Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Most existing work on evolutionary optimization assumes that there are analytic functions for evaluating the objectives and constraints. In the real world, however, the objective or constraint values of many optimization problems can be evaluated solely based on data and solving such optimization problems is often known as data-driven optimization. In this paper, we divide data-driven optimization problems into two categories, i.e., offline and online data-driven optimization, and discuss the main challenges involved therein. An evolutionary algorithm is then presented to optimize the design of a trauma system, which is a typical offline data-driven multiobjective optimization problem, where the objectives and constraints can be evaluated using incidents only. As each single function evaluation involves a large amount of patient data, we develop a multifidelity surrogate-management strategy to reduce the computation time of the evolutionary optimization. The main idea is to adaptively tune the approximation fidelity by clustering the original data into different numbers of clusters and a regression model is constructed to estimate the required minimum fidelity. Experimental results show that the proposed algorithm is able to save up to 90% of computation time without much sacrifice of the solution quality.

[1]  Luc De Raedt,et al.  Active Learning for High Throughput Screening , 2008, Discovery Science.

[2]  Silvana Castano,et al.  Global Viewing of Heterogeneous Data Sources , 2001, IEEE Trans. Knowl. Data Eng..

[3]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[4]  D. Wolfe,et al.  Nonparametric Statistical Methods. , 1974 .

[5]  Bernhard Sendhoff,et al.  On Evolutionary Optimization with Approximate Fitness Functions , 2000, GECCO.

[6]  Bernhard Sendhoff,et al.  Comparing neural networks and Kriging for fitness approximation in evolutionary optimization , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[7]  Jürgen Branke,et al.  Faster convergence by means of fitness estimation , 2005, Soft Comput..

[8]  Qingfu Zhang,et al.  Multiobjective evolutionary algorithms: A survey of the state of the art , 2011, Swarm Evol. Comput..

[9]  A. E. Eiben,et al.  Interactive Evolutionary Algorithms , 2015 .

[10]  António Gaspar-Cunha,et al.  A Multi-Objective Evolutionary Algorithm Using Neural Networks to Approximate Fitness Evaluations , 2005, Int. J. Comput. Syst. Signals.

[11]  Michèle Sebag,et al.  Comparison-Based Optimizers Need Comparison-Based Surrogates , 2010, PPSN.

[12]  Lamjed Ben Said,et al.  Steady state IBEA assisted by MLP neural networks for expensive multi-objective optimization problems , 2014, GECCO.

[13]  Yaochu Jin,et al.  Quality Measures for Approximate Models in Evolutionary Computation , 2003 .

[14]  Bin Li,et al.  An evolution strategy assisted by an ensemble of local Gaussian process models , 2013, GECCO '13.

[15]  Qingfu Zhang,et al.  A Gaussian Process Surrogate Model Assisted Evolutionary Algorithm for Medium Scale Expensive Optimization Problems , 2014, IEEE Transactions on Evolutionary Computation.

[16]  Xin Yao,et al.  Using Class Imbalance Learning for Software Defect Prediction , 2013, IEEE Transactions on Reliability.

[17]  Handing Wang,et al.  Feasibility and utility of population-level geospatial injury profiling: prospective, national cohort study , 2015, The journal of trauma and acute care surgery.

[18]  John W. Tukey,et al.  Data Analysis and Regression: A Second Course in Statistics , 1977 .

[19]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[20]  Bernhard Sendhoff,et al.  Generalizing Surrogate-Assisted Evolutionary Computation , 2010, IEEE Transactions on Evolutionary Computation.

[21]  Handing Wang,et al.  Optimizing trauma system design: The GEOS (Geospatial Evaluation of Systems of Trauma Care) approach , 2014, The journal of trauma and acute care surgery.

[22]  Xin Yao,et al.  Corner Sort for Pareto-Based Many-Objective Optimization , 2014, IEEE Transactions on Cybernetics.

[23]  Kaisa Miettinen,et al.  A survey on handling computationally expensive multiobjective optimization problems using surrogates: non-nature inspired methods , 2015, Structural and Multidisciplinary Optimization.

[24]  Bernhard Sendhoff,et al.  Structure optimization of neural networks for evolutionary design optimization , 2005, Soft Comput..

[25]  Peter J. Fleming,et al.  Evolutionary algorithms in control systems engineering: a survey , 2002 .

[26]  Daniel O Scharfstein,et al.  The value of trauma center care. , 2010, The Journal of trauma.

[27]  Yoel Tenne,et al.  A framework for memetic optimization using variable global and local surrogate models , 2009, Soft Comput..

[28]  Handing Wang,et al.  Access to specialist care: Optimizing the geographic configuration of trauma systems , 2015, The journal of trauma and acute care surgery.

[29]  Andy J. Keane,et al.  Combining Global and Local Surrogate Models to Accelerate Evolutionary Optimization , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[30]  Licheng Jiao,et al.  A Sparse Spectral Clustering Framework via Multiobjective Evolutionary Algorithm , 2016, IEEE Transactions on Evolutionary Computation.

[31]  Graham J. Williams,et al.  Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum] , 2014, IEEE Computational Intelligence Magazine.

[32]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[33]  G. De Soete,et al.  Clustering and Classification , 2019, Data-Driven Science and Engineering.

[34]  Zbigniew Michalewicz,et al.  Evolutionary Algorithms in Engineering Applications , 1997, Springer Berlin Heidelberg.

[35]  Grad Dip Biostat,et al.  Improved Functional Outcomes for Major Trauma Patients in a Regionalized, Inclusive Trauma System , 2012, Annals of surgery.

[36]  Qingfu Zhang,et al.  Expensive Multiobjective Optimization by MOEA/D With Gaussian Process Model , 2010, IEEE Transactions on Evolutionary Computation.

[37]  Rommel G. Regis,et al.  Evolutionary Programming for High-Dimensional Constrained Expensive Black-Box Optimization Using Radial Basis Functions , 2014, IEEE Transactions on Evolutionary Computation.

[38]  Michèle Sebag,et al.  A mono surrogate for multiobjective optimization , 2010, GECCO '10.

[39]  Lothar Thiele,et al.  Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach , 1999, IEEE Trans. Evol. Comput..

[40]  Bernhard Sendhoff,et al.  Efficient evolutionary optimization using individual-based evolution control and neural networks: A comparative study , 2005, ESANN.

[41]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[42]  Ujjwal Maulik,et al.  A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I , 2014, IEEE Transactions on Evolutionary Computation.

[43]  Petros Koumoutsakos,et al.  Accelerating evolutionary algorithms with Gaussian process fitness function models , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[44]  Hideyuki Takagi,et al.  Interactive evolutionary computation: fusion of the capabilities of EC optimization and human evaluation , 2001, Proc. IEEE.

[45]  James L. Arbuckle,et al.  Full Information Estimation in the Presence of Incomplete Data , 1996 .

[46]  Charles Mock,et al.  Guidelines for essential trauma care , 2004 .

[47]  Hong Cheng,et al.  Trace Norm Regularized CANDECOMP/PARAFAC Decomposition With Missing Data , 2015, IEEE Transactions on Cybernetics.

[48]  LiuBo,et al.  A Gaussian Process Surrogate Model Assisted Evolutionary Algorithm for Medium Scale Expensive Optimization Problems , 2014 .

[49]  Andreas Zell,et al.  Evolution strategies assisted by Gaussian processes with improved preselection criterion , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[50]  Hirotaka Nakayama,et al.  Meta-Modeling in Multiobjective Optimization , 2008, Multiobjective Optimization.

[51]  K. Alagappan,et al.  Guidelines for Essential Trauma Care. World Health Organization (2005), 103 pages, $21.60, ISBN: 92-4-154640-9 , 2006 .

[52]  Scott D. Sudhoff,et al.  An Evolutionary Computing Approach to Robust Design in the Presence of Uncertainties , 2010, IEEE Transactions on Evolutionary Computation.

[53]  Bernhard Sendhoff,et al.  Reducing Fitness Evaluations Using Clustering Techniques and Neural Network Ensembles , 2004, GECCO.

[54]  Michael T. M. Emmerich,et al.  Single- and multiobjective evolutionary optimization assisted by Gaussian random field metamodels , 2006, IEEE Transactions on Evolutionary Computation.

[55]  Yaochu Jin,et al.  Surrogate-assisted evolutionary computation: Recent advances and future challenges , 2011, Swarm Evol. Comput..

[56]  Qingfu Zhang,et al.  Regularity Model for Noisy Multiobjective Optimization , 2016, IEEE Transactions on Cybernetics.

[57]  Xindong Wu,et al.  Data mining with big data , 2014, IEEE Transactions on Knowledge and Data Engineering.

[58]  Bernhard Sendhoff,et al.  A framework for evolutionary optimization with approximate fitness functions , 2002, IEEE Trans. Evol. Comput..

[59]  Kyriakos C. Giannakoglou,et al.  Design of optimal aerodynamic shapes using stochastic optimization methods and computational intelligence , 2002 .

[60]  Bernhard Sendhoff,et al.  A study on metamodeling techniques, ensembles, and multi-surrogates in evolutionary computation , 2007, GECCO '07.

[61]  Pierre Hansen,et al.  Variable Neighborhood Search , 2018, Handbook of Heuristics.

[62]  Marion K Campbell,et al.  The GEOS study: designing a geospatially optimised trauma system for Scotland. , 2014, The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland.

[63]  Qingfu Zhang,et al.  Fitness Modeling With Markov Networks , 2013, IEEE Transactions on Evolutionary Computation.

[64]  Bernhard Sendhoff,et al.  A Multiobjective Evolutionary Algorithm Using Gaussian Process-Based Inverse Modeling , 2015, IEEE Transactions on Evolutionary Computation.

[65]  G. W. Milligan,et al.  A Study of the Comparability of External Criteria for Hierarchical Cluster Analysis. , 1986, Multivariate behavioral research.

[66]  Yaochu Jin,et al.  A comprehensive survey of fitness approximation in evolutionary computation , 2005, Soft Comput..

[67]  Qingfu Zhang,et al.  Multiobjective optimization Test Instances for the CEC 2009 Special Session and Competition , 2009 .

[68]  Yew-Soon Ong,et al.  A study on polynomial regression and Gaussian process global surrogate model in hierarchical surrogate-assisted evolutionary algorithm , 2005, 2005 IEEE Congress on Evolutionary Computation.

[69]  Xin Yao,et al.  A framework for finding robust optimal solutions over time , 2013, Memetic Comput..

[70]  Yaochu Jin,et al.  Reconstructing biological gene regulatory networks: where optimization meets big data , 2014, Evol. Intell..

[71]  Aimin Zhou,et al.  A Multioperator Search Strategy Based on Cheap Surrogate Models for Evolutionary Optimization , 2015, IEEE Transactions on Evolutionary Computation.

[72]  Martin Holena,et al.  Surrogate Model for Continuous and Discrete Genetic Optimization Based on RBF Networks , 2010, IDEAL.

[73]  Alessandro Turco,et al.  Metamodels for Fast Multi-objective Optimization: Trading Off Global Exploration and Local Exploitation , 2010, SEAL.

[74]  Sanja Petrovic,et al.  Hybrid variable neighbourhood approaches to university exam timetabling , 2010, Eur. J. Oper. Res..

[75]  Qingfu Zhang,et al.  Stable Matching-Based Selection in Evolutionary Multiobjective Optimization , 2014, IEEE Transactions on Evolutionary Computation.

[76]  Eckart Zitzler,et al.  Indicator-Based Selection in Multiobjective Search , 2004, PPSN.

[77]  Pierre Hansen,et al.  Variable neighborhood search: Principles and applications , 1998, Eur. J. Oper. Res..

[78]  G. Dunteman.  Principal Components Analysis , 1989 .

[79]  Xin Yao,et al.  Two_Arch2: An Improved Two-Archive Algorithm for Many-Objective Optimization , 2015, IEEE Transactions on Evolutionary Computation.

[80]  JinYaochu,et al.  A systems approach to evolutionary multiobjective structural optimization and beyond , 2009 .

[81]  Bernhard Sendhoff,et al.  A systems approach to evolutionary multiobjective structural optimization and beyond , 2009, IEEE Computational Intelligence Magazine.

[82]  Sanghamitra Bandyopadhyay,et al.  Multiobjective GAs, quantitative indices, and pattern classification , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[83]  Saúl Zapotecas Martínez,et al.  MOEA/D assisted by rbf networks for expensive multi-objective optimization problems , 2013, GECCO '13.

[84]  Jürgen Branke,et al.  Evolutionary optimization in uncertain environments-a survey , 2005, IEEE Transactions on Evolutionary Computation.

[85]  A. Peitzman,et al.  The Effects of Trauma Center Care, Admission Volume, and Surgical Volume on Paralysis After Traumatic Spinal Cord Injury , 2009, Annals of surgery.