Recent Submissions

  • Method for Collecting Relevant Topics from Twitter supported by Big Data

    Silva, Jesús; Senior Naveda, Alexa; Gamboa Suarez, Ramiro; Hernández Palma, Hugo; Niebles Núẽz, William (Institute of Physics Publishing, 2020-01-07)
    There is a fast increase of information and data generation in virtual environments due to microblogging sites such as Twitter, a social network that produces an average of 8, 000 tweets per second, and up to 550 million tweets per day. That's why this and many other social networks are overloaded with content, making it difficult for users to identify information topics because of the large number of tweets related to different issues. Due to the uncertainty that harms users who created the content, this study proposes a method for inferring the most representative topics that occurred in a time period of 1 day through the selection of user profiles who are experts in sports and politics. It is calculated considering the number of times this topic was mentioned by experts in their timelines. This experiment included a dataset extracted from Twitter, which contains 10, 750 tweets related to sports and 8, 758 tweets related to politics. All tweets were obtained from user timelines selected by the researchers, who were considered experts in their respective subjects due to the content of their tweets. The results show that the effective selection of users, together with the index of relevance implemented for the topics, can help to more easily find important topics in both sport and politics.
  • Time Series Decomposition using Automatic Learning Techniques for Predictive Models

    Silva, Jesús; Hernández Palma, Hugo; Niebles Núẽz, William; Ovallos-Gazabon, David; Varela, Noel (Institute of Physics Publishing, 2020-01-07)
    This paper proposes an innovative way to address real cases of production prediction. This approach consists in the decomposition of original time series into time sub-series according to a group of factors in order to generate a predictive model from the partial predictive models of the sub-series. The adjustment of the models is carried out by means of a set of statistic techniques and Automatic Learning. This method was compared to an intuitive method consisting of a direct prediction of time series. The results show that this approach achieves better predictive performance than the direct way, so applying a decomposition method is more appropriate for this problem than non-decomposition.
    Acceso abierto
  • Neural Networks for the Web Services Classification

    Silva, Jesús; Senior Naveda, Alexa; Solórzano Movilla, José; Niebles Núẽz, William; Hernández Palma, Hugo (Institute of Physics Publishing, 2020-01-07)
    This article introduces a n-gram-based approach to automatic classification of Web services using a multilayer perceptron-type artificial neural network. Web services contain information that is useful for achieving a classification based on its functionality. The approach relies on word n-grams extracted from the web service description to determine its membership in a category. The experimentation carried out shows promising results, achieving a classification with a measure F=0.995 using unigrams (2-grams) of words (characteristics composed of a lexical unit) and a TF-IDF weight.
    Acceso abierto
  • Forecasting Electric Load Demand through Advanced Statistical Techniques

    Silva, Jesús; Senior Naveda, Alexa; García Guliany, Jesús; Niebles Núẽz, William; Hernández Palma, Hugo (Institute of Physics Publishing, 2020-01-07)
    Traditional forecasting models have been widely used for decision-making in production, finance and energy. Such is the case of the ARIMA models, developed in the 1970s by George Box and Gwilym Jenkins [1], which incorporate characteristics of the past models of the same series, according to their autocorrelation. This work compares advanced statistical methods for determining the demand for electricity in Colombia, including the SARIMA, econometric and Bayesian methods.
    Acceso abierto
  • Parallel Algorithm for Reduction of Data Processing Time in Big Data

    Silva, Jesús; Hernández Palma, Hugo; Niebles Núẽz, William; Ovallos-Gazabon, David; Varela, Noel (Institute of Physics Publishing, 2020-01-07)
    Technological advances have allowed to collect and store large volumes of data over the years. Besides, it is significant that today's applications have high performance and can analyze these large datasets effectively. Today, it remains a challenge for data mining to make its algorithms and applications equally efficient in the need of increasing data size and dimensionality [1]. To achieve this goal, many applications rely on parallelism, because it is an area that allows the reduction of cost depending on the execution time of the algorithms because it takes advantage of the characteristics of current computer architectures to run several processes concurrently [2]. This paper proposes a parallel version of the FuzzyPred algorithm based on the amount of data that can be processed within each of the processing threads, synchronously and independently.
    Acceso abierto
  • Temporary Variables for Predicting Electricity Consumption Through Data Mining

    Silva, Jesús; Senior Naveda, Alexa; Hernández Palma, Hugo; Niebles Núẽz, William; Niebles Núẽz, Leonardo (Institute of Physics Publishing, 2020-01-07)
    In the new global and local scenario, the advent of intelligent distribution networks or Smart Grids allows real-time collection of data on the operating status of the electricity grid. Based on this availability of data, it is feasible and convenient to predict consumption in the short term, from a few hours to a week. The hypothesis of the study is that the method used to present time variables to a prediction system of electricity consumption affects the results.
    Acceso abierto
  • Natural Language Explanation Model for Decision Trees

    Silva, Jesús; Hernández Palma, Hugo; Niebles Núẽz, William; Ruiz-Lazaro, Alex; Varela, Noel (Institute of Physics Publishing, 2020-01-07)
    This study describes a model of explanations in natural language for classification decision trees. The explanations include global aspects of the classifier and local aspects of the classification of a particular instance. The proposal is implemented in the ExpliClas open source Web service [1], which in its current version operates on trees built with Weka and data sets with numerical attributes. The feasibility of the proposal is illustrated with two example cases, where the detailed explanation of the respective classification trees is shown.
    Acceso abierto
  • Neural Networks for Tea Leaf Classification

    Silva, Jesús; Hernández Palma, Hugo; Niebles Núẽz, William; Ruiz-Lazaro, Alex; Varela, Noel (Institute of Physics Publishing, 2020-01-07)
    The process of classification of the raw material, is one of the most important procedures in any tea dryer, being responsible for ensuring a good quality of the final product. Currently, this process in most tea processing companies is usually handled by an expert, who performs the work manually and at his own discretion, which has a number of associated drawbacks. In this work, a solution is proposed that includes the planting, design, development and testing of a prototype that is able to correctly classify photographs corresponding to samples of raw material arrived at a dryer, using intelligence techniques (IA) type supervised for Classification by Artificial Neural Networks and not supervised with K-means Grouping for class preparation. The prototype performed well and is a reliable tool for classifying the raw material slammed into tea dryers.
    Acceso abierto
  • Identification of Patterns of Fatal Injuries in Humans through Big Data

    Silva, Jesus; Romero, Ligia; Pineda, Omar Bonerge; Herazo-Beltran, Yaneth; Zilberman, Jack (Elsevier BV, 2020)
    External cause injuries are defined as intentionally or unintentionally harm or injury to a person, which may be caused by trauma, poisoning, assault, accidents, etc., being fatal (fatal injury) or not leading to death (non-fatal injury). External injuries have been considered a global health problem for two decades. This work aims to determine criminal patterns using data mining techniques to a sample of patients from Mumbai city in India.
    Acceso abierto
  • Analyzing the critical success factor of CSR for the Chinese textile industry

    Li, Y. (Elsevier Ltd, 2020-07-01)
    Increasing population and urbanization motivates the capability of consuming more fashion goods than ever. This push creates more momentum on global companies to focus on clothing sectors. Recent advancements, including globalization and e-commerce, have made this sector as one of the top businesses worldwide. Top clothing brands made several strategies to satisfy the stakeholders to sustain in this hot, profitable business. This results in practicing more sustainable strategies, including corporate social responsibility in their clothing business throughout their operations, including the supply chain. However, most of the developed nations are consumers of textiles, which are produced and processed by any of the developing and under developing nations. Meanwhile, achieving sustainability in clothing business includes promoting sustainability in the whole chain of suppliers. Pressure from developed nations urges developing nations to promote sustainable practices in their operations. Several studies discussed the CSR related strategies in textile sectors but failed to explore their critical success factors based on their region. With this concern, this study attempts to study the critical success factors of CSR in textile industries situated in one of the developing nations, China. This study collected the critical success factors from literature and validated with the field experts; then the same were evaluated with the assistance of Chinese textile case industrial managers. Decision-making trial and evaluation laboratory tool has been used to evaluate the influential critical success factors of CSR to promote CSR through motivating those most influential success factors. These results could help the Chinese textile industrial managers to further extend strong roots on CSR implementation. Finally, this study sheds some light on future opportunities that exist within Chinese contexts with the implementation of CSR.
    Acceso restringido temporalmente
  • Perceptual map teaching strategy

    Chipoco Quevedo, Mario; pcadmchi@upc.edu.pe (Universidad Peruana de Ciencias Aplicadas (UPC), 2016-11-15)
    Este documento contiene el diseño de una estrategia para enseñar mapas perceptuales en un curso de gerencia de marca, con la adición de una técnica de modelado para elaborarlos. Los mapas perceptuales son herramientas para el análisis del posicionamiento de marca, y se enseñan en cursos de pregrado y postgrado. Sin embargo, es muy usual utilizar un marco puramente descriptivo y teórico, sin explicar los mecanismos para construirlos. Se presentan métodos basados en regresión multilineal y en análisis factorial como herramientas de modelado, para explicar en clase y proporcionar una mejor comprensión de esta materia.
    Acceso abierto
  • Pricing and spread components at the Lima Stock Exchange

    Universidad Peruana de Ciencias Aplicadas (UPC) (United Nations Publications, 2015-08-18)
    This paper analyses three aspects of the share market operated by the Lima Stock Exchange: (i) the short-term relationship between the pricing, direction and volume of order flows; (ii) the components of the spread and the equilibrium point of the limit order book per share, and (iii) the pricing, order direction and trading volume dynamic resulting from shocks in the same variables when lagged. The econometric results for intraday data from 2012 show that the short-run dynamic of the most and least liquid shares in the General Index of the Lima Stock Exchange is explained by the direction of order flow, whose price impact is temporary in both cases.
    Acceso abierto