Abstract
The kernel parameters setting of SVM influences prediction precision. The hybrid model based on SVM for regression and improved differential evolution is proposed to enhance the prediction precision. The improved differential evolution is used to optimize the kernel parameters. The improved differential evolution algorithm employs two trial vector generation strategies and two control parameter settings. The first-generation strategy is with best solution, and the second strategy is without best solution. Three categories of disasters time series including flood, drought and storm from Ministry of agriculture of China are used to verify the validity of the proposed model. Compared with the grid SVM and other models, the proposed hybrid model improves the prediction precision of SVM.
Similar content being viewed by others
References
African Union (AU) (2006) Status of food security and prospects for agricultural development in Africa. African Union (AU), Addis Ababa
Ali M, Pant M (2011) Improving the performance of differential evolution algorithm using Cauchy mutation. Soft Comput 15:991–1007
Azadeh A, Ghaderi SF, Tarverdian S, Saberi M (2007) Integration of artificial neural networks and genetic algorithm to predict electrical energy consumption. Appl Math Comput 186:1731–1741
Babu BV, Jehan MML (2003) Differential evolution for multi-objective optimization. In: Proceeding IEEE congress on evolutionary computation pp 2696–2703
Brest J, Greiner S, Boskovic B, Mernik M, Zumer V (2006) Self-adapting control parameters in differential evolution: a comparative study on numerical benchmark problems. IEEE Trans Evolut Comput 10:646–657
Cai ZH, Goertzel B, Zhou CL, Zhang YF, Jiang M, Yu GN (2012) Dynamics of a computational affective model inspired by Dorner’s PSI theory. Cogn Syst Res 17–18:63–80
Cai ZH, Goertzel B, Zhou CL, Huang DH, Ke SJ, Yu GN, Jiang M (2013) OpenPsi: a novel computational affective model and its application in video games. Eng Appl Artif Intell 26:1–12
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27
Chao F, Wang ZS, Shang CJ, Meng QG, Jiang M, Zhou CL, Shen Q (2014a) A developmental approach to robotic pointing via human-robot interaction. Inf Sci 283:288–303
Chao F, Lee MH, Jiang M, Zhou CL (2014b) An infant development-inspired approach to robot hand-eye coordination. Int J Adv Rob Syst 11:1–15
Chen FY, Tong K, Yang JC (1992) The proposal about constructing the National Disaster Monitoring, Forecast and Control System. Acta Astronaut 28:135–138
Chu F (2008) Analyzing and forecasting tourism demand with ARAR algorithm. Tour Manag 29:1185–1196
Feng Y, Zhang WF, Sun DZ, Zhang LQ (2011) Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification. Atmos Environ 45:1979–1985
Fro¨hlich H, Chapelle O (2003) Feature selection for support vector machines by means of genetic algorithms. In: Proceedings of the 15th IEEE international conference on tools with artificial intelligence, Sacramento, CA, USA, pp 142–148
Gaalman G, Disney SM (2006) State space investigation of the bullwhip problem with ARMA(1, 1) demand processes. Int J Prod Econ 104:327–339
Gamperle R, Muller SD, Koumoutsakos P (2002) A parameter study for differential evolution. In: Proceeding advances in intelligent systems, fuzzy systems, evolutionary computation, Crete, Greece, pp 293–298
Ghosh A, Mondal A, Ghosh S (2014) Moving object detection using Markov random field and distributed differential evolution. Appl Soft Comput 15:121–135
Gong ZW, Chen CQ, Ge XM (2014) Risk prediction of low temperature in Nanjing city based on grey weighted Markov model. Nat Hazards 71:1159–1180
Guo XP, Li DC, Zhang AH (2012) Improved support vector machine oil price forecast model based on genetic algorithm optimization parameters. AASRI Procedia 1:525–530
Hsu CW, Lin J (2002) A simple decomposition method for support vector machine. Mach Learn 46:219–314
Huang CL, Dun JF (2008) A distributed PSO–SVM hybrid system with feature selection and parameter optimization. Appl Soft Comput 8:1381–1391
Huang CL, Wang CJ (2006) A GA-based feature selection and parameters optimization for support vector machines. Expert Syst Appl 31:231–240
Iorio A, Li X (2004) Solving rotated multi-objective optimization problems using differential evolution. In Australian conference on artificial intelligence, Cairns, Australia, pp 861–872
Jiang M, Huang WZ, Huang ZQ, Gary GY (2015) Integration of global and local metrics for domain adaptation learning via dimensionality reduction. IEEE Trans Cybern 99:1–14
Kgakatsi IB, Rautenbach CJdeW (2014) The contribution of seasonal climate forecasts to the management of agricultural disaster-risk in South Africa. Int J Disaster Risk Reduct 8:100–113
Kim KJ (2003) Financial time series forecasting using support vector machines. Neurocomputing 55:307–319
Kung HY, Chen CH, Ku HH (2012) Designing intelligent disaster prediction models and systems for debris-flow disasters in Taiwan. Expert Syst Appl 39:5838–5856
Kunga HY, Kua HH, Lin CWCY (2008) Intelligent and situation-aware pervasive system to support debris-flow disaster prediction and alerting in Taiwan. J Netw Comput Appl 31:1–18
LaValle SM, Branicky MS (2002) On the relationship between classical grid search and probabilistic roadmaps. Int J Robot Res 23:673–692
Mallipeddi R, Suganthan PN, Pan QK, Tasgetiren MF (2011) Differential evolution algorithm with ensemble of parameters and mutation strategies. Appl Soft Comput 11:1679–1696
Mezura-Montes E, Velazquez-Reyes J, Coello Coello CA (2006) Modified differential evolution for constrained optimization. In: Proceeding IEEE congress on evolutionary computation, Vancouver, BC, pp 25–32
Murat YS, Ceylan H (2006) Use of artificial neural networks for transport energy demand modeling. Energy Policy 34:3165–3172
Pahner U, Hameyer K (2000) Adaptive coupling of differential evolution and multiquadrics approximation for the tuning of the optimization process. IEEE Trans Magn 36:1047–1051
Price K, Storn R, Lampinen J (2005) Differential evolution—a practical approach to global optimization. Springer, Berlin
Qi W (2010) Product demand forecasts using wavelet kernel support vector machine and particle swarm optimization in manufacture system. J Comput Appl Math 233:2481–2491
Qin AK, Huang VL, Suganthan PN (2009) Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans Evol Comput 13:398–417
Sharma H, Bansal JC, Arya KV (2012) Fitness based differential evolution. Memet Comput 4:303–316
Sousa SIV, Martins FG, Alvim-Ferraz MCM, Pereira MC (2007) Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations. Environ Model Softw 22:97–103
Storn R (1996) Differential evolution design of an iir-filter. IEEE international conference on evolutionary computation IEEE, pp 268–273
Storn R, Price K (1997) Differential evolution a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim 11:341–359
Tang Y, Wang Z, Gao H, Swift S, Kurths J (2012) A constrained evolutionary computation method for detecting controlling regions of cortical networks. IEEE/ACM Trans Comput Biol Bioinf 9:1569–1581
Tang Y, Gao H, Kurths J (2013) Multiobjective identification of controlling areas in neuronal networks. IEEE/ACM Trans Comput Biol Bioinf 10:708–720
UN (2006) Global survey of early warning systems: an assessment of capacities, gaps and opportunities toward building a comprehensive global early warning system for all natural hazards. In: Proceeding of the third internal conference on early warning
Vapnik V (1995) The nature of statistical learning. Springer, New York
Wang B, Liu SD, Jing L, Huang LY, Zhao LG (2011a) Advanced prediction for multiple disaster sources of laneway under complicated geological conditions. Min Sci Technol 21:749–754
Wang H, Wu ZJ, Rahnamayan S (2011b) Enhanced opposition-based differential evolution for solving high-dimensional continuous optimization problems. Soft Comput 15:127–2140
Wang Y, Cai ZX, Zhang QF (2011c) Differential evolution with composite trial vector generation strategies and control parameters. IEEE Trans Evol Comput 15:55–66
Wang L, Zeng Y, Chen T (2015) Back propagation neural network with adaptive differential evolution algorithm for time series forecasting. Expert Syst Appl 42:855–863
Wong WK, Xia M, Chu WC (2010) Adaptive neural network model for time-series forecasting. Eur J Oper Res 2:807–816
Wu Y, Jiang M, Huang ZQ, Chao F, Zhou CL (2015) An NP-complete fragment of fibring logic. Ann Math Artif Intell 75:391–417
Wua CI, Kung HY, Chen CH, Kuo LC (2014) An intelligent slope disaster prediction and monitoring system based on WSN and ANP. Expert Syst Appl 41:4554–4562
Yu L (2012) An evolutionary programming based asymmetric weighted least squares support vector machine ensemble learning methodology for software repository mining. Inf Sci 191:31–46
Yu L, Yao X, Wang SY, Lai KK (2011) Credit risk evaluation using a weighted least squares SVM classifier with design of experiment for parameter selection. Expert Syst Appl 38:15392–15399
Yu XB, Cai M, Cao J (2015) A novel mutation differential evolution for global optimization. J Intell Fuzzy Syst 28:1047–1060
Zhang F (2007) An application of vector GARCH model in semiconductor demand planning. Eur J Oper Res 181:288–297
Zhang J, Sanderson AC (2009) JADE: adaptive differential evolution with optional external archive. IEEE Trans Evol Comput 13:945–958
Acknowledgments
This work was supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD), Social Science Foundation of Chinese Ministry of Education (No.12YJC630271), China Natural Science Foundation (No. 71273139, 71401078, 71503134, 91546117, 61673328/F030603), Research Center for Prospering Jiangsu Province with Talents (No. skrc201400-14) and philosophy and Social Sciences in Universities of Jiangsu (No. 2016SJB630016).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, X. Disaster prediction model based on support vector machine for regression and improved differential evolution. Nat Hazards 85, 959–976 (2017). https://doi.org/10.1007/s11069-016-2613-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-016-2613-5