Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Implementación de un sistema de detección de señales débiles de futuro mediante técnicas de minería de textos, System implementation for detection of future weak signals using text mining

  • Griol Barres, Israel|||0000-0002-2197-9161
  • Millet Roig, José|||0000-0002-8879-003X
  • Milla, Sergio
[EN] Nowadays, one of the biggest threats for companies is not being able to cope with the constant changes occurring in the market by not predicting them well in advance. For this reason, the development of new processes that facilitate the detection of future phenomena and significant changes is a key component for correct decision making that can mark a correct course in the company. A business intelligence based architecture system is proposed to allow discrete changes or weak signals detection in the present that are indicative of more significant phenomena and transcendental changes in the future. In contrast with current available works, which are focused on structured information sources or, at most, with only a single type of data source, in this paper the detection of these signals is done quantitatively from various kinds of heterogeneous and unstructured documents (scientific articles, journalistic articles and social networks) on which text mining techniques are applied. The system has been tested in the study of the future of solar panels sector, obtaining promising results that can help business experts in the recognition of new driving factors of their markets and the development of new opportunities., [ES] Actualmente, una de las mayores amenazas para las empresas es no ser capaces de hacer frente a los cambios constantes que se dan en el mercado, por no predecirlos con la suficiente antelación. Por ello, el desarrollo de nuevos procesos que faciliten la detección de fenómenos y cambios futuros significativos es una componente clave para una correcta toma de decisiones que marque un rumbo correcto para la empresa. Por esta razón, se propone un sistema basado en una arquitectura de inteligencia de negocio que permite detectar cambios discretos o señales débiles (weak signals) en el presente, pero que son indicativos de fenómenos más significativos y cambios trascendentales en el futuro. Frente a los trabajos actuales que se centran en fuentes de información estructuradas, o como mucho, con un único tipo de fuente de datos, en este trabajo la detección de estas señales se realiza de forma cuantitativa a partir de documentos heterogéneos y no estructurados de diversa índole (artículos científicos, periodísticos y redes sociales) sobre los que se aplican técnicas de minería de textos. El sistema ha sido testeado para estudiar el futuro del sector de los paneles solares, habiéndose obtenido resultados prometedores para ayudar a expertos en el reconocimiento de nuevos factores de peso en sus mercados y en el desarrollo de nuevas oportunidades., This work is partially supported by EIT Climate KIC of the European Union (project Accelerator - TC2018B_2.2.5-ACCUPV_P066-1A). This research is also part of the PhD programme of the Departamento de Ingeniería Electrónica of the Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Improving strategic decision making by the detection of weak signals in heterogeneous documents by text mining techniques

  • Griol Barres, Israel|||0000-0002-2197-9161
  • Millet Roig, José|||0000-0002-8879-003X
  • Milla, Sergio
[EN] At present, one of the greatest threats to companies is not being able to cope with the constant changes that occur in the market because they do not predict them well in advance. Therefore, the development of new processes that facilitate the detection of significant phenomena and future changes is a key component for correct decision making that sets a correct course in the company. For this reason, a business intelligence architecture system is hereby proposed to allow the detection of discrete changes or weak signals in the present, indicative of more significant phenomena and transcendental changes in the future. In contrast to work currently available focusing on structured information sources, or at most with a single type of data source, the detection of these signals is here quantitatively based on heterogeneous and unstructured documents of various kinds (scientific journals, newspaper articles and social networks), to which text mining and natural language processing techniques (a multi-word expression analysis) are applied. The system has been tested to study the future of the artificial intelligence sector, obtaining promising results to help business experts in the recognition of new driving factors of their markets and the development of new opportunities., This work is partially supported by EIT Climate KIC of the European Union (project Accelerator TC2018B-2.2.5-ACCUPV-P066-1A) and Erasmus+ InnoCENS (573965-EPP-1-2016-1-SE-EPPKA2-CBHE-JP).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Detecting Weak Signals of the Future: A System Implementation Based on Text Mining and Natural Language Processing

  • Griol Barres, Israel|||0000-0002-2197-9161
  • Cebrián Ferriols, Antonio José|||0000-0003-0519-5284
  • Millet Roig, José|||0000-0002-8879-003X
  • Milla, Sergio
  • Fan, Huaan
[EN] Organizations, companies and start-ups need to cope with constant changes on the market which are difficult to predict. Therefore, the development of new systems to detect significant future changes is vital to make correct decisions in an organization and to discover new opportunities. A system based on business intelligence techniques is proposed to detect weak signals, that are related to future transcendental changes. While most known solutions are based on the use of structured data, the proposed system quantitatively detects these signals using heterogeneous and unstructured information from scientific, journalistic and social sources, applying text mining to analyze the documents and natural language processing to extract accurate results. The main contributions are that the system has been designed for any field, using different input datasets of documents, and with an automatic classification of categories for the detected keywords. In this research paper, results from the future of remote sensors are presented. Remote sensing services are providing new applications in observation and analysis of information remotely. This market is projected to witness a significant growth due to the increasing demand for services in commercial and defense industries. The system has obtained promising results, evaluated with two different methodologies, to help experts in the decision-making process and to discover new trends and opportunities., This research is partially supported by EIT Climate-KIC of the European Institute of Technology (project EIT Climate-KIC Accelerator-TC_3.1.5_190607_P066-1A) and InnoCENS from Erasmus + (573965-EPP-1-2016-1-SE-EPPKA2-CBHE-JP).