Browsing by Author "Tello Guerrero, Marco Andrés"

Now showing 1 - 10 of 10

A process collection methodology towards TDABC costing optimization of IT services: a case study in an Ecuadorian university
(2019) Ribadeneira Espinoza, Carlos Andrés; Tuapante Vanegas, Tania Lorena; Sigüenza Guzmán, Lorena Catalina; Ayabaca Mogrovejo, Orlando Fabián; Tello Guerrero, Marco Andrés; Vanegas Peña, Paúl Fernando
ICT plays a paramount role in successful organizations. In order to achieve organizational goals, ICT services have to be closely overseen. Tools such as costing methods allow managers to be alert. Implementing a costing method for ICT services not only helps to justify investments, but also optimizes the cost of services. However, methodologies related to providing input to develop a costing model are limited. This research ameliorates ICT service manageMent by proposing a process collection methodology that contributes to the creation of a costing model with TDABC. The proposed methodology has been tested in an IT department in an Ecuadorian University. It matched the collected information with ITIL enabling the department to manage its IT service performance. The obtained processes, activities, times and resources from operative IT services displayed substantive input to design a costing model to improve the IT department and; thereby, the organization’s management as a whole.
An automatic method for the enrichment of DICOM metadata using biomedical ontologies
(INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS INC., 2015-08-25) Pérez Rocano, Wilson Rodrigo; La Cruz Puente Alexandra; Saquicela Galarza, Víctor Hugo; Tello Guerrero, Marco Andrés
This work is a novel contribution for enriching medical images using semantic annotations with a strategy for unifying different ontologies and instances of DICOM medical files. We present the L-MOM library (Library for Mapping of Ontological Metadata) as a tool for making an automatic mapping between instances of DICOM medical files and different medical ontologies (e.g., FMA, RadLex, MeSH). The main contributions are: i) the domain independent L-MOM library which is able to integrate DICOM metadata with ontologies from different domains; ii) a strategy to automatically annotate DICOM data with universally accepted medical ontologies, and provide values of similarity between ontologies and DICOM metadata; and iii) a framework to traverse ontological concepts that characterized clinical studies of patients registered in the framework catalog.
Descripción de fuentes de datos heterogéneas utilizando tecnologías semánticas
(2018) Angüisaca Landivar, Adrián Francisco; Japa Loja, Juan Pablo; Tello Guerrero, Marco Andrés; Saquicela Galarza, Víctor Hugo
The Semantic Web, propound potential opportunities to give meaning to web content. Ontologies are one of the main tools to explicitly specify the concepts of a particular domain, its properties and its relationships; so that the information is published in formats that are understandable by machine agents that can locate and manage the information accurately. This thesis presents an application for the generation of a common ontological model, which describes different data sources through its metadata, specifically worked with sources such as Database, CSV, XML and EXCEL. For this, different ontologies of metadata description were analyzed, among which DCAT, PHDD and DISCO are available. These three sources were united in a single model, on which some modifications were made, the most important being the incorporation of a structure, which allows me to describe the different types of data that have the attributes of the sources. Afterwards, a common relational model was created, where the extracted metadata is temporarily stored, for its subsequent mapping with the common ontological model. Finally, we proceeded to generate an RDF file on the common ontological model and publish the same for its exploitation. In order to experimentally validate the created model, an integration scenario was set up for several data sources, where a comparison was made by consulting the common ontological model and manually inspecting the metadata and data of said sources, this with the purpose to obtain the utility of the common ontological model. Concluding that through the common ontological model, the user in charge of integration can extract the possible semantic assignments in terms of data integration, easily and at a lower cost, since it is done on a single common repository.
Detecting Similar Areas of Knowledge Using Semantic and Data Mining Technologies
(ELSEVIER B.V., 2016-12-09) Sumba, X; Baculima Cumbe, John Fernando; Espinoza Mejía, Jorge Mauricio; Saquicela Galarza, Víctor Hugo; Sumba, F; Tello Guerrero, Marco Andrés
Searching for scientific publications online is an essential task for researchers working on a certain topic. However, the extremely large amount of scientific publications found in the web turns the process of finding a publication into a very difficult task whereas, locating peers interested in collaborating on a specific topic or reviewing literature is even more challenging. In this paper, we propose a novel architecture to join multiple bibliographic sources, with the aim of identifying common research areas and potential collaboration networks, through a combination of ontologies, vocabularies, and Linked Data technologies for enriching a base data model. Furthermore, we implement a prototype to provide a centralized repository with bibliographic sources and to find similar knowledge areas using data mining techniques in the domain of Ecuadorian researchers community.
E-waste management in Ecuador, current situation and perspectives
(Elsevier, 2020) Izquierdo Torres, Ismael Fernando; Vanegas Peña, Paúl Fernando; Tello Guerrero, Marco Andrés; Craps, Marc; Martínez Moscoso, Fernando Andrés; Sucozhañay Calle, Dolores Catalina; Paño Yáñez, Pablo José
E-Waste is a global concern because of its accelerated generation rate and increasing impact on the environment. Latin America generated 4.2 Mt of E-waste in 2016. In Ecuador, the amount of E-waste generated increased from 73 kt in 2014 to 90 kt in 2016. This chapter presents an overview of the current situation of E-waste management in Ecuador. The study starts by exploring common issues in Latin America. Then, the country’s situation is analyzed under the lens of the integrated and sustainable waste management framework. This analysis reveals that although the country faces several challenges, such as inefficient collection, improper disposal, limited financial resources, lack of a legal framework, and insufficient data on generation and composition, there are also opportunities for improvement. The Constitution of Ecuador considers nature as a subject of rights, which supports the development of environmental policies and legislation. This work presents a diagnostic for decision making performed in a National Workshop on E-waste management using the Systemic Design of Solutions, and sets a baseline for further research. © 2020 Elsevier Inc. All rights reserved.
Implementación GeosPARQL sobre una base de datos NoSQL-RDF
(2017-10-01) Gallegos Aguilar, Paul Fernando; Tello Guerrero, Marco Andrés; Saquicela Galarza, Víctor Hugo
Data in RDF format grows greatly and more so if combined with geographic informa- tion. The GeoSPARQL standard defines a vocabulary and functions for defining geograp- hic information in RDF. Currently, there are tools that use various technologies to store and process RDF. One of them are the NoSQL-RDF tools that use NoSQL technologies and others are those that use relational databases. NoSQL technologies are optimized for handling large volumes of information and distributed processing, while relational ones are not. Within tools that use relational databases there is a GeoSPARQL implementation, however for NoSQL-RDF tools does not yet exist. In this work, the GeoSPARQL standard was implemented on a NoSQL-RDF database to take advantage of the NoSQL technologies on large volumes of RDF data. The imple- mentation consists of two components, the query processor and the operations processor that work together to process GeoSPARQL. Once the implementation was completed, its operation was evaluated by the execution and comparison of the results obtained from our tool with those provided by the GeoSPARQL implementation performed on Apache Marmotta.
Prediction of imports of household appliances in Ecuador using LSTM networks
(Springer Nature Switzerland AG 2020, 2020) Tello Guerrero, Marco Andrés; Izquierdo Torres, Ismael Fernando; Pacheco Portilla, Mario Gustavo; Vanegas Peña, Paúl Fernando
Time series forecasting is an important topic widely addressed with traditional statistical models such as regression, and moving average. This work uses the state-of-the-art Long Short-Term Memory (LSTM) Networks to predict Ecuadorian imports of Home Appliances, and to compare the results against those obtained by traditional methods. First, an ARIMA model was used to forecast imports data. Then, the predictions were calculated by a Univariate LSTM network. The time series used in both experiments was the monthly average of imports from 1996 to April 2019. In addition, time series of GDP Growth, Population, and Inflation were included in the model to test prediction improvements. The performance of the models was assessed comparing the Mean Squared, Root Mean Square and Mean Absolute Error metrics. The results show that a LSTM network produces a better fit of the imports data and improved predictions compared against those produced by the ARIMA model. Furthermore, the use of multivariate time series (i.e., GDP Growth, Population, Inflation) data, for the LSTM model, did not produce significant improvements compared to the univariate imports time series.
Sistema para soporte a la toma de decisiones en la comercialización de insumos para el sector minero; caso de uso: Grupo Empresarial Campoverde del cantón Camilo Ponce Enríquez de la provincia del Azuay
(2017) Ochoa Caicedo, Heckler Rothwell; Tello Guerrero, Marco Andrés
According to data from the Central Bank of Ecuador in January 2017 indicates that of the 85% is developed in Canton Camilo Ponce Enríquez. The mining sector has two peculiar characteristics (high risk market and high capital investment), therefore, this industry requires conditions to enhance its activities it can achieve through the suppliers to acquire new knowledge, feed on new technologies and innovations to improve their competitiveness. Therefore, the managers of companies that supply inputs are forced to make decisions based on their own experiences with real and historical data, and it is necessary to implement a system that supports decision making in each of the areas that supply it require. The present research aims to develop a methodology to develop a data warehouse (DW) oriented to the mining sector, proposing techniques for the collection, transformation and interpretation of the data. The methodology embraces the ISO 21500 standard and the PMBOK standard for project management, DW architecture and workflow as well as the tasks implicit in this process is a compendium of two specific methodologies (DWEP and HEFESTO) . The methodology is validated with data provided by the Campoverde business group in the canton Camilo Ponce Enríquez of the province of Azuay who provide inputs to the mining sector. As a result of the application of the methodology, a consistent DW was obtained and framed in the strategic objectives of the Campoverde business group.
Virtualización de servidores con herramientas de software libre
(2009) Guerrero Peñafiel, Rodrigo José; Tello Guerrero, Marco Andrés; Parra González, Luis Otto
WebMedSA: A web-based framework for segmenting and annotating medical images using biomedical ontologies
(SPIE, 2015-11-17) Vega, F; Espinoza Mejía, Jorge Mauricio; La Cruz Puente Alexandra; Pérez Rocano, Wilson Rodrigo; Saquicela Galarza, Víctor Hugo; Solano Quinde, Lizandro Damián; Tello Guerrero, Marco Andrés
Advances in medical imaging have fostered medical diagnosis based on digital images. Consequently, the number of studies by medical images diagnosis increases, thus, collaborative work and tele-radiology systems are required to effectively scale up to this diagnosis trend. We tackle the problem of the collaborative access of medical images, and present WebMedSA, a framework to manage large datasets of medical images. WebMedSA relies on a PACS and supports the ontological annotation, as well as segmentation and visualization of the images based on their semantic description. Ontological annotations can be performed directly on the volumetric image or at different image planes (e.g., axial, coronal, or sagittal); furthermore, annotations can be complemented after applying a segmentation technique. WebMedSA is based on three main steps: (1) RDF-ization process for extracting, anonymizing, and serializing metadata comprised in DICOM medical images into RDF/XML; (2) Integration of different biomedical ontologies (using L-MOM library), making this approach ontology independent; and (3) segmentation and visualization of annotated data which is further used to generate new annotations according to expert knowledge, and validation. Initial user evaluations suggest that WebMedSA facilitates the exchange of knowledge between radiologists, and provides the basis for collaborative work among them.