作者：
Ahmadi, ArasUniv Toulouse
INSA UPS INPLISBP 135 Ave Rangueil F-31077 Toulouse France INRA
UMR792 Lab Ingn Syst Biol & Proc F-31400 Toulouse France CNRS
UMR5504 F-31400 Toulouse France
A new algorithm, dubbed memory-based adaptive partitioning (MAP) of search space, which is intended to provide a better accuracy/speed ratio in the convergence of multi-objective evolutionary algorithms (MOEAs) is pre...
详细信息
A new algorithm, dubbed memory-based adaptive partitioning (MAP) of search space, which is intended to provide a better accuracy/speed ratio in the convergence of multi-objective evolutionary algorithms (MOEAs) is presented in this work. This algorithm works by performing an adaptive-probabilistic refinement of the search space, with no aggregation in objective space. This work investigated the integration of MAP within the state-of-the-art fast and elitist non-dominated sorting genetic algorithm (NSGAII). Considerable improvements in convergence were achieved, in terms of both speed and accuracy. Results are provided for several commonly used constrained and unconstrained benchmark problems, and comparisons are made with standalone NSGAII and hybrid NSGAII-efficient local search (eLS). (C) 2016 Elsevier B.V. All rights reserved.
Case-Base Reasoning is a problem-solving methodology that uses old solved problems, called cases, to solve new problems. The case-base is the knowledge source where the cases are stored, and the amount of stored cases...
详细信息
Case-Base Reasoning is a problem-solving methodology that uses old solved problems, called cases, to solve new problems. The case-base is the knowledge source where the cases are stored, and the amount of stored cases is critical to the problem-solving ability of the Case-Base Reasoning system. However, when the case-base has many cases, then performance problems arise due to the time needed to find those similar cases to the input problem. At this point, Case-Base Maintenance algorithms can be used to reduce the number of cases and maintain the accuracy of the Case-Base Reasoning system at the same time. Whereas Case-Base Maintenance algorithms typically use a particular heuristic to remove (or select) cases from the case-base, the resulting maintained case-base relies on the proportion of redundant and noisy cases that are present in the case-base, among other factors. That is, a particular Case-Base Maintenance algorithm is suitable for certain types of case-bases that share some indicators, such as redundancy and noise levels. In the present work, we consider Case-Base Maintenance as a multi-objective optimization problem, which is solved with a multi-objectiveevolutionary Algorithm. To this end, a fitness function is introduced to measure three different objectives based on the Complexity Profile model. Our hypothesis is that the multi-objectiveevolutionary Algorithm performing Case-Base Maintenance may be used in a wider set of case-bases, achieving a good balance between the reduction of cases and the problem-solving ability of the Case-Based Reasoning system. Finally, from a set of the experiments, our proposed multi-objectiveevolutionary Algorithm performing Case-Base Maintenance shows regularly good results with different sets of case-bases with different proportion of redundant and noisy cases.
We present a multi-objectiveevolutionary algorithm to exploit a medium-sized fuzzy outranking relation to derive a partial order of classes of alternatives (we call it RP2-NSGA-II). To measure the performance of RP2-...
详细信息
We present a multi-objectiveevolutionary algorithm to exploit a medium-sized fuzzy outranking relation to derive a partial order of classes of alternatives (we call it RP2-NSGA-II). To measure the performance of RP2-NSGA-II, we present an empirical study over a set of simulated multi-criteria ranking problems. The result of this study shows that RP2-NSGA-II can effectively exploit a medium-sized fuzzy outranking relation. Finally, we present a real-case study for ranking the municipalities of the state of Guanajuato, Mexico by their levels of marginalization.
The design of robust classifiers, for instance Artificial Neural Networks (ANNs), is a critical aspect in all complex pattern recognition or classification tasks. Poor design choices may undermine the ability of the s...
详细信息
ISBN:
(纸本)9783319326955;9783319326948
The design of robust classifiers, for instance Artificial Neural Networks (ANNs), is a critical aspect in all complex pattern recognition or classification tasks. Poor design choices may undermine the ability of the system to correctly classify the data samples. In this context, evolutionary techniques have proven particularly successful in exploring the complex state-space underlying the design of ANNs. Here, we report an extensive comparative study on the application of several modern multi-objective evolutionary algorithms to the design and training of an ANN for the classification of samples from two different biomedical datasets. Numerical results show that different algorithms have different strengths and weaknesses, leading to ANNs characterized by different levels of classification accuracy and network complexity.
multi-objective evolutionary algorithms(MOEAs) are likely used to identify non-dominated solutions or Pareto front(the known Pareto front) in multi-objective optimization problems. The quality of Pareto front depends ...
详细信息
ISBN:
(纸本)9781510833890
multi-objective evolutionary algorithms(MOEAs) are likely used to identify non-dominated solutions or Pareto front(the known Pareto front) in multi-objective optimization problems. The quality of Pareto front depends on evolution strategies that are evaluated under performance metrics of generational distance, spacing, and error ratio. In this paper, a procedure of Elite optimality is proposed to transform the known Pareto front(PFknown) into the true Pareto front(PFtrue). The Elite optimality procedure improves the quality of the Pareto fronts that deals with the biggest challenge in the multi-objective evolutionary algorithms.
This paper puts forward a comprehensive study of the design of global stopping criteria for multi-objective optimization. In this study we propose a global stopping criterion, which is terms as MGBM after the authors ...
详细信息
This paper puts forward a comprehensive study of the design of global stopping criteria for multi-objective optimization. In this study we propose a global stopping criterion, which is terms as MGBM after the authors surnames. MGBM combines a novel progress indicator, called mutual domination rate (MDR) indicator, with a simplified Kalman filter, which is used for evidence-gathering purposes. The MDR indicator, which is also introduced, is a special-purpose progress indicator designed for the purpose of stopping a multi-objective optimization. As part of the paper we describe the criterion from a theoretical perspective and examine its performance on a number of test problems. We also compare this method with similar approaches to the issue. The results of these experiments suggest that MGBM is a valid and accurate approach. (C) 2016 Elsevier Inc. All rights reserved.
Over the past decade, subdividing evolutionary search into multiple local evolutionary searches has been identified as an effective method to search for optimal solutions of multi-objective optimization problems (MOPs...
详细信息
Over the past decade, subdividing evolutionary search into multiple local evolutionary searches has been identified as an effective method to search for optimal solutions of multi-objective optimization problems (MOPs). The existing multi-objective evolutionary algorithms that benefit from the multiple local searches (multiple-MOEAs, or MMOEAs) use different dividing methods and/or collaborations (information sharing) strategies between the created divisions. Their local evolutionary searches are implicitly or explicitly guided toward a part of global optimal solutions instead of converging to local ones in some divisions. In this reviewed paper, the dividing methods and the collaborations strategies are reviewed, while their advantage and disadvantage are mentioned.
The decentralization of electrical power production is conducive to a more effective and harmonious use of energy resources. For this reason, photovoltaic grid-connected plants (PVGCPs) as well as other renewable ener...
详细信息
The decentralization of electrical power production is conducive to a more effective and harmonious use of energy resources. For this reason, photovoltaic grid-connected plants (PVGCPs) as well as other renewable energy sources have come into the spotlight in recent years since they improve the supply of electrical power to the grid. The optimization of PVGCP design has been previously addressed in terms of electrical losses with successful results. However. PVGCP performance can be further enhanced if other characteristics, such as power capacity, are taken into consideration. This paper focuses on the optimization of the design of photovoltaic plants with solar tracking. The research described had the following two objectives: (i) the maximization of power capacity: (ii) the minimization of electrical losses. This problem was solved with multi-objective evolutionary algorithms, which have proved to be powerful optimization techniques that are useful for a wide range of objectives. This paper focuses on the NSGA-Il and SPEA2, two well-known multi-objectivealgorithms, and describes how they were used to optimize PVGCPs. The resulting sets of solutions provide the flexibility and adaptability needed to build a PVGCP. These algorithms were thus found to be an effective tool for enhancing PVGCP performance. (C) 2014 Elsevier Ltd. All rights reserved.
Traffic Engineering (TE) approaches are increasingly important in network management to allow an optimized configuration and resource allocation. In link-state routing, the task of setting appropriate weights to the l...
详细信息
ISBN:
(纸本)9783319158921;9783319158914
Traffic Engineering (TE) approaches are increasingly important in network management to allow an optimized configuration and resource allocation. In link-state routing, the task of setting appropriate weights to the links is both an important and a challenging optimization task. A number of different approaches has been put forward towards this aim, including the successful use of evolutionaryalgorithms (EAs). In this context, this work addresses the evaluation of three distinct EAs, a single and two multi-objective EAs, in two tasks related to weight setting optimization towards optimal intra-domain routing, knowing the network topology and aggregated traffic demands and seeking to minimize network congestion. In both tasks, the optimization considers scenarios where there is a dynamic alteration in the state of the system, in the first considering changes in the traffic demand matrices and in the latter considering the possibility of link failures. The methods will, thus, need to simultaneously optimize for both conditions, the normal and the altered one, following a preventive TE approach towards robust configurations. Since this can be formulated as a bi-objective function, the use of multi-objective EAs, such as SPEA2 and NSGA-II, came naturally, being those compared to a single-objective EA. The results show a remarkable behavior of NSGA-II in all proposed tasks scaling well for harder instances, and thus presenting itself as the most promising option for TE in these scenarios.
multi-objective evolutionary algorithms (MOEAs) are well-suited for solving several complex multi-objective problems with two or three objectives. However, as the number of conflicting objectives increases, the perfor...
详细信息
multi-objective evolutionary algorithms (MOEAs) are well-suited for solving several complex multi-objective problems with two or three objectives. However, as the number of conflicting objectives increases, the performance of most MOEAs is severely deteriorated. How to improve MOEAs' performance when solving many-objective problems, i.e. problems with four or more conflicting objectives, is an important issue since a large number of this type of problems exists in science and engineering;thus, several researchers have proposed different alternatives. This paper presents a review of the use of MOEAs in many-objective problems describing the evolution of the field, the methods that were developed, as well as the main findings and open questions that need to be answered in order to continue shaping the field.
暂无评论