Filters








367 Hits in 5.7 sec

A Non-parametric Statistical Dominance Operator for Noisy Multiobjective Optimization [chapter]

Dung H. Phan, Junichi Suzuki
2012 Lecture Notes in Computer Science  
This paper describes and evaluates a new noise-aware dominance operator for evolutionary algorithms to solve the multiobjective optimization problems (MOPs) that contain noise in their objective functions  ...  This operator is designed with the Mann-Whitney U -test, which is a non-parametric (i.e., distribution-free) statistical significance test.  ...  end for 12: if p A = 1 and p B = 0 then 13: return 1 /*** a U-dominates b. ***/ 14: else if p A = 0 and p B = 1 then 15: return −1 /*** b U-dominates a. ***/ 16: else 17: return 0 /*** a and b are non-U-dominated  ... 
doi:10.1007/978-3-642-34859-4_5 fatcat:b4evkezaafewdfnw46fgfhud3e

Robust Design Optimization and Emerging Technologies for Electrical Machines: Challenges and Open Problems

Tamás Orosz, Anton Rassõlkin, Ants Kallaste, Pedro Arsénio, David Pánek, Jan Kaska, Pavel Karban
2020 Applied Sciences  
However, from the mathematical point of view, these problems belong to the most general branch of non-linear optimization problems, where these tools cannot guarantee that a global minimum is found.  ...  In practice, these optimization problems are even more challenging, because engineers are looking for robust designs, which are not sensitive to the tolerances and the manufacturing uncertainties.  ...  AMOPSO Another Multiobjective It selects leaders from a non-dominated external archive.  ... 
doi:10.3390/app10196653 doaj:9bb6606346f14e0ba83de62fe04591ff fatcat:s7igiflkafbundtozrzklinnk4

Multiobjective Neural Network Ensembles Based on Regularized Negative Correlation Learning

Huanhuan Chen, Xin Yao
2010 IEEE Transactions on Knowledge and Data Engineering  
The paper analyzes this problem and proposes the multiobjective regularized negative correlation learning (MRNCL) algorithm which incorporates an additional regularization term for the ensemble and uses  ...  the evolutionary multiobjective algorithm to design ensembles.  ...  Yaochu Jin for providing the source code on regularizing neural networks using multi-objective evolutionary algorithms [12] for comparison with our algorithm.  ... 
doi:10.1109/tkde.2010.26 fatcat:le4ioh3lfrf3pfelbidg64jo6a

Noise-aware evolutionary TDMA optimization for neuronal signaling in medical sensor-actuator networks

Junichi Suzuki, Pruet Boonma
2014 Proceedings of the 2014 conference companion on Genetic and evolutionary computation companion - GECCO Comp '14  
This paper formulates a noisy optimization problem for a neuronal signaling protocol based on Time Division Multiple Access (TDMA) and solves the problem with a noise-aware optimizer that leverages an  ...  Simulation results show that the proposed optimizer efficiently obtains quality TDMA signaling schedules and operates a TDMA protocol by balancing conflicting objectives in noisy environments.  ...  This paper formulates a noisy multiobjective optimization problem for a neuronal signaling protocol, called Neuronal TDMA, and approaches the problem with a noise-aware evolutionary multiobjective optimization  ... 
doi:10.1145/2598394.2609854 dblp:conf/gecco/SuzukiB14 fatcat:buea5yixsrapjc6pz7g77j7bse

APPLICATIONS OF MULTIOBJECTIVE OPTIMIZATION IN CHEMICAL ENGINEERING

V. Bhaskar, Santosh K. Gupta, Ajay K. Ray
2000 Reviews in chemical engineering  
We then present the several methods available for generating these optimal solutions.  ...  Multiobjective optimization involves the simultaneous optimization of more than one objective function. This is quite commonly encountered in Chemical Engineering.  ...  If we compare points A and C, we observe that these two points are non-dominating.  ... 
doi:10.1515/revce.2000.16.1.1 fatcat:u3qyo5bpfza27hmf23p7w7wynu

MOI-MBO: Multiobjective Infill for Parallel Model-Based Optimization [chapter]

Bernd Bischl, Simon Wessing, Nadja Bauer, Klaus Friedrichs, Claus Weihs
2014 Lecture Notes in Computer Science  
Internally, an evolutionary algorithm is used to optimize this criterion. We verify the usefulness of the approach on a large set of established benchmark problems for black-box optimization.  ...  The aim of this work is to compare different approaches for parallelization in model-based optimization.  ...  use a multiobjective optimizer.  ... 
doi:10.1007/978-3-319-09584-4_17 fatcat:jjtkakjd2zeidpf6v4xnvqftyu

Pareto-optimality of oblique decision trees from evolutionary algorithms

Jose Maria Pangilinan, Gerrit K. Janssens
2010 Journal of Global Optimization  
The results also show that a classifier, whether exhaustive or evolutionary, that generates the most accurate trees does not necessarily generate the shortest trees or the best Pareto-optimal sets.  ...  , tree size, and Pareto-optimality of their solution sets.  ...  Averages do not show tradeoff solutions in a multiobjective optimization problem, i.e. solutions in the search space that are Pareto-optimal or non-dominated cannot be described by averages [33] .  ... 
doi:10.1007/s10898-010-9614-9 fatcat:nqvsrkmanrdxvcmeqjagb4bsnq

Joint inversion of multiple data types with the use of multiobjective optimization: problem formulation and application to the seismic anisotropy investigations

E. Kozlovskaya, L. Vecsey, J. Plomerová, T. Raita
2007 Geophysical Journal International  
In the present paper we demonstrate that this standard approach is not always justified and propose to consider a joint inversion problem as a multiobjective optimization problem (MOP), for which the misfit  ...  We illustrate the multiobjective approach with a non-linear problem of the joint inversion of shear wave splitting parameters and longitudinal wave residuals.  ...  a multiobjective optimization problem (MOP).  ... 
doi:10.1111/j.1365-246x.2007.03540.x fatcat:pv4p5wqg6zcdfpzln2nqmnqqk4

Combining RMT-based filtering with time-stamped resampling for robust portfolio optimization

David Quintana, Sandra García-Rodríguez, Silvano Cincotti, Pedro Isasi
2015 International Journal of Computational Intelligence Systems  
Finding the optimal weights for a set of financial assets is a difficult task.  ...  This paper suggests that a combination of a filtering mechanism based on random matrix theory with time-stamped resampled evolutionary multiobjective optimization algorithms enhances the robustness of  ...  The first one is the Non-dominated Sorting Genetic Algorithm II, NSGA-II, proposed by Deb et al. 30 .  ... 
doi:10.1080/18756891.2015.1084707 fatcat:hrnxm7tq5ravhokskdboiyi55e

Efficient dynamic resampling for dominance-based multiobjective evolutionary optimization

Alejandro Cervantes, David Quintana, Gustavo Recio
2016 Engineering optimization (Print)  
Multi-objective optimization problems are often subject to the presence of objectives that require expensive resampling for their computation.  ...  This paper proposes the integration of dominance based statistical testing methods as part of the selection mechanism of MOEAs with the aim of reducing the amount of fitness evaluations.  ...  The crowding operator was used to select the best 1000 non-dominated solutions in each of these combined fronts.  ... 
doi:10.1080/0305215x.2016.1187729 fatcat:ry55ue2bzjdy5lnut22sqtez24

A robust multiobjective model for the integrated berth and quay crane scheduling problem at seaside container terminals

Abtin Nourmohammadzadeh, Stefan Voß
2021 Annals of Mathematics and Artificial Intelligence  
The three methods are compared based on some multiobjective metrics and a statistical test. The advantage of the integration of berth and quay crane scheduling is examined as well.  ...  Hence, a robust model is devised for the problem having three objectives of minimising the deviations from target berthing locations and times as well as departure delays of all vessels.  ...  An SA algorithm for noisy multiobjective optimisation with continuous decision variables is presented in [31] .  ... 
doi:10.1007/s10472-021-09743-5 fatcat:2bhowazokzgczftgdxl26xsurm

Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm

Eric Bradford, Artur M. Schweidtmann, Alexei Lapkin
2018 Journal of Global Optimization  
Many engineering problems require the optimization of expensive, black-box functions involving multiple conflicting criteria, such that commonly used methods like multiobjective genetic algorithms are  ...  The reference point required for the hypervolume calculation is estimated within TSEMO. Further, a simple extension was proposed to carry out batch-sequential design.  ...  Schweidtmann thanks the Ernest-Solvay-Foundation and the ERASMUS+ program for a scholarship for his exchange at the University of Cambridge.  ... 
doi:10.1007/s10898-018-0609-2 fatcat:bimpiiowbvfc5ltqeycevjgjuy

Navigation in multiobjective optimization methods

Richard Allmendinger, Matthias Ehrgott, Xavier Gandibleux, Martin Josef Geiger, Kathrin Klamroth, Mariano Luque
2016 Journal of Multi-Criteria Decision Analysis  
to identify the mostpreferred solution among the Pareto set for a multiobjective optimization problem.  ...  KEY WORDS: Multiobjective optimization, multiple criteria decision making, preference learning, navigation Definition 1.1 (Navigation) Navigation is the interactive procedure of traversing through a set  ...  Acknowledgement This paper is a product of discussions initiated in the Dagstuhl Seminar 12041: Learning in Multiobjective Optimization. The authors acknowledge gratefully Prof.  ... 
doi:10.1002/mcda.1599 fatcat:4tvr3dj5xfdxhpaat7apmhkh4q

Optimization Using Multiple Dominance Criteria for Aerospace Design Under Uncertainty

Laurence W. Cook, Jerome P. Jarrett
2018 AIAA Journal  
In optimization under uncertainty for aerospace design, statistical moments of the quantity of interest are often treated as separate objectives and are traded off in a multi-objective optimization formulation  ...  We consider various orders of stochastic dominance as criteria to use alongside statistical moment based Pareto dominance, and illustrate how this gives rise to improved designs using a limited computational  ...  The replacement operator, which consists of non-dominated sorting and a crowding distance operator, along with the selection operator require modifying for use with multiple nondominance criteria.  ... 
doi:10.2514/1.j056951 fatcat:g5qbasnhmbcqjcvislq5gzuwl4

Enhanced Evolutionary Algorithms for Multidisciplinary Design Optimization: A Control Engineering Perspective [chapter]

G. Dellino, P. Lino, C. Meloni, A. Rizzo
2007 Studies in Computational Intelligence  
The computational experiments show the ability of the proposed method for finding a satisfactory set of efficient solutions.  ...  To tackle such a situation, a multi-objective optimization formulation of the problem is proposed.  ...  The authors wish to thank two anonymous referees for their valuable comments and criticisms which have contributed to improve the quality of the presentation of their work.  ... 
doi:10.1007/978-3-540-73297-6_3 fatcat:uniwyzmbgngbhdgtjgudwwkjdy
« Previous Showing results 1 — 15 out of 367 results