Cumbajín Alferez, Myriam

Preferred name

Main Affiliation

Facultad de Arquitectura, Diseño y Artes

Ambato

myriamcumbajin@uti.edu.ec

ORCID

0000-0001-9993-7095

Scopus Author ID

57198450868

Now showing 1 - 10 of 21

Some of the metrics are blocked by your
consent settings
Improving PV Power Prediction Based on GRU and Meteorological Factors
(2026)
Cumbajín Alferez, Myriam
;
Ruxandra Stoean
;
José Aguado
;
Gonzalo Joya
The gradual integration of renewable solar energy sources represents a major step toward sustainability, which is why the main objective of this study is to design an optimized GRU architecture for hourly prediction of photovoltaic generation, considering both single-step and multi-step forecasting. A recurrent neural network with a four-layer GRU structure was implemented, selected after a comparative validation process in which different depths were evaluated. This configuration balanced accuracy, stability, and generalization capacity, improving the model’s ability to capture complex relationships between the endogenous variable (photovoltaic generation) and a set of eight exogenous meteorological variables. This architecture proved robust to different sets of predictors, maintaining consistent performance under different input configurations. The result is a reliable prediction and forecast error for a power generation system with meteorological factors typical of Ibarra, Ecuador. Among the evaluation metrics used, the mean square error decreased by 19.61% and 23.69% for single-step prediction and multi-step forecasting, respectively. Therefore, the GRU model has managed to reduce the error by a moderate percentage, with a significant difference, supported by the evaluation metrics and the Wilcoxon-Mann-Whitney U test, it was possible to reduce the error obtaining a p-value less than 0.05, which represents that the data groups without meteorological factors and the data groups with meteorological factors are statistically different and therefore the error reduction is significant. Through this, it is demonstrated that including eight exogenous attributes reduces prediction and forecasting errors
27
Some of the metrics are blocked by your
consent settings
Biosignal Monitoring System Through an Interface to Optimize People’s Emotional Well-Being
(2025)
Kevin Gamboa
;
Dario Guaman
;
Carlos Gordon
;
Myriam Cumbajin
This document presents the development of a Node-RED application with an interactive graphical interface for the visualization of emotional biosignals, allowing users to monitor and analyze their emotional state. The objective is to record relevant information on the implementation of algorithms in real time and the integration of sensors such as the MAX30100 and AD8232 ECG, together with an ESP32 and electrodes to take the samples, in order to identify emotional patterns using predefined thresholds. The aim is to optimize the efficiency of the system by improving biosignal transmission algorithms, minimizing resource consumption, and guaranteeing fast and fluid visualization of emotions on OLED screens, to improve the overall user experience. In this study, a methodology divided into four phases was used: research, development, integration, and optimization. Once the application was implemented, the results obtained in the identification of emotional patterns were compared and the algorithms that offered the best performance were optimized. Finally, an intuitive graphical interface was created in Node-RED that allows users to efficiently visualize and monitor their emotional biosignals, functioning as a tool to optimize people’s emotional well-being.
10
Some of the metrics are blocked by your
consent settings
Smart Antenna Array for Optimal Electromagnetic Energy Capture
(2023)
Cumbajín Alferez, Myriam
;
Sánchez, Patricio
;
Escobar E.
;
Gordón C.
Smart antennas are currently one of the most exploited fields in terms of wireless networks, allowing high data transmission capacities, this is achieved by focusing the radiation on the desired direction and adjusting to the environment and conditions in which communications are developed. Smart antennas employ a set of radiating and emitting and combining elements organized in the form of arrangements connected at a common point to guarantee the required power, the signals from these elements are combined to form a moving beam pattern that follows a pattern determined by the user or designer. The consumption of energy within communication systems is considered a big problem and a challenge when carrying out implementations in media where the storage or recharging of the end terminals is complicated by their location, this trend grows with the presence of the Internet of the IoT things, where it is directly dependent on the construction of a large wireless network that allows everything to be interconnected, for this reason there are investigations in the 2.4 and 5.8 GHz bands and represents future work for the 5th Generation (5G) cell phone. The great possibility of collecting electromagnetic energy from densely populated urban areas becomes a great renewable source of power for communication devices for both existing Wi-Fi technology and new technologies such as the 5G network. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
22
Some of the metrics are blocked by your
consent settings
Rectenna Patch-Type Array for Capture of Electromagnetic Energy
(2024)
Cumbajín Alferez, Myriam
;
Sánchez, Patricio
;
Fausto Tello
;
Carlos Gordón
This research project is focused on gathering information on rectennas, as well as on patch antenna arrays for Energy Harvesting Systems designed at frequencies up to 3 Ghz, in addition to a simulation and implementation of a rectenna consisting of elements and technology suitable for electromagnetic energy harvesting systems; and at the same time analyze the results obtained from the tests carried out in order to demonstrate its efficiency in the aforementioned systems. The design of this prototype was made in Ansys HFSS software, which allowed us to make a 2×2 array of rectangular patch antennas, in which λ/4 transformers are used to couple the transmission lines to a characteristic impedance of 50 Ω; at the same time the design of a multiplier and voltage rectifier for high frequencies is also performed, in this case for 2.4 Ghz; in such a way that by joining the antenna array with the rectifier, a useful rectenna for electromagnetic energy collection is obtained.
11
Some of the metrics are blocked by your
consent settings
Low-Cost Signal Generator: Design and Implementation
(2025)
Sharon Solano
;
Kevin Diaz
;
Carlos Gordon
;
Cumbajín Alferez, Myriam
This document meticulously details the design and implementation process of a Low-Cost Signal Generator using the AD9833 module. This device can generate sinusoidal, triangular, and square signals with a high degree of precision, making it ideal for applications in electronics laboratories and educational projects. The methodology employed is divided into four main stages: circuit design, simulation, fabrication, and characterization tests of the signal generator. Operational tests demonstrated that the generator meets the design specifications, producing stable signals in a frequency range of 0.1 Hz to 12.5 MHz. The features of the AD9833 module allow for flexible configuration of waveforms and frequencies, facilitating its use in various testing and development applications. This work was developed to provide a solid foundation for the creation of economical and efficient signal generators, thus contributing to the accessibility of advanced tools in educational and research environments.
29
Some of the metrics are blocked by your
consent settings
Machine Learning Algorithms for Filtering Data Acquired by Arduino
(2024)
Mateo Llerena
;
Jessica López
;
Cumbajín Alferez, Myriam
;
Carlos Gordón
In this paper, we developed an artificial intelligence-based data filtering algorithm to improve the accuracy and reliability of MPU6050 sensor measurements. Using the Edge Impulse platform, we trained and optimized the machine learning model for real-time processing of accelerometer and gyroscope readings. The solution was implemented on the ESP32 with a sampling rate of 600 Hz. The experimental results validated the effectiveness of the solution, highlighting its relevance in applications requiring real-time monitoring
10
Some of the metrics are blocked by your
consent settings
Absorber length optimization of on-chip colliding pulse mode-locked semiconductor laser
(2018)
Gordon C.
;
Cumbajín Alferez, Myriam
;
Carpintero G.
;
Bente E.
;
Javaloyes J.
We present theoretical and experimental results regarding the saturable absorber length optimization for the generation of stable mode-locked regimes of a novel on-chip colliding pulse mode-locked semiconductor laser structure. We have been able to apply the design criteria acquired from previous theoretical and experimental reports to define a suitable gain section length for a given saturable absorber section length. The latter is independent from the cavity length and allows obtaining stable mode-locked regimes with the required repetition rate and pulse width in the range of picoseconds for different applications. We have developed four on-chip colliding pulse mode-locked laser structures with saturable absorber lengths ranging from 20 to 50 μm in steps of 10 μm with fundamental repetition rate at 25 GHz and twice this frequency at 50 GHz when operated in the colliding pulse mode-locked regime. The theoretical study was carried out by using the simulation tool called FreeTWM which is a free travelling wave model software designed for the study of the dynamics of multisection semiconductor lasers, while the experimental analysis was executed on the samples fabricated on a generic InP photonic integrated technology through a multi-project wafer run. © 1995-2012 IEEE.
Scopus© Citations 5 27
Some of the metrics are blocked by your
consent settings
Integration of renewable energies in conventional power systems based on computational reliability
(2019)
Cumbajín Alferez, Myriam
;
Ramírez L.
;
Gordón C.
We report the successful computational reliability of integrating renewable energy into conventional electric power systems. According to renewable resources available in the province of Imbabura in Ecuador, where there are sufficient renewable resources to generate clean energy with three types of technology, such as wind energy, photovoltaic solar energy and thermoelectric energy. We have been able to conduct two fundamental case studies, and then calculate reliability indices using the non-sequential Monte Carlo method using Matlab programming. The reliability indices allowed us to evaluate the reliability of the system. Due to the fact that the lower the reliability index, the higher the reliability of the system. As a result, this paper provides a promising method for increasing the reliability of electric power systems and supporting the future integration of renewable energies. © 2019, Associacao Iberica de Sistemas e Tecnologias de Informacao. All rights reserved.
23
Some of the metrics are blocked by your
consent settings
Reverse Engineering for the Ecowitt WS90 Weather Station
(2026)
Cumbajín Alferez, Myriam
This article presents a comprehensive reverse engineering study applied to the Ecowitt WS90 weather station, a self-contained device designed to collect essential environmental data such as temperature, humidity, wind direction and speed, light and UV radiation levels, and precipitation. The main objective of this work is to gain a deep understanding of the internal workings of the weather station through meticulous analysis of its hardware and software components. The methods used are described in detail, including careful disassembly of the device, precise identification of key components, and scanning and disassembling the embedded firmware. Additionally, significant challenges encountered during the rigorous reverse engineering process are discussed and possible improvements or modifications to the original design based on the findings are proposed. The results obtained in this study provide an unprecedented insight into the internal workings of the Ecowitt WS90 weather station, contributing to a deeper understanding of environmental monitoring systems in general. The detailed findings presented in this article can be very useful for future developments and advances in the field of environmental monitoring, by facilitating the optimization of existing devices or the design of new innovative solutions. Furthermore, this work lays the foundation for future research and more specialized studies in the area of reverse engineering applied to environmental data acquisition systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
3
Some of the metrics are blocked by your
consent settings
Convolutional neural network oriented to the gesticulation control of an interactive social robot with humanoid aspect [Red neuronal convolucional orientado a la gesticulación de un robot social interactivo con aspecto humanoide]
(2019)
Arias E.
;
Encalada P.
;
García M.
;
Granizo C.
;
Tigre F.
Social robots present the boom of an infinity of investigations in terms of design and control, these in turn approach with greater intensity to be our partners at home or work, however, still lack similar social interaction skills to the human being. This paper presents the implementation of a convolutional neuronal network algorithm aimed at the arrest of emotions for decision-making in the gesticulation of the social robot with a humanoid appearance. In addition, emphasis is placed on the use of visemas as a unit of labial movement for improve the human-robot interaction in any field in which the social robot can be used, be it teaching, therapies, safe navigation, etc., simultaneously coordinating and similar to the human naturalness the movement of servomechanisms of the mouth and the synthesized audio of the text that the robot gives in response. © 2019, Associacao Iberica de Sistemas e Tecnologias de Informacao. All rights reserved.
22

Cumbajín Alferez, Myriam

Filters

Settings

Sort By

Results per page