Showing papers on "Genetic algorithm published in 1970"
01 Jan 1970
TL;DR: The experiments show that the proposed Real coded genetic algorithms (RCGA) could reach near optimum solution and the hybridization can improve the performance of the RCGA.
Abstract: This paper addresses two NP-hard and strongly related problems in production planning of flexible manufacturing system (FMS), part type selection problem and machine loading problem. Various flexibilities such as alternative machines, tools, and production plans are considered. Real coded genetic algorithms (RCGA) that uses an array of real numbers as chromosome representation is developed to handle these flexibilities. Hybridizing with variable neighbourhood search (VNS) is performed to improve the power of the RCGA exploring and exploiting the large search space of the problems. The effectiveness of this hybrid genetic algorithm (HGA) is tested using several test bed problems. The HGA improves the FMS effectiveness by considering two objectives, maximizing system throughput and minimizing system unbalance. The resulted objective values are compared to the optimum values produced by branch-and-bound method. The experiments show that the proposed RCGA could reach near optimum solution and the hybridization can improve the performance of the RCGA.
21 citations
TL;DR: This work presents a novel methodology for pattern recognition that uses genetic learning to get an optimized classification system, applied to a real problem, in which it is required to distinguish three nuclear accidents that may occur in a nuclear power plant.
Abstract: This work presents a novel methodology for pattern recognition that uses genetic learning to get an optimized classification system. Each class is represented by several time series in a data base. The idea is to find clusters in the set of the training patterns of each class so that their centroids can distinguish the classes with a minimum of misclassifications. Due to the high level of difficulty found in this optimization problem and the poor prior knowledge about the patterns domain, a model based on genetic algorithm is proposed to extract this knowledge, searching for the minimum number of subclasses that leads to a maximum correctness in the classification. The goal of this model is to find how many and which are the clusters to consider. To validate the methodology, reference problems, where the best solution is wellknown, are proposed. Extending the scope of the application, the methodology is applied to a real problem, in which it is required to distinguish three nuclear accidents that may occur in a nuclear power plant. The misclassification rate was 5% in a total of 180 trials. To ratify the results an artificial neural network was designed and trained to solve the same problem. The results and comparisons are shown and commented. Transactions on Information and Communications Technologies vol 19 © 1998 WIT Press, www.witpress.com, ISSN 1743-3517
18 citations
Journal Article•
TL;DR: The approach to develop a library for inducing the context free grammar using Genetic Algorithms is discussed and the library has been implemented and the results obtained for the set of various problems like balanced parenthesis, two symbol palindromes and equal number of 0s and 1s are presented.
Abstract: Grammar Induction is the process of learning grammar from training data of the positive (S+) and negative (S-) strings of the language. The paper discusses the approach to develop a library for inducing the context free grammar using Genetic Algorithms. Genetic Algorithm used for the induction library produces successive generations of individualsâ chromosome, computes their fitness value in every step of generation and finally select the best out of the total number of generation or when the termination condition (threshold) is meet. The library also deals with the issues in implementation of the algorithm, chromosome representation, evaluation, selection and replacement strategy and the genetic operators for crossover and mutation. The paper also addresses the solution of the problem like useless production, left recursion, left factor, and unit production etc. The library has been implemented and the results obtained for the set of various problems like balanced parenthesis, two symbol palindromes and equal number of 0s and 1s are presented.
14 citations
01 Jan 1970
TL;DR: Comparison of the conventional tuning method with the performance of tuning method by using genetic algorithm can be seen and population size of 40 delivers the fastest rise time and settling time.
Abstract: Controller tuning is one of the important aspect in industry. With a good tuning method, it can ensure the quality of the process and product produce. Apart from that, it can protect the environment and help the company to reduce the cost. Genetic algorithm is one of the tuning method that increase usage and awareness in industry. Thus, the objective of this research is to compare the performance of the conventional tuning method with the performance of tuning method by using genetic algorithm can be seen. Optimization was done on stripping section of distillation column by using genetic algorithm with population size of 20, 40, 60 and 80 and comparing the result with previous optimization using Ziegler-Nichols method. The result obtain showed large improvement in the process response especially on rise time from 1.33 s to 1.31s and settling time from 4.56 to 4.46. Finally, population size of 40 deliver the fastest rise time and settling time.
8 citations
Journal Article•
TL;DR: In this article, the authors proposed a method to minimise a network routing time taken by the mobile agents to collect information from different sites using genetic algorithm (GA), which repeated travelling over short routes and avoid longer ones.
Abstract: Mobile agents often have a task to collect data from several predefined sites. This should be done in an efficient way by minimising the elapsed time. Usually these agents only know the list of sites but not the distances between them. This paper proposes a method to minimise a network routing time taken by the mobile agents to collect information from different sites using genetic algorithm (GA). The mobile agents repeat travelling over short routes and avoid longer ones. Mobile agents for query retrieval have used the GA to select the best routes that minimise the query retrieval time. The result shows that the proposed method provides good time minimisation in retrieving the query results by the mobile agents based on different GA parameters.
5 citations
TL;DR: The application of the genetic algorithm to several problems in optimization is described and the performances in each of these experiments were compared with those of conventional methods.
Abstract: The application of the genetic algorithm to several problems in optimization is described. The performances in each of these experiments were compared with those of conventional methods. The pros and cons of using the genetic algorithm in the examples are also discussed.
4 citations
01 Jan 1970
TL;DR: The experimental results show that c2GA outperforms cGA and is a robust algorithm.
Abstract: Compressed compact genetic algorithm (c2GA) is an algorithm that utilizes the compressed chromosome encoding and compact genetic algorithm (cGA). The advantage of c2GA is to reduce the memory usage by representing population as a probability vector. In this paper, we analyze the performance in term of robustness of c2GA. Since the compression and decompression strategy employ two parameters, which are the length of repeating value and the repeat count, we vary these two parameters to see the performance affected in term of convergence speed. The experimental results show that c2GA outperforms cGA and is a robust algorithm.
3 citations
TL;DR: In this article, a shape optimization scheme of two-dimensional continuum structures by GA and boundary element method (BEM) is described, where the profiles of the objects under consideration are represented by Free-Form Deformation (FFD) method.
Abstract: This paper describes a shape optimization scheme of two-dimensional continuum structures by genetic algorithm (GA) and boundary element method (BEM). The profiles of the objects under consideration are represented by Free-Form Deformation (FFD) method. The chromosomes for the profiles are defined by the FFD control points. The population constructed by many chromosomes is modified by the genetic operations such as the selection, the crossover and the mutation in order to determine the profile satisfying the design objective. The boundary element method is employed for estimating the fitness functions. The present method is applied to the shape optimization of a cantilever beam.
3 citations
TL;DR: A parallel implementation of genetic algorithms is applied to routing protocols with low bandwidth consumption, including the (LSP) link state packet protocols and a strategy is proposed that allows the algorithm to replace segments of the entire path.
Abstract: A parallel implementation of genetic algorithms is applied to routing protocols with low bandwidth consumption. In particular, the paper discusses the (LSP) link state packet protocols. The first part of the paper deals with network topology and transmission parameters, together with the structure for storing the network. The second part discusses the Genetic Algorithm implementation. To this end, it considers the generation of the initial population that is a subset of all the possible paths connecting couples of nodes. As far as the mating and mutation policy is concerned, a strategy is proposed that allows the algorithm to replace segments of the entire path The implementation is carried out in parallel, thus letting different populations to evolve separately. Subsets of different populations migrate periodically to avoid the populations to persist in some local minima. These are the equilibrium states, where no better path, with a lower cost, can be found for a given period. As for conclusions, comparisons between the results of the sequential and distributed implementations of Genetic Algorithms are reported.
2 citations
1 citations
TL;DR: The proposed operational rules for reservoir management in real time to obtain the maximum of hydropower energy have shown that proposed technique with operators of selection and crossing is very effective and can approach the optimum area more rapidly than other methods.
Abstract: The study presents the results of genetic algorithm application to optimize energy utilization of the reservoir Sance on the river Ostravice The aim of our research was a proposal of operational rules for reservoir management in real time to obtain the maximum of hydropower energy Our solution has shown that proposed technique with operators of selection and crossing is very effective and can approach the optimum area more rapidly than other methods.
01 Jan 1970
TL;DR: This paper proposes a hybrid of PSO and Generalized Generation Gap model with Parent- Centric Recombination operator (G3PCX) with PSPG, a well-known real-coded genetic algorithm that combines fast convergence and rotational invariance of G3 PCX as well as global search ability ofPSO.
Abstract: Particle Swarm Optimization (PSO) algorithm has recently gained more attention in the global optimization research due to its simplicity and global search ability. This paper proposes a hybrid of PSO and Generalized Generation Gap model with Parent- Centric Recombination operator (G3PCX) [25], a well-known real-coded genetic algorithm. The proposed hybrid algorithm, namely PSPG, combines fast convergence and rotational invariance of G3PCX as well as global search ability of PSO. The performance of PSPG algorithm is evaluated using 8 widely-used nonlinear benchmark functions of 30 and 200 decision variables having different properties. The experiments study the effects of its new probability parameter Px and swarm size for optimizing those functions. The results are analyzed and compared with those from the Standard PSO [14] and G3PCX algorithms. The proposed PSPG with Px = 0.10 and 0.15 can outperform both algorithms with a statistical significance for most functions. In addition, the PSPG is not much sensitive to its swarm size as most PSO algorithms are. The best swarm sizes are 40 and 50 for unimodal and multimodal functions, respectively, of 30 decision variables.
TL;DR: In this paper, the optimum design of concrete slab is solved and investigated using genetic algorithm, where the constraints are restricted to the stresses in concrete and reinforcing bars, however, in order to obtain durable concrete structures, the constraint for crack width is very important.
Abstract: The optimum design of concrete slab is solved and investigated using genetic algorithm. In ordinal optimum design of slabs, the constraints are restricted to the stresses in concrete and reinforcing bars However, in order to obtain durable concrete structures, the constraint for crack width is very important. Adding to this, the variables like spacings of reinforcing bars are usually determined as discrete one. Therefore, the genetic algorithm is useful for this kind of problems.