City, from which 403,185 records were used. In situations where positive cases of COVID-19 are detected, it is predicted whether it will be a serious case in which the patient needs to be intubated or admitted to the Intensive Care Unit. For this, classification and regression decision trees (CART) are used. Different parameters were considered to define the CART model, and the stepwise variable selection process was also used to determine the significant variables that offer the best results, obtaining an accuracy of 87.04%. This study shows progress in the detection of COVID-19 using only the symptoms presented by the patients.

3 July 2024 in Journal of Animal Behaviour and Biometeorology
Verified
Journal Article
Open access
PDF file
ÚMÚrsula Samantha Morales-Rodríguez
Úrsula Samantha Morales-Rodríguez
JCJosé Juan Carbajal-Hernández
José Juan Carbajal-Hernández
Benjamín Luna BenosoBenjamín Luna Benoso
Benjamín Luna Benoso
GRGabriel de Jesús Rodríguez-Jordán
Gabriel de Jesús Rodríguez-Jordán
JPJose Cruz Martínez Perales
Jose Cruz Martínez Perales
The cat (Felis catus) lives around or with humans and is considered one of the most popular pets in the world. Domestic cats have an extensive and complex vocalisation repertoire, and little is known about the meaning of their vocalisations; these animal sounds have been studied to determine their behavioural characteristics. This work implemented a computational model for cat vocalisation as a signal process to characterise it. Additionally, a recognition model is proposed to identify and associate domestic cat vocalisations with cat intentions. Domestic cat vocalisations were studied by obtaining sounds from audio and video sources stored in the web cloud and processing signals (distress, hiss, howl, meow, fright, purr, sexual call, and trill vocalisations) that belong to some cat situations (soliciting attention, complaining, surprise, threatening, welcoming, fighting, feeling hungry, mating, etc.). In measured signals, environmental noise was removed using a computational algorithm to increase the effectiveness of the recognition process. As a first approach, cat vocalisation patterns were extracted using Welch's method for spectral density estimation, appreciating vocalisation frequency characteristics and statistics. Additionally, a similarity function to compare cat vocalisation signals was developed, excluding useless patterns that could introduce computational problems in the learning phase of the recognition model. Then, an associative memory, the Lernmatrix Thresholded model, was used to recognise the domestic cat vocalisation needed, and pair associations between sounds and moods related to the recognition process result were established, i.e., identifying cat intention through vocalisation by analysing the signals emitted. The experimental results show the performance of the thresholded Lernmatrix among different pattern recognition models, where accurate vocalisation recognition rates are obtained. This computational model emerges as a suitable tool that could be helpful in animal care and ethology science to characterise the behaviour of animals through their vocalisation.