Empirical Analysis and Random Respectful Recombination of Crossover and Mutation in Genetic Algorithms
12 Jan 2010-International Journal of Computer Applications (Foundation of Computer Science FCS)-Iss: 1, pp 25-30
TL;DR: This paper studies the problem of how changes in the four GA parameters (population size, number of generations, crossover & mutation probabilities) have an effect on GA’s performance from a practical stand point and tests the robustness of GA to control parameters.
Abstract: Genetic algorithms (GAs) are multi-dimensional, blind & heuristic search methods which involves complex interactions among parameters (such as population size, number of generations, various type of GA operators, operator probabilities, representation of decision variables etc.). Our belief is that GA is robust with respect to design changes. The question is whether the results obtained by GA depend upon the values given to these parameters is a matter of research interest. This paper studies the problem of how changes in the four GA parameters (population size, number of generations, crossover & mutation probabilities) have an effect on GA’s performance from a practical stand point. To examine the robustness of GA to control parameters, we have tested two groups of parameters & the interaction inside the group (a) Crossover & mutation alone (b) Crossover combined with mutation . Based on calculations and simulation results it is seen that for simple problems mutation plays an momentous role. For complex problems crossover is the key search operator. Based on our study complementary crossover & mutation probabilities is a reliable approach.
Citations
More filters
TL;DR: The results of experiments demonstrate that the optimized rule obtained using the GA can increase the profit generated significantly as compare to traditional moving average lengths trading rules taken from financial literature.
Abstract: Recent studies have shown that in the context of financial markets, technical analysis is a very useful tool for predicting trends. Moving Average rules are usually used to make “buy” or “sell” decisions on a daily basis. Due their ability to cover large search spaces with relatively low computational effort, Genetic Algorithms (GA) could be effective in optimization of technical trading systems. This paper studies the problem: how can GA be used to improve the performance of a particular trading rule by optimizing its parameters, and how changes in the design of the GA itself can affect the solution quality obtained in context of technical trading system. In our study, we have concentrated on exploiting the power of genetic algorithms to adjust technical trading rules parameters in background of financial markets. The results of experiments based on real timeseries data demonstrate that the optimized rule obtained using the GA can increase the profit generated significantly as compare to traditional moving average lengths trading rules taken from financial literature.
11 citations
Additional excerpts
...Mutation operator is used to add random diversity in the solution [16]....
[...]
TL;DR: Wang et al. as discussed by the authors investigated the effect of stewing temperature, stewing time, and amount of oil on the capsaicin and capsorubin contents of Chinese chili oil.
Abstract: Chili oil, which contains large amounts of capsaicin and capsorubin, is one of the most consumed seasonings in China. These compounds significantly affect the quality, antioxidant activity, pungency, and color of chili oil. This study aimed to investigate the effect of stewing temperature, stewing time, and amount of oil on the capsaicin and capsorubin contents of Chinese chili oil. The partial least squares (PLS) regression and genetic algorithm–artificial neural network models were established and used to predict capsaicin and capsorubin contents. The genetic algorithm was applied to optimize the parameters of the network. The developed genetic algorithm–artificial neural network, which included ten hidden neurons, predicted capsaicin and capsorubin contents with correlation coefficients of 0.995 and 0.986, respectively. The neural network exhibited more accurate prediction and practicability compared with the PLS regression model.
11 citations
Cites background from "Empirical Analysis and Random Respe..."
...Empirical analysis and random recombination of crossover and mutations in GA were reported by Kapoor et al. (2010)....
[...]
TL;DR: In this paper, a computer-aided diagnosis (CAD) system to assist a radiologist for diagnosing pulmonary emphysema from chest computed tomography (CT) slices is developed.
5 citations
Journal Article•
TL;DR: The methodology provides the novel function of adaptive parameter adjustment during each evolution generation of GA to enhance search efficiency towards optimal solutions and improve search effectiveness and algorithm robustness.
Abstract: This paper presents a new methodology for improving the efficiency and generality of Genetic Algorithms (GA). The methodology provides the novel function of adaptive parameter adjustment during each evolution generation of GA. The important characteristics of the methodology are mainly from the following two aspects: (1) superior performance members in GA are preserved and inferior performance members are deteriorated to enhance search efficiency towards optimal solutions; (2) adaptive crossover and mutation management is applied in GA based on the transformation functions to explore wider spaces so as to improve search effectiveness and algorithm robustness. The research was successfully applied for a luggage design chain to generate optimal solutions (minimized lifecycle cost). Experiments were conducted to compare the work with the prior art to demonstrate the characteristics and advantages of the research.
5 citations
TL;DR: In this article, the authors investigated the effect of different pretreatment and reducing sugar content on furfural and 5-hydroxymethylfurfural (HMF) contents of fermented lotus root by vinegar.
Abstract: Abstract The aim of this study was to investigate the effect of different pretreatment and reducing sugar content on furfural (F) and 5-hydroxymethylfurfural (HMF) contents of fermented lotus root by vinegar. The lotus root samples were fermented using vinegar for 15 days, at different solution concentrations and temperatures. The processing conditions were considered as inputs of neural network to predict the F and HMF contents of lotus root. Genetic algorithm was applied to optimize the structure and learning parameters of ANN. The developed genetic algorithm-artificial neural network (GA-ANN) which included 23 and 17 neurons in the first and second hidden layers, respectively, gives the lowest mean squared error (MSE). The correlation coefficient of ANN was compared with multiple linear regression-based models. The GA-ANN model was found to be a more accurate prediction method for the F and HMF contents of fermented lotus root than linear regression-based models. In addition, sensitivity analysis and Pearson’s correlation coefficient were also analyzed to find out the relation between input and output variables.
5 citations
Cites background from "Empirical Analysis and Random Respe..."
...reported that the set of crossover and mutation parameters [29]....
[...]
References
More filters
Proceedings Article•
15 Jul 1995
TL;DR: A simple method for testing the usefulness of crossover for a particular problem is presented, which makes it possible to identify situations in which crossover is apparently useful but is in fact producing gains that are only equal to those that can be obtained with macromutation and no population.
Abstract: A Genetic Algorithm (GA) maintains a population of individuals for the express purpose of improving performance via communication of information between contemporary individuals. This is achieved in a GA through the use of a crossover operator. If crossover is not a useful method for this exchange, the GA should not, on average, perform any better than a variety of simpler algorithms that are not population-based. A simple method for testing the usefulness of crossover for a particular problem is presented. This makes it possible to identify situations in which crossover is apparently useful but is in fact producing gains that are only equal to (or less than) those that can be obtained with macromutation and no population.
157 citations
"Empirical Analysis and Random Respe..." refers methods in this paper
...A crossover hill climbing algorithm is presented by Jones(1995) that illustrates the power of mechanics of crossover....
[...]
Posted Content•
TL;DR: In this article, a simple method for testing the usefulness of crossover for a particular problem is presented, which makes it possible to identify situations in which crossover is apparently useful but is in fact producing gains that are only equal to (or less than) those that can be obtained with macromutation and no population.
Abstract: A Genetic Algorithm (GA) maintains a population of individuals for the express purpose of improving performance via communication of information between contemporary individuals. This is achieved in a GA through the use of a crossover operator. If crossover is not a useful method for this exchange, the GA should not, on average, perform any better than a variety of simpler algorithms that are not population-based. A simple method for testing the usefulness of crossover for a particular problem is presented. This makes it possible to identify situations in which crossover is apparently useful but is in fact producing gains that are only equal to (or less than) those that can be obtained with macromutation and no population.
112 citations
Proceedings Article•
01 Jun 1993
TL;DR: It is argued that the optimal mutation rate depends strongly on the choice of encoding, and that problems requiring nonbinary encodings may benefit from utation rates much higher than those generally used with binaryencodings.
Abstract: It is part of the traditional lore of genetic algorithms that low mutation rates lead to efficient search of the solution space, while high mutation rates result in diffusion of search effort and premature xtinction of favorable schemata in the population. We argue that the optimal mutation rate depends strongly on the choice of encoding, and that problems requiring nonbinary encodings may benefit from utation rates much higher than those generally used with binary encodings. We introduce the notion of the expected allele coverage of a population, and discuss its role in guiding the choice of mutation rate and population size.
88 citations
"Empirical Analysis and Random Respe..." refers background in this paper
...Tate & Smith (1993) has shown that optimal mutation probability is dependent on the representation being used....
[...]
TL;DR: In this paper, the authors compare the search power of crossover and mutation in genetic algorithms and provide theoretical evidence that traditional GAs use mutation more effectively than crossover, but dispute claims that mutation is a better search mechanism than crossover.
Abstract: We compare the search power of crossover and mutation in genetic algorithms. Our discussion is framed within a model of computation using search space structures induced by these operators. Isomorphisms between the search spaces generated by these operators on small populations are identified and explored. These are closely related to the binary reflected Gray code. Using these we generate discriminating functions that are hard for one operator but easy for the other and show how to transform from one case to the other.
We use these functions to provide theoretical evidence that traditional GAs use mutation more effectively than crossover, but dispute claims that mutation is a better search mechanism than crossover. To the contrary, we show that methods that exploit crossover more effectively can be designed and give evidence that these are powerful search mechanisms. Experimental results using GIGA, the Gene Invariant Genetic Algorithm, and the well-known GENESIS program support these theoretical claims.
Finally, this paper provides the initial approach to a different method of analysis of GAs that does not depend on schema analysis or the notions of increased allocations of trials to hyperplanes of above-average fitness. Instead it focuses on the search space structure induced by the operators and the effect of a population search using them.
56 citations