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

44
Reset filters

Settings
Now showing 1 - 10 of 44
No Thumbnail Available
Publication

Power Flow Optimization in Electrical Networks using Gekko

2025 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo, Fátima , Carles Riba Romevá

La optimización del flujo de potencia en la red eléctrica es fundamental para mejorar la estabilidad y el desempeño de los sistemas de energía. El principal desafío reside en encontrar una distribución óptima de la generación de potencia que cumpla con las restricciones impuestas por la red, tales como los límites de voltaje y las condiciones de estabilidad del sistema eléctrico. El objetivo de esta investigación fue evaluar el desempeño de Gekko en la optimización del flujo de potencia en redes eléctricas. Para ello, se realizó una comparación con SciPy, un marco de referencia ampliamente utilizado en optimización numérica, con el fin de evaluar su eficiencia relativa en problemas con restricciones complejas. La comparación se basa en métricas como precisión de la solución, velocidad de convergencia y número de evaluaciones de la función objetivo. Los resultados mostraron que ambos métodos lograron el mismo valor objetivo: SciPy (19,7) y Gekko (19,7). Sin embargo, SciPy fue ligeramente más rápido (0,01496 segundos frente a 0,0191 segundos), pero requirió 60 evaluaciones de la función objetivo. En contraste, Gekko demostró mayor eficiencia computacional, reduciendo la cantidad de evaluaciones necesarias para la convergencia. Aunque SciPy es más eficiente en problemas pequeños con restricciones explícitas, Gekko ofrece mayor flexibilidad en problemas con restricciones más complejas, lo que lo hace más adecuado para sistemas eléctricos de mayor envergadura.

View
No Thumbnail Available
Publication

Optimizing Natural Language Processing: A Comparative Analysis of GPT-3.5, GPT-4, and GPT-4o

2024 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo, Fátima

In the last decade, the advancement of artificial intelligence has transformed multiple sectors, with natural language processing standing out as one of the most dynamic and promising areas. This study focused on comparing the GPT-3.5, GPT-4 and GPT-4o language models, evaluating their efficiency and performance in Natural Language Processing tasks such as text generation, machine translation and sentiment analysis. Using a controlled experimental design, the response speed and quality of the outputs generated by each model were measured. The results showed that GPT-4o significantly outperforms GPT-4 in terms of speed, completing tasks 25% faster in text generation and 20% faster in translation. In sentiment analysis, GPT-4o was 30% faster than GPT-4. Additionally, analysis of response quality, assessed using human reviews, showed that while GPT-3.5 delivers fast and consistent responses, GPT-4 and GPT-4o produce higher quality and more de-tailed content. The findings suggest that GPT-4o is ideal for applications that require speed and consistency, while GPT-4, although slower, might be preferred in contexts where text accuracy and quality are important. This study highlights the need to balance efficiency and quality in the selection of language models and suggests implementing additional automatic evaluations in future research to complement the current findings.

View
No Thumbnail Available
Publication

Towards Smart Agriculture: An Overview of Big Data in the Agricultural Industry

2025 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo, Fátima

Agriculture is currently undergoing progressive diversification and expansion, as demonstrated by the wide range of research topics and methodologies being employed. The growing need for technology to enhance agricultural processes is increasingly evident and prominently highlighted in recent studies. To assess the influence of Big Data on agriculture and its potential to advance Smart Agriculture, this bibliometric study was conducted. The research consolidates bibliometric data from the Scopus database, using the Bibliometrix package to identify trends in this field. The findings show a growing annual publication rate, indicating increasing interest in the integration of data analysis methodologies within agriculture. The collaborative nature of the research, combined with a high citation rate per document and diversity of key terms, underscores the importance of this field and its potential contribution to achieving Smart Agriculture. The convergence of Big Data, the Internet of Things, and agriculture is particularly noteworthy, as these technologies are improving decision-making and efficiency in the agricultural sector. Despite certain limitations, this study highlights the transformative potential of these advancements and suggests areas for future research, thus laying the groundwork for a more sustainable, productive, and intelligent agricultural future.

View
No Thumbnail Available
Publication

Predictive Maintenance in Industrial Robotics Using Big Data: Techniques, Challenges, and Opportunities

2024 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo, Fátima , Dayanara Yánez-Arcos , Buele, Jorge

In industrial robotics, predictive maintenance is important to improve efficiency and reduce costs, addressing early detection and diagnosis of failures. The use of Big Data allows us to identify patterns and trends that at first glance are complex. This review examines research on the application of big data in predictive maintenance of industrial robots, which use advanced techniques such as cloud-based architectures, filtering algorithms, and machine learning. The review methodology included an analysis of the big data techniques used, the challenges identified, and the opportunities presented. The results show significant improvements in the accuracy of predictions and fault diagnoses. Key anomaly drivers were identified that improved production performance and enabled accurate fault identification and reduced downtime in industrial robots. Despite the benefits, challenges remain in data security and communications latency, underscoring the need to develop innovative algorithms and techniques to balance computing load and minimize delays. The continuous evolution of these techniques promises to improve the failure management capacity in industrial robotics, thus optimizing the operability and efficiency of robotic systems.

View
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

Data Analysis for Performance Improvement of University Students Using IoT

2024 , Ayala-Chauvin, Manuel Ignacio , Lara-Álvarez P. , Castro R.

Using Internet of Things (IoT) devices and data analysis techniques can potentially transform how universities approach improving student achievement. In this sense, the project is based on implementing a remotely operated pneumatic bank applying IoT for university education. With this technology, it is possible to obtain information about the factors that impact student achievement and design targeted interventions to help students improve their performance. The control system with low-cost technology was developed with Raspberry Pi, AnyDesk, and Canvas LMS for the remote connection. The experiment was carried out with two groups of 7 people, and it was identified that there are correlations of 0.87 and 0.62 between the performance of the students and the time they dedicate to studying and the hours they spend on the platform; this suggests a positive correlation between these variables. Therefore, as students spend more time studying and spending more hours on the platform, they are more likely to achieve better academic results. On the other hand, the study time of the group of students who used the bank remotely increased by 32% compared to those who used the bank in person; therefore, we can infer that with the implementation of the IoT, the use of the system is encouraged. Finally, based on the insights gained from the analysis, targeted interventions can be designed to help students improve their academic performance. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View
No Thumbnail Available
Publication

Web-based pulmonary telehabilitation: a systematic review

2024 , Ayala-Chauvin, Manuel Ignacio , Chicaiza Claudio, Fernando , Patricia Acosta-Vargas , Jadán Guerrero, Janio , Verónica Maldonado-Garcés , Esteban Ortiz-Prado , Gloria Acosta-Vargas , Mayra Carrión-Toro , Marco Santórum , Mario Gonzalez-Rodriguez , Camila Madera , Wilmer Esparza

Web-based pulmonary telerehabilitation (WBPTR) can serve as a valuable tool when access to conventional care is limited. This review assesses a series of studies that explore pulmonary telerehabilitation programmes delivered via web-based platforms. The studies involved participants with moderate to severe chronic obstructive pulmonary disease (COPD). Of the 3190 participants, 1697 engaged in WBPTR platforms, while the remaining 1493 comprised the control groups. Sixteen studies were included in the meta-analysis. Web-based pulmonary telerehabilitation led to an increase in daily step count (MD 446.66, 95% CI 96.47 to 796.86), though this did not meet the minimum clinically important difference. Additionally, WBPTR did not yield significant improvements in the six-minute walking test (MD 5.01, 95% CI − 5.19 to 15.21), health-related quality of life as measured by the St. George’s Respiratory Questionnaire (MD − 0.15, 95% CI − 2.24 to 1.95), or the Chronic Respiratory Disease Questionnaire (MD 0.17, 95% CI − 0.13 to 0.46). Moreover, there was no significant improvement in dyspnoea-related health status, as assessed by the Chronic Respiratory Disease Questionnaire (MD − 0.01, 95% CI − 0.29 to 0.27) or the modified Medical Research Council Dyspnoea Scale (MD − 0.14, 95% CI − 0.43 to 0.14). Based on these findings, this review concludes that WBPTR does not offer substantial advantages over traditional care. While slight improvements in exercise performance were observed, no meaningful enhancements were noted in dyspnoea or quality of life metrics. Overall, WBPTR remains a complementary and accessible option for managing and monitoring COPD patients. However, further research and innovation are required to improve its efficacy and adapt it to various clinical environments.

View
No Thumbnail Available
Publication

Exploring the Landscape of Data Analysis: A Review of Its Application and Impact in Ecuador

2023 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo F. , Buele, Jorge

Latin America has shown increased big data adoption since 2012; Ecuador is now entering this transformative field. Science and engineering in Ecuador have benefited most from data analysis, with untapped potential in health and services sectors. Big data is shaping sectors in Ecuador, including disaster prediction, agriculture, smart city development, and electoral data analysis. Despite public sector inefficiencies, residential ICT adoption provides opportunities for Ecuador’s smart city advancements. Despite some data underutilization, big data’s transformative potential is evident in Ecuador’s healthcare and education advancements. Highlights: Data analysis is increasingly critical in aiding decision-making within public and private institutions. This paper scrutinizes the status quo of big data and data analysis and its applications within Ecuador, focusing on its societal, educational, and industrial impact. A detailed literature review was conducted from academic databases such as SpringerLink, Scopus, IEEE Xplore, Web of Science, and ACM, incorporating research from inception until May 2023. The search process adhered to the PRISMA statement, employing specific inclusion and exclusion criteria. The analysis revealed that data implementation in Ecuador, while recent, has found noteworthy applications in six principal areas, classified using ISCED: education, science, engineering, health, social, and services. In the scientific and engineering sectors, big data has notably contributed to disaster mitigation and optimizing resource allocation in smart cities. Its application in the social sector has fortified cybersecurity and election data integrity, while in services, it has enhanced residential ICT adoption and urban planning. Health sector applications are emerging, particularly in disease prediction and patient monitoring. Educational applications predominantly involve student performance analysis and curricular evaluation. This review emphasizes that while big data’s potential is being gradually realized in Ecuador, further research, data security measures, and institutional interoperability are required to fully leverage its benefits. © 2023 by the authors.

View
No Thumbnail Available
Publication

IoT Monitoring to Control a Bicycle Parking Lot

2022 , Ruales, María Belén , Lara-Alvarez P. , Riba C. , Ayala-Chauvin, Manuel Ignacio

In recent years, the development of new technologies has improved the management of resources and services at the urban level. In this sense, several cities worldwide have developed intelligent infrastructures such as Smart Cities in which, through data collection and management, they aim to achieve social, environmental and economic improvements. Innovative bike racks are a promising solution to traffic-related problems in major cities around the world; however, there is a lack of low-cost solutions for controlling and monitoring bike racks and thus boosting the mobility of cyclists. This paper presents a system to monitor and control a bicycle parking lot. In order to achieve this goal, software and hardware specifications were defined and characterised by the control system. The conceptual design and detail of the prototype and the materialisation proceeded, where technology with ESP8266 microcontrollers and Raspberry Pi+Ethernet/WiFi microprocessors was used in the MQTT communication protocol to implement its architecture. The system implements in the bicycle parking lot of the Universidad Tecnológica Indoamérica. The series of data collected allowed for determining the frequency of use. With this, a database creates where the information on the frequency of use of bicycles is stored. Finally, through a mobile application, the availability of parking spaces can be consulted, and bikes in the parking lot can monitor. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

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