Browsing by Author "Tello Guerrero, Marco Andres"

Now showing 1 - 6 of 6

Challenges and trends about smart big geospatial data: a position paper
(Institute of Electrical and Electronics Engineers Inc., 2018) Saquicela Galarza, Víctor Hugo; Vilches Blázquez, Luis Manuel; Tello Guerrero, Marco Andres
Currently, we are witnessing an exponential growth in the amount of data being generated and captured at multiple locations. This trend will continue over the next years. Hence, we have envisioned a scenario in which many objects will be referencing to or generating location information. Thus, the need for appropriately managing geospatial data is evident. In this paper, we present our vision for an integral Geo Linked Data platform; pointing out the current limitations and challenges in the GeoRDFization, Storage, Query Federation, and Visualization of data with an inherent spatial context.
LOD-GF: an integral linked open data generation framework
(Springer Nature, 2019) Saquicela Galarza, Víctor Hugo; Segarra Flores, José Luis; Tello Guerrero, Marco Andres; Espinoza Mejía, Jorge Mauricio; Lupercio Novillo, Rosa Lucía; Villazón Terrazas, Boris Marcelo; Saquicela Galarza, Víctor Hugo
Linked Open Data (LOD) generation is a common activity within organizations due to its advantages for sharing and reusing information. Since these technologies require specialized knowledge, the development of technological and methodological tools that allows its implementation is limited. Most of the current solutions are built on top of specific tools which require considerable effort to consolidate into an integral solution. Moreover, those tools work on specific domains, or they do not support some of the phases required for LOD life cycle (e.g., data cleaning, data exploitation). In this paper, we present a framework for LOD management which follows methodological principles presented in the state of the art in scientific literature and provides an unified software tool for publishing LOD for multiple domains and technologies. Our platform leverages a modular ETL processor, allowing a transparent and flexible integration, providing an integral environment for LOD. This framework was tested, successfully, using data sources from different domains, e.g., digital repositories, libraries.
Methodological guidelines for publishing library data as linked data
(Institute of Electrical and Electronics Engineers Inc., 2017) Higaldo Delgado, Yusniel; Estrada Nelson, Reina; Xu, Bing; Villazón Terrazas, Boris Marcelo; Leiva Mederos, Amed Abel; Tello Guerrero, Marco Andres; Higaldo Delgado, Yusniel
Publishing data as Linked Data increases the interoperability and discoverability of resources over the web space. This process involves several design decisions and technologies. However, there is no one-size-fits-all formula for publishing data as Linked Data. Also, the quality of linked data published is a key issue to take into account. In the library domain, the quality of linked data is a crucial point for improving the retrieval and use of the data. In this paper, we propose a set of methodological guidelines based on five activities for publishing library data as Linked Data. The proposed guidelines consider the quality of published data as a key issue. In this line, our approach includes a preprocessing task for data cleansing and normalization. The proposed approach has been applied in a use case for publishing bibliographic data from Open Access journals in Cuba. The results obtained show the applicability of the methodological guidelines proposed in a real environment.
Modeling 911 emergency events in Cuenca-Ecuador using geo-spatial data
(CITT 2018, 2019) Robles Granda, Pablo Dario; Tello Guerrero, Marco Andres; Zúñiga Prieto, Miguel Ángel; Solano Quinde, Lizandro Damián
We present several techniques for modeling emergency events using data from 911 emergency calls in the city of Cuenca-Ecuador. We apply three types of models. First, we use a probabilistic description of events using Gaussian kernels based on both, regular segmentation and mixture models, to represent the spatial distribution of occurrences. Second, we verify the qualitative relation of the clusters obtained with our kernel model with respect to the geo-political organization of the city. Finally, we develop an emergency model using a large dataset corresponding to the period January 1st 2015 through December 31st 2016 and test various data mining algorithms for prediction purposes. We verify the usefulness of our approach experimentally.
Temporal analysis of 911 emergency calls through time series modeling
(Springer, 2020) Robles Granda, Pablo Dario; Tello Guerrero, Marco Andres; Solano Quinde, Lizandro Damián; Zúñiga Prieto, Miguel Ángel
We present two techniques for modeling time series of emergency events using data from 911 emergency calls in the city of Cuenca-Ecuador. We study state-of-the-art methods for time series analysis and assess the benefits and drawbacks of each one of them. In this paper, we develop an emergency model using a large dataset corresponding to the period January 1st 2015 through December 31st 2016 and test a Gaussian Process and an ARIMA model for temporal prediction purposes. We assess the performance of our approaches experimentally, comparing the standard residual error (SRE) and the execution time of both models. In addition, we include climate and holidays data as explanatory variables of the regressions aiming to improve the prediction. The results show that ARIMA model is the most suitable one for forecasting emergency events even without the support of additional variables.
TV program recommender using user authentication on middleware ginga
(Institute of Electrical and Electronics Engineers Inc., 2018) Crespo Crespo, Jorge Efrain; Espinoza Mejía, Jorge Mauricio; Palacio Baus, Kenneth Samuel; Saquicela Galarza, Víctor Hugo; Tello Guerrero, Marco Andres
The system proposed in this article aims to identify and recognize television users with the objective of offering personalized television programming. In this setting, the authentication and recommendation mechanisms used require to collect the necessary information in an implicit manner as much as possible, such that the leisure and entertainment objectives this broadcasting medium brings are not interrupted. The design proposed for the implementation of the interactive application uses an authentication process based on facial recognition and a recommendation algorithm based on contextual information, which is mainly implicitly captured. Experimental obtained results show that the system offers more accurate recommendations when the user exhibits a habitual behavior; e.g. watching TV programs of a same category in a specific channel and schedule.