Ayala-Chauvin, Manuel Ignacio
Thumbnail Image
Preferred name
Ayala-Chauvin, Manuel Ignacio
Main Affiliation
Ambato
Email
mayala@uti.edu.ec
ORCID
Scopus Author ID
57215428914

Research Output

Filters

41
Reset filters

Settings
Now showing 1 - 10 of 41
No Thumbnail Available
Publication

U-Net Models for Breast Cancer Detection: Improving Diagnostic Accuracy and Specificity

2024 , Dayanara Yánez-Arcos , Ayala-Chauvin, Manuel Ignacio , Elena Blanco-Romero

Breast cancer remains a critical global health issue, necessitating continuous research and innovative approaches for diagnosis, treatment, and prevention. This study evaluates the effectiveness of U -Net models in enhancing diagnostic precision and efficiency using real hospital samples. We aim to improve key diagnostic metrics such as accuracy, sensitivity, and specificity through the application of U-Net models. Our image classification model, tailored for 256 × 256 × 3 input images, excels in detecting and categorizing tumor cells. The architecture begins with initial convolutional layers featuring 64 filters, progresses to layers with 128 filters, and includes a Dropout layer to prevent overfitting. The deep network for object detection utilizes both region proposal and regression/classification approaches, achieving 92.27% confidence and 100% accuracy. Additionally, our deep learning algorithms accurately segment nuclei in histopathological images, employing a clustering strategy that delivers 88.81% confidence and 100% accuracy. Visual results demonstrate precise tumor cell localization and prediction confidence. Performance metrics from ten experimental runs indicate average confidence levels between 74.19% and 92.31%, with 90.0% accuracy and specificity in benign analysis. The model's ability to classify non-carcinomas versus carcinomas achieved an AUC of 0.78, illustrating its effective differentiation between classes.

View
No Thumbnail Available
Publication

Control System Test Platform for a DC Motor

2022 , Saá-Tapia F. , Mayorga-Miranda L. , Ayala-Chauvin, Manuel Ignacio , Domènech-Mestres C.

Currently, control systems are used to improve the behavior of actuators that are part of an equipment or process. However, to enhance their performance, it is necessary to perform tests to evaluate the responses of its operation depending on the type of controller. In this sense, a test platform was developed to compare and optimize the speed control of a DC motor with three types of controllers: Predictive Model Control (MPC), Proportional Integral Derivative (PID) and Fuzzy Logic. Data acquisition was performed using the Arduino MEGA board and LabVIEW software. The mathematical model of the three controllers was developed, taking into account the electrical and physical properties of the DC motor. Through MATLAB IDENT, the state space (SS) and transfer function F(S) equations were generated for the MPC and PID controller, respectively; on the other hand, input/output ranges for the Fuzzy Logic controller were input/output ranges defined by assigning belonging functions and linguistic variables. Experimental tests were carried out with these models under no-load and load. Tests performed in vacuum show that performance index with the motor at 100 rpm results in a PID of 0.2245, a Fuzzy Logic of 0.3212 and an MPC of 0.3576. On the other hand, with load at 100 rpm, a PID of 0.2343, a Fuzzy Logic of 0.3871 and an MPC of 0.3104 were obtained. It was determined that the Fuzzy Logic controller presents a higher over impulse; the PID and MPC have a faster stabilization time and with negligible over impulses. Finally, the MPC controller presents a better performance index analysis according to the Integral Square Error criterion (ISE). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Anthropization and growth of the electricity grid as variables for the analysis of urban infrastructure

2020 , Ayala-Chauvin, Manuel Ignacio , Huaraca D. , Varela Aldas, José , Ordóñez A. , Riba G.

City growth goes together with the development of infrastructure, and the power network is one of the most relevant towards economic development. The study of urban infrastructure through the analysis of anthropization coupled with power network growth can produce a tool that supports sustainable infrastructure planning, both economic and environmental. The case study focuses on Ambato, Ecuador, in the period from 1950 to 2019, and assesses quantitatively the changes in the city layout and the evolution of its power network. The data are adjusted to a sigmoid-type objective function through a non-linear least squares problem, that is solved using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method. Anthropization data show how the urban area grew during the study period: 37% (1950-1960), 53% (1960-1970), 80% (1970-1980), 35% (1980-1990), 39% (1990-2000), 38% (2000-2010), and 11% (2010-2019), mostly at the expense of agricultural land. The forecast for new power network users by 2050 yields a result of 203,630 total users with a population density of 4850 people/km2. The conclusion is that this type of analysis can help city planners and decision makers further understand city and infrastructure growth dynamics and produce policies that bolster sustainable city growth. © 2020 by the authors.

View
No Thumbnail Available
Publication

Vortex Optimization of a Low-Head Gravity Hydroelectric Power Plant

2022 , Ayala-Chauvin, Manuel Ignacio , Rojas-Asuero H. , Riba-Sanmartí G. , Ramón-Campoverde J.

Gravitational Water Vortex Power Plant (GWVPP) is a Small-Scale Hydropower System which converts energy in a moving fluid to rotational energy. The main advantage of this technology is the low head hydraulic requirements. The aim of this work is to optimize the hydraulic geometry of the vortex, to achieve this, two prototypes (A and B) were designed and built to validate the proposed design process. The prototype A has a flat-bottom chamber and prototype B has a conical chamber outlet; both induce spiraling fluid streamlines. Prototypes were studied numerically and experimentally. The numerical study was developed in ANSYS CFX R19.0 software and the experimental phase was carried out in the fluid’s laboratory of the Technical University of Loja in Ecuador. The results show that the conical chamber improves strong free-surface vortex formation and increases water velocity in the center of the vortex flow. Finally, the proposed design method was validated and allows to reproduce the hydraulic structures of the gravity water vortex power plant. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

View
No Thumbnail Available
Publication

Evaluation of Accessibility on the PAR Platform from the Perspective of Physicians

2024 , Patricia Acosta-Vargas , Gloria Acosta-Vargas , Marco Santórum , Mayra Carrión-Toro , Ayala-Chauvin, Manuel Ignacio , Verónica Maldonado-Garcés , Mario Gonzalez-Rodriguez

View
No Thumbnail Available
Publication

Static reactive power compensator design, based on three-phase voltage converter

2021 , Ayala-Chauvin, Manuel Ignacio , Kavrakov B.S. , Buele, Jorge , Varela Aldas, José

At present, electrical network stability is of the utmost importance because of the increase in electric demand and the integration of distributed generation deriving from renewable energy. In this paper, we proposed a static reactive power compensator model with common direct current voltage sources. Converter parameters were calculated and designed to fulfill specifications. In order to ascertain the device response for different operating modes as reactive power consumer and generator, we developed the model’s power and control circuits in Matlab Simulink. Simulations were performed for different conditions, and as a result, the current and voltage waveforms and the circular power chart were obtained. This paper has theoretically proven it is possible to achieve the consumption or generation of purely active or reactive power by implementing a static reactive power compensator with common DC voltage sources. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

View
No Thumbnail Available
Publication

Big Data as a Tool for Analyzing Academic Performance in Education

2024 , Ayala-Chauvin, Manuel Ignacio , Chucuri-Real B. , ESCUDERO VILLA, PEDRO FERNANDO , Buele, Jorge

Educational processes are constantly evolving and need upgrading according to the needs of the students. Every day an immense amount of data is generated that could be used to understand children’s behavior. This research proposes using three machine learning algorithms to evaluate academic performance. After debugging and organizing the information, the respective analysis is carried out. Data from eight academic cycles (2014–2021) of an elementary school are used to train the models. The algorithms used were Random Trees, Logistic Regression, and Support Vector Machines, with an accuracy of 93.48%, 96.86%, and 97.1%, respectively. This last algorithm was used to predict the grades of a new group of students, highlighting that most students will have acceptable grades and none with a grade lower than 7/10. Thus, it can be corroborated that the daily stored data of an elementary school is sufficient to predict the academic performance of its students using computational algorithms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

View
No Thumbnail Available
Publication

Predicting Academic Performance in Mathematics Using Machine Learning Algorithms

2022 , Espinosa Pinos, Carlos Alberto , Ayala-Chauvin, Manuel Ignacio , Buele, Jorge

Several factors, directly and indirectly, influence students’ performance in their various activities. Children and adolescents in the education process generate enormous data that could be analyzed to promote changes in current educational models. Therefore, this study proposes using machine learning algorithms to evaluate the variables influencing mathematics achievement. Three models were developed to identify behavioral patterns such as passing or failing achievement. On the one hand, numerical variables such as grades in exams of other subjects or entrance to higher education and categorical variables such as institution financing, student’s ethnicity, and gender, among others, are analyzed. The methodology applied was based on CRISP-DM, starting with the debugging of the database with the support of the Python library, Sklearn. The algorithms used are Decision Tree (DT), Naive Bayes (NB), and Random Forest (RF), the last one being the best, with 92% accuracy, 98% recall, and 97% recovery. As mentioned above, the attributes that best contribute to the model are the entrance exam score for higher education, grade exam, and achievement scores in linguistic, scientific, and social studies domains. This confirms the existence of data that help to develop models that can be used to improve curricula and regional education regulations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Modeling of Electric Vehicle Energy Demand: A Big Data Approach to Energy Planning

2025 , Iván Sánchez-Loor , Ayala-Chauvin, Manuel Ignacio

The rapid expansion of electric vehicles in high-altitude Andean cities, such as the Metropolitan District of Quito, Ecuador’s capital, presents unique challenges for electrical infrastructure planning, necessitating advanced methodologies that capture behavioral heterogeneity and mass synchronization effects in high-penetration scenarios. This study introduces a hybrid approach that combines agent-based modelling with Monte Carlo simulation and a TimescaleDB architecture project charging demand with quarter-hour resolution through 2040. The model calibration deployed real-world data from 764 charging points collected over 30 months, which generated 2.1 million charging sessions. A dynamic coincidence factor (FC=0.222+0.036∗e(−0.0003n)) was incorporated, resulting in a 52% reduction in demand overestimation compared to traditional models. The results for the 2040 project show a peak demand of 255 MW (95% CI: 240–270 MW) and an annual consumption of 800 GWh. These findings reveal that non-optimized time-of-use tariffs can generate a critical “cliff effect,” increasing peak demand by 32%, whereas smart charging management with randomization reduces it by 18 ± 2.5%. Model validation yields a MAPE of 4.2 ± 0.8% and an RMSE of 12.3 MW. The TimescaleDB architecture demonstrated processing speeds of 2398.7 records/second and achieved 91% data compression. This methodology offers robust tools for urban energy planning and demand-side management policy optimization in high-altitude contexts, with the source code available to ensure reproducibility.

View
No Thumbnail Available
Publication

Evolution, Collaborations, and Impacts of Big Data Research in Ecuador: Bibliometric Analysis

2024 , Avilés-Castillo, Fátima , Ayala-Chauvin, Manuel Ignacio , Buele J.

Big Data has been gaining significant attention globally due to its potential to drive innovation, guide decision-making, and stimulate economic growth. As part of this global trend, Ecuador has also witnessed a surge in Big Data-related research over the past decade. This study comprehensively analyzes Big Data research evolution, collaborations, and impacts in Ecuador from 2012 to 2023. By examining the patterns of publication, researcher demographics, primary languages, significant publishers, most cited research papers, patterns of author collaboration, and prevalent keywords, we strive to construct a detailed portrayal of the Big Data research landscape in the country. Our investigation reveals a noticeable increase in Big Data research activity post-2015, particularly within major cities like Quito and Guayaquil. Notably, the study also underscores the predominance of English in research publications, with leading publishers such as IEEE and Springer playing significant roles. The diverse themes of the most cited articles illustrate the wide-ranging applications of Big Data research within the country. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View