Scientists and decision-makers need tools that can assess which specific pressures lead to ecosystem deterioration, and which measures could reduce these pressures and/or limit their effects. In this context, species ...
详细信息
Scientists and decision-makers need tools that can assess which specific pressures lead to ecosystem deterioration, and which measures could reduce these pressures and/or limit their effects. In this context, species distribution models are tools that can be used to help asses these pressures. evolutionary algorithms represent a collection of promising techniques, inspired by concepts observed in natural evolution, to support the development of species distribution models. They are suited to solve non-trivial tasks, such as the calibration of parameter-rich models, the reduction of model complexity by feature selection and/or the optimization of hyperparameters of other machine learning algorithms. Although widely used in other scientific domains, the full potential of evolutionary algorithms has yet to be explored for applied ecological research. In this synthesis, we study the role of evolutionary algorithms as a machine learning technique to develop the next generation of species distribution models. To do so, we review available methods for species distribution modelling and synthesize literature using evolutionary algorithms. In addition, we discuss specific advantages and weaknesses of evolutionary algorithms and present a guideline for their application. We find that evolutionary algorithms are increasingly used to solve specific and challenging problems. Their flexibility, adaptability and transferability in addition to their capacity to find adequate solutions to complex, non-linear problems are considered as main strengths, especially for species distribution models with a large degree of complexity. The need for programming and modelling skills can be considered as a drawback for novice modellers. In addition, setting values for hyperparameters is a challenge. Future ecological research should focus on exploring the potential of evolutionary algorithms that combine multiple tasks in one learning cycle. In addition, studies should focus on the use of novel
Offering Product-Service Systems (PSS) becomes an established strategy for companies to increase the provided customer value and ensure their competitiveness. Designing PSS business models, however, remains a major ch...
详细信息
Offering Product-Service Systems (PSS) becomes an established strategy for companies to increase the provided customer value and ensure their competitiveness. Designing PSS business models, however, remains a major challenge. One reason for this is the fact that PSS business models are characterized by a long-term nature. Decisions made in the development phase must take into account possible scenarios in the operational phase. Risks must already be anticipated in this phase and mitigated with appropriate measures. Another reason for the design phase being a major challenge is the size of the solution space for a possible business model. Developers are faced with a multitude of possible business models and have the challenge of selecting the best one. In this article, a simheuristic optimization approach is developed to test and evaluate PSS business models in the design phase in order to select the best business model configuration beforehand. For optimization, a proprietary evolutionary algorithm is developed and tested. The results validate the suitability of the approach for the design phase and the quality of the algorithm for achieving good results. This could even be transferred to already established PSS.
Soil and tire interaction is a complex process that involves the exchange of variable stresses along the contact area of soil and tire. Despite this complexity, the description of this process in the form of mathemati...
详细信息
Soil and tire interaction is a complex process that involves the exchange of variable stresses along the contact area of soil and tire. Despite this complexity, the description of this process in the form of mathematical models has long been of interest to the researchers. The same complexity has led the wheels and soil interaction patterns to be constantly evolving and optimizing. This evolution has coincided with the scientific progress of mathematics, modeling and computer until today. Nowadays, optimizing and predicting a model based on input variables using machine learning techniques and conventional evolutionary algorithms play an important role in predicting the relationships between input and output. These methods can be far better than the conventional statistical techniques. The modeling and prediction of wheel rolling resistance on the soil have many parameters. Using new techniques such as genetic, BAT and PSO algorithms to optimize them seems to be suitable approaches. The aim of this research is to investigate and optimize the parameters of the Wismer-Luth model using the evolutionary algorithms. To improve the model, the variables of multi-pass, forward velocity and depth of the cone index, are also incorporated to the Wismer-Luth model, and the corresponding parameters are optimized with the BAT algorithm. Analysis of experimental data showed that the correlation of the output of the proposed model with the experimental data is 0.87 where it is 0.77 for the Wismer-Luth model. Furthermore, experimental results in this study showed that there is a significant relationship between rolling resistance and multi-pass effect, neglected in most models.
In this contribution we give a short overview about actual developments in hybrid systems combining self-organizing maps and evolutionary algorithms. Thereby, we pay attention to both directions of influence: neural n...
详细信息
In this contribution we give a short overview about actual developments in hybrid systems combining self-organizing maps and evolutionary algorithms. Thereby, we pay attention to both directions of influence: neural network improvement by incorporating evolutionary elements and evolutionary design using ideas of learning in neural maps. In more detail, we highlight neighborhood cooperation in evolutionary systems for multiple population systems as well as genetic operators. We show the possibilities and properties of these approaches for exemplary real world applications. (C) 2004 Elsevier B.V. All rights reserved.
In this paper, we propose an evolutionary Algorithm (EA) with a deterministic mutation operator which is a combination of EA with the Broyden, Fletcher, Goldfarb and Shanno (BFGS) method. The advantages of both optimi...
详细信息
In this paper, we propose an evolutionary Algorithm (EA) with a deterministic mutation operator which is a combination of EA with the Broyden, Fletcher, Goldfarb and Shanno (BFGS) method. The advantages of both optimization algorithms are retained and interconnected. The proposed algorithm shows faster convergence as well as increased reliability in the search for the global optimum. Results referring to the Fletcher and Powel test function in comparison with EA (Evolution Strategies, evolutionary Programming, and Genetic algorithms), provide sufficient indication for the performance of the new method. Finally, the proposed method is successfully implemented for the trajectory optimization of a four-bar mechanism. (C) 2003 IMACS. Published by Elsevier B.V. All rights reserved.
Thirty years, 1993-2023, is a huge time frame in science. We address some major developments in the field of evolutionary algorithms, with applications in parameter optimization, over these 30 years. These include the...
详细信息
Thirty years, 1993-2023, is a huge time frame in science. We address some major developments in the field of evolutionary algorithms, with applications in parameter optimization, over these 30 years. These include the covariance matrix adaptation evolution strategy and some fast-growing fields such as multimodal optimization, surrogate-assisted optimization, multiobjective optimization, and automated algorithm design. Moreover, we also discuss particle swarm optimization and differential evolution, which did not exist 30 years ago, either. One of the key arguments made in the paper is that we need fewer algorithms, not more, which, however, is the current trend through continuously claiming paradigms from nature that are suggested to be useful as new optimization algorithms. Moreover, we argue that we need proper benchmarking procedures to sort out whether a newly proposed algorithm is useful or not. We also briefly discuss automated algorithm design approaches, including configurable algorithm design frameworks, as the proposed next step toward designing optimization algorithms automatically, rather than by hand.
This paper compares three evolutionary computation techniques, namely Steady-State Genetic algorithms, evolutionary Strategies and Differential Evolution for the Unit Commitment Problem. The comparison. is based on a ...
详细信息
This paper compares three evolutionary computation techniques, namely Steady-State Genetic algorithms, evolutionary Strategies and Differential Evolution for the Unit Commitment Problem. The comparison. is based on a set of experiments conducted on benchmark datasets as well as on real-world data obtained from the Turkish Interconnected Power System. The results of two state-of-the-art evolutionary approaches, namely a Generational Genetic Algorithm and a Memetic Algorithm for the same benchmark datasets are also included in. the paper for comparison. The tests show that Differential Evolution is the best performer among all approaches on the test data used in the paper. The performances of the other two evolutionary algorithms are also comparable to Differential Evolution. and the results of the algorithms taken from literature showing that all EA approaches tested here are applicable to the Unit Commitment Problem. The results of this experimental study are very promising and promote further study.
PID controllers are a reliable, robust, practical and easy to implement control solution for industrial processes. They provide the first control layer for a vast majority of industrial applications. Owing to this, se...
详细信息
PID controllers are a reliable, robust, practical and easy to implement control solution for industrial processes. They provide the first control layer for a vast majority of industrial applications. Owing to this, several researches invest time and resources to improve their performance. The research lines in this field scope with new tuning methods, new types of structures and integral design methods. For tuning methods, improvements could be fulfilled stating an optimization problem, which could be non-linear, non-convex and highly constrained. In such instances, evolutionary algorithms have shown a good performance and have been used in various proposals related with PM controllers tuning. This work shows a review of these proposals and the benefits obtained in each case. Some trends and possible future research lines are also identified.
evolutionary algorithms, a form of meta-heuristic, have been successfully applied to a number of classes of complex combinatorial problems such as the well-studied travelling salesman problem, bin packing problems, et...
详细信息
evolutionary algorithms, a form of meta-heuristic, have been successfully applied to a number of classes of complex combinatorial problems such as the well-studied travelling salesman problem, bin packing problems, etc. They have provided a method other than an exact solution that will, within a reasonable execution time, provide either optimal or near optimal results. In many cases near optimal results are acceptable and the additional resources that may be required to provide exact optimal results prove uneconomical. The class of project scheduling problems (PSP) exhibit a similar type of complexity to the previous mentioned problems, also being NP-hard, and therefore would benefit from solution via meta-heuristic rather than exhaustive search. Improvement to a project schedule in terms of total duration or resource utilisation can be of major financial advantage and therefore near optimal solution via evolutionary techniques should be considered highly applicable. In preparation for further research this paper reviews the application of evolutionary algorithms to the PSP to date extending previous reviews in this area by also encompassing the study of PSP using the design structure matrix. In order to better examine the coverage of this research, this paper also utilises the PSP classification system proposed by (Herroelen, W., Demeulemeester, E. and de Reyck, B., A note on the paper 'Resource-constrained project scheduling: notation, classification, models and methods' by Brucker et al., Euro. J. Op. Res., 2001, 128, 679-688.) to identify the problems being studied in each application and to identify the areas lacking in research. The paper concludes with an examination of areas that in the opinion of the authors would particularly benefit from further research.
This paper presents the application of two classes of evolutionary algorithms (EA) to determine optimum design of Single-Phase Switched Reluctance Machine (SPSRM). The EA used is Genetic algorithms (GA) and Differenti...
详细信息
This paper presents the application of two classes of evolutionary algorithms (EA) to determine optimum design of Single-Phase Switched Reluctance Machine (SPSRM). The EA used is Genetic algorithms (GA) and Differential Evolution (DE). Due to sensitivity of the output torque to the stator and rotor pole arcs, these are selected as design variables for a multi-objective optimization with the objective of maximizing average torque and torque density, and minimizing copper loss. The proposed optimization is tested on a 4/4 1,25 kW SPSRM, and the results of both algorithms are compared. The performance of the optimized motor is compared to the initial motor through the finite element analysis. The results show improvement in both efficiency and output torque.
暂无评论