We present a new methodology called J-SIGMA to infer state change information using the minimum Jensen- Shannon distance to describe a continuous optimization problem as a Boltzmannian system, as well as its applicati...
详细信息
We present a new methodology called J-SIGMA to infer state change information using the minimum Jensen- Shannon distance to describe a continuous optimization problem as a Boltzmannian system, as well as its applications to population-based metaheuristics. In general, a Boltzmannian system describes a macrostate from the statistics of the constituent microstate where the minimum energy is the most probable. If we model an optimization problem as a Boltzmann process, the global optimum would be the most probable state. To achieve this, we propose an analytical derivation of the minimum distance to the Boltzmann distribution using the parameters and to fit this model. As a case study, we implemented the J-SIGMA methodology on three families of population-based metaheuristics: Swarm, Evolutionary, and estimation of distribution, and used a set of continuous optimization functions from CEC'17 to evaluate their performance against other metaheuristics of each family. Finally, from a statistical analysis of the convergence performance, the evidence is shown to affirm that the J-SIGMA methodology can significantly improve the convergence performance of the algorithms, regardless of the metaheuristic family to which it belongs.
The offshore wind turbines are dynamically sensitive, whose fundamental frequency can be very close to the forcing frequencies activated by the environmental and turbine loads. Minor changes of support conditions may ...
详细信息
The offshore wind turbines are dynamically sensitive, whose fundamental frequency can be very close to the forcing frequencies activated by the environmental and turbine loads. Minor changes of support conditions may lead to the shift of natural frequencies, and this could be disastrous if resonance happens. To monitor the support conditions and thus to enhance the safety of offshore wind turbines, a model updating method is developed in this study. A hybrid sensing system was fabricated and set up in the laboratory to investigate the long-term dynamic behaviour of the offshore wind turbine system with monopile foundation in sandy deposits. A finite element model was constructed to simulate structural behaviours of the offshore wind turbine system. Distributed nonlinear springs and a roller boundary condition are used to model the soil-structure interaction properties. The finite element model and the test results were used to analyse the variation of the support condition of the monopile, through an finite element model updating process using estimation of distribution algorithms. The results show that the fundamental frequency of the test model increases after a period under cyclic loading, which is attributed to the compaction of the surrounding sand instead of local damage of the structure. The hybrid sensing system is reliable to detect both the acceleration and strain responses of the offshore wind turbine model and can be potentially applied to the remote monitoring of real offshore wind turbines. The estimation of distribution algorithm-based model updating technique is demonstrated to be successful for the support condition monitoring of the offshore wind turbine system, which is potentially useful for other model updating and condition monitoring applications.
A large number of classification algorithms have been proposed in the machine learning literature. These algorithms have different pros and cons, and no algorithm is the best for all datasets. Hence, a challenging pro...
详细信息
A large number of classification algorithms have been proposed in the machine learning literature. These algorithms have different pros and cons, and no algorithm is the best for all datasets. Hence, a challenging problem consists of choosing the best classification algorithm with its best hyper-parameter settings for a given input dataset. In the last few years, Automated Machine Learning (Auto-ML) has emerged as a promising approach for tackling this problem, by doing a heuristic search in a large space of candidate classification algorithms and their hyper-parameter settings. In this work we propose an improved version of our previous Evolutionary Algorithm (EA) - more precisely, an estimation of distribution Algorithm - for the Auto-ML task of automatically selecting the best classifier ensemble and its best hyper-parameter settings for an input dataset. The new version of this EA was compared against its previous version, as well as against a random forest algorithm (a strong ensemble algorithm) and a version of the well-known Auto-ML method Auto-WEKA adapted to search in the same space of classifier ensembles as the proposed EA. In general, in experiments with 21 datasets, the new EA version obtained the best results among all methods in terms of four popular predictive accuracy measures: error rate, precision, recall and F-measure. (C) 2019 Elsevier B.V. All rights reserved.
As a type of model-based metaheuristic, estimation of distribution algorithms (EDAs) show certain advantages over other metaheuristics by using statistical learning method to estimate the distribution of promising sol...
详细信息
As a type of model-based metaheuristic, estimation of distribution algorithms (EDAs) show certain advantages over other metaheuristics by using statistical learning method to estimate the distribution of promising solutions. However, the commonly-used Gaussian EDAs (GEDAs) usually suffer from premature convergence that severely limits their efficiency. In this paper, we first attempt to enhance the performance of GEDA by improving its model estimation method. The new estimation method shifts the weighted mean of high-quality solutions towards the fitness improvement direction and estimates the covariance matrix by taking the shifted mean as the center. Theoretical analyses show that the new covariance matrix is essentially a rank-one modification (R1M) of the original one. It could effectively adjust both the search scope and the search direction of GEDA, and thus improving the search efficiency. Furthermore, considering the importance of the population size tuning in GEDA, we develop a population reduction (PR) strategy which linearly reduces the population size throughout the evolution. By this means, the exploration and exploitation ability of GEDA could be balanced better in different search stages and a more proper utilization of limited computation resource can be achieved. Combining GEDA with the R1M and PR strategies, a novel EDA variant named EDA-R1M-PR is developed. The performance of EDA-R1M-PR was comprehensively evaluated and compared with that of several state-of-the-art evolutionary algorithms. Experimental results indicate that the R1M and PR strategies effectively enhance the global optimization ability of GEDA and the resultant EDA-R1M-PR significantly outperforms its competitors on a set of benchmark functions.
Dynamic environments are still a big challenge for optimization algorithms. In this paper, a Genetic Algorithm using both Multiploid representation and the Bayesian Decision method is proposed. By Multiploid represent...
详细信息
Dynamic environments are still a big challenge for optimization algorithms. In this paper, a Genetic Algorithm using both Multiploid representation and the Bayesian Decision method is proposed. By Multiploid representation, an implicit memory scheme is introduced to transfer useful information to the next generations. In this representation, there are more than one genotypes and only one phenotype. The phenotype values are determined based on the corresponding genotypes values. To determine phe-notype values, the well-known Bayesian Optimization Algorithm (BOA) has been injected into our algo-rithm to create a Bayes Network by using the previous population to exploit interactions between variables. With this algorithm, we have solved the well-known Dynamic Knapsack Problem (DKP) with 100, 250, and 500 items. Also, we have compared our algorithm with the most recent algorithm in the literature by using the DKP with 100 items. Experiments have shown that the proposed algorithm is effi-cient and faster than the peer algorithms in the manner of tracking moving optima without using an explicit memory scheme. In conclusion, using relationships between variables within the optimization algorithms is useful when concerning dynamic environments.(c) 2022 Karabuk University. Publishing services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).
estimation of distribution algorithms (EDAs) focus on explicitly modelling dependencies between solution variables. A Gaussian distribution over continuous variables is commonly used, with several different covariance...
详细信息
ISBN:
(纸本)9781467315098
estimation of distribution algorithms (EDAs) focus on explicitly modelling dependencies between solution variables. A Gaussian distribution over continuous variables is commonly used, with several different covariance matrix structures ranging from diagonal i.e. Univariate Marginal distribution Algorithm (UMDA(c)) to full i.e. estimation of Multivariate Normal density Algorithm (EMNA). A diagonal covariance model is simple but is unable to directly represent covariances between problem variables. On the other hand, a full covariance model requires estimation of (more) parameters from the selected population. In practice, numerical issues can arise with this estimation problem. In addition, the performance of the model has been shown to be sometimes undesirable. In this paper, a modified Gaussian-based continuous EDA is proposed, called sEDA, that provides a mechanism to control the amount of covariance parameters estimated within the Gaussian model. To achieve this, a simple variable screening technique from experimental design is adapted and combined with an idea inspired by the Pareto-front in multi-objective optimization. Compared to EMNA(global), the algorithm provides improved numerical stability and can use a smaller selected population. Experimental results are presented to evaluate and compare the performance of the algorithm to UMDA(c) and EMNA(global)
When searching for input configurations that optimise the output of a system, it can be useful to build a statistical model of the system being optimised. This is done in approaches such as surrogate model-based optim...
详细信息
When searching for input configurations that optimise the output of a system, it can be useful to build a statistical model of the system being optimised. This is done in approaches such as surrogate model-based optimisation, estimation of distribution algorithms, and linkage learning algorithms. This article presents a method for modelling pseudo-Boolean fitness functions using Walsh bases and an algorithm designed to discover the non-zero coefficients while attempting to minimise the number of fitness function evaluations required. The resulting models reveal linkage structure that can be used to guide a search of the model efficiently. It presents experimental results solving benchmark problems in fewer fitness function evaluations than those reported in the literature for other search methods such as EDAs and linkage learners.
The estimation of distribution algorithms (EDAs) is a novel class of evolutionary algorithms which is motivated by the idea of building probabilistic graphical model of promising solutions to represent linkage informa...
详细信息
ISBN:
(纸本)9781457715846
The estimation of distribution algorithms (EDAs) is a novel class of evolutionary algorithms which is motivated by the idea of building probabilistic graphical model of promising solutions to represent linkage information between variables in chromosome. Through learning of and sampling from probabilistic graphical model, new population is generated and optimization procedure is repeated until the stopping criteria are met. In this paper, the mechanism of the estimation of distribution algorithms is analyzed. Currently existing EDAs are surveyed and categorized according to the probabilistic model they used, then the strengths and weakness and the future perspective of EDAs are concluded.
We present a new estimation of distribution algorithms (EDA) based on two novel Variational Autoencoders generative model building algorithms. The first method, Variational Autoencoder with Population Queue (VAE-EDA-Q...
详细信息
ISBN:
(纸本)9781728121536
We present a new estimation of distribution algorithms (EDA) based on two novel Variational Autoencoders generative model building algorithms. The first method, Variational Autoencoder with Population Queue (VAE-EDA-Q), employs a queue of historical populations, which is updated at each iteration of EDA in order to smooth the data generation process. The second method uses Adaptive Variance Scaling (AVS) with VAE-EDA-Q to dynamically update the variance at which the probabilistic model is sampled. The results obtained prove our methods to be significantly more computationally efficient than state-of-the-art algorithms and perform significantly less number of fitness evaluations when tested on benchmark problems such as Trap-k and NK Landscapes. Moreover, we report results of applying our approach successfully to highly complex problems such as Trap 11, Trap 13, and NK Landscapes with neighborhood size K = 8 and K = 10.
Linkage learning is frequently employed in state-of-the-art methods dedicated to discrete optimization domains. Information about linkage identifies a subgroup of genes that are found dependent on each other. If such ...
详细信息
ISBN:
(纸本)9783030581114;9783030581121
Linkage learning is frequently employed in state-of-the-art methods dedicated to discrete optimization domains. Information about linkage identifies a subgroup of genes that are found dependent on each other. If such information is precise and properly used, it may significantly improve a method's effectiveness. The recent research shows that to solve problems with so-called overlapping blocks, it is not enough to use linkage of high quality - it is also necessary to use many different linkages that are diverse. Taking into account that the overlapping nature of problem structure is typical for practical problems, it is important to propose methods that are capable of gathering many different linkages (preferably of high quality) to keep them diverse. One of such methods is a Parameter-less Population Pyramid (P3) that was shown highly effective for overlapping problems in binary domains. Since P3 does not apply to permutation optimization problems, we propose a new P3-based method to fill this gap. Our proposition, namely the Parameter-less Population Pyramid for Permutations (P4), is compared with the state-of-the-art methods dedicated to solving permutation optimization problems: Generalized Mallows estimation of distribution Algorithm (GM-EDA) and Linkage Tree Gene-pool Optimal Mixing Evolutionary Algorithm (LT-GOMEA) for Permutation Spaces. As a test problem, we use the Permutation Flowshop Scheduling problem (Taillard benchmark). Statistical tests show that P4 significantly outperforms GM-EDA for almost all considered problem instances and is superior compared to LT-GOMEA for large instances of this problem.
暂无评论