Big-Data and the Question of Horizontal and Vertical Intelligence: A Discussion on Disaster Management

Due to the unexpected context of disaster management (with heterogeneous and non-dedicated potential data sources), the classical Big-Data approaches within this business domain (schematically focused on data storage and pattern recognition) appear to be

  • PDF / 535,554 Bytes
  • 7 Pages / 439.37 x 666.14 pts Page_size
  • 62 Downloads / 182 Views

DOWNLOAD

REPORT


)

Toulouse University, Mines Albi – Campus Jarlard, Route de Teillet, 81000 Albi, France {frederick.benaben,aurelier.montarnal,audrey.fertier, sebastien.truptil}@mines-albi.fr

Abstract. Due to the unexpected context of disaster management (with hetero‐ geneous and non-dedicated potential data sources), the classical Big-Data approaches within this business domain (schematically focused on data storage and pattern recognition) appear to be limited, especially when trying to get a situational level of such crises from data gathered from the field. That is why this article aims at discussing a specific vision of Big-Data for data management, in two steps: (i) analyzing this business domain to identify relevant characteristics, impacted or concerned by Big-Data, and describe the new key challenges that need to be tackled, and (ii) designing an innovative Big-Data framework dedi‐ cated to this particular business domain. After having highlighted the importance to push abstraction levels and especially data interpretation as a way to perform vertical intelligence in data analysis (instead of horizontal intelligence with usual approaches), the proposed Big-Data framework brings a layered approach according to three dimensions: gathering (data level), interpretation (information level), exploitation (knowledge level). Keywords: Big-Data · Collaborative situation · Data interpretation · Metamodel · Modeling · Intelligence · Disaster management

1

Introduction

Just like any domain of human civilization, Disaster Management (DM) has to take into account the unavoidable increasing of generated and potentially accessible data. On any crisis site, heterogeneous and potentially not-dedicated data sources (sensors, opendata, witnesses and social networks, etc.) generate a deluge of data. Those emerging data could be very useful to characterize crisis situations and, thus, allow to better support DM and the decision-makers awareness. However, dealing with their specificities leads to raise new key challenges, and to the necessity of implementing a new Big-Data approach adapted to the needs of this business domain. That question of Big-Data is usually considered through the angle of emerging new technological solutions and platforms to manage this unprecedented amount of data. Though, the question of Big-Data definitely concerns so many human and social domains that it could be relevant to imagine that all domains do not require the same technological (or philosophical) approach for Big-Data management.

© IFIP International Federation for Information Processing 2016 Published by Springer International Publishing Switzerland 2016. All Rights Reserved H. Afsarmanesh et al. (Eds.): PRO-VE 2016, IFIP AICT 480, pp. 156–162, 2016. DOI: 10.1007/978-3-319-45390-3_14

Big-Data and the Question of Horizontal and Vertical Intelligence

157

Hence, this article aims at giving a vision of Big-Data applied to the DM, by exploring those various challenges raised both in terms of technological and philosophical points of view. Answering those iss