Person:
Peña Ortega, Mario Patricio

Birth Date

1987-12-26

ORCID

0000-0002-3986-7707

Scopus Author ID

57202190504

Afiliación

Universidad de Cuenca, Cuenca, Ecuador
Universidad de Cuenca, Facultad de Ciencias Químicas, Cuenca, Ecuador

País

Ecuador

Organizational Units

Organizational Unit

Facultad de Ciencias Químicas

Fundada en 1955 como la Escuela de Química Industrial, la facultad ha sido un pilar fundamental en la formación de profesionales altamente capacitados, comprometidos con el desarrollo de la ciencia, la educación y el bienestar social. La Facultad de Ciencias Químicas pone a consideración su trabajo académico, investigativo y de vinculación con la sociedad, desarrollado a través de la práctica de una docencia de calidad, investigación e innovación en su área de estudio. Desde su oficio de conocimiento se permite contribuir a la sociedad con cuatro carreras: Bioquímica y Farmacia, Ingeniería Química, Ingeniería Ambiental e Ingeniería Industrial. Su carta de presentación en la Academia, la coloca como una dependencia dinámica, donde confluye la solidez de una trayectoria de más de sesenta años. Aquí se trabaja en una continua formación de pregrado y posgrado de la más alta calidad, mediante la mejora continua con la innovación y a la vanguardia de las ciencias químicas.

Job Title

Profesor (T)

Last Name

Peña Ortega

First Name

Mario Patricio

Full item page

Search Results

Now showing 1 - 10 of 28

Red neuronal para clasificación de riesgo en cooperativas de ahorro y crédito
(UNIVERSIDAD DE LAS FUERZAS ARMADAS ESPE, 2018) Peña Ortega, Mario Patricio; Orellana Parapi, Jose Miguel; Peña Ortega, Mario Patricio
In Ecuador exists a great number of credit unions (COAC) specifically 852, which are divided into 5 segments depending on their amount of assets. Nowadays, 66% of the microcredit obtained within the country corresponds to the cooperative system. Nevertheless, just 35 of 58 COAC (segments 1 and 2) present risk rating histories. The purpose of this research is create a neural network that achieves an acceptable percentage of accuracy, to classify a COAC within a scale of risk based on the value of its financial indexes; in order to helping the early detection of future problems. The artificial neural network (ANN) was fitted from data obtained through the Public and solidary economy Superintendence for COAC that presented a high index of assets. In addition, the history of quarterly risk ratings generated by rating agencies in the same period was used: January 2015 - September 2017. An ANN with a classification accuracy of 79.59% was obtained, percentage that is within the range of precision obtained by studies reviewed for classification activities in financial entities. The classification results could be further improved with the use of a hierarchical classification structure.
Anova and cluster distance based contributions for feature empirical analysis to fault diagnosis in rotating machinery
(Institute of Electrical and Electronics Engineers, 2017) Peña Ortega, Mario Patricio; Álvarez Palomeque, Lourdes Ximena; Jadán Avilés, Diana Carolina; Lucero, Pablo; Barragán Landy, Milton Francisco; Guamán Guachichullca, Noé Rodrigo; Cerrada Lozada, Mariela; Peña Ortega, Mario Patricio
The number of extracted features for fault diagnosis in rotating machinery can grow considerably due to the large amount of available data collected from different monitored signals. Usually, feature selection or reduction are conducted through several techniques proposing a unique set of representative features for all available classes; nevertheless, in feature selection, it has been recognized that a set of individually good features do not necessarily lead to good classification. This paper proposes a general framework to analyse the feature selection oriented to identify the features that can produce clusters of data with a proper structure. In the first stage, the framework uses Analysis of Variance (ANOVA) combined with Tukey's test for ranking the significant features individually. In the second stage, a further analysis based on inter-cluster and intra-cluster distances, is accomplished to rank subsets of significant features previously identified. In this sense, our contribution aims at discovering the subset of features that are discriminating better the clusters of data associated to several faulty conditions of the mechanical devices, to build more robust fault multi-classifiers. Fault severity classification in rolling bearings is studied to test the proposed framework, with data collected from an experimental test bed under real conditions of speed and load on the rotating device. © 2017 IEEE.
A Methodological Framework for Creating Large-Scale Corpus for Natural Language Processing Models
(Springer, 2021) Santos Leon, David Enrique; Auquilla Sangolquí, Andrés Vinicio; Sigüenza Guzmán, Lorena Catalina; Peña Ortega, Mario Patricio; Santos Leon, David Enrique
Currently, there is a boom in introducing Machine Learning models to various aspects of everyday life. A relevant field consists of Natural Language Processing (NLP) that seeks to model human language. A key and basic component for these models to learn properly consists of the data. This article proposes a methodological framework for constructing a large-scale corpus to feed NLP models. The development of this framework emerges from the problem of finding inputs in languages other than English to feed NLP models. With an approach focused on producing a high-quality resource, the construction phases were designed along with the considerations that must be taken. The stages implemented consist of the corpus characterization to be obtained, collecting documents, cleaning, translation, storage, and evaluation. The proposed approach implemented automatic translators to take advantage of the vast amount of English literature and implemented through non-cost libraries. Finally, a case study was developed, resulting in a corpus in Spanish with more than 170,000 documents within a specific domain, i.e., opinions on textile products. Through the evaluations carried out, it is established that the proposed framework can build a large-scale and high-quality corpus.
Key performance indicators for the supply chain in small and medium sized enterprises based on balance score card
(2020) Llivisaca Villazhañay, Juan Carlos; Jadán Avilés, Diana Carolina; Guamán Guachichullca, Noé Rodrigo; Arcentales Carrión, Rodrigo Nicanor; Peña Ortega, Mario Patricio; Sigüenza Guzmán, Lorena Catalina
A supply chain is a network of interaction between different actors, and indi-cators govern its behavior. The current research deals with the analysis and ranking of critical indicators for the supply chain in small and medium-sized enterprises (SMEs). To this end, firstly, a systematic review of supply chain management indicators for SMEs was carried out. Using data sources such as Scopus, ProQuest, and Google Scholar, 189 metrics were selected. Then, through practical and methodological filters, this number was reduced to 149. To organize these indicators, both models, the Balanced Scorecard (BSC) and the Supply Chain Operations Reference (SCOR-model), were used to connect company strategies to their performance. Secondly, these measures formed part of a questionnaire answered by 30 SME experts. From their responses, critical indicators were evaluated through Principal Component Analysis (PCA), resulting in 50 key indicators. Finally, these indicators were ranked using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). For SCM in SMEs, findings indicate that the primary key perfor-mance indicators (KPIs) are cash flow, satisfaction rate, inventory rotation, and exchange of information through the supply chain.
Optimization models used in the textile sector: a systematic review
(Springer Science and Business Media Deutschland GmbH, 2022) Llivisaca Villazhañay, Juan Carlos; Veintimilla Reyes, Jaime Eduardo; Sigüenza Guzmán, Lorena Catalina; Torres Torres, Christian Marcelo; Toledo Illescas, María Belén; Peña Ortega, Mario Patricio
In recent years, several works have been published dedicated to obtaining optimization models. Many of them have been applied in the textile sector because they are part of the economic development areas of a country. This article’s main objective is to review the literature published on optimization models and understand what methods their authors used to solve the optimization problems in the textile sector. A systematic methodology was applied to select research questions, digital databases, and search terms to utilize practical and methodological filters later to carry out this systematic review. This procedure allowed performing a review and synthesis of the results obtained on the optimization models. It was found that the models resulting from the systematic review vary depending on the areas to be optimized. The most frequent applications were logistics and production, followed by cost minimization. They were optimized mainly with linear programming, integer programming, Markov chains, genetic algorithms, and multi-objective programming
Demand forecasting for textile products using machine learning methods
(Springer International Publishing, 2022) Medina Samaniego, Héctor Wilfrido; Sigüenza Guzmán, Lorena Catalina; Peña Ortega, Mario Patricio; Guamán Guachichullca, Noé Rodrigo
Due to its close relationship with various operational decisions, market demand forecasting has been considered one of the essential activities in all organizations. Unfortunately, the textile industry has been the most difficulty generating forecasts, mainly due to the volatility caused in the market by short product life cycles, special events, and competitions. From the beginning, forecasting has been using traditional statistical methods. However, the increasing use of artificial intelligence has opened a new catalog of prediction methods currently being studied for their high precision. This study explores machine learning (ML) as a tool to generate forecasts for the textile industry, applying regression-focused algorithms such as Linear Regression, Ridge, Lasso, K-nearest neighbor, Support Vector Regression (SVR), and Random Forest (RF). To this end, time series were used as inputs for the models, supported by external variables such as Google Trends and special events. The results show that ML as a prediction method has higher precision than purely statistical basic prediction models
New hybrid algorithm for supply chain optimization
(Springer, Cham, 2021) Cevallos Tapia, Carlos Patricio; Peña Ortega, Mario Patricio; Sigüenza Guzmán, Lorena Catalina; Sigüenza Guzmán, Lorena Catalina
Optimization is the process of obtaining the best solutions to specific problems. In the literature, those problems have been optimized through a plethora of algorithms. However, these algorithms have many advantages but also disadvantages. In this article, a New Hybrid Algorithm for Supply Chain Optimization, NHA-SCO has been proposed in order to improve the benefits of objective function convergence. For the analysis of the results, three assembly companies have been utilized as case studies. These companies present their supply chains, i.e., networks where products flow from their raw material to the final products delivered to clients. These supply chains must satisfy different objectives, such as maximize benefits and service level and minimize scrap. For the evaluation of results, NHA-SCO has been compared to other well-known optimization algorithms. In the presented case studies, the NHA-SCO algorithm performs faster, or it converges in fewer iterations, obtaining similar or even better results than the other algorithms tested.
Learning analytics, dashboard for academic trajectory
(CEUR-WSceurws@sunsite.informatik.rwth-aachen.de, 2019) Peña Ortega, Mario Patricio; Illescas Peña, Lourdes Eugenia; Bravo Guerrero, Fabián Eugenio
© 2019 CEUR-WS. All rights reserved. In the context of university academic management, several proposals have been developed for the study of analysis and visualization of learning trajectories. Bearing in mind that the educational trajectory is the trajectory of the student traveled at a given time from entry to the end of the stay, it can be considered that the use of technology could extract or highlight relevant information that is not seen directly with the tools traditional The visualization of data in educational environments has become a challenge due to the large amounts of information available. The responsibilities of educational administrators require a clear visual proposal adapted to queries based on an academic context. Therefore, it was proposed to generate a tool that generates dashboard based on relevant variables of the students. To do this, the proposal began with a review of the literature that helped analyze the different ways of visualizing the data of academic trajectories. Subsequently, a dynamic visualization was formulated to explain the teachers and authorities through the learning analysis panel, based on the use of parallel coordinates that present multidimensional data over time. The sample was constituted by records of 1975 students of an Ecuadorian university, of the cohort that began in March 2013, distributed by faculties and careers. The technique used allowed us to discover trends and relationships between dimensions, improving the understanding of the trajectory patterns of students, the trends of school dropout, either increase or decrease performance, among other relationships. The consultations allowed to filter data by variables such as: faculties, careers, students and intervals of scores. Finally, the validation of the proposal was made based on the relevance of the dashboard, in response to the inquiries of the academic manager.
Gráficas de trayectorias escolares de estudiantes de bachillerato
(2021) Illescas Peña, Lourdes Eugenia; Bravo Guerrero, Fabián Eugenio; Peña Ortega, Mario Patricio; Bojorque Pazmiño, Miriam Eliana
For school authorities it is important to know how the students of the institution are progressing in their studies, because in this way they can detect any type of difficulties that arise, however, that information is not always known in time. The objective of this research is to propose a methodology that allows to visualize school trajectories of the students and in this way identify the difficulties that students have in mathematics. To show the potential of the methodology, high school students from an Ecuadorian educational institution were investigated between 2015 and 2019, their grades were processed and graphs of school trajectories were generated, which present the evolution of their grades during the school period. Through this methodology, the identification of individual trajectories of low performance is facilitated, in addition, it was found that collaborative activities have higher scores than individual ones, performance differences between courses were also evidenced. The presentation of grades through graphs is a powerful tool for academic management since it facilitates the detection of difficulties and the making of timely decisions.
Mathematical modeling to standardize times in assembly processes: application to four case studies
(2021) Colina Morles, Eliezer Null; Peña Ortega, Mario Patricio; Morocho Zurita, Carlos Villie; Sigüenza Guzmán, Lorena Catalina
Purpose: This paper proposes model-based standard times estimates, using multiple linear regression, nonlinear optimization, and fuzzy systems in four real cases assembly lines. The work includes a description of the models and a comparison of their performance with values obtained using the conventional chronometer method. These models allow estimating standard times without reconducting field studies. Design/methodology/approach: For the development of the time study, the methodology applied by the International Labour Organization (ILO) was used as a baseline. This methodology is structured in three phases: selection of the case study, registration of the process by direct observation, and calculation/estimation of the standard time. The selected case studies belong to real assembly lines of motorcycles, television sets, printed circuit boards, and bicycles. Findings: In the motorcycle’s assembly case, the study allowed constructing seven linear regression models to estimate standard times for assembling the front parts, and seven linear regression models to predict standard times for the rear parts of the different motorcycle types. Compared to the classical chronometer method, the results obtained never exceeded 10%. Regarding the case studies of assembling TV sets and PCBs, the study considered the construction of nonlinear optimization models that allow making appropriate predictions of the standard times in their assembly lines. Finally, for the bicycle assembly line, a fuzzy logic model to represent the standard time was constructed and validated. Research limitations/implications: For reasons of confidentiality of information, this work omitted the names of companies, services, and models of manufactured products. Originality/value: The literature consulted does not refer to the representation of standard time on assembly lines using mathematical models. The construction of these models with empirical data from actual assembly lines was a valuable aid to the companies involved in supporting activity planning.