Implementation of Linear and Multiple Regression Analysis for a Visual Analytic Approach to Understanding the Poverty Assessment Through Disaster Impacts in India

  • Danya Ganapathy
  • K S Nandu
  • M S PallaviEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 14)


Data mining techniques is used to predict the data its relationships that have not previously been discovered. This paper is based on work which assesses the poverty caused due to the disasters occurred in various states of India and predict the future poverty that are likely to be incur using data mining techniques. The disasters like flood, landslide, earthquake, cyclone, hail storm etc. are studied through literature review considering the data of past five years in different parts of the country and then poverty is predicted. The Main reason for this work is that these disasters have devastated the people dwelling there and have made the area economically and socially weak, causing damage of infrastructure, land, crops also the death of animals and people of all communities no matter what their social status is. All these aspects are directly associated with the poverty. This study adapts the linear regression analysis and multiple regression analysis techniques of data mining. Linear regression efforts to predict the poverty are based by considering year wise feature selection. However, it lacks in predicting many relationships existing in data, so the multiple regressions are used instead. The data sets are normalized to get the values within a range for the purpose of estimation. The visual analytic approach is used to graphically represent the obtained results. Based on the history of the disasters, which are fetched from various sources in internet like news bulletin, news reports, etc., this system predicts the poverty that will probably be hitting the area in the upcoming years. This can be useful for surveyors, and government officials for prediction of poverty and also for sketching the risk management plans.


Data mining Regression analysis Linear regression Multiple regression Regression errors Visual analytic approach 


  1. 1.
    Han J, Kamber M. Data mining: concepts and techniques, Simon Fraser UniversityGoogle Scholar
  2. 2.
    Dinesh Kumar U. IIMB, Predictive analytics: QM901.1x on EDXGoogle Scholar
  3. 3.
    Monali D, Priyanka G, Monika P, Mamta A (2015) Distributed event detection in wireless sensor network for disaster management. In: Proceedings of 11th IRF international conference, Bengaluru, India, 15 Feb 2015. ISBN: 978-93-84209-90-2Google Scholar
  4. 4.
    Olorunfemi F, Raheem UA (2007) Urban development and environmental implications: the challenge of urban sustainability in Nigeria. the Australas Rev Afr Stud XXVIII 2006/2007Google Scholar
  5. 5.
    Ogato GS The human ecology of disasters in Ethiopia: The quest for participatory disaster management and sustainable livelihood improvement of pastoral communities. In: Institute of cooperatives and development studies, Ambo University, EthiopiaGoogle Scholar
  6. 6.
    Kienberger S. Assessing the vulnerability to natural hazards on the provincial/community level in Mozambique: the contribution of GIscience and remote sensing. Centre for Geo-informatics -Salzburg UniversityGoogle Scholar
  7. 7.
    Flanagan BE, Gregory EW, Hallisey EJ, Heitgerd JL, Lewis B (2011) A social vulnerability index for disaster management. J Homel Secur Emerg Manage 8(1) (Article 3)Google Scholar
  8. 8.
    Heltberg R, Siegel PB, Jorgensen SL (2008) Addressing human vulnerability to climate change: toward a “no-regrets” approach. The World Bank, United States, 23 Nov 2008Google Scholar
  9. 9.
    Miller HE, Engemann KJ Yager RR (2006) Disaster planning and management. Commun IIMA 6(2)Google Scholar
  10. 10.
    Baez J, Santos I (2008) On shaky ground: the effects of earthquakes on household income and poverty. RPP LAC–MDGs and Poverty – 02/2008, RBLAC-UNDP, New YorkGoogle Scholar
  11. 11.
    Hagiwara AT, Sugiyarto G (2005) Poverty impact of the Tsunami: an initial assessment and scenario analyses. In: 4th PEP research network general meeting, Colombo, Sri Lanka. 13–17 June 2005Google Scholar
  12. 12.
    Fothergill A, Peek LA (2003) Poverty and disasters in the united states: a review of recent sociological findings. Department of Sociology, 30 Apr 2003Google Scholar
  13. 13.
    Tomaszewski B (2008) Examining the effects of the global economic crisis on poverty through natural disasters impacts. Cartographic J 45:165–181CrossRefGoogle Scholar
  14. 14.
    Pineda MVG (2012) Exploring the potentials of a community-based disaster risk management system (CBDRMS), the Philippine experience. Int J Innov Manage Technol 3(6)Google Scholar
  15. 15.
    Lal PN, Singh R, Holland P (2009) Relationship between natural disasters and poverty. SOPAC Miscellaneous Report 678, Apr 2009Google Scholar
  16. 16.
    Sumarto S, Moselle S (2015) Addressing poverty and vulnerability in ASEAN: an analysis of measures and implications going forward. In: The SMERU Research Institute, Sept 2015Google Scholar
  17. 17.
    Karim A, Noy I (2016) Poverty and natural disasters—a qualitative survey of the empirical literature. Singapore Econ Rev 61:1640001Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceAmrita University, Mysore CampusMysoreIndia

Personalised recommendations