Search

• A hybrid DE–MARS–based model is a good predictive model of the phosphorus and chlorophyll presences. • Algal abnormal proliferation is dangerous for environment in lakes. • The biological and physical-chemical input variables in this process are studied in depth. • The results of this hybrid model for the eutrophication evaluation is compared with the M5 model tree. • The obtained correlation coefficients of two hybrid DE–MARS–based models are about 90%. Algal atypical proliferation is a consequence of water fertilization (also called eutrophication) and one of the main causes of the degradation of reservoir and lake ecosystems. Its intensification during the last decades has led the stakeholders to seek water management and restoration solutions, including those based on modelling approaches. In this way, this paper presents one reservoir eutrophication modelling based on a new hybrid algorithm that combines multivariate adaptive regression splines (MARS) and differential evolution (DE) to estimate the algal abnormal proliferation from physical-chemical and biological variables. This technique involves the optimization of the MARS hyperparameters during the training process. Additionally, an M5 model tree was fitted to the experimental data for comparison purposes. Apart from successfully forecasting algal atypical growth (coefficients of determination equal to 0.83 and 0.91), the model showed here can establish the significance of each biological and physical-chemical parameter of the algal enhanced growth. Finally, the main conclusions of this research work are exposed. [ABSTRACT FROM AUTHOR]

Abstract: Magneto-electro-elastic structures are built from materials that provide them the ability to convert in an interchangeable way, magnetic, electric and mechanical forms of energy. This characteristic can therefore provide an adaptive behaviour to a general configuration elastic structure, being commonly used in association with any type of composite material in an embedded or surface mounted mode, or by considering the usage of multiphase materials that enable achieving different magneto-electro-elastic properties. In a first stage of this work, a few cases studies will be considered to enable the validation of the model considered and the influence of the coupling characteristics of this type of adaptive structures. After that we consider the application of a recent computational intelligence technique, the differential evolution, in a deflection profile minimization problem. Studies on the influence of optimization parameters associated to the problem considered will be performed as well as the adoption of an adaptive scheme for the perturbation factor. Results are also compared with those obtained using an enhanced particle swarm optimization technique. [Copyright &y& Elsevier]

Abstract: In construction industry, cost escalation is a major cause of project failure. The reason is that construction prices fluctuate over time and they are influenced by numerous factors. This study establishes a hybrid intelligence system, named as ELSVM, for modeling construction price variations quantified by the construction cost index (CCI). The proposed method is developed based on the fusion of Least Squares Support Vector Machine (LS-SVM) and Differential Evolution (DE). LS-SVM is used for mining the mapping function between CCI and its causative input factors. Meanwhile, DE is employed to optimize LS-SVM tuning parameters. In this research, a database consisting of 122 historical cases was collected to establish the intelligence system. Based on experimental results, ELSVM can successfully model CCI fluctuations since it has achieved a comparatively low MAPE which is less than 1%. Thus, the proposed system can be a promising tool to assist decision-makers in construction management. [Copyright &y& Elsevier]

Abstract: This paper presents how an algorithm based on Differential Evolution (DE) with no constant control parameters solves the dimensional synthesis of four and six-bar mechanisms for path generation. The selection of values of DE control parameters is not always an easy and obvious job. In this paper a DE with auto-adaptive control parameters is proposed which includes a new mutation operator to solve stagnation in local minima and, on top of all this, the choice of a control parameters value in a simple way. For a set of 6 representative cases related to dimensional synthesis from bibliography, the performance of this new DE algorithm, called Ingeniería Mecánica Málaga (IMMa) Optimization Algorithm with Self-Adaptive Technique, IOAs-at, has been tested. An explanation of how the new mutation operator works is also included. The results obtained, compared with other synthesis techniques from literature, present significant improvements for every case studied. The new version does not require control input parameters to be chosen by the user. Those are auto-tuned during the algorithm execution, that is, we use an algorithm with adaptive control parameters and it continues being easy-to-use, robust and fast. [Copyright &y& Elsevier]

Abstract: The real world contains many sources of natural variation. Useful simulation models of real-world problems, such as the optimal allocation of beef cattle into feedlot pens, need to take this into account. Monte Carlo simulation is the usual method of achieving this, using multiple model runs, each with a different set of randomly generated variables. However, when the goal is system optimisation, this approach can make the computation extremely intensive, and difficult for the optimisation of even moderately-sized models. This problem was addressed in an industry model of feedlot operations, where animals are selected and drafted into separate pens, and grown to the optimal weight and fat ranges in the pricing grid. For each pen, it is planned that the majority of the animals achieve this targeted region of the price grid, so that the number of discounted carcasses will be minimal. The main problem is that animals which appear reasonably similar at intake then display variable growth and fattening rates. Hence deterministic predictions are unrealistic, and stochasticity needs to be factored in. However this interferes with the efficient optimisation of this feedlot operation, which ultimately needs to be done ‘real-time’ (at animal induction), and on-site at the feedlot. Our solution to this dilemma was to transfer all of the modelled stochastic processes onto the evaluation side of this problem, by integrating over Normal distributions applied to the expected prices for each animal. This allows the optimisation runs to directly estimate the expected economic outcome using just one model evaluation for each trial management strategy. This process is illustrated with two case-studies, based on separate past intakes of animals into a commercial feedlot. For both intakes, the simulated results as reflected by the carcass values for the actual times on feed matched well with the observed values. Simulated results indicate that increases in profitability can be obtained both by altering the days on feed, and by better allocation of the animals to the pens. The overall predicted increase in profit per animal was $34 for the first intake, where the actual allocation of animals to the pens was approximately random (the order they were offloaded), and $20 for the second example where the animals had been allocated to pens on a more structured basis (by weights). This optimised allocation scheme appears to offer obvious improvements for feedlot operations, and is currently being trialed by a number of industry collaborators. [Copyright &y& Elsevier]

• Multi-population mechanism is introduced into salp swarm algorithm. • The proposed method is abbreviated as MCSSA. • Chaos-assisted exploitation strategy is introduced into MCSSA. • MCSSA is tested over 30 benchmark functions and 5 real-world problems. • The greater effectiveness of MCSSA is confirmed over the advanced algorithms. Salp swarm algorithm (SSA) is a recently presented algorithm, which is simple in structure and relatively mediocre in its performance. However, the original SSA still has features to be improved because it may face problems in convergence trends or easily being trapped into local optima for more advanced problems. To alleviate this limitation, we propose a new SSA-based method (MCSSA) that performs the chaotic exploitative trends and has a multi-population structure. The new structure can assist SSA in making a more stable tradeoff between global exploration and local exploitation capabilities. First, the exploitation trends and neighborhood searching commands of SSA are enriched using the chaos-assisted exploitation strategy. Next, we arrange a multi-population structure with three sub-strategies to augment the global exploration capabilities of the algorithm. To test the performance of this proposed MCSSA, a set of comprehensive algorithms is used, including 11 other original methods, conventional SSA, and 13 advanced techniques including SCA, SSA, GWO, MFO, WOA, BA, FPA, PSO, ALO, MVO, DE, ABC, CSSA, ESSA, CLSGMFO, LGCMFO, SaDE, jDE, EPSO, ALCPSO, CBA, RCBA, BWOA, CCMWOA, and GA-MPC based on 30 IEEE CEC2017 benchmark functions and 5 IEEE CEC2011 practical test problems. Also, the non-parametric statistics Wilcoxon signed-rank test and Friedman test are also used as an enabling tool to validate the performance of the proposed algorithm. From the result analysis, it can be concluded that the introduced strategy significantly improves the speed of the algorithm converging to the optimal value, and the improvement of the search ability also helps the algorithm to find a better solution than the basic SSA. As a conclusion, it can be said that MCSSA is reliable and efficient in solving complex optimization problems. An online website at https://aliasgharheidari.com supports this research for any guide or info. [ABSTRACT FROM AUTHOR]

It is usually very difficult to elicit the parameter values of models representing decision makers' preferences. Consequently, some imprecision, ill-determination and arbitrariness are unavoidable. Moreover, such elicitation cannot be performed by traditional optimization techniques in a reasonable time. Therefore, we present here a novel elicitation method guided by a genetic algorithm whose main contribution is coping with imperfect knowledge. The latter is done by using interval numbers representing all the possible values that the parameters can attain. The assessment of the method showed its high ability to reproduce the decision maker's preferences. Finally, as the method proposed in this paper is the complement of the authors' previous work regarding the optimization of stock portfolios, we provide a case study in such a field. We use differential evolution to obtain the most satisfactory portfolio. The results reported here show that the best portfolio returns are obtained when the elicitation method is exploited, and we conclude that the new overall approach might be an interesting alternative to the already-existing methods. • We present a novel method to infer the parameters of decision makers' systems of preferences using evolutionary algorithms. • The method's main contribution is coping with imperfect knowledge on the decision maker's preferences and criterion scores. • An application in an extensive case study on optimization of stock portfolios is provided. • The results support the convenience of the proposed method in situations of uncertainty over all the benchmarks used. [ABSTRACT FROM AUTHOR]