China 
Africa 
Explore chapters and articles related to this topic
Development of extremely low energy dwellings through life cycle optimization
Published in Paul Fazio, Hua Ge, Jiwu Rao, Guylaine Desmarais, Research in Building Physics and Building Engineering, 2020
Besides, global optimization of a building as a whole is a complex optimization problem due to the amount of parameters and variables, the nonlinear relations and second order effects. During the two last decades evolutionary computation techniques, such as Genetic Algorithms (GA), have been receiving increasing attention regarding their potential as optimization techniques for such complex problems. (Michalewicz et al. 1996). They are a class of related stochastic global search and optimization techniques, which are based upon the principles of evolution by natural selection and its operators and terminology are drawn from the field of population genetics (Craw 2002, Asiedu etal. 2000). One of their main advantages is that they do not have much mathematical requirements about the optimization problem (Michalewicz et al. 1996). Application in building related engineering is still rare until now (Asiedu et al. 2000).
Artificial Agentss
Published in Mariam Kiran, X-Machines for Agent-Based Modeling, 2017
Evolutionary computation is a sub-field under artificial intelligence (AI) research area, involving optimization to automatically solve difficult problems. These contain the following:Always include an iterative process where models progressively update their performance.Allow growth of given agent populations such that are internally modified based on performance.Processes can involve parallel processing.Mostly all processes are inspired by principles of natural evolution.
CONCLUDING REMARKS
Published in Kumar S. Ray, Soft Computing and Its Applications, Volume Two, 2014
The genetic algorithms are members of a collection of methodologies known as evolutionary computation (EC). These techniques are based on the selection and evolution processes that are met in nature and imitate these principles in many scientific domains. One of the researchers that worked for the establishment of the genetic algorithms’ theory was Holland. A few years later Goldberg, studied several aspects of the implementation of genetic algorithms and examined their potential in the context of optimization and learning for large-scale complex systems. By changing their focus to engineering design, Bullock et al. [24] investigated the advances of the genetic algorithms, while Rosenman [201] performed an even more specific survey on evolutionary models that are applicable to non-routine design problems. Another important review about approaches that apply both evolutionary and adaptive search in engineering design problems was authored by Parmee [179]. Genetic algorithms have also been utilized as creative design tools [89] or as support tools to computer-based systems applied to detailed design [199].
Calibration of a sedimentation model through a continuous genetic algorithm
Published in Inverse Problems in Science and Engineering, 2019
Aníbal Coronel, Stefan Berres, Richard Lagos
Evolutionary computation techniques applied to the numerical optimization mimic the principles of natural selection formulated by Darwin. The foundations of evolutionary computation are the following four paradigms: genetic algorithms [11], genetic programming [18], evolutionary strategies [19] and evolutionary programming [20]. Genetic algorithms are the most popular technique because of their simplicity of implementation, global convergence and several other advantages extensively described in [21]. The first genetic algorithm was proposed by Holland in his pioneering work [11]. Following this work, various improvements have been developed and proposed by several researchers. The most complete and technically advanced reference is the book of Michalewicz [12]. In the following the standard terminology of genetic algorithms is used. For completeness of the presentation the main concepts are recalled: chromosomes, genes, population and generation, for more details see [9,11,13,21].
Elitism-based multi-objective differential evolution with extreme learning machine for feature selection: a novel searching technique
Published in Connection Science, 2018
Subrat Kumar Nayak, Pravat Kumar Rout, Alok Kumar Jagadev, Tripti Swarnkar
A large number of features usually associated with a classification problem. Out of that, few features may be essential or relevant for classification. These redundant and erroneous features may reduce the potential of a classification algorithm. Hence, the data representation with a minimum number of relevant features is an important challenge in this present world. Feature selection (FS) is a data mining application that helps to find out the relevant features of a dataset. So the issue of dealing with the irrelevant features can be well handled by FS. Once the redundant and irrelevant features are removed, the dimensionality of the dataset gets reduced too. In turn, it simplifies the classifier model, makes the learning process quicker, and in a nutshell, it enhances the overall performance. Furthermore, the complicated relations among features makes it more challenging to extract most relevant features. There is a possibility that a feature that works great as single may not be that relevant while working in a group or vice versa (Xue, Zhang, & Browne, 2013). The task of selecting good features can be more difficult with the increase in the size of the search space. When number of features grows, the search space for selecting good feature subset grows exponentially. So, in most of the cases, an exhaustive search for most relevant features is not possible because of this large search space. A variety of search algorithms have been developed in the last few decades to handle this problem. However, many of these possess a high computational cost. Most importantly, they are getting trapped in a local optimum easily. Hence, researchers have been motivated to find a search method that can tackle this local minima problem efficiently. The evolutionary computation (EC) techniques are fairly efficient in finding global optimum while solving an optimisation problem. This fetched the attention of many people in the field of FS for best feature subset selection.
User satisfaction-based genetic algorithm for load shifting in smart grid
Published in International Journal of Computers and Applications, 2023
Abderezak Touzene, Manar Al Moqbali
Evolutionary computation algorithms such as genetic algorithms GA have shown potential for solving complex and large-scale optimization problems. GA provides a near-optimal solution for the given problems. Hence, we use a GA approach to solve our load shifting optimization problem. One of the main advantages of the proposed algorithm is flexibility in modeling the problem and the ease of implementing the GA algorithm.