2021
|
53. | Ana C. Umaquinga-Criollo; Juan D. Tamayo Quintero, María N. Moreno-García adn Yahya Aalaila; Diego H. Peluffo-Ordóñez Developments on Support Vector Machines for Multiple-Expert Learning Conference International Conference on Intelligent Data Engineering and Automated Learning., vol. 13113 , no. 22, Intelligent Data Engineering and Automated Learning – IDEAL 2021 Spinger Intelligent Data Engineering and Automated Learning – IDEAL 2021, 2021, ISBN: 978-3-030-91607-7. @conference{umaquinga2021SVM,
title = {Developments on Support Vector Machines for Multiple-Expert Learning},
author = {Ana C. Umaquinga-Criollo and Juan D. Tamayo Quintero, María N. Moreno-García adn Yahya Aalaila and Diego H. Peluffo-Ordóñez },
editor = {Springer},
url = {https://link.springer.com/chapter/10.1007/978-3-030-91608-4_57},
doi = {https://doi.org/10.1007/978-3-030-91608-4_57},
isbn = {978-3-030-91607-7},
year = {2021},
date = {2021-11-23},
urldate = {2021-11-23},
booktitle = {International Conference on Intelligent Data Engineering and Automated Learning.},
volume = {13113 },
number = {22},
pages = { 587–598},
publisher = {Intelligent Data Engineering and Automated Learning – IDEAL 2021},
organization = {Spinger},
series = {Intelligent Data Engineering and Automated Learning – IDEAL 2021},
abstract = {In supervised learning scenarios, some applications require solve a classification problem wherein labels are not given as a single ground truth. Instead, the criteria of a set of experts is used to provide labels aimed at compensating for the erroneous influence with respect to a single labeler as well as the error bias (excellent or lousy) due to the level of perception and experience of each expert. This paper aims to briefly outline mathematical developments on support vector machines (SVM), and overview SVM-based approaches for multiple expert learning (MEL). Such MEL approaches are posed by modifying the formulation of a least-squares SVM, which enables to obtain a set of reliable, objective labels while penalizing the evaluation quality of each expert. Particularly, this work studies both two-class (binary) MEL classifier (BMLC) and its extension to multiclass through one-against all (OaA-MLC) including penalization of each expert’s influence. Formal mathematical developments are stated, as well as remarkable discussion on key aspects about the least-squares SVM formulation and penalty factors are provided.},
key = {Multiple expert learning, Supervised learning, Support vector machines},
keywords = {Multiple expert learning, Supervised Learning, Support Vector Machines},
pubstate = {published},
tppubtype = {conference}
}
In supervised learning scenarios, some applications require solve a classification problem wherein labels are not given as a single ground truth. Instead, the criteria of a set of experts is used to provide labels aimed at compensating for the erroneous influence with respect to a single labeler as well as the error bias (excellent or lousy) due to the level of perception and experience of each expert. This paper aims to briefly outline mathematical developments on support vector machines (SVM), and overview SVM-based approaches for multiple expert learning (MEL). Such MEL approaches are posed by modifying the formulation of a least-squares SVM, which enables to obtain a set of reliable, objective labels while penalizing the evaluation quality of each expert. Particularly, this work studies both two-class (binary) MEL classifier (BMLC) and its extension to multiclass through one-against all (OaA-MLC) including penalization of each expert’s influence. Formal mathematical developments are stated, as well as remarkable discussion on key aspects about the least-squares SVM formulation and penalty factors are provided. |
52. | Ana C. Umaquinga-Criollo; Sandra K Narváez-Pupiales; Tatyana K. Saltos-Echeverria; Edgar D. Jaramillo-Vinueza Las TIC y aplicaciones en la nube. Un enfoque práctico Book Editorial Universitaria UTN, 2021, ISBN: 978-9942-845-07-8. @book{UmaquingaABook2021,
title = {Las TIC y aplicaciones en la nube. Un enfoque práctico},
author = {Ana C. Umaquinga-Criollo and Sandra K Narváez-Pupiales and Tatyana K. Saltos-Echeverria and Edgar D. Jaramillo-Vinueza},
editor = {Editorial Universitaria UTN},
url = {https://issuu.com/utnuniversity/docs/ebook-las-tics-y-aplicaiones-en-la-nube},
isbn = {978-9942-845-07-8},
year = {2021},
date = {2021-09-21},
urldate = {2021-09-21},
volume = {1},
publisher = {Editorial Universitaria UTN},
keywords = {TIC},
pubstate = {published},
tppubtype = {book}
}
|
51. | Fernández-Fernández Y; Peluffo-Ordóñez D.H.; Umaquinga-Criollo A.C.; Lorente-Leyva L.L.; Cabrera-Alvarez E.N A Brief Review on Instance Selection Based on Condensed Nearest Neighbors for Data Classification Tasks Conference International Conference on Communication, Computing and Electronics Systems. Proceedings of ICCCES 2020, vol. 733, Springer Science and Business Media Deutschland GmbH, 2021, ISBN: 978-981-33-4908-7. @conference{fernandez2021_,
title = {A Brief Review on Instance Selection Based on Condensed Nearest Neighbors for Data Classification Tasks},
author = {Fernández-Fernández Y and Peluffo-Ordóñez D.H. and Umaquinga-Criollo A.C. and Lorente-Leyva L.L. and Cabrera-Alvarez E.N},
editor = {Lecture Notes in Electrical Engineering},
url = {https://link.springer.com/chapter/10.1007%2F978-981-33-4909-4_23},
doi = {https://doi.org/10.1007/978-981-33-4909-4_23},
isbn = {978-981-33-4908-7},
year = {2021},
date = {2021-03-26},
booktitle = {International Conference on Communication, Computing and Electronics Systems. Proceedings of ICCCES 2020},
volume = {733},
pages = {313-324},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {The condensed nearest neighbor (CNN) classifier is one of the techniques used and known to perform recognition tasks. It has also proven to be one of the most interesting algorithms in the field of data mining despite its simplicity. However, CNN suffers from several drawbacks, such as high storage requirements and low noise tolerance. One of the characteristics of CNN is that it focuses on the selection of prototypes, which consists of reducing the set of training data. One of the goals of CNN seeks to achieve the reduction of information in such a way that the reduced information can represent large amounts of data to exercise decision-making on them. This paper mentions some of the most recent contributions to CNN-based unsupervised algorithms in a review that builds on the mathematical principles of condensed methods.},
keywords = {Classification, Nearest neighbor algorithms, Prototypes},
pubstate = {published},
tppubtype = {conference}
}
The condensed nearest neighbor (CNN) classifier is one of the techniques used and known to perform recognition tasks. It has also proven to be one of the most interesting algorithms in the field of data mining despite its simplicity. However, CNN suffers from several drawbacks, such as high storage requirements and low noise tolerance. One of the characteristics of CNN is that it focuses on the selection of prototypes, which consists of reducing the set of training data. One of the goals of CNN seeks to achieve the reduction of information in such a way that the reduced information can represent large amounts of data to exercise decision-making on them. This paper mentions some of the most recent contributions to CNN-based unsupervised algorithms in a review that builds on the mathematical principles of condensed methods. |
50. | Yasmani Fernández; Iris Marrufo; Marcelo Páez; A. C. Umaquinga-Criollo; P. D. Rosero; D. H. Peluffo-Ordónez Overview on kernels for least-squares support-vector-machine-based clustering: Explaining kernel spectral clustering Conference Investigacion Operacional, vol. 42, no. 1, Investigacion Operacional, 2021, ISBN: 0257-4306. @conference{fernandez2021,
title = {Overview on kernels for least-squares support-vector-machine-based clustering: Explaining kernel spectral clustering},
author = {Yasmani Fernández and Iris Marrufo and Marcelo Páez and A. C. Umaquinga-Criollo and P. D. Rosero and D. H. Peluffo-Ordónez},
editor = {Universidad de La Habana},
url = {https://rev-inv-ope.pantheonsorbonne.fr/sites/default/files/inline-files/42121-10.pdf},
isbn = {0257-4306},
year = {2021},
date = {2021-01-01},
booktitle = {Investigacion Operacional},
volume = {42},
number = {1},
pages = {113-123},
publisher = {Investigacion Operacional},
abstract = {ABSTRACT
This letter presents an overview on some remarkable basics on kernels as well as the formulation of a clustering approach based on least-squares support vector machines. Specifically, the method known as kernel spectral clustering (KSC) is of interest. We explore the links between KSC and a weighted version of kernel principal component analysis (WKPCA). Also, we study the solution of the KSC problem by means of a primal-dual scheme. All mathematical developments are carried out following an entirely matrix formulation. As a result, in addition to the elegant KSC formulation, important insights and hints about the use and design of kernel-based approaches for clustering are provided.
En esta investigación se presenta una descripción general de algunos conceptos básicos e importantes sobre kernels, así como la formulación de un enfoque de agrupación basado en máquinas de vectores de soporte de mínimos cuadrados. Específicamente, el método conocido como kernel espectral clustering (KSC) es de interés. Exploramos los enlaces entre KSC y una versión ponderada del análisis de componentes principales del núcleo (WKPCA). Además, estudiamos la solución del problema KSC
por medio de un esquema primal-dual. Todos los desarrollos matemáticos se llevan a cabo siguiendo una formulación completamente matricial. Como resultado, además de una formulación de KSC, se proporcionan ideas y sugerencias importantes sobre el uso y el diseño de enfoques basados en el kernels para clustering.},
keywords = {Clustering, kernel principal component analysis WKPC., Kernel spectral clustering KSC, Support Vector Machine (SVM)},
pubstate = {published},
tppubtype = {conference}
}
ABSTRACT
This letter presents an overview on some remarkable basics on kernels as well as the formulation of a clustering approach based on least-squares support vector machines. Specifically, the method known as kernel spectral clustering (KSC) is of interest. We explore the links between KSC and a weighted version of kernel principal component analysis (WKPCA). Also, we study the solution of the KSC problem by means of a primal-dual scheme. All mathematical developments are carried out following an entirely matrix formulation. As a result, in addition to the elegant KSC formulation, important insights and hints about the use and design of kernel-based approaches for clustering are provided.
En esta investigación se presenta una descripción general de algunos conceptos básicos e importantes sobre kernels, así como la formulación de un enfoque de agrupación basado en máquinas de vectores de soporte de mínimos cuadrados. Específicamente, el método conocido como kernel espectral clustering (KSC) es de interés. Exploramos los enlaces entre KSC y una versión ponderada del análisis de componentes principales del núcleo (WKPCA). Además, estudiamos la solución del problema KSC
por medio de un esquema primal-dual. Todos los desarrollos matemáticos se llevan a cabo siguiendo una formulación completamente matricial. Como resultado, además de una formulación de KSC, se proporcionan ideas y sugerencias importantes sobre el uso y el diseño de enfoques basados en el kernels para clustering. |
49. | Andrés M. Vargas-Muñoz; Diana C. Chamorro-Sangoquiza; Ana C. Umaquinga-Criollo; Paul D. Rosero-Montalvo; Miguel A. Becerra; Diego H. Peluffo-Ordóñez; E. Javier Revelo-Fuelagán Design of a low computational cost prototype for cardiac arrhythmia detection Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação, vol. 40, pp. 470-479, 2021, ISBN: 16469895. @article{nokey,
title = {Design of a low computational cost prototype for cardiac arrhythmia detection},
author = {Andrés M. Vargas-Muñoz and Diana C. Chamorro-Sangoquiza and Ana C. Umaquinga-Criollo and Paul D. Rosero-Montalvo and Miguel A. Becerra and Diego H. Peluffo-Ordóñez and E. Javier Revelo-Fuelagán},
editor = {Risti},
url = {https://www.proquest.com/docview/2483998641?pq-origsite=gscholar&fromopenview=true},
isbn = {16469895},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação},
volume = {40},
pages = { 470-479},
abstract = {Resumen: Esta investigación presenta el diseño de un prototipo para la detección de arritmias cardíacas que incorpora un sistema embebido de bajo costo computacional en un entorno de recursos computacionales limitados capaz de analizar características de los complejos QRS. Para ello, se desarrolla
una estrategia de clasificación de latidos cardiacos, normales y patológicos, en registros electrocardiográficos de larga duración (Holter), los cuales son ondas representativas del latido y su análisis permite identificar arritmias de tipo ventricular. Para el desarrollo de este prototipo inicial, se comprueba que el uso del algoritmo de k vecinos más cercanos (k-NN) junto con una etapa de selección de variables del conjunto de entrenamiento es una buena alternativa y representa una contribución importante de este trabajo a nivel experimental. Los experimentos se realizaron sobre la base de datos de arritmias cardiacas del Massachusetts Institute of Technology (MIT). Los resultados son satisfactorios y promisorios. },
keywords = {Arduino Mega, Cardiac arrhythmias, Holter ECG signal, MIT arrhythmia database},
pubstate = {published},
tppubtype = {article}
}
Resumen: Esta investigación presenta el diseño de un prototipo para la detección de arritmias cardíacas que incorpora un sistema embebido de bajo costo computacional en un entorno de recursos computacionales limitados capaz de analizar características de los complejos QRS. Para ello, se desarrolla
una estrategia de clasificación de latidos cardiacos, normales y patológicos, en registros electrocardiográficos de larga duración (Holter), los cuales son ondas representativas del latido y su análisis permite identificar arritmias de tipo ventricular. Para el desarrollo de este prototipo inicial, se comprueba que el uso del algoritmo de k vecinos más cercanos (k-NN) junto con una etapa de selección de variables del conjunto de entrenamiento es una buena alternativa y representa una contribución importante de este trabajo a nivel experimental. Los experimentos se realizaron sobre la base de datos de arritmias cardiacas del Massachusetts Institute of Technology (MIT). Los resultados son satisfactorios y promisorios. |
2020
|
48. | Ana C. Umaquinga-Criollo; Cristina E. Molina-Martínez; Wendy M. Guerrero-Loyola; Tatyana K. Saltos-Echeverria; Edgar D. Jaramillo-Vinueza Innovation in Biodegradable Textile Fibers for the Creation of Ecological Textiles Book Chapter In: Springer, Cham (Ed.): vol. 1, pp. 545-554, International Conference on Innovation and Research, 2020, ISBN: 978-3-030-60466-0. @inbook{umaquinga2020t,
title = {Innovation in Biodegradable Textile Fibers for the Creation of Ecological Textiles},
author = {Ana C. Umaquinga-Criollo and Cristina E. Molina-Martínez and Wendy M. Guerrero-Loyola and Tatyana K. Saltos-Echeverria and Edgar D. Jaramillo-Vinueza},
editor = {Springer, Cham},
doi = {https://doi.org/10.1007/978-3-030-60467-7_44},
isbn = {978-3-030-60466-0},
year = {2020},
date = {2020-11-22},
volume = {1},
pages = {545-554},
publisher = {International Conference on Innovation and Research},
abstract = {This research carries out a systematic, descriptive, documentary study in the textile area focus on biodegradability in textile fibers to know in this first approach the processes that have detected the material obtained by biological action to change and lose its original properties and chemical level decreasing in as much as possible the damage environment, benefic to the areas: textile, construction, agriculture, livestock, fish farming, among others. 40 relevant articles or review articles of interest of factor-impact Q1, Q2, Q3 are selected: 22 selected articles are Q1, 17 articles are Q2 and 1 articles Q3 of the last 10 years, which answered the research question asked on impact investigations in this area.},
keywords = {Biodegradable, Ecology, Environment, Fiber, Pollution, Textile},
pubstate = {published},
tppubtype = {inbook}
}
This research carries out a systematic, descriptive, documentary study in the textile area focus on biodegradability in textile fibers to know in this first approach the processes that have detected the material obtained by biological action to change and lose its original properties and chemical level decreasing in as much as possible the damage environment, benefic to the areas: textile, construction, agriculture, livestock, fish farming, among others. 40 relevant articles or review articles of interest of factor-impact Q1, Q2, Q3 are selected: 22 selected articles are Q1, 17 articles are Q2 and 1 articles Q3 of the last 10 years, which answered the research question asked on impact investigations in this area. |
47. | A. C. Umaquinga-Criollo; J. D. Tamayo-Quintero; M. N. Moreno-García; J. A. Riascos; D. H. Peluffo-Ordóñez Multi-expert Methods Evaluation on Financial and Economic Data: Introducing Bag of Experts Journal Article In: Hybrid Artificial Intelligent Systems, no. 15th, pp. 437-449, 2020, ISBN: 978-3-030-61704-2. @article{umaquingame,
title = {Multi-expert Methods Evaluation on Financial and Economic Data: Introducing Bag of Experts},
author = {A. C. Umaquinga-Criollo and J. D. Tamayo-Quintero and M. N. Moreno-García and J. A. Riascos and D. H. Peluffo-Ordóñez},
editor = {Springer, Cham},
url = {https://link.springer.com/chapter/10.1007/978-3-030-61705-9_36},
doi = {https://doi.org/10.1007/978-3-030-61705-9_36},
isbn = {978-3-030-61704-2},
year = {2020},
date = {2020-11-04},
urldate = {2020-08-20},
journal = {Hybrid Artificial Intelligent Systems},
number = {15th},
pages = { 437-449},
abstract = {The use of machine learning into economics scenarios results appealing since it allows for automatically testing economic models and predict consumer/client behavior to support decision-making processes. The finance market typically uses a set of expert labelers or Bureau credit scores given by governmental or private agencies such as Experian, Equifax, and Creditinfo, among others. This work focuses on introducing a so-named Bag of Expert (BoE): a novel approach for creating multi-expert Learning (MEL) frameworks aimed to emulate real experts labeling (human-given labels) using neural networks. The MEL systems “learn” to perform decision-making tasks by considering a uniform number of labels per sample or individuals along with respective descriptive variables. The BoE is created similarly to Generative Adversarial Network (GANs), but rather than using noise or perturbation by a generator, we trained a feed-forward neural network to randomize sampling data, and either add or decrease hidden neurons. Additionally, this paper aims to investigate the performance on economics-related datasets of several state-of-the-art MEL methods, such as GPC, GPC-PLAT, KAAR, MA-LFC, MA-DGRL, and MA-MAE. To do so, we develop an experimental framework composed of four tests: the first one using novice experts; the second with proficient experts; the third is a mix of novices, intermediate and proficient experts, and the last one uses crowd-sourcing. Our BoE method presents promising results and can be suitable as an alternative to properly assess the reliability of both MEL methods and conventional labeler generators (i.e., virtual expert labelers).},
keywords = {Bag of experts, clasificadores, Crowd-sourcing, Feed-forward neural network, Finance, Investment banking, MATLAB, multi-clasificadores, Multi-expert, patrones de desempeño académico, selección de características},
pubstate = {published},
tppubtype = {article}
}
The use of machine learning into economics scenarios results appealing since it allows for automatically testing economic models and predict consumer/client behavior to support decision-making processes. The finance market typically uses a set of expert labelers or Bureau credit scores given by governmental or private agencies such as Experian, Equifax, and Creditinfo, among others. This work focuses on introducing a so-named Bag of Expert (BoE): a novel approach for creating multi-expert Learning (MEL) frameworks aimed to emulate real experts labeling (human-given labels) using neural networks. The MEL systems “learn” to perform decision-making tasks by considering a uniform number of labels per sample or individuals along with respective descriptive variables. The BoE is created similarly to Generative Adversarial Network (GANs), but rather than using noise or perturbation by a generator, we trained a feed-forward neural network to randomize sampling data, and either add or decrease hidden neurons. Additionally, this paper aims to investigate the performance on economics-related datasets of several state-of-the-art MEL methods, such as GPC, GPC-PLAT, KAAR, MA-LFC, MA-DGRL, and MA-MAE. To do so, we develop an experimental framework composed of four tests: the first one using novice experts; the second with proficient experts; the third is a mix of novices, intermediate and proficient experts, and the last one uses crowd-sourcing. Our BoE method presents promising results and can be suitable as an alternative to properly assess the reliability of both MEL methods and conventional labeler generators (i.e., virtual expert labelers). |
46. | M. C. Ortega-Bustamante, W. Hasperué, D. H. Peluffo-Ordóñez, M. Paéz-Jaime, I. Marrufo-Rodríguez, P. Rosero-Montalvo, A. C. Umaquinga-Criollo, M. Vélez-Falconí Introducing the Concept of Interaction Model for Interactive Dimensionality Reduction and Data Visualization Conference Computational Science and Its Applications – ICCSA 2020, vol. 12250, no. Part II, 2020, ISBN: 978-3-030-58801-4. @conference{ortega2020,
title = {Introducing the Concept of Interaction Model for Interactive Dimensionality Reduction and Data Visualization},
author = {M. C. Ortega-Bustamante, W. Hasperué, D. H. Peluffo-Ordóñez, M. Paéz-Jaime, I. Marrufo-Rodríguez, P. Rosero-Montalvo, A. C. Umaquinga-Criollo, M. Vélez-Falconí},
editor = {Springer, Cham
Lecture Notes in Computer Science},
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-58802-1_14
},
doi = {https://doi.org/10.1007/978-3-030-58802-1_14 },
isbn = {978-3-030-58801-4},
year = {2020},
date = {2020-10-02},
booktitle = {Computational Science and Its Applications – ICCSA 2020},
volume = {12250},
number = {Part II},
pages = {193-203},
abstract = {This letter formally introduces the concept of interaction model (IM), which has been used either directly or tangentially in previous works but never defined. Broadly speaking, an IM consists of the use of a mixture of dimensionality reduction (DR) techniques within an interactive data visualization framework. The rationale of creating an IM is the need for simultaneously harnessing the benefit of several DR approaches to reach a data representation being intelligible and/or fitted to any user’s criterion. As a remarkable advantage, an IM naturally provides a generalized framework for designing both interactive DR approaches as well as readily-to-use data visualization interfaces. In addition to a comprehensive overview on basics of data representation and dimensionality reduction, the main contribution of this manuscript is the elegant definition of the concept of IM in mathematical terms.},
keywords = {Data visualization, Dimensionality reduction, Interaction model Kernel functions},
pubstate = {published},
tppubtype = {conference}
}
This letter formally introduces the concept of interaction model (IM), which has been used either directly or tangentially in previous works but never defined. Broadly speaking, an IM consists of the use of a mixture of dimensionality reduction (DR) techniques within an interactive data visualization framework. The rationale of creating an IM is the need for simultaneously harnessing the benefit of several DR approaches to reach a data representation being intelligible and/or fitted to any user’s criterion. As a remarkable advantage, an IM naturally provides a generalized framework for designing both interactive DR approaches as well as readily-to-use data visualization interfaces. In addition to a comprehensive overview on basics of data representation and dimensionality reduction, the main contribution of this manuscript is the elegant definition of the concept of IM in mathematical terms. |
45. | Miguel A. Becerra; Edilson Delgado Trejos; Cristian Mejía-Arboleda; Diego H. Peluffo-Ordóñez; Ana C. Umaquinga-Criollo Stochastic-and Neuro-Fuzzy-Analysis-based characterization and classification of 4-Channel Phonocardiograms for Cardiac Murmur Detection Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação. , vol. 2020, no. E33, pp. 65-78, 2020, ISBN: 1646-9895. @article{becerra2020,
title = {Stochastic-and Neuro-Fuzzy-Analysis-based characterization and classification of 4-Channel Phonocardiograms for Cardiac Murmur Detection},
author = {Miguel A. Becerra and Edilson Delgado Trejos and Cristian Mejía-Arboleda and Diego H. Peluffo-Ordóñez and Ana C. Umaquinga-Criollo},
editor = {AISTI 2020},
url = {http://www.risti.xyz/issues/ristie33.pdf},
isbn = {1646-9895},
year = {2020},
date = {2020-08-20},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação. },
volume = {2020},
number = {E33},
pages = {65-78},
abstract = {Abstract: Cardiac murmurs (CMs) are the most common heart’s diseases that are typically diagnosed from phonocardiogram (PCG) and echocardiogram tests -often supported by computerized systems. Research works have traditionally addressed the automatic CM diagnosis with no distinctively use of the four auscultation areas (one of each cardiac valve), resulting -most probably- in a constrained, nonimpartial diagnostic procedure. This study presents a comparison among four different CM detection systems from a 4-channel PCG. We first evaluate the acoustic characteristics derived from Mel-Frequency Cepstral Coefficients, Empirical Mode Decomposition (EMD), and statistical measures. Secondly, a relevance analysis is carried out using Fuzzy Rough Feature Selection. Thirdly, Hidden Markov Models (HMM), Adaptative Neuro-Fuzzy Inference System (ANFIS), Naïve Bayes, and Gaussian Mixture Model were applied for classification and validated using a 50-fold cross-validation procedure with a 70/30 split demonstrating the functionality and capability of EMD, Hidden Markov Model and ANFIS for CM classification.},
keywords = {ANFIS, cardiac murmur, empirical mode decomposition, hidden markov models, phonocardiogram.},
pubstate = {published},
tppubtype = {article}
}
Abstract: Cardiac murmurs (CMs) are the most common heart’s diseases that are typically diagnosed from phonocardiogram (PCG) and echocardiogram tests -often supported by computerized systems. Research works have traditionally addressed the automatic CM diagnosis with no distinctively use of the four auscultation areas (one of each cardiac valve), resulting -most probably- in a constrained, nonimpartial diagnostic procedure. This study presents a comparison among four different CM detection systems from a 4-channel PCG. We first evaluate the acoustic characteristics derived from Mel-Frequency Cepstral Coefficients, Empirical Mode Decomposition (EMD), and statistical measures. Secondly, a relevance analysis is carried out using Fuzzy Rough Feature Selection. Thirdly, Hidden Markov Models (HMM), Adaptative Neuro-Fuzzy Inference System (ANFIS), Naïve Bayes, and Gaussian Mixture Model were applied for classification and validated using a 50-fold cross-validation procedure with a 70/30 split demonstrating the functionality and capability of EMD, Hidden Markov Model and ANFIS for CM classification. |
44. | David Bastidas; Camilo Piñeros; Diego H Peluffo-Ordóñez; Luz Marina Sierra; Miguel A. Becerra; Ana C Umaquinga-Criollo Analytic study on the performance of multi- classification approaches in case-based reasoning systems: Medical data exploration Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação. , vol. 2020, no. E33, pp. 40-51, 2020, ISSN: 1646-9895. @article{bastidas2020,
title = {Analytic study on the performance of multi- classification approaches in case-based reasoning systems: Medical data exploration},
author = {David Bastidas and Camilo Piñeros and Diego H Peluffo-Ordóñez and Luz Marina Sierra and Miguel A. Becerra and Ana C Umaquinga-Criollo},
editor = {AISTI 2020},
url = {http://www.risti.xyz/issues/ristie33.pdf},
issn = {1646-9895},
year = {2020},
date = {2020-08-20},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação. },
volume = {2020},
number = {E33},
pages = {40-51},
abstract = {Abstract: This paper compares the main combinations of classifiers (Sequential, Parallel and Stacking) over two remarkable medical data collections: Cleveland and Dermatology. The principal rationale underlying the use of multiple classifiers is that together the methods may be powered rather than their individual behavior. Such a premise is validated through the identification of the best the combination reaching the lowest error rate within a case-based reasoning system (CBR). The different combinations are essentially formed by five different classifiers greatly different regarding their nature and inception: SVM (Support Vector Machines), Parzen, Random Forest, K-NN (k-nearest neighbors) and Naive Bayes. From experimental results, it can be inferred that the combination of techniques is greatly useful. Also, in this work, some key aspects and hints are discussed about the relationship between the nature of the input data and the classification (either individual or mixture of classifiers) stage building within a CBR framework.},
keywords = {case based reasoning, classifiers fusion, dermatology disease, heart disease},
pubstate = {published},
tppubtype = {article}
}
Abstract: This paper compares the main combinations of classifiers (Sequential, Parallel and Stacking) over two remarkable medical data collections: Cleveland and Dermatology. The principal rationale underlying the use of multiple classifiers is that together the methods may be powered rather than their individual behavior. Such a premise is validated through the identification of the best the combination reaching the lowest error rate within a case-based reasoning system (CBR). The different combinations are essentially formed by five different classifiers greatly different regarding their nature and inception: SVM (Support Vector Machines), Parzen, Random Forest, K-NN (k-nearest neighbors) and Naive Bayes. From experimental results, it can be inferred that the combination of techniques is greatly useful. Also, in this work, some key aspects and hints are discussed about the relationship between the nature of the input data and the classification (either individual or mixture of classifiers) stage building within a CBR framework. |
43. | Diana C. Chamorro-Sangoquiza; Andrés M. Vargas-Muñoz; Ana C. Umaquinga-Criollo; Miguel A. Becerra; Diego H. Peluffo-Ordóñez Comparative study of data mining techniques to reveal patterns of academic performance in secondary education Journal Article In: RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao, vol. E32, pp. 455–468, 2020, ISSN: 1646-9895. @article{chamorro2020_,
title = {Comparative study of data mining techniques to reveal patterns of academic performance in secondary education},
author = {Diana C. Chamorro-Sangoquiza and Andrés M. Vargas-Muñoz and Ana C. Umaquinga-Criollo and Miguel A. Becerra and Diego H. Peluffo-Ordóñez},
editor = {RISTI},
issn = {1646-9895},
year = {2020},
date = {2020-08-01},
journal = {RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao},
volume = {E32},
pages = {455–468},
abstract = {Las técnicas de minería de datos permiten develar conocimiento a partir de grandes volúmenes de información, los cuales han sido poco exploradas en análisis de información de instituciones de educación, pero con una creciente demanda por este sector para apoyar la toma de decisiones. En esta investigación se propone una metodología de comparación de técnicas de minería de datos, aplicado al análisis de patrones académicos en estudiantes de educación media. Múltiples métodos de selección de atributos son aplicados para reducir la dimensionalidad y se comparan tres clasificadores y dos multi-clasificadores. Los experimentos se realizan en una base de datos de 285 instancias y 36 atributos obtenidos de una encuesta educativa aplicada a los alumnos del Tercer Año de Bachillerato de la Unidad Educativa Ibarra 2017-2018. Los mejores resultados de clasificación fueron alcanzados por los multiclasifiadores Boosted Tree y Bagged Tree con 93.24% de exactitud usando los datos seleccionados con el algoritmo BestFirst.},
keywords = {clasificadores, MATLAB, multi-clasificadores, patrones de desempeño académico, selección de características},
pubstate = {published},
tppubtype = {article}
}
Las técnicas de minería de datos permiten develar conocimiento a partir de grandes volúmenes de información, los cuales han sido poco exploradas en análisis de información de instituciones de educación, pero con una creciente demanda por este sector para apoyar la toma de decisiones. En esta investigación se propone una metodología de comparación de técnicas de minería de datos, aplicado al análisis de patrones académicos en estudiantes de educación media. Múltiples métodos de selección de atributos son aplicados para reducir la dimensionalidad y se comparan tres clasificadores y dos multi-clasificadores. Los experimentos se realizan en una base de datos de 285 instancias y 36 atributos obtenidos de una encuesta educativa aplicada a los alumnos del Tercer Año de Bachillerato de la Unidad Educativa Ibarra 2017-2018. Los mejores resultados de clasificación fueron alcanzados por los multiclasifiadores Boosted Tree y Bagged Tree con 93.24% de exactitud usando los datos seleccionados con el algoritmo BestFirst. |
42. | Fabián Cuzme-Rodríguez; Ana Cristina Umaquinga; Luis Suárez Zambrano; Henry Farinango-Endara; Hernán Domínguez-Limaico; Mario Mediavilla-Valverde Simulation Tools for Solving Engineering Problems. Case Study Conference Applied Technologies, vol. Part I, Springer, 2020, ISBN: 978-3-030-42516-6, (Print ISBN 978-3-030-42516-6 Online ISBN 978-3-030-42517-3). @conference{cuzme2020,
title = {Simulation Tools for Solving Engineering Problems. Case Study},
author = {Fabián Cuzme-Rodríguez and Ana Cristina Umaquinga and Luis Suárez Zambrano and Henry Farinango-Endara and Hernán Domínguez-Limaico and Mario Mediavilla-Valverde},
editor = {Springer},
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-42517-3_21
https://doi.org/10.1007/978-3-030-42517-3_21},
doi = {https://doi.org/10.1007/978-3-030-42517-3_21},
isbn = {978-3-030-42516-6},
year = {2020},
date = {2020-03-03},
booktitle = { Applied Technologies},
journal = {First International Conference ICAT 2019},
volume = {Part I},
pages = { 271-285},
publisher = {Springer},
abstract = {The areas of Engineering in Applied Sciences have contributed significantly to the social, economic and technological advances of the world, being of interest to the academy mainly in the university system and specialization in Ecuador and in several countries both in the teaching-learning process as well as in research, which makes it increasingly stronger and proposes better and new solutions to environmental problems. This article performs a quantitative, descriptive and systemic analysis, which combines with the analysis of the ISO/IEC 25010 standard considers criteria such as functionality, performance, compatibility, usability, reliability, maintainability, portability to evaluate the quality of the software; The analysis involves simulation tools immersed in the teaching-learning processes of the engineering area with the determination to identify the tools used to solve specific problems in this field, particularly in the Telecommunications Engineering Degree at the “Universidad Técnica del Norte” University. This study is based on the opinion of experts in the university and business field who validate the established criteria. The results of this article identify the use of the different simulation tools in the university education and research environment, in addition to promoting the inclusion of these tools in the process of training students so that they can propose solutions at a scientific level and/or technological.},
note = {Print ISBN 978-3-030-42516-6 Online ISBN 978-3-030-42517-3},
keywords = {ISO-25010, MATLAB, NS2, NS3, Simulators},
pubstate = {published},
tppubtype = {conference}
}
The areas of Engineering in Applied Sciences have contributed significantly to the social, economic and technological advances of the world, being of interest to the academy mainly in the university system and specialization in Ecuador and in several countries both in the teaching-learning process as well as in research, which makes it increasingly stronger and proposes better and new solutions to environmental problems. This article performs a quantitative, descriptive and systemic analysis, which combines with the analysis of the ISO/IEC 25010 standard considers criteria such as functionality, performance, compatibility, usability, reliability, maintainability, portability to evaluate the quality of the software; The analysis involves simulation tools immersed in the teaching-learning processes of the engineering area with the determination to identify the tools used to solve specific problems in this field, particularly in the Telecommunications Engineering Degree at the “Universidad Técnica del Norte” University. This study is based on the opinion of experts in the university and business field who validate the established criteria. The results of this article identify the use of the different simulation tools in the university education and research environment, in addition to promoting the inclusion of these tools in the process of training students so that they can propose solutions at a scientific level and/or technological. |
41. | Ana C. Ramírez–Recalde; Ana Cristina Umaquinga; Edgar Maya; Carlos Vásquez-Ayala Metodología de enseñanza y aprendizaje en tecnologías de Cloud Computing: Un estudio de caso en la Carrera de Ingeniería Electrónica y Redes de Comunicación de la Universidad Técnica del Norte Journal Article In: risti revista ibérica de sistemas e tecnologias de informação, vol. N.º E25, pp. 72-86, 2020, ISSN: 1646-9895. @article{ramirez2020,
title = {Metodología de enseñanza y aprendizaje en tecnologías de Cloud Computing: Un estudio de caso en la Carrera de Ingeniería Electrónica y Redes de Comunicación de la Universidad Técnica del Norte},
author = {Ana C. Ramírez–Recalde and Ana Cristina Umaquinga and Edgar Maya and Carlos Vásquez-Ayala},
editor = {Risti},
url = {http://www.risti.xyz/issues/ristie25.pdf
https://search.proquest.com/openview/6134a93593c6b2f1ecbd8da095e3d5ef/1?cbl=1006393&pq-origsite=gscholar},
issn = {1646-9895},
year = {2020},
date = {2020-01-20},
journal = {risti revista ibérica de sistemas e tecnologias de informação},
volume = {N.º E25},
pages = {72-86},
abstract = {Este trabajo expone el diseño e implementación de un Entorno Virtual de Aprendizaje (EVA) en la Carrera de Ingeniería en Electrónica y Redes de Comunicación (CIERCOM) de la Universidad Técnica del Norte (UTN), IbarraEcuador, referente al área de estudio Cloud Computing (CC), se considera: Un sistema de Gestión de Aprendizaje Moodle diseñado de acuerdo a directrices establecidas por la metodología de PACIE (Presencia, Alcance, Capacitación, Interacción, E-learning); contenido se basa en información de seis trabajos de grado que formaron parte del proyecto puesto en marcha en la Facultad de Ingeniería en Ciencias Aplicadas de la UTN, misma que ha sido complementada y transformada en material didáctico del EVA con el fin de difundir los
estudios de caso y contribuir con conocimientos para los estudiantes de la carrera acerca del tema.
La investigación es de tipo descriptivo y documental permitiendo abarcar los siguientes temas: (i) Fundamentos básicos de Cloud Computing; (ii) Definiciones de un Centro de Datos TIER I bajo el estándar TIA 942; (iii) Plataformas de Infraestructura como Servicio Openstack; (iv) Plataformas de Infraestructura como Servicio Opennebula y (v) Plataformas de Infraestructura como Servicio Eucalyptus.},
keywords = {Aprendizaje Virtual, Computación en la Nube, Entorno Virtual de Aprendizaje, PACIE; Moodle},
pubstate = {published},
tppubtype = {article}
}
Este trabajo expone el diseño e implementación de un Entorno Virtual de Aprendizaje (EVA) en la Carrera de Ingeniería en Electrónica y Redes de Comunicación (CIERCOM) de la Universidad Técnica del Norte (UTN), IbarraEcuador, referente al área de estudio Cloud Computing (CC), se considera: Un sistema de Gestión de Aprendizaje Moodle diseñado de acuerdo a directrices establecidas por la metodología de PACIE (Presencia, Alcance, Capacitación, Interacción, E-learning); contenido se basa en información de seis trabajos de grado que formaron parte del proyecto puesto en marcha en la Facultad de Ingeniería en Ciencias Aplicadas de la UTN, misma que ha sido complementada y transformada en material didáctico del EVA con el fin de difundir los
estudios de caso y contribuir con conocimientos para los estudiantes de la carrera acerca del tema.
La investigación es de tipo descriptivo y documental permitiendo abarcar los siguientes temas: (i) Fundamentos básicos de Cloud Computing; (ii) Definiciones de un Centro de Datos TIER I bajo el estándar TIA 942; (iii) Plataformas de Infraestructura como Servicio Openstack; (iv) Plataformas de Infraestructura como Servicio Opennebula y (v) Plataformas de Infraestructura como Servicio Eucalyptus. |
40. | Ana C. Umaquinga-Criollo; Diego H. Peluffo-Ordóñez; Paúl D. Rosero-Montalvo; Pamela E. Godoy-Trujillo; Henry Benítez-Pereira Interactive Visualization Interfaces for Big Data Analysis Using Combination of Dimensionality Reduction Methods: A Brief Review Conference Technology, Sustainability and Educational Innovation (TSIE), Springer, Cham, 2020, ISBN: 978-3-030-37220-0, ( Print ISBN 978-3-030-37220-0 Online ISBN 978-3-030-37221-7 ). @conference{umaquinga2020,
title = {Interactive Visualization Interfaces for Big Data Analysis Using Combination of Dimensionality Reduction Methods: A Brief Review},
author = {Ana C. Umaquinga-Criollo and Diego H. Peluffo-Ordóñez and Paúl D. Rosero-Montalvo and Pamela E. Godoy-Trujillo and Henry Benítez-Pereira},
editor = {Springer Charm },
url = {https://link.springer.com/chapter/10.1007/978-3-030-37221-7_17
https://doi.org/10.1007/978-3-030-37221-7_17},
doi = {https://doi.org/10.1007/978-3-030-37221-7_17},
isbn = {978-3-030-37220-0},
year = {2020},
date = {2020-01-03},
booktitle = {Technology, Sustainability and Educational Innovation (TSIE)},
pages = {193-203},
publisher = {Springer, Cham},
abstract = {The Big Data analysis allows to generate knowledge based on mathematical models that surpass human capabilities, and therefore it is necessary to have robust computer systems. In this connection, the dimensionality reduction (DR) allows to perform approximations to make data perceptible in a simple and compact way while also the computational cost is reduced. Additionally, interactive interfaces enable the user to work with algorithms involving complex mathematical and statistical processes typically aimed at providing weighting factors to each RD algorithm to find the best way to represent data at a low dimension. In this study, a bibliographic re-view of the different models of interactive interfaces for the analysis of Big Data using RD is presented, by considering different, existing proposals and approaches on how to display the information. Particularly, those approaches based on mental processes and uses of color along with an intuitive handling are of special interest.},
note = { Print ISBN 978-3-030-37220-0 Online ISBN 978-3-030-37221-7 },
keywords = {Big data, Business intelligence, data mining, Dimensionality reduction, Interactive interface},
pubstate = {published},
tppubtype = {conference}
}
The Big Data analysis allows to generate knowledge based on mathematical models that surpass human capabilities, and therefore it is necessary to have robust computer systems. In this connection, the dimensionality reduction (DR) allows to perform approximations to make data perceptible in a simple and compact way while also the computational cost is reduced. Additionally, interactive interfaces enable the user to work with algorithms involving complex mathematical and statistical processes typically aimed at providing weighting factors to each RD algorithm to find the best way to represent data at a low dimension. In this study, a bibliographic re-view of the different models of interactive interfaces for the analysis of Big Data using RD is presented, by considering different, existing proposals and approaches on how to display the information. Particularly, those approaches based on mental processes and uses of color along with an intuitive handling are of special interest. |
2019
|
39. | Emil Vega-Gualán; Andrés Vargas; Miguel Becerra; Ana Umaquinga; Jaime A. Riascos; Diego Peluffo Exploring the Characterization and Classification of EEG Signals for a Computer-Aided Epilepsy Diagnosis System Conference Brain Informatics, vol. BI 2019, no. 12, 12th International Conference Springer, Cham, 2019, ISBN: 978-3-030-37078-7, ( Print ISBN 978-3-030-37077-0 Online ISBN 978-3-030-37078-7 ). @conference{vega2019,
title = {Exploring the Characterization and Classification of EEG Signals for a Computer-Aided Epilepsy Diagnosis System},
author = {Emil Vega-Gualán and Andrés Vargas and Miguel Becerra and Ana Umaquinga and Jaime A. Riascos and Diego Peluffo},
editor = {Springer, Charm},
url = {https://link.springer.com/chapter/10.1007/978-3-030-37078-7_19},
doi = {https://doi.org/10.1007/978-3-030-37078-7_19},
isbn = {978-3-030-37078-7},
year = {2019},
date = {2019-12-15},
booktitle = {Brain Informatics},
volume = {BI 2019},
number = {12},
pages = {189-198},
publisher = {Springer, Cham},
organization = {12th International Conference},
abstract = {Epilepsy occurs when localized electrical activity of neurons suffer from an imbalance. One of the most adequate methods for diagnosing and monitoring is via the analysis of electroencephalographic (EEG) signals. Despite there is a wide range of alternatives to characterize and classify EEG signals for epilepsy analysis purposes, many key aspects related to accuracy and physiological interpretation are still considered as open issues. In this paper, this work performs an exploratory study in order to identify the most adequate frequently-used methods for characterizing and classifying epileptic seizures. In this regard, a comparative study is carried out on several subsets of features using four representative classifiers: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The framework uses a well-known epilepsy dataset and runs several experiments for two and three classification problems. The results suggest that DWT decomposition with SVM is the most suitable combination.},
note = { Print ISBN 978-3-030-37077-0 Online ISBN 978-3-030-37078-7 },
keywords = {Electroencephalogram (EEG) Epilepsy diagnosis, K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machine (SVM)},
pubstate = {published},
tppubtype = {conference}
}
Epilepsy occurs when localized electrical activity of neurons suffer from an imbalance. One of the most adequate methods for diagnosing and monitoring is via the analysis of electroencephalographic (EEG) signals. Despite there is a wide range of alternatives to characterize and classify EEG signals for epilepsy analysis purposes, many key aspects related to accuracy and physiological interpretation are still considered as open issues. In this paper, this work performs an exploratory study in order to identify the most adequate frequently-used methods for characterizing and classifying epileptic seizures. In this regard, a comparative study is carried out on several subsets of features using four representative classifiers: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The framework uses a well-known epilepsy dataset and runs several experiments for two and three classification problems. The results suggest that DWT decomposition with SVM is the most suitable combination. |
38. | Ana Cristina Umaquinga Criollo; Edgar Daniel Jaramillo Vinueza Seguimiento académico a estudiantes con repitencia en la Carrera de Ingeniería en Telecomunicaciones: Fase dos periodo académico septiembre 2018 febrero 2019 Conference Memorias ACOFI Retos en la Formación de Ingenieros en la era digital, 2019, ISSN: 2665-5918. @conference{umaquinga2019a,
title = {Seguimiento académico a estudiantes con repitencia en la Carrera de Ingeniería en Telecomunicaciones: Fase dos periodo académico septiembre 2018 febrero 2019},
author = {Ana Cristina Umaquinga Criollo and Edgar Daniel Jaramillo Vinueza},
url = {https://www.acofipapers.org/index.php/eiei/article/view/122},
issn = {2665-5918},
year = {2019},
date = {2019-08-31},
booktitle = {Memorias ACOFI Retos en la Formación de Ingenieros en la era digital},
journal = {Memorias ACOFI Retos en la formación de ingenieros en la era digital},
abstract = {Resumen:
En esta segunda fase de estudio se presenta la continuación de un estudio cuantitativo, exploratorio y descriptivo del seguimiento académico a estudiantes con repitencia de segundas y terceras matrículas de la actual Carrera de Ingeniería en Telecomunicaciones y de la Carrera de Ingeniería en Redes y Comunicación con el fin de identificar las causas de repitencia manteniendo los factores de clasificación de su primera fase: familiares, económicos, sociológicos de los estudiantes en el periodo académico Septiembre 2018- Febrero 2019.
El universo de estudiantes matriculados lo conforman: 289 estudiantes hombres y 81 estudiantes mujeres, dando un total de 370 estudiantes que iniciaron el ciclo de estudios en periodo académico en mención. En la segunda fase se analiza la muestra de 34 estudiantes con segundas y terceras matrículas asignados a una docente para seguimiento académico, el mismo que realiza un estudio comparativo con la fase 1, con el fin de confirmar los factores previamente identificados o en el descubrimiento de nuevos factores a ser considerados para un mejor análisis de las principales causas de repitencia en esta Carrera.
Abstract:
In this second phase of the study, the continuation of a quantitative, exploratory and descriptive study of academic follow-up is presented to students with second and third enrollment repeats of the current Career in Telecommunications Engineering and the Career in Network and Communication Engineering with the In order to identify the causes of repetition maintaining the classification factors of its first phase: family, economic, sociological of students in the academic period September 2018 - February 2019.
The universe of students enrolled is made up of: 289 male students and 81 female students, giving a total of 370 students who started the cycle of studies in academic period in mention. In the second phase, the sample of 34 students with second and third enrollments assigned to a teacher for academic follow-up is analyzed, the same one that performs a comparative study with phase 1, in order to confirm the previously identified factors or in the discovery of new factors to be considered for a better analysis of the main causes of repetition in this Career},
keywords = {academic accompaniment, academic follow-up, acompañamiento académico, engineering students, estudiantes de ingeniería, ingeniería en telecomunicaciones, repetition, repitencia, seguimiento académico, telecommunications engineering},
pubstate = {published},
tppubtype = {conference}
}
Resumen:
En esta segunda fase de estudio se presenta la continuación de un estudio cuantitativo, exploratorio y descriptivo del seguimiento académico a estudiantes con repitencia de segundas y terceras matrículas de la actual Carrera de Ingeniería en Telecomunicaciones y de la Carrera de Ingeniería en Redes y Comunicación con el fin de identificar las causas de repitencia manteniendo los factores de clasificación de su primera fase: familiares, económicos, sociológicos de los estudiantes en el periodo académico Septiembre 2018- Febrero 2019.
El universo de estudiantes matriculados lo conforman: 289 estudiantes hombres y 81 estudiantes mujeres, dando un total de 370 estudiantes que iniciaron el ciclo de estudios en periodo académico en mención. En la segunda fase se analiza la muestra de 34 estudiantes con segundas y terceras matrículas asignados a una docente para seguimiento académico, el mismo que realiza un estudio comparativo con la fase 1, con el fin de confirmar los factores previamente identificados o en el descubrimiento de nuevos factores a ser considerados para un mejor análisis de las principales causas de repitencia en esta Carrera.
Abstract:
In this second phase of the study, the continuation of a quantitative, exploratory and descriptive study of academic follow-up is presented to students with second and third enrollment repeats of the current Career in Telecommunications Engineering and the Career in Network and Communication Engineering with the In order to identify the causes of repetition maintaining the classification factors of its first phase: family, economic, sociological of students in the academic period September 2018 - February 2019.
The universe of students enrolled is made up of: 289 male students and 81 female students, giving a total of 370 students who started the cycle of studies in academic period in mention. In the second phase, the sample of 34 students with second and third enrollments assigned to a teacher for academic follow-up is analyzed, the same one that performs a comparative study with phase 1, in order to confirm the previously identified factors or in the discovery of new factors to be considered for a better analysis of the main causes of repetition in this Career |
37. | Julio Arcesio Yépez; Ana Cristina Umaquinga Estudio analítico y situacional de los factores relacionados con la deserción estudiantil en el Instituto Superior Tecnológico "Ibarra" Conference Memorias ACOFI Retos en la Formación de Ingenieros en la era digital, 2019, ISSN: 2665-5918. @conference{yepez2019,
title = {Estudio analítico y situacional de los factores relacionados con la deserción estudiantil en el Instituto Superior Tecnológico "Ibarra" },
author = {Julio Arcesio Yépez and Ana Cristina Umaquinga},
url = {https://www.acofipapers.org/index.php/eiei/article/view/103},
issn = {2665-5918},
year = {2019},
date = {2019-08-31},
booktitle = {Memorias ACOFI Retos en la Formación de Ingenieros en la era digital},
abstract = {El Instituto Tecnológico Superior Ibarra (ITSI) es una Institución de Educación Superior de derecho privado ubicado en la ciudad de Ibarra-Ecuador, es una institución acreditada en la categoría "A" de los Institutos Técnicos Tecnológicos del país, es reconocido por la Secretaría Nacional de Educación Superior, Ciencia, Tecnología e Innovación SENECYT del Ecuador, cuenta con tres carreras de estudio: Tecnologías en Desarrollo de Software; Diseño Gráfico; Redes y Telecomunicaciones, en tres horarios diurno, vespertino y nocturno al servicio
La deserción estudiantil es una realidad no ajena para esta institución. La presente investigación presenta el estudio y resultados de una investigación descriptiva, exploratoria y cuantitativa en la que se identifica y analiza los factores causantes de la deserción estudiantil en esta institución, tras la toma de datos resultantes en una encuesta propuesta a los 205 estudiantes matriculados en el periodo actual de estudio con el fin aportar en la toma de decisiones en la consecución de soluciones para este problema crítico presente en las instituciones del país y del mundo .},
keywords = {calidad de la educación superior, deserción educación superior, deserción estudiantil, ISTI, rendimiento académico},
pubstate = {published},
tppubtype = {conference}
}
El Instituto Tecnológico Superior Ibarra (ITSI) es una Institución de Educación Superior de derecho privado ubicado en la ciudad de Ibarra-Ecuador, es una institución acreditada en la categoría "A" de los Institutos Técnicos Tecnológicos del país, es reconocido por la Secretaría Nacional de Educación Superior, Ciencia, Tecnología e Innovación SENECYT del Ecuador, cuenta con tres carreras de estudio: Tecnologías en Desarrollo de Software; Diseño Gráfico; Redes y Telecomunicaciones, en tres horarios diurno, vespertino y nocturno al servicio
La deserción estudiantil es una realidad no ajena para esta institución. La presente investigación presenta el estudio y resultados de una investigación descriptiva, exploratoria y cuantitativa en la que se identifica y analiza los factores causantes de la deserción estudiantil en esta institución, tras la toma de datos resultantes en una encuesta propuesta a los 205 estudiantes matriculados en el periodo actual de estudio con el fin aportar en la toma de decisiones en la consecución de soluciones para este problema crítico presente en las instituciones del país y del mundo . |
36. | P R Roldán-Robles; A C Umaquinga-Criollo; J A García-Santillán; I D Herrera-Granda; I D García-Santillán A conceptual architecture for content analysis about abortion using the Twitter platform Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação., vol. 2019, no. E22, pp. 363-374, 2019, ISSN: 16469895. @article{Roldan2019,
title = {A conceptual architecture for content analysis about abortion using the Twitter platform},
author = {P R Roldán-Robles and A C Umaquinga-Criollo and J A García-Santillán and I D Herrera-Granda and I D García-Santillán},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85075303429&partnerID=40&md5=ba7996fb63672b80f3111934cc4dc083
http://www.risti.xyz/issues/ristie22.pdf
https://www.researchgate.net/publication/337621778_A_conceptual_architecture_for_content_analysis_about_abortion_using_the_twitter_platform},
issn = {16469895},
year = {2019},
date = {2019-08-01},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação.},
volume = {2019},
number = {E22},
pages = {363-374},
abstract = {This paper presents a conceptual architecture for content analysis about the opinions expressed on Twitter about abortion. The architecture consisted of five stages: authentication, data collection, data cleaning & processing, modeling & analysis, and presentation of results. In the data collection, a simple size of tweets sent from Ecuador was taken in 2018. All tweets that were not related to the topic were eliminated. In the modeling, it was separated into two categories for and against abortion, where the Naive Bayes and decision tree classifiers were used. Finally, the results were presented in the form of statistical graphs, word clouds and heat maps. During the development, the Google maps platform was also used, where the scripts were made in Python using the Integrated Development Environment (IDE) Spyder (Python 3.6), which is part of the Anaconda platform. The results obtained showed, on average, a majority position against abortion in Ecuador},
keywords = {abortion, content analysis, data mining, social networks, Twitter},
pubstate = {published},
tppubtype = {article}
}
This paper presents a conceptual architecture for content analysis about the opinions expressed on Twitter about abortion. The architecture consisted of five stages: authentication, data collection, data cleaning & processing, modeling & analysis, and presentation of results. In the data collection, a simple size of tweets sent from Ecuador was taken in 2018. All tweets that were not related to the topic were eliminated. In the modeling, it was separated into two categories for and against abortion, where the Naive Bayes and decision tree classifiers were used. Finally, the results were presented in the form of statistical graphs, word clouds and heat maps. During the development, the Google maps platform was also used, where the scripts were made in Python using the Integrated Development Environment (IDE) Spyder (Python 3.6), which is part of the Anaconda platform. The results obtained showed, on average, a majority position against abortion in Ecuador |
35. | Ana C Ramírez-Recalde; Ana C Umaquinga-Criollo; Edgar Maya-Olalla; Carlos Vásquez Computación en la Nube: Impacto en el modelo de consumo de las TI Cloud Computing: Impact on the TI consumption model Conference Tendencias tecnológicas aplicadas a la Ingeniería, vol. 1, UTN, 2019, ISBN: 978-9942-784-39-1. @conference{umaquingaCC2019,
title = {Computación en la Nube: Impacto en el modelo de consumo de las TI Cloud Computing: Impact on the TI consumption model},
author = {Ana C Ramírez-Recalde and Ana C Umaquinga-Criollo and Edgar Maya-Olalla and Carlos Vásquez},
editor = {UTN},
url = {https://issuu.com/utnuniversity/docs/ebook_tendencias_tecnol_gicas/122
https://www.researchgate.net/publication/335256842_Computacion_en_la_Nube_Impacto_en_el_modelo_de_consumo_de_las_TI_Cloud_Computing_Impact_on_the_TI_consumption_model},
isbn = {978-9942-784-39-1},
year = {2019},
date = {2019-06-29},
booktitle = {Tendencias tecnológicas aplicadas a la Ingeniería},
volume = {1},
pages = {123-135},
publisher = {UTN},
abstract = {Dada la necesidad actual de las empresas de ampliar la capacidad de sus recursos computacionales, Cloud Computing se ha convertido en una de las alternativas para resolver sus requerimientos con el uso de software, plataformas e infraestructura a través de la nube, reduciendo el costo de uso de hardware, mejorando el desempeño de las prestaciones de sus servicios. Cloud Computing se determina como un conglomerado de servicios referentes al almacenamiento y al tratamiento de aplicaciones desplegados a través de la red de acuerdo a los requerimientos de los usuarios que demandan cada vez mayor capacidad y disponibilidad de recursos. Este estudio señala los aspectos básicos de Cloud Computing; sus Modelos de servicio: Software como servicio (SaaS), Plataforma como servicio (PaaS), e Infraestructura como servicio (IaaS); Modelos de despliegue: Cloud pública, privada, híbrida, comunitaria; Arquitecturas de referencia: Cloud Consumer, Cloud provider, Cloud auditor, Cloud broker, Cloud carrier; y su impacto en el modelo de consumo de Tecnologías de Información. La investigación pretende dar una perspectiva del uso de Cloud Computing dirigido a personas y empresas que se inician o requieren utilizarlo, emplea el método descriptivo y documental que abarca un estudio de los fundamentos de Cloud Computing y del impacto que ha tenido en el campo empresarial, así como, procura ser material de estudio para la Carrera de Ingeniería en Electrónica y Redes de Comunicación de la Universidad Técnica del Norte en Entorno Virtual de Aprendizaje (EVA) utilizando Moodle y la metodología PACIE (Presencia, Alcance, Capacitación, Interacción, E-learning).},
keywords = {Computación en la nube; Cloud computing; Modelos de despliegue; modelos de servicio cloud computing; Arquitectura Cloud computing},
pubstate = {published},
tppubtype = {conference}
}
Dada la necesidad actual de las empresas de ampliar la capacidad de sus recursos computacionales, Cloud Computing se ha convertido en una de las alternativas para resolver sus requerimientos con el uso de software, plataformas e infraestructura a través de la nube, reduciendo el costo de uso de hardware, mejorando el desempeño de las prestaciones de sus servicios. Cloud Computing se determina como un conglomerado de servicios referentes al almacenamiento y al tratamiento de aplicaciones desplegados a través de la red de acuerdo a los requerimientos de los usuarios que demandan cada vez mayor capacidad y disponibilidad de recursos. Este estudio señala los aspectos básicos de Cloud Computing; sus Modelos de servicio: Software como servicio (SaaS), Plataforma como servicio (PaaS), e Infraestructura como servicio (IaaS); Modelos de despliegue: Cloud pública, privada, híbrida, comunitaria; Arquitecturas de referencia: Cloud Consumer, Cloud provider, Cloud auditor, Cloud broker, Cloud carrier; y su impacto en el modelo de consumo de Tecnologías de Información. La investigación pretende dar una perspectiva del uso de Cloud Computing dirigido a personas y empresas que se inician o requieren utilizarlo, emplea el método descriptivo y documental que abarca un estudio de los fundamentos de Cloud Computing y del impacto que ha tenido en el campo empresarial, así como, procura ser material de estudio para la Carrera de Ingeniería en Electrónica y Redes de Comunicación de la Universidad Técnica del Norte en Entorno Virtual de Aprendizaje (EVA) utilizando Moodle y la metodología PACIE (Presencia, Alcance, Capacitación, Interacción, E-learning). |
34. | Ana C Umaquinga-Criollo; Edgar Jaramillo D Vinueza Seguimiento y Acompañamiento académico a estudiantes con repitencia en la Carrera de Ingeniería en Electrónica y Redes de Comunicación: Fase Inicial Periodo Académico Marzo –Agosto 2016 Conference Rol de la Educación Superior frente a los desafíos sociales., vol. II, II Seminario Internacional. “Desarrollo Latinoamericano de la Educación Superior” UTN, Pasto 2018, 2019, ISBN: 978-9942-784-54-4. @conference{umaquinga2018redec,
title = {Seguimiento y Acompañamiento académico a estudiantes con repitencia en la Carrera de Ingeniería en Electrónica y Redes de Comunicación: Fase Inicial Periodo Académico Marzo –Agosto 2016},
author = {Ana C Umaquinga-Criollo and Edgar Jaramillo D Vinueza},
editor = {UTN},
url = {https://issuu.com/utnuniversity/docs/ebook_rol-de-la-educacion-superior-/53
https://www.researchgate.net/publication/335244335_Seguimiento_y_Acompanamiento_academico_a_estudiantes_con_repitencia_en_la_Carrera_de_Ingenieria_en_Electronica_y_Redes_de_Comunicacion_Fase_Inicial_Periodo_Academico_Marzo_-Agosto_2016},
isbn = {978-9942-784-54-4},
year = {2019},
date = {2019-05-14},
booktitle = {Rol de la Educación Superior frente a los desafíos sociales.},
volume = {II},
pages = {53},
publisher = {UTN},
address = {Pasto 2018},
organization = {II Seminario Internacional. “Desarrollo Latinoamericano de la Educación Superior”},
abstract = {La Carrera de Ingeniería en Electrónica y Redes de comunicación (CIERCOM) actualmente Carrera de Ingeniería en Telecomunicaciones (CITEL) de la Facultad de Ingeniería en Ciencias Aplicadas (FICA) de la Universidad Técnica del Norte (UTN) realiza seguimiento y acompañamiento académico a estudiantes con pérdida de semestre matriculados con segunda y tercera matrícula con el fin de disminuir el número de estudiantes con repitencia por semestre y mejorar el rendimiento académico de los estudiantes. La presente investigación realiza un estudio cualitativo, cuantitativo y descriptivo posterior a la elaboración de fichas de seguimiento a estudiantes con repitencia, como fase inicial se analiza la muestra de 15 estudiantes con 2da. matrícula asignados a una docente de la carrera de Ingeniería en Electrónica y Redes de Comunicación (CIERCOM) con el fin de determinar las principales causas de repitencia considerando factores familiares, económicos, sociológicos del estudiante por una parte mientras que por otra el proceso de enseñanza-aprendizaje del profesor en el periodo académico Marzo 2016 – Agosto 2016.},
keywords = {acompañamiento académico, educación superior, estudiantes de ingeniería, repitencia, seguimiento académico},
pubstate = {published},
tppubtype = {conference}
}
La Carrera de Ingeniería en Electrónica y Redes de comunicación (CIERCOM) actualmente Carrera de Ingeniería en Telecomunicaciones (CITEL) de la Facultad de Ingeniería en Ciencias Aplicadas (FICA) de la Universidad Técnica del Norte (UTN) realiza seguimiento y acompañamiento académico a estudiantes con pérdida de semestre matriculados con segunda y tercera matrícula con el fin de disminuir el número de estudiantes con repitencia por semestre y mejorar el rendimiento académico de los estudiantes. La presente investigación realiza un estudio cualitativo, cuantitativo y descriptivo posterior a la elaboración de fichas de seguimiento a estudiantes con repitencia, como fase inicial se analiza la muestra de 15 estudiantes con 2da. matrícula asignados a una docente de la carrera de Ingeniería en Electrónica y Redes de Comunicación (CIERCOM) con el fin de determinar las principales causas de repitencia considerando factores familiares, económicos, sociológicos del estudiante por una parte mientras que por otra el proceso de enseñanza-aprendizaje del profesor en el periodo académico Marzo 2016 – Agosto 2016. |
33. | M T Encalada-Grijalva; S K Narváez-Pupiales; A C Umaquinga-Criollo; L E Suárez-Zambrano; D H Peluffo-Ordóñez Medical dispenser of control and monitoring services for the elderly health care institute hogar del anciano “San Vicente de Paúl” from atuntaqui (Ecuador) Journal Article In: Revista Ibérica de Sistemas e Tecnologias de Informação., vol. 2019, no. E19, pp. 595-607, 2019, ISSN: 1646-9895. @article{Encalada2019,
title = {Medical dispenser of control and monitoring services for the elderly health care institute hogar del anciano “San Vicente de Paúl” from atuntaqui (Ecuador)},
author = {M T Encalada-Grijalva and S K Narváez-Pupiales and A C Umaquinga-Criollo and L E Suárez-Zambrano and D H Peluffo-Ordóñez},
url = {https://search.proquest.com/openview/ca355d43bc1ac0d2c3428cf5f1030ce1
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85069226730&partnerID=40&md5=47b09604229078717e7fb0d094134ab8
http://www.risti.xyz/issues/ristie19.pdf
https://www.researchgate.net/publication/337621992_Medical_dispenser_of_control_and_monitoring_services_for_the_elderly_health_care_institute_hogar_del_anciano_San_Vicente_de_Paul_from_atuntaqui_Ecuador_Dispensador_medico_de_control_y_monitoreo_para_e},
issn = {1646-9895},
year = {2019},
date = {2019-04-01},
journal = {Revista Ibérica de Sistemas e Tecnologias de Informação.},
volume = {2019},
number = {E19},
pages = {595-607},
abstract = {Abstract: Aging is a stage of life of the human being that presents psychological, social, physiological changes, as well as the deterioration of their physical capacities. Elderly Home “San Vicente de Paúl” of the city of Atuntaqui (Ecuador), older adults take medicines to treat diseases such as high blood pressure, osteoarthritis, osteoporosis, cognitive deterioration, depression, hypothyroidism, gastritis, anemia, among others. The medical staff, because they do not keep a record of the dosage of medications in the pre-established hours, has caused delays, omissions in the same and a decline in their health status. The present research designs and develops an embedded system to control and monitor the supply of medicines through two types of notifications to the medical department: In the first instance, by sending text messages via GSM; in the absence of a response, the second notification is issued by means of a voice call to the nurse on duty in order to safeguard the adequate intake of medicine and comply fully with the treatments prescribed by the doctor and improve the quality of life of the adult higher.
Resumen: El envejecimiento es una etapa de vida del ser humano que presenta cambios psicológicos, sociales, fisiológicos, así como el deterioro de sus capacidades físicas. En el Hogar del Anciano “San Vicente de Paúl” de la ciudad de Atuntaqui (Ecuador), los adultos mayores toman medicinas para tratar enfermedades como: la hipertensión arterial, artrosis, osteoporosis, deterioro cognitivo, depresión, hipotiroidismo, gastritis, anemia, entre otras. El personal médico al no llevar un registro de la posología de medicamentos en los horarios preestablecidos ha
ocasionado retrasos, omisiones en los mismos y recaídas en su estado de salud.
La presente investigación diseña y desarrolla un sistema embebido para controlar y monitorear el suministro de medicinas mediante dos tipos de notificaciones al departamento médico: en primera instancia por el envío de mensajes de texto vía GSM; al no existir respuesta se emite la segunda notificación por medio de una llamada de voz a la enfermera de turno con la finalidad de precautelar la ingesta adecuada de medicina y cumplir a cabalidad con los tratamientos prescritos por el médico y mejorar la calidad de vida del adulto mayor.},
keywords = {Adultos mayores, Arduino, Base de Datos, Dispensador Electrónico, MySQL},
pubstate = {published},
tppubtype = {article}
}
Abstract: Aging is a stage of life of the human being that presents psychological, social, physiological changes, as well as the deterioration of their physical capacities. Elderly Home “San Vicente de Paúl” of the city of Atuntaqui (Ecuador), older adults take medicines to treat diseases such as high blood pressure, osteoarthritis, osteoporosis, cognitive deterioration, depression, hypothyroidism, gastritis, anemia, among others. The medical staff, because they do not keep a record of the dosage of medications in the pre-established hours, has caused delays, omissions in the same and a decline in their health status. The present research designs and develops an embedded system to control and monitor the supply of medicines through two types of notifications to the medical department: In the first instance, by sending text messages via GSM; in the absence of a response, the second notification is issued by means of a voice call to the nurse on duty in order to safeguard the adequate intake of medicine and comply fully with the treatments prescribed by the doctor and improve the quality of life of the adult higher.
Resumen: El envejecimiento es una etapa de vida del ser humano que presenta cambios psicológicos, sociales, fisiológicos, así como el deterioro de sus capacidades físicas. En el Hogar del Anciano “San Vicente de Paúl” de la ciudad de Atuntaqui (Ecuador), los adultos mayores toman medicinas para tratar enfermedades como: la hipertensión arterial, artrosis, osteoporosis, deterioro cognitivo, depresión, hipotiroidismo, gastritis, anemia, entre otras. El personal médico al no llevar un registro de la posología de medicamentos en los horarios preestablecidos ha
ocasionado retrasos, omisiones en los mismos y recaídas en su estado de salud.
La presente investigación diseña y desarrolla un sistema embebido para controlar y monitorear el suministro de medicinas mediante dos tipos de notificaciones al departamento médico: en primera instancia por el envío de mensajes de texto vía GSM; al no existir respuesta se emite la segunda notificación por medio de una llamada de voz a la enfermera de turno con la finalidad de precautelar la ingesta adecuada de medicina y cumplir a cabalidad con los tratamientos prescritos por el médico y mejorar la calidad de vida del adulto mayor. |
2018
|
32. | Paul D Rosero-Montalvo; Jorge A Caraguay-Procel; Edgar D Jaramillo; Jaime M Michilena-Calderón; Ana C Umaquinga-Criollo; Mario Mediavilla-Valverde; Miguel A Ruiz; Luis A Beltrán; Diego H Peluffo Air Quality Monitoring Intelligent System Using Machine Learning Techniques Conference 2018 International Conference on Information Systems and Computer Science (INCISCOS), IEEE, 2018, ISBN: 978-1-5386-7612-7, (ISBN Information: Electronic ISBN: 978-1-5386-7612-7 Print on Demand(PoD) ISBN: 978-1-5386-7613-4). @conference{Rosero2018I,
title = {Air Quality Monitoring Intelligent System Using Machine Learning Techniques},
author = {Paul D Rosero-Montalvo and Jorge A Caraguay-Procel and Edgar D Jaramillo and Jaime M Michilena-Calderón and Ana C Umaquinga-Criollo and Mario Mediavilla-Valverde and Miguel A Ruiz and Luis A Beltrán and Diego H Peluffo},
editor = {IEEE Xplore},
url = {https://ieeexplore.ieee.org/document/8564511/authors#authors},
doi = {10.1109/INCISCOS.2018.00019},
isbn = {978-1-5386-7612-7},
year = {2018},
date = {2018-12-06},
booktitle = {2018 International Conference on Information Systems and Computer Science (INCISCOS)},
publisher = {IEEE},
abstract = {Environment monitoring is so important because it is based on the first right of people, life and health. For this reason, this system monitoring air quality with different sensor nodes in the Ibarra that evaluate the parameters of CO2, NOx, UV Light, Temperature and Humidity. The data analysis through machine learning algorithms allow the system to classify autonomously if a certain geographical location is exceeding the established emission limits of gases. As a result, the k-Nearest Neighbor algorithm presented a great classification performance when selecting the most contaminated sectors.},
note = {ISBN Information: Electronic ISBN: 978-1-5386-7612-7 Print on Demand(PoD) ISBN: 978-1-5386-7613-4},
keywords = {air quality, intelligent system, monitoring system},
pubstate = {published},
tppubtype = {conference}
}
Environment monitoring is so important because it is based on the first right of people, life and health. For this reason, this system monitoring air quality with different sensor nodes in the Ibarra that evaluate the parameters of CO2, NOx, UV Light, Temperature and Humidity. The data analysis through machine learning algorithms allow the system to classify autonomously if a certain geographical location is exceeding the established emission limits of gases. As a result, the k-Nearest Neighbor algorithm presented a great classification performance when selecting the most contaminated sectors. |
31. | Tatyana K Saltos-Echeverría; Ana C Umaquinga-Criollo; Sandra K Narváez-Pupiales Presupuesto participativo, inclusión y desarrollo social en el Municipio de Cotacachi, en el período 2001 – 2008 Inproceedings In: REDU (Ed.): REDU VI Memorias del Congreso, pp. 199, UTN, 2018, ISBN: 978-9942-784-30-8. @inproceedings{saltosb12018,
title = {Presupuesto participativo, inclusión y desarrollo social en el Municipio de Cotacachi, en el período 2001 – 2008},
author = {Tatyana K Saltos-Echeverría and Ana C Umaquinga-Criollo and Sandra K Narváez-Pupiales},
editor = {REDU},
url = {https://issuu.com/utnuniversity/docs/ebook_memorias_del_vi_congreso_redu},
isbn = {978-9942-784-30-8},
year = {2018},
date = {2018-12-05},
booktitle = {REDU VI Memorias del Congreso},
volume = {VI},
pages = {199},
publisher = {UTN},
abstract = {En esta investigación se presenta el caso de estudio del proceso de implementación del Presupuesto Participativo en el cantón Cotacachi entre los periodos 2001 y 2008. Se aborda la formalización del presupuesto como un instrumento o herramienta para fortalecer la Democracia Participativa. Este estudio presenta el mecanismo por el cual el Presupuesto Participativo opera en el cantón, describiendo el proceso metodológico implementado a través de los diferentes espacios de análisis, priorización y concertación de las obras y proyectos que aportan al desarrollo local inclusivo, equitativo, solidario y con justicia social. Finalmente, se presentan los resultados obtenidos de los cambios democráticos y participativos introducidos en Cotacachi, gracias a la aplicación del modelo de gestión participativo.
Palabras clave: Democracia Participativa, Presupuesto Participativo, Legitimidad, Desarrollo Local Inclusivo, Cotacachi.
Abstract
This research presents the case study of the Participatory Budget’s implementation process in Cotacachi between 2001 and 2008. The budget was formalized as an instrument or tool to strengthen the Participative Democracy. This paper presents the mechanism by which the Participatory Budget operates in the town, describing the methodological process implemented through the different spaces of analysis, prioritization and coordination of the works and projects that contribute to inclusive, equitable, supportive, and socially just local development. Finally, it presents the results obtained from the democratic and participative changes, thanks to the application of the participatory management model.
Keywords: Participative Democracy, Participative Budget, Legitimacy, inclusive local development, Cotacachi.},
keywords = {: Democracia Participativa, Cotacachi, Desarrollo Local Inclusivo, legitimidad, Presupuesto Participativo},
pubstate = {published},
tppubtype = {inproceedings}
}
En esta investigación se presenta el caso de estudio del proceso de implementación del Presupuesto Participativo en el cantón Cotacachi entre los periodos 2001 y 2008. Se aborda la formalización del presupuesto como un instrumento o herramienta para fortalecer la Democracia Participativa. Este estudio presenta el mecanismo por el cual el Presupuesto Participativo opera en el cantón, describiendo el proceso metodológico implementado a través de los diferentes espacios de análisis, priorización y concertación de las obras y proyectos que aportan al desarrollo local inclusivo, equitativo, solidario y con justicia social. Finalmente, se presentan los resultados obtenidos de los cambios democráticos y participativos introducidos en Cotacachi, gracias a la aplicación del modelo de gestión participativo.
Palabras clave: Democracia Participativa, Presupuesto Participativo, Legitimidad, Desarrollo Local Inclusivo, Cotacachi.
Abstract
This research presents the case study of the Participatory Budget’s implementation process in Cotacachi between 2001 and 2008. The budget was formalized as an instrument or tool to strengthen the Participative Democracy. This paper presents the mechanism by which the Participatory Budget operates in the town, describing the methodological process implemented through the different spaces of analysis, prioritization and coordination of the works and projects that contribute to inclusive, equitable, supportive, and socially just local development. Finally, it presents the results obtained from the democratic and participative changes, thanks to the application of the participatory management model.
Keywords: Participative Democracy, Participative Budget, Legitimacy, inclusive local development, Cotacachi. |
30. | Umaquinga A C ¿La canción del pollito pío en clase de programación? Journal Article In: Para el Aula, no. 28, pp. 36-37, 2018, ISSN: 2528-8113. @article{umaquingasf2018,
title = {¿La canción del pollito pío en clase de programación?},
author = {Umaquinga A C },
editor = {IDEA Instituto Enseñanza Aprendizaje. Universidad San Francisco de de Quito},
url = {https://issuu.com/usfq/docs/para_el_aula_ed-28_digital/36
http://www.usfq.edu.ec/publicaciones/para_el_aula/Documents/para_el_aula_28/pea_028_0015.pdf
http://www.usfq.edu.ec/publicaciones/para_el_aula/Paginas/revistas/paraelaula28.aspx},
issn = {2528-8113},
year = {2018},
date = {2018-12-01},
journal = {Para el Aula},
number = {28},
pages = {36-37},
abstract = {Testimonio de una orgullosa profesora de Programación Orientada a Objetos de la carrera de Ingeniería en Electrónica y Redes de Comunicación de la Universidad Técnica del Norte, cuyos alumnos utilizaron canciones conocidas y populares para explicar y entender el tema de “herencia” en clase, así como practicar el trabajo en equipo.},
keywords = {herencia, motivación, pollito pío, programación, Universidad Técnica del Norte},
pubstate = {published},
tppubtype = {article}
}
Testimonio de una orgullosa profesora de Programación Orientada a Objetos de la carrera de Ingeniería en Electrónica y Redes de Comunicación de la Universidad Técnica del Norte, cuyos alumnos utilizaron canciones conocidas y populares para explicar y entender el tema de “herencia” en clase, así como practicar el trabajo en equipo. |
29. | Paul D Rosero-Montalvo; Anderson Dibujes; Carlos Vásquez-Ayala; Ana Umaquinga-Criollo; Jaime R Michilena; Luis Suaréz; Stefany Flores; Daniel Jaramillo Intelligent System of Squat Analysis Exercise to Prevent Back Injuries Conference Intelligent Technologies and Robotics, Springer, Cham, 2018, ISBN: Print ISBN 978-3-030-02827-5, (Online ISBN 978-3-030-02828-2
Information and Communication Technologies of Ecuador (TIC.EC)). @conference{RoseroMontalvo2019a,
title = {Intelligent System of Squat Analysis Exercise to Prevent Back Injuries},
author = {Paul D Rosero-Montalvo and Anderson Dibujes and Carlos Vásquez-Ayala and Ana Umaquinga-Criollo and Jaime R Michilena and Luis Suaréz and Stefany Flores and Daniel Jaramillo},
editor = {Springer},
url = {https://link.springer.com/chapter/10.1007/978-3-030-02828-2_15},
doi = {10.1007/978-3-030-02828-2_15},
isbn = {Print ISBN 978-3-030-02827-5},
year = {2018},
date = {2018-10-18},
booktitle = {Intelligent Technologies and Robotics},
pages = {193-205},
publisher = {Springer, Cham},
abstract = {The sports ergonomics study allows a bio-mechanical analysis in order to evaluate the impact produced by different muscle conditioning exercises such as the squat. This exercise, if carried out in an erroneous way, it can cause lumbar injuries. The present electronic system acquire the data of the Smith bar and the back by means of accelerometer sensors. This is done in order to implement an intelligent algorithm that allows to recognize if the athlete performs the exercise properly. For this, a stage of prototypes selection and a comparison of classification algorithms (CA) is carried out. Finally, a quantitative measure of equilibrium between both criteria is established for its proper selection. As a result, the k-Nearest Neighbors algorithm with k = 5 achieves a 96% performance and a 50% training matrix reduction.},
note = {Online ISBN 978-3-030-02828-2
Information and Communication Technologies of Ecuador (TIC.EC)},
keywords = {Back injuries, Embedded systems, Intelligent systems, Squat analysis},
pubstate = {published},
tppubtype = {conference}
}
The sports ergonomics study allows a bio-mechanical analysis in order to evaluate the impact produced by different muscle conditioning exercises such as the squat. This exercise, if carried out in an erroneous way, it can cause lumbar injuries. The present electronic system acquire the data of the Smith bar and the back by means of accelerometer sensors. This is done in order to implement an intelligent algorithm that allows to recognize if the athlete performs the exercise properly. For this, a stage of prototypes selection and a comparison of classification algorithms (CA) is carried out. Finally, a quantitative measure of equilibrium between both criteria is established for its proper selection. As a result, the k-Nearest Neighbors algorithm with k = 5 achieves a 96% performance and a 50% training matrix reduction. |
28. | Ariana De Los Ángeles Anrrango Sanguino; Ómar Ricardo Oña Rocha; Ana Cristina Umaquinga Criollo Electrónica Educativa que promueve el desarrollo de las habilidades motoras gruesas básicas en niños de edad temprana Conference Gestión, Calidad y desarrollo en las Facultades de Ingeniería.
Encuentro Internacional De Educación en Ingeniería , Asociación Colombiana de Facultades de Ingeniería 2018, ISBN: 978-958-680-084-6. @conference{Anrrango2018,
title = {Electrónica Educativa que promueve el desarrollo de las habilidades motoras gruesas básicas en niños de edad temprana},
author = {Ariana De Los Ángeles Anrrango Sanguino and Ómar Ricardo Oña Rocha and Ana Cristina Umaquinga Criollo},
url = {https://www.acofipapers.org/index.php/eiei/article/view/368},
isbn = {978-958-680-084-6},
year = {2018},
date = {2018-09-18},
booktitle = {Gestión, Calidad y desarrollo en las Facultades de Ingeniería.
Encuentro Internacional De Educación en Ingeniería },
organization = {Asociación Colombiana de Facultades de Ingeniería},
abstract = {La motricidad se define como "el control que el niño(a) es capaz de tener sobre su propio cuerpo".(Madrona, Jordán, & Barreto, 2008) El desarrollo de las habilidades motoras gruesas a temprana edad en los niños de 3 a 6 años involucra el movimiento de los músculos largos de su cuerpo, incrementa la conciencia de su actividad muscular como el correr, brincar, promueve el desarrollo del sistema nervioso vestibular, así como su confianza y el dominio de su entorno espacial. Entre los métodos de enseñanza-aprendizaje para este rango de edades se encuentra el aprendizaje lúdico como los métodos: Educación personalizada, Agazzi que se enfoca al desarrollo de la vista, el Fröebeliano aporta al desarrollo para el oído y audición, mientras que, el Montessori se orienta al control postural y equilibrio, los mismos que, tienen como característica principal el juego, ya que genera en ellos un mejor uso de sus emociones y comportamientos, reduciendo su estrés y convirtiéndose un incentivo para aprender. Según (Piaget & Inhelder, 1997) "El conocimiento no se obtiene de los objetos sino de las acciones que realice sobre los objetos", en consecuencia, la aplicación de métodos lúdicos de enseñanza-aprendizaje mediante el uso de la tecnología, como dispositivos electrónicos y TICs pretende lograr dicha meta. En este contexto, la implementación de dispositivos electrónicos entre ellos prototipos electrónicos como recursos que faciliten el aprendizaje y enseñanza lúdicos, pretende contribuir a los beneficios significativos sobre la enseñanza tradicional.
Abstract
Motor skills are defined as "the control that the child is able to have on his own body." (Madrona, Jordán, & Barreto, 2008)
The development of gross motor skills at an early age in children aged 3 to 6 years involves the movement of the long muscles of their body, increases the awareness of their muscular activity such as running, jumping, promotes the development of the vestibular nervous system, as well as their confidence and the control of their space environment.
Among the methods of teaching and learning for this age range is ludic learning as the methods: Personalized education, Agazzi that focuses on the development of sight, the Fröebeliano contributes to the development for hearing and hearing, while the Montessori it is oriented to postural control and balance, the same ones that have the main characteristic of the game, since it generates in them a better use of their emotions and behaviors, reducing their stress and becoming an incentive to learn.
According to (Piaget & Inhelder, 1997) "Knowledge is not obtained from the objects but from the actions that are performed on the objects", consequently, the application of playful methods of teaching and learning through the use of technology, such as electronic devices and ICTs aims to achieve that goal.
In this context, the implementation of electronic devices including electronic prototypes as resources that facilitate ludic learning and teaching, aims to contribute to the significant benefits of traditional teaching.
This study is descriptive, it covers the main approaches in the aspect of play methods and their application, as well as the results of these proposals, in order to be a base material or reference for future research in the area.},
keywords = {dispositivos electrónicos, enseñanza lúdica, innovación tecnológica, metodologías lúdicas, Motricidad gruesa},
pubstate = {published},
tppubtype = {conference}
}
La motricidad se define como "el control que el niño(a) es capaz de tener sobre su propio cuerpo".(Madrona, Jordán, & Barreto, 2008) El desarrollo de las habilidades motoras gruesas a temprana edad en los niños de 3 a 6 años involucra el movimiento de los músculos largos de su cuerpo, incrementa la conciencia de su actividad muscular como el correr, brincar, promueve el desarrollo del sistema nervioso vestibular, así como su confianza y el dominio de su entorno espacial. Entre los métodos de enseñanza-aprendizaje para este rango de edades se encuentra el aprendizaje lúdico como los métodos: Educación personalizada, Agazzi que se enfoca al desarrollo de la vista, el Fröebeliano aporta al desarrollo para el oído y audición, mientras que, el Montessori se orienta al control postural y equilibrio, los mismos que, tienen como característica principal el juego, ya que genera en ellos un mejor uso de sus emociones y comportamientos, reduciendo su estrés y convirtiéndose un incentivo para aprender. Según (Piaget & Inhelder, 1997) "El conocimiento no se obtiene de los objetos sino de las acciones que realice sobre los objetos", en consecuencia, la aplicación de métodos lúdicos de enseñanza-aprendizaje mediante el uso de la tecnología, como dispositivos electrónicos y TICs pretende lograr dicha meta. En este contexto, la implementación de dispositivos electrónicos entre ellos prototipos electrónicos como recursos que faciliten el aprendizaje y enseñanza lúdicos, pretende contribuir a los beneficios significativos sobre la enseñanza tradicional.
Abstract
Motor skills are defined as "the control that the child is able to have on his own body." (Madrona, Jordán, & Barreto, 2008)
The development of gross motor skills at an early age in children aged 3 to 6 years involves the movement of the long muscles of their body, increases the awareness of their muscular activity such as running, jumping, promotes the development of the vestibular nervous system, as well as their confidence and the control of their space environment.
Among the methods of teaching and learning for this age range is ludic learning as the methods: Personalized education, Agazzi that focuses on the development of sight, the Fröebeliano contributes to the development for hearing and hearing, while the Montessori it is oriented to postural control and balance, the same ones that have the main characteristic of the game, since it generates in them a better use of their emotions and behaviors, reducing their stress and becoming an incentive to learn.
According to (Piaget & Inhelder, 1997) "Knowledge is not obtained from the objects but from the actions that are performed on the objects", consequently, the application of playful methods of teaching and learning through the use of technology, such as electronic devices and ICTs aims to achieve that goal.
In this context, the implementation of electronic devices including electronic prototypes as resources that facilitate ludic learning and teaching, aims to contribute to the significant benefits of traditional teaching.
This study is descriptive, it covers the main approaches in the aspect of play methods and their application, as well as the results of these proposals, in order to be a base material or reference for future research in the area. |
27. | Sandra Karina Narvaez-Pupiales; Ana Cristina Umaquinga Criollo; Tatyana Katherine Saltos ; Echeverria Provisión de Mecanismos de Calidad de Servicio (QoS) para WLANs Unificadas. Provision of Quality of Service (QoS) Mechanisms for Unified WLANs Conference El papel de la Ingeniería en tiempos de construcción de paz y buen vivir, Universidad de Nariño, 2018, ISBN: 978-958-8958-65-1. @conference{narvaezb,
title = {Provisión de Mecanismos de Calidad de Servicio (QoS) para WLANs Unificadas. Provision of Quality of Service (QoS) Mechanisms for Unified WLANs},
author = {Sandra Karina Narvaez-Pupiales and Ana Cristina Umaquinga Criollo and Tatyana Katherine Saltos ; Echeverria},
editor = {Universidad de Nariño},
url = {https://www.researchgate.net/publication/336749747_PROVISION_DE_MECANISMOS_DE_CALIDAD_DE_SERVICIO_QoS_PARA_WLANs_UNIFICADAS},
isbn = {978-958-8958-65-1},
year = {2018},
date = {2018-09-15},
booktitle = {El papel de la Ingeniería en tiempos de construcción de paz y buen vivir},
pages = {184-192},
publisher = {Universidad de Nariño},
abstract = {Resumen:
El presente trabajo destacó la importancia de gestionar, optimizar los recursos y performance de las WLANs unificadas, con el objetivo principal de potenciar el acceso a la información de los diferentes entes del quehacer diario tanto para instituciones de carácter público o privado. De manera que las necesidades actuales de movilidad y capacidad de los usuarios requiere una especial atención para el fortalecimiento de la infraestructura inalámbrica y de los recursos de red traducidos en una prestación de servicios de mejor calidad que pueden ser potenciados a través del análisis e implementación de mecanismos de QoS WLAN, sin dejar de lado las consideraciones de diseño, planficación y tecnología robusta que estén en la capacidad de solventar o satisfacer la demanda actual de aplicaciones críticas y en tiempo real.
Inicialmente, el estándar que define las WLANs (IEEE 802.11) no consideraba mecanismos de calidad de servicio, pero a raíz de solventar las necesidades aparece la variante 802.11e para dar fin a los inconvenientes presentados en este tipo de infraestructuras debido a la evolución y convergencia de los servicios. Es por eso que este estudio pretende dar a conocer los lineamientos y recomendaciones fundamentales para el despliegue de Calidad de Servicio en las redes inalámbricas de área Local.
Abstract:
This paper highlights the importance of managing, optimizing the resources and performance of unified WLANs. The main objective is related with the access to information of the different entities of the daily task both public or private institutions. Thereby, the current mobility and capacity needs of users require special attention for the strengthening of the wireless infrastructure and network resources translated into a provision of better quality services that can be enhanced through the analysis and implementation of WLAN QoS mechanisms, without leaving aside the consideration of design, planning and robust technology which are able to satisfy the current demand of critical applications in real time.
Initially, the standard that defines the WLANs (IEEE 802.11) did not consider quality of service mechanisms, but as a result of solving the needs, the 802.11e variant appears to put an end to the inconveniences presented in this type of infrastructure due to the evolution and convergence of services. That is why this study aims to publicize the fundamental guidelines and recommendations for the deployment of Quality of Service in local area wireless networks.},
keywords = {Access Categories, Access Points, Calidad de Servicio, Categorías de Acceso, cobertura, coverage, Puntos de Acceso, Quality of Service, WLAN},
pubstate = {published},
tppubtype = {conference}
}
Resumen:
El presente trabajo destacó la importancia de gestionar, optimizar los recursos y performance de las WLANs unificadas, con el objetivo principal de potenciar el acceso a la información de los diferentes entes del quehacer diario tanto para instituciones de carácter público o privado. De manera que las necesidades actuales de movilidad y capacidad de los usuarios requiere una especial atención para el fortalecimiento de la infraestructura inalámbrica y de los recursos de red traducidos en una prestación de servicios de mejor calidad que pueden ser potenciados a través del análisis e implementación de mecanismos de QoS WLAN, sin dejar de lado las consideraciones de diseño, planficación y tecnología robusta que estén en la capacidad de solventar o satisfacer la demanda actual de aplicaciones críticas y en tiempo real.
Inicialmente, el estándar que define las WLANs (IEEE 802.11) no consideraba mecanismos de calidad de servicio, pero a raíz de solventar las necesidades aparece la variante 802.11e para dar fin a los inconvenientes presentados en este tipo de infraestructuras debido a la evolución y convergencia de los servicios. Es por eso que este estudio pretende dar a conocer los lineamientos y recomendaciones fundamentales para el despliegue de Calidad de Servicio en las redes inalámbricas de área Local.
Abstract:
This paper highlights the importance of managing, optimizing the resources and performance of unified WLANs. The main objective is related with the access to information of the different entities of the daily task both public or private institutions. Thereby, the current mobility and capacity needs of users require special attention for the strengthening of the wireless infrastructure and network resources translated into a provision of better quality services that can be enhanced through the analysis and implementation of WLAN QoS mechanisms, without leaving aside the consideration of design, planning and robust technology which are able to satisfy the current demand of critical applications in real time.
Initially, the standard that defines the WLANs (IEEE 802.11) did not consider quality of service mechanisms, but as a result of solving the needs, the 802.11e variant appears to put an end to the inconveniences presented in this type of infrastructure due to the evolution and convergence of services. That is why this study aims to publicize the fundamental guidelines and recommendations for the deployment of Quality of Service in local area wireless networks. |
26. | Ana Cristina Umaquinga-Criollo; Luis Edilberto Suárez-Zambrano; Omar Ricardo Oña-Rocha El aprendizaje automático: Importancia, avances, técnicas y aplicaciones. Machine learning: Importance, advances, techniques and applications Conference El papel de la Ingeniería en tiempos de construcción de paz y buen vivir., Universidad de Nariño, 2018, ISBN: 978-958-8958-65-1.. @conference{umaquinga2018b,
title = {El aprendizaje automático: Importancia, avances, técnicas y aplicaciones. Machine learning: Importance, advances, techniques and applications},
author = {Ana Cristina Umaquinga-Criollo and Luis Edilberto Suárez-Zambrano and Omar Ricardo Oña-Rocha},
editor = {Universidad de Nariño},
url = {https://www.researchgate.net/publication/336749930_El_aprendizaje_automatico_Importancia_avances_tecnicas_y_aplicaciones_Machine_learning_Importance_advances_techniques_and_applications},
isbn = {978-958-8958-65-1.},
year = {2018},
date = {2018-09-15},
booktitle = {El papel de la Ingeniería en tiempos de construcción de paz y buen vivir.},
pages = {176-186},
publisher = {Universidad de Nariño},
abstract = {Resumen
Este trabajo presenta un estudio descriptivo de las técnicas de aprendizaje automático llamado machine learning, enfocándose en las técnicas de aprendizaje supervisado y no supervisado, con la presentación de las técnicas exitosas para determinados casos de estudio, experimentación y puesta en producción.
Esta investigación pretende ser de aporte a la comunidad científica y empresarial, principalmente investigadores que inician y quienes experimentan sus estudios en análisis comparativos en esta área de vital importancia.
Este trabajo es de tipo investigativo, documental y exploratorio. Se realiza un recorrido por los principales tipos de aprendizaje automático, avances y proyectos enfocados a Inteligencia Artificial.
Abstract
This paper presents a descriptive study of machine learning techniques called machine learning, focusing on supervised and unsupervised learning techniques, with the presentation of successful techniques for specific cases of study, experimentation and production.
This research aims to be of contribution to the scientific and business community, mainly researchers who initiate and who experience their studies in comparative analysis in this area of vital importance.
This work is of investigative, documentary and exploratory type. A tour through the main types of machine learning, advances and projects focused on Artificial Intelligence.},
keywords = {Aplicaciones de Aprendizaje Automático, Aprendizaje Automático, Aprendizaje no-Supervisado, Aprendizaje Supervisado, Artificial Intelligence, Inteligencia Artificial, Machine Learning, Machine Learning Applications, Supervised Learning, Unsupervised Learning},
pubstate = {published},
tppubtype = {conference}
}
Resumen
Este trabajo presenta un estudio descriptivo de las técnicas de aprendizaje automático llamado machine learning, enfocándose en las técnicas de aprendizaje supervisado y no supervisado, con la presentación de las técnicas exitosas para determinados casos de estudio, experimentación y puesta en producción.
Esta investigación pretende ser de aporte a la comunidad científica y empresarial, principalmente investigadores que inician y quienes experimentan sus estudios en análisis comparativos en esta área de vital importancia.
Este trabajo es de tipo investigativo, documental y exploratorio. Se realiza un recorrido por los principales tipos de aprendizaje automático, avances y proyectos enfocados a Inteligencia Artificial.
Abstract
This paper presents a descriptive study of machine learning techniques called machine learning, focusing on supervised and unsupervised learning techniques, with the presentation of successful techniques for specific cases of study, experimentation and production.
This research aims to be of contribution to the scientific and business community, mainly researchers who initiate and who experience their studies in comparative analysis in this area of vital importance.
This work is of investigative, documentary and exploratory type. A tour through the main types of machine learning, advances and projects focused on Artificial Intelligence. |
25. | Jose Alejandro Salazar-Castro; Paul D Rosero-Montalvo; Diego Fernando Peña-Unigarro; Ana Cristina Umaquinga-Criollo; Zenaida Castillo-Marrero; Edgardo Javier Revelo-Fuelagán; Diego Hernán Peluffo-Ordóñez; César Germán Castellanos-Domínguez A Novel Color-Based Data Visualization Approach Using a Circular Interaction Model and Dimensionality Reduction Conference Advances in Neural Networks - ISNN 2018, vol. 10878, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-92537-0, (Print ISBN: 978-3-319-92536-3). @conference{10.1007/978-3-319-92537-0_64,
title = {A Novel Color-Based Data Visualization Approach Using a Circular Interaction Model and Dimensionality Reduction},
author = {Jose Alejandro Salazar-Castro and Paul D Rosero-Montalvo and Diego Fernando Peña-Unigarro and Ana Cristina Umaquinga-Criollo and Zenaida Castillo-Marrero and Edgardo Javier Revelo-Fuelagán and Diego Hernán Peluffo-Ordóñez and César Germán Castellanos-Domínguez},
editor = {Tingwen Huang and Jiancheng Lv and Changyin Sun and Alexander V Tuzikov},
url = {https://link.springer.com/chapter/10.1007%2F978-3-319-92537-0_64},
doi = {10.1007/978-3-319-92537-0_64},
isbn = {978-3-319-92537-0},
year = {2018},
date = {2018-05-26},
booktitle = {Advances in Neural Networks - ISNN 2018},
volume = {10878},
pages = {557-567},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Dimensionality reduction (DR) methods are able to produce low-dimensional representations of an input data sets which may become intelligible for human perception. Nonetheless, most existing DR approaches lack the ability to naturally provide the users with the faculty of controlability and interactivity. In this connection, data visualization (DataVis) results in an ideal complement. This work presents an integration of DR and DataVis through a new approach for data visualization based on a mixture of DR resultant representations while using visualization principle. Particularly, the mixture is done through a weighted sum, whose weighting factors are defined by the user through a novel interface. The interface's concept relies on the combination of the color-based and geometrical perception in a circular framework so that the users may have a at hand several indicators (shape, color, surface size) to make a decision on a specific data representation. Besides, pairwise similarities are plotted as a non-weighted graph to include a graphic notion of the structure of input data. Therefore, the proposed visualization approach enables the user to interactively combine DR methods, while providing information about the structure of original data, making then the selection of a DR scheme more intuitive.},
note = {Print ISBN: 978-3-319-92536-3},
keywords = {Data visualization, Dimensionality reduction, Interactive interface, Pairwise similarity},
pubstate = {published},
tppubtype = {conference}
}
Dimensionality reduction (DR) methods are able to produce low-dimensional representations of an input data sets which may become intelligible for human perception. Nonetheless, most existing DR approaches lack the ability to naturally provide the users with the faculty of controlability and interactivity. In this connection, data visualization (DataVis) results in an ideal complement. This work presents an integration of DR and DataVis through a new approach for data visualization based on a mixture of DR resultant representations while using visualization principle. Particularly, the mixture is done through a weighted sum, whose weighting factors are defined by the user through a novel interface. The interface's concept relies on the combination of the color-based and geometrical perception in a circular framework so that the users may have a at hand several indicators (shape, color, surface size) to make a decision on a specific data representation. Besides, pairwise similarities are plotted as a non-weighted graph to include a graphic notion of the structure of input data. Therefore, the proposed visualization approach enables the user to interactively combine DR methods, while providing information about the structure of original data, making then the selection of a DR scheme more intuitive. |
24. | P D Rosero-Montalvo; A C Umaquinga-Criollo; S Flores; L Suarez; J Pijal; K L Ponce-Guevara; D Nejer; A Guzman; D Lugo; K Moncayo Neighborhood Criterion Analysis for Prototype Selection Applied in WSN Data Conference 2017 International Conference on Information Systems and Computer Science (INCISCOS), IEEE, 2018, ISBN: 978-1-5386-2644-3, (Electronic ISBN: 978-1-5386-2644-3
Print on Demand(PoD) ISBN: 978-1-5386-2645-0). @conference{rosero-montalvo_neighborhood_2017,
title = {Neighborhood Criterion Analysis for Prototype Selection Applied in WSN Data},
author = {P D Rosero-Montalvo and A C Umaquinga-Criollo and S Flores and L Suarez and J Pijal and K L Ponce-Guevara and D Nejer and A Guzman and D Lugo and K Moncayo},
url = {https://ieeexplore.ieee.org/document/8328096},
doi = {10.1109/INCISCOS.2017.47},
isbn = {978-1-5386-2644-3},
year = {2018},
date = {2018-04-02},
booktitle = {2017 International Conference on Information Systems and Computer Science (INCISCOS)},
pages = {128-132},
publisher = {IEEE},
abstract = {The present work presents an analysis of the neighborhood criterion for the prototype selection (PS) in supervised machine learning classification algorithms. To do this, we use the condensed neighbor algorithm CNN to eliminate redundant data with the normalization of the distance to the centroid of each data subset criterion. This is done, in order to obtain the training matrix of the most optimal model. A selection of neighborhood criterion has been created from the quantification of the balance between the performance of the classification and the reduction of data set (CER). As proof of the test, we performed: (i) CER and (ii) real-time tests with the implementation of the algorithm within the WSN. The result is a data reduction of up to 88 % and a performance of the kNN classifier of 75%. It is concluded that the criterion of neighborhood with normalized distance must be less than or equal to 0.2 and the implementation of kNN with k = 1 obtains the best CER.},
note = {Electronic ISBN: 978-1-5386-2644-3
Print on Demand(PoD) ISBN: 978-1-5386-2645-0},
keywords = {{WSN} data, classification and the reduction of data set, Computer science, data reduction, data subset criterion, Information systems, learning (artificial intelligence), Machine learning algorithms, neighborhood criterion analysis, normalized distance, pattern classification, prototype selection, Prototypes, redundant data, set theory, Silicon, supervised machine learning classification algorithms, Training, training matrix, wireless sensor networks},
pubstate = {published},
tppubtype = {conference}
}
The present work presents an analysis of the neighborhood criterion for the prototype selection (PS) in supervised machine learning classification algorithms. To do this, we use the condensed neighbor algorithm CNN to eliminate redundant data with the normalization of the distance to the centroid of each data subset criterion. This is done, in order to obtain the training matrix of the most optimal model. A selection of neighborhood criterion has been created from the quantification of the balance between the performance of the classification and the reduction of data set (CER). As proof of the test, we performed: (i) CER and (ii) real-time tests with the implementation of the algorithm within the WSN. The result is a data reduction of up to 88 % and a performance of the kNN classifier of 75%. It is concluded that the criterion of neighborhood with normalized distance must be less than or equal to 0.2 and the implementation of kNN with k = 1 obtains the best CER. |