{"title":"Sensitivity Analysis during the Optimization Process Using Genetic Algorithms","authors":"M. A. Rubio, A. Urquia","volume":124,"journal":"International Journal of Mathematical and Computational Sciences","pagesStart":140,"pagesEnd":145,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10006659","abstract":"Genetic algorithms (GA) are applied to the solution
\r\nof high-dimensional optimization problems. Additionally, sensitivity
\r\nanalysis (SA) is usually carried out to determine the effect on optimal
\r\nsolutions of changes in parameter values of the objective function.
\r\nThese two analyses (i.e., optimization and sensitivity analysis)
\r\nare computationally intensive when applied to high-dimensional
\r\nfunctions. The approach presented in this paper consists in performing
\r\nthe SA during the GA execution, by statistically analyzing the data
\r\nobtained of running the GA. The advantage is that in this case
\r\nSA does not involve making additional evaluations of the objective
\r\nfunction and, consequently, this proposed approach requires less
\r\ncomputational effort than conducting optimization and SA in two
\r\nconsecutive steps.","references":"[1] C. D. Chio, A. Brabazon, M. Ebner, M. Farooq, A. Fink, J. Grahl,\r\nG. Greenfield, P. Machado, M. O\u2019Neill, E. Tarantino, and N. Urquhart,\r\nApplications of Evolutionary Computation. Springer, 2010.\r\n[2] R. L. Johnston, Applications of Evolutionary Computation in Chemistry.\r\nSpringer, 2004.\r\n[3] C. Karr and L. M. Freeman, Industrial Applications of Genetic\r\nAlgorithms. CRC Press, 1998.\r\n[4] T. Back, U. Hammel, and H.-P. Schwefel, \u201cEvolutionary computation:\r\nComments on the history and current state,\u201d IEEE Trans. Evol. Comput.,\r\nvol. 1, no. 1, pp. 3\u201317, 1997.\r\n[5] D. E. Goldberg, Genetic Algorithms in Search, Optimization, and\r\nMachine Learning. Addison-Wesley, 1989.\r\n[6] L. Davis, Handbook of Genetic Algorithms. Van Nostrand Reinhold\r\nCompany, 1991.\r\n[7] A. E. Eiben and J. Smith, Introduction to Evolutionary Computing.\r\nSpringer, 2010.\r\n[8] M. A. Rubio, A. Urquia, and S. Dormido, \u201cAn approach to the calibration\r\nof Modelica models,\u201d in Proceedings of the 1st International Workshop\r\non Equation-Based Object-Oriented Languages and Tools, 2007.\r\n[9] K. Edwards, T. F. Edgar, and V. Manousiouthakis, \u201cKinetic model\r\nreduction using genetic algorithms,\u201d Computers chem. Engng., vol. 22,\r\npp. 239\u2013246, 1998.\r\n[10] M. L. Raymer, W. F. Punch, E. D. Goodman, L. A. Kuhn, and A. K. Jain,\r\n\u201cDimensionality reduction using genetic algorithms,\u201d IEEE Transactions\r\non Evolutionary Computation, vol. 4, no. 2, pp. 164 \u2013 171, 2000.\r\n[11] K. Chan, A. Saltelli, and S. Tarantola, \u201cSensitivity analysis of model\r\noutput: variance-based methods make the difference,\u201d in Proceedings of\r\nthe Winter Simulation Conference, 1997.\r\n[12] A. Saltelli, M. Ratto, T. Andres, F. Campolongo, J. Cariboni, D. Gatelli,\r\nM. Saisana, and S. Tarantola, Global Sensitivity Analysis: The Primer.\r\nWiley, 2008.\r\n[13] A. Saltelli, K. Chan, and E. M. Scott, Sensitivity Analysis. Wiley, 2008.\r\n[14] W. Chen, X. Lu, C. Yao, G. Zhu, and Z. Xu, \u201cAn efficient approach\r\nbased on bi-sensitivity analysis and genetic algorithm for calibration of\r\nactivated sludge models,\u201d Chemical Engineering Journal, vol. 259, pp.\r\n845\u2013853, 2015.\r\n[15] M. Vazquez-Cruz, R. Guzman-Cruz, O. C.-P. I.L. Lopez-Cruz,\r\nI. Torres-Pacheco, and R. Guevara-Gonzalez, \u201cGlobal sensitivity analysis\r\nby means of efast and sobol methods and calibration of reduced\r\nstate-variable tomgro model using genetic algorithms,\u201d Computers and\r\nElectronics in Agriculture, vol. 100, pp. 1\u201312, 2014.\r\n[16] C. Andres, C. F. Valerio, and P. Franz, \u201cValidation of an advanced\r\nlithium-ion battery model for electric and hybrid drive trains,\u201d in\r\nEET-2008 European Ele-Drive Conference. International Advanced\r\nMobility Forum, 2008.\r\n[17] N. Nishida, Y. Takahashi, and S. Wakao, \u201cRobust design optimization\r\napproach by combination of sensitivity analysis and sigma level\r\nestimation,\u201d IEEE Transactions on Magnetics, vol. 44, no. 6, pp.\r\n998\u20131001, 2008.\r\n[18] D. G. Vieira, D. A. G. Vieira, W. M. Caminhas, and J. A.\r\nVasconcelos, \u201cA hybrid approach combining genetic algorithm and\r\nsensitivity information extracted from a parallel layer perceptron,\u201d IEEE\r\nTransactions on Magnetics, vol. 41, no. 5, pp. 1740 \u2013 1743, 2005.\r\n[19] W. T. Eadie, Statistical Methods in Experimental Physics. Elsevier,\r\n1983.\r\n[20] R. L. Plackett, \u201cKarl Pearson and the chi-squared test,\u201d International\r\nStatistical Review, vol. 51, no. 1, pp. 59\u201372, 1983.\r\n[21] H. Shimazaki and S. Shinomoto, \u201cA method for selecting the bin size of\r\na time histogram,\u201d Neural Computation, vol. 19, no. 6, pp. 1503\u20131527,\r\n2007.\r\n[22] K. A. D. Jong, \u201cAn analysis of the behavior of a class of genetic adaptive\r\nsystems,\u201d Ph.D. dissertation, University of Michigan Ann Arbor, MI,\r\nUSA, 1975.\r\n[23] H. Muhlenbein, M. Schomisch, and J. Born, \u201cThe parallel genetic\r\nalgorithm as function optimizer,\u201d Parallel Computing, vol. 17, no. 6-7,\r\npp. 619 \u2013 632, 1991.\r\n[24] T. Back, D. Fogel, and Z. Michalewicz, Handbook of Evolutionary\r\nComputation. Bristol and Oxford University Press, 1997. ","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 124, 2017"}