A Hybrid Data Model for Prediction of Disaster using Data Mining Approaches

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2016 by IJETT Journal
Volume-41 Number-7
Year of Publication : 2016
Authors : Arjun Singh, Prof. AmitSaxena
DOI :  10.14445/22315381/IJETT-V41P270

Citation 

Arjun Singh, Prof. AmitSaxena "A Hybrid Data Model for Prediction of Disaster using Data Mining Approaches", International Journal of Engineering Trends and Technology (IJETT), V41(7),384-392 November 2016. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
The disasters are the unwanted event which affect the human life and human not able to recover form it’s effects by available resources. Therefore these events are classified according to the natural or the human initiated. The human initiated disasters are controllable but the natural events are unpredictable in nature. In the literature the different data models are available that claims to understand and predict the much nearer data for any unpredictable events such as stock market, frauds and others. All these techniques are developed with the help of data mining techniques. That involves the computational algorithms for learning with historical patterns and predicts the data according to current situations. By the motivations of these techniques in this presented work a new data model is proposed which collect the real world knowledge from the web data sources and use with the data mining algorithms for predicting the unpredictable natural disasters. In order to perform this K-means clustering and HMM based hybrid model is proposed. The k-means clustering algorithm helps to prepare the disaster observations and the HMM algorithm is used for training and prediction of the disaster events. The implementation of this model is performed using the JAVA technology. After implementation the results are considered in conditions of exactness, error rate, memory expenditure and the time consumption. The results show the presentation of the futuremethod is accurate and efficient for prediction with any kind of other data also.

 References

[1] Li Zheng, Chao Shen, Liang Tang, ChunqiuZeng, Tao Li, Steve Luis, and Shu-Ching Chen, ?Data Mining Meets the Needs of Disaster Information Management?, IEEE Transactions on Human-Machine Systems, Vol. 43, No. 5, September 2013 451
[2] Disaster Risk and Resilience, UN System task team on the post 2015 UN development agenda,http://www.un.org/en/development/desa/policy/unta skteam_undf/thinkpieces/3_disaster_risk_resilience.pdf
[3] Safer Homes, StrongerCommunities: A Hand Book For Reconstructing After Natural Disasters, http://www.gfdrr.org/sites/gfdrr.org/files/Disaster_Types_an d-Impacts.pdf
[4] UCL, ?EM-DAT: The OFDA/CRED International Disaster Database,? UCL, http://www.emdat.be.
[5] NATURAL HAZARDS AND DISASTER MANAGEMENT, CENTRAL BOARD OF SECONDARY EDUCATION PREET VIHAR, DELHI – 110092
[6] T. Tingsanchali, ?Urban flood disaster management?, Procedia Engineering 32 (2012) 25 – 37, Published by Elsevier Ltd.
[7] Shitangsu Kumar Paul and Jayant K. Routray, ?An Analysis of the Causes of Non-Responses to Cyclone Warnings and the Use of Indigenous Knowledge for Cyclone Forecasting in Bangladesh?, Climate Change and Disaster Risk Management, Climate Change Management, DOI: 10.1007/978-3-642-31110-9_2, Springer-Verlag Berlin Heidelberg 2013
[8] Tsun-Hua Yang, Sheng-Chi Yang, Jui-Yi Ho, Gwo-Fong Lin, Gong-Do Hwang, Cheng-Shang Lee, ?Flash flood warnings using the ensemble precipitation forecasting technique: A case study on forecasting floods in Taiwan caused by typhoons?, Journal of Hydrology, 520 (2015) 367–378
[9] Roger S. Pulwarty, Mannava V.K. Sivakumar, ?Information systems in a changing climate: Early warnings and drought risk management?, Weather and Climate Extremes, 3 (2014) 14–21
[10] Lorenzo Alfieri, Peter Salamon, Florian Pappenberger, Fredrik Wetterhall, JuttaThielen, ?Operational early warning systems for water-related hazards in Europe?, environmental science & policy 21 (2012) 35 – 49
[11] Muhammad Atiq Ur Rehman Tariq, Nick van de Giesen, ?Floods and flood management in Pakistan?, Physics and Chemistry of the Earth, 47–48 (2012) 11–20
[12] Hans J.P. Marvin, Gijs A. Kleter, H.J. (Ine) Van der Fels- Klerx, Maryvon Y. Noordam, Eelco Franz, Don J.M. Willems, Alistair Boxall, ?Proactive systems for early warning of potential impacts of natural disasters on food safety: Climate-change-induced extreme events as case in point?, Food Control 34 (2013) 444e456
[13] Florian Pappenberger, Hannah L. Cloke, Dennis J. Parker, Fredrik Wetterhall, David S. Richardson, JuttaThielen, ?The monetary benefit of early flood warnings in Europe?, environmental science & policy 51 ( 2015 ) 278 – 291
[14] Emma E.H. Doyle, John McClure, David M. Johnston, Douglas Paton, ?Communicating likelihoods and probabilities in forecasts of volcanic eruptions?, Journal of Volcanology and Geothermal Research 272 (2014) 1–15
[15] Jean Dominique Creutin, Marco Borga, Eve Gruntfest, Céline Lutoff, DavideZoccatelli, Isabelle Ruin, ?A space and time framework for analyzing human anticipation of flash floods?, Journal of Hydrology 482 (2013) 14–24
[16] JACK HERRMANN, ?Disaster Response Planning & Preparedness: PHASES OF DISASTER?, Copyright 2007 – New York Disaster Interfaith Services (NYDIS)
[17] KainazBomiSheriwala, ?Data Mining Techniques in Stock Market?, INDIAN JOURNAL OF APPLIED RESEARCH, Volume 4, August 2014.
[18] S. L. Pandhripande and Aasheesh Dixit, ?Prediction of 2 Scrip Listed in NSE using Artificial Neural Network?, International Journal of Computer Applications (IJCA), Volume 134, No.2, January 2016.
[19] Data Mining - Classification & Prediction, available online: http://www.tutorialspoint.com/data_mining/dm_classificatio n_prediction.htm, [accessed 27 April 2016].
[20] Samuel OdeiDanso, ?An Exploration of Classification Prediction Techniques in Data Mining: The insurance domain?, Master’s Degree in Advanced Software Engineering, School of Design, Engineering, and Computing. Bournemouth University, September, 2006.
[21] Dr. B. Srinivasan and K. Pavya, ?A STUDY ON DATA MINING PREDICTION TECHNIQUES IN HEALTHCARE SECTOR?, International Research Journal of Engineering and Technology (IRJET), PP. 552-556, Volume 3, Mar-2016
[22] Vipin Kumar, JoydeepGhosh and • David J. Hand, ?Top 10 algorithms in data mining?, Knowledge and Information System, PP. 1–37, (2008).
[23] Vapnik V (1995), the nature of statistical learning theory. Springer, New York.
[24] Kavitha G, Udhayakumar A and Nagarajan D, ?Stock Market Trend Analysis Using Hidden Markov Models?, available online: https://arxiv.org/ftp/arxiv/papers/1311/1311.4771.pdf.
[25] Haiqin Yang, Laiwan Chan, and Irwin King, ?Support Vector Machine Regression for Volatile Stock Market Prediction?, Intelligent Data Engineering and Automated Learning IDEAL, PP. 391- 396, Springer-Verlag Berlin Heidelberg 2002
[26] RoshaniChoudhary, JagdishRaikwal, ?An Ensemble Approach to Enhance Performance of Webpage Classification?, International Journal of Computer Science and Information Technologies, Vol. 5 (4) , 2014, 5614-5619
[27] Juntao Wang, Xiaolong Su, ?An improved K-Means clustering algorithm?, 978-1-61284-486-2/111$26.00 ©2011 IEEE.
[28] ShwetaJaiswal, Atish Mishra, Praveen Bhanodia,? Grid Host Load Prediction Using GridSim Simulation and Hidden Markov Model?, International Journal of Emerging Technology and Advanced Engineering (ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 4, Issue 7, July 2014).

Keywords
natural disaster, prediction, data mining, HMM, K-means, Hybrid data mining.