By Topic

Evolutionary Computation, 2001. Proceedings of the 2001 Congress on

Date 27-30 May 2001

Go

Filter Results

Displaying Results 1 - 25 of 99
  • Proceedings Congress on Evolutionary Computation 2001

    Page(s): 0_2 - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (850 KB)  
    Freely Available from IEEE
  • Author index

    Page(s): AI_1 - AI_5
    Save to Project icon | Request Permissions | PDF file iconPDF (218 KB)  
    Freely Available from IEEE
  • Effect of localized selection on the evolution of unplanned coordination in a market selection game

    Page(s): 1011 - 1018 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (648 KB) |  | HTML iconHTML  

    This paper examines the evolution of unplanned coordination among independent agents in a market selection game, which is a non-cooperative repeated game with many agents and several markets. Every agent is supposed to simultaneously choose a single market for maximizing its own payoff obtained by selling its product at the selected market. It is assumed that the market price is determined by the total supply of products. For example, if many agents choose a particular market, the market price at that market is low. The point of the market selection is to choose a market that is not chosen by many other agents. In this paper, game strategies are genetically updated by localized selection and mutation. A new strategy of an agent is probabilistically selected from its neighbors' strategies by the selection operation or randomly updated by the mutation operation. We examine the effect of the localized selection on the evolution of unplanned coordination of the market selection where the undesired concentration of agents is avoided View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture detection by genetic programming

    Page(s): 867 - 872 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (548 KB) |  | HTML iconHTML  

    This paper presents an approach to blind texture detection in images based on adaptation of the 2D-lookup algorithm by genetic programming. The task of blind texture detection is to separate textured regions of an image from non-textured (as e.g. homogeneous) ones, without any reference to a priori knowledge about image content. The 2D-lookup algorithm, which generalizes the well-known co-occurrence matrix approach of texture analysis, is based on two arbitrary image processing operations. By genetic programming, those image operations can be designed and adapted to a given recognition goal of the whole algorithm. The idea to employ such a framework for texture detection is to use a random image as adaptation goal. Despite of the fact that such a task has no exact solution, the system is able to fulfill this task to a certain degree. This degree is related to textureness in the image: the more texture, the higher the degree. The paper exemplifies this approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Enzyme genetic programming

    Page(s): 1183 - 1190 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (744 KB) |  | HTML iconHTML  

    The work reported in the paper follows from the hypothesis that better performance in certain domains of artificial evolution can be achieved by adhering more closely to the features that make natural evolution effective within biological systems. An important issue in evolutionary computation is the choice of solution representation. Genetic programming, whilst borrowing from biology in the evolutionary axis of behaviour, remains firmly rooted in the artificial domain with its use of a parse tree representation. Following concerns that this approach does not encourage solution evolvability, the paper presents an alternative method modelled upon representations used by biology. Early results are encouraging, demonstrating that the method is competitive when applied to problems in the area of combinatorial circuit design View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using a co-operative co-evolutionary genetic algorithm to solve a three-dimensional container loading problem

    Page(s): 1197 - 1204 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (800 KB) |  | HTML iconHTML  

    The paper presents the use of a co-operative co-evolutionary genetic algorithm (CCGA) in conjunction with a heuristic rule for solving a 3D container loading or bin packing problem. Unlike previous works which concentrate on using either a heuristic rule or an optimisation technique to find an optimal sequence of the packages which must be loaded into the containers, the proposed heuristic rule is used to partition the entire loading sequence into a number of shorter sequences. Each partitioned sequence is then represented by a species member in the CCGA search. The simulation results indicate that the use of the heuristic rule and the CCGA is proven to be highly efficient in terms of the minimal number of containers required in comparison to the results given by a standard genetic algorithm search. In addition, this helps to confirm that the CCGA is also suitable for use in a sequence-based optimisation problem View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An application of genetic algorithm for designing a Wiener-model controller to regulate the pH value in a pilot plant

    Page(s): 1055 - 1061 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (492 KB) |  | HTML iconHTML  

    Utilises computational intelligence techniques, such as genetic algorithms (GAs) and multi-objective evolutionary algorithms (MOEAs), to design a Wiener-model controller for regulating the pH level in an acid-base titration process. A Wiener-model control structure comprises (i) an inverse model of the system nonlinearity and (ii) a simple linear controller. The inverse model serves to simplify the control problem by eliminating the bulk of the nonlinear characteristics from the pH control loop. A PID controller can then be used to control the linearised system. A GA was employed to identify the parameters of the inverse titration equation while the PID parameters were obtained by using a MOEA. Experimental results demonstrating the viability of the proposed methodology are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • When sharing fails

    Page(s): 873 - 879 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB) |  | HTML iconHTML  

    Sharing, introduced by D.E. Goldberg and J. Richardson (1987), is probably one of the most investigated ideas for multimodal optimization. Empirical tests have indicated that sharing is capable of maintaining multiple peaks located simultaneously, a feature that allows a final human selection among the found solutions. The author presents a theoretical argument regarding the performance of sharing. The argument is supported with a series of tests on variants of a simple problem, which is one of Goldberg and Richardson's original test functions where a constant is added. The results from these tests indicated that sharing is very sensitive to the range of fitness values. Finally, three extensions of sharing are proposed and discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coordination of multiple behavior modules evolved on CAM-Brain

    Page(s): 1414 - 1421 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (848 KB) |  | HTML iconHTML  

    In behavior-based robotics the control of a robot is shared between a set of purposive perception-action units, called behaviors. A major issue in the design of behavior-based control systems is the formulation of effective mechanisms for coordination of the behaviors' activities into strategies for rational and coherent behavior. There has been extensive work to construct an optimal controller for a mobile robot by evolutionary approaches such as genetic algorithm, genetic programming, and so on. In this line of research, we have also presented a method of applying CAM-Brain, evolved neural networks based on cellular automata (CA), to control a mobile robot. However, this approach has limitations to make the robot to perform appropriate behavior in complex environments. The multi module coordination method can make complex and general behaviors by combining several modules evolved or programmed, to do a simple behavior. In this paper, we coordinate several modules evolved to do a simple behavior by Maes's action selection mechanism. Maes (1989) has proposed a mechanism for action selection, which is reviewed here and is evaluated using a simulation environment. Experimental results show that this approach has potential to develop a sophisticated evolutionary neural controller for complex environments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic logical inference using quantities of DNA strands

    Page(s): 797 - 804 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (672 KB) |  | HTML iconHTML  

    We overview a series of our research on DNA-based supervised learning of Boolean formulae and its application to gene expression analyses. In our previous work, we have presented methods for encoding and evaluating Boolean formulae on DNA strands and supervised learning of Boolean formulae on DNA computers which is known as NP-hard problem in computational learning theory. We have also applied those methods to executing logical operations of gene expression profiles in test tube. These proposed methods are discrete (qualitative) algorithms and do not deal with quantitative analysis and are not robust for noise and errors. Recently, we have proposed several methods to execute quantitative inferences using large quantities of DNA strands in test tube and extend the previous algorithms to robust ones for noise and errors in the data. These methods include probabilistic inference and randomized prediction, and weighted majority prediction and learning by amplification in the test tube based on the weighted majority algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Co-evolutionary computation for constrained min-max problems and its applications for pursuit-evasion games

    Page(s): 1205 - 1212 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB) |  | HTML iconHTML  

    The co-evolutionary computation method for solving constrained min-max problems is proposed. Many engineering problems can be practically expressed as constrained min-max problems. Min-max problems have two groups of variables. Each group will minimize or maximize payoffs and is subject to equality and inequality constraints. Lagrange multipliers are implemented for handling constraints. Primal constrained min-max problems are transformed into dual unconstrained min-max problems by using the Lagrange multipliers. The co-evolutionary computation is used for solving the dual min-max problems. The proposed method deals with separable and inseparable constraints of two groups. The proposed algorithm is applied for pursuit-evasion games with various constraints. Numerical results are compared with those of conventional methods View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to focus selectively on possible lines of play in checkers

    Page(s): 1019 - 1024 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (560 KB) |  | HTML iconHTML  

    Ongoing work in coevolution of neural networks for checkers play is described. An unusual aspect is that the fitness of a neural net is not reduced to a scalar fitness score. Instead, nets are sorted primarily in non-decreasing order of number of games lost to other members of the population, and secondarily in non-increasing order of number of wins. The first n nets in the sorted list are selected as parents. The main thrust of the present work, however, is to learn to prioritize the extension of possible lines of play in the minimax game tree. Neural nets not only assign static values to leaf nodes, as is common in minimax play, but priorities for dynamic evaluation, as well. At each iteration of the game tree evaluation, the highest-priority leaf node of the current game tree has its children generated. Thus the conventional minimax control strategy is replaced by one that seeks to extend lines of play selectively. Although none of the neural-net players is rated yet, tournaments pitting later generations against earlier indicate that quality of play is improving View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid parallel, evolutionary algorithms for constrained optimization utilizing PC clustering

    Page(s): 1436 - 1441 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB) |  | HTML iconHTML  

    This paper proposes a hybrid parallelization of evolutionary algorithms (EAs) utilizing PC clustering environments to solve constrained numerical optimization problems. In the proposed parallel structure, the coarse-grained parallel EAs (PEAs) were implicated in upper level and the fine-grained PEAs were used in lower level. The design of effective evolutionary algorithms (EAs) is to obtain a proper balance between exploration and exploitation. The balance can be controlled by the spread rate and the migration of the best individuals. In the hybrid structure, the spread rate is high in lower level coarse-grained structure and low in upper level globally structure. The diversity is promoted by dividing individuals to several groups and migrating individual between them. By utilizing large number of processors, the optimization performance as well as the computation time were improved. Simulation results indicate that hybrid parallel EAs using the proposed structure have better performance in constrained numerical optimization problems than coarse-grained, or fine-grained parallel EAs, which are dedicated parallelization methods in previous work View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visualization of EC landscape to accelerate EC conversion and evaluation of its effect

    Page(s): 880 - 886 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (600 KB) |  | HTML iconHTML  

    We evaluate how visualization of an evolutionary computation (EC) landscape is effective using a geophysical task. This technique allows us to actively participate in EC optimization by viewing the distribution of searching points on 2D space mapped from an n-D EC landscape, and indicating where in the EC is the possible global optimum. We construct a Visualized GA system that includes self-organizing maps for visualization and compare its performance with that of a normal GA using the geophysical simulation task. Sign tests for the comparisons show that the Visualized GA converges significantly faster than the normal EC (p<0.01), which suggests further extensions to enhance user interactivity View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applications of genetic algorithms, geostatistics, and fuzzy c-means clustering to image segmentation

    Page(s): 741 - 746 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (424 KB) |  | HTML iconHTML  

    We apply different advantages of the optimal genetic searching, geostatistics, and fuzzy c-means clustering to the segmentation of gray-level images. The proposed method can deal effectively with noisy image segmentation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Genetic programming of polynomial harmonic models using the discrete Fourier transform

    Page(s): 902 - 909 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (724 KB) |  | HTML iconHTML  

    The paper presents a genetic programming (GP) system that evolves polynomial harmonic networks. The hybrid tree-structured network representation suggests that terminal harmonics with non-multiple frequencies may enter polynomial function nodes as variables. The harmonics with non-multiple, irregular frequencies are derived analytically using the discrete Fourier transform. The development of polynomial harmonic GP includes also design of a regularized statistical fitness function for improved search control and overfitting avoidance. Empirical results show that this hybrid version outperforms the previous GP system manipulating polynomials STROGANOFF, the traditional Koza-style GP, and the harmonic GMDH network algorithm on processing time series View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of evolutionary computation and neural network hybrids for breast cancer classification using mammogram and history data

    Page(s): 1147 - 1154 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (664 KB) |  | HTML iconHTML  

    Mammography is the modality of choice for the early detection of breast cancer, primarily because of its sensitivity to the detection of breast cancer. However, because of its high rate of false positive predictions, a large number of biopsies of benign lesions result. The paper explores the use and evaluates the performance of two neural network hybrids as an aid to radiologists in avoiding biopsies of these benign lesions. These hybrids provide the potential to improve both the sensitivity and specificity of breast cancer diagnosis. The first hybrid, the Generalized Regression Neural Network (GRNN) Oracle, focuses on improving the performance output of a set of learning algorithms that operate and are accurate over the entire (defined) learning space. The second hybrid, an evolutionary programming (EP)/adaptive boosting (AB) based hybrid, intelligently combines the outputs from an iteratively called “weak” learning algorithm (one which performs at least slightly better than random guessing), in order to “boost” the performance of the weak learner. The second part of the paper discusses modifications to improve the EP/AB hybrid's performance, and further evaluates how the use of the EP/AB hybrid may obviate biopsies of benign lesions (as compared to an EP only classification system), given the requirement of missing few if any cancers View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An application of genetic algorithms in smoothing automotive body surface

    Page(s): 1296 - 1302 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (436 KB) |  | HTML iconHTML  

    In car body design, reflection lines of automotive body surface have been used to identify and remove the bump or irregular curves on the outer skin surfaces of car body. Traditional approaches to correcting such reflection lines involve tedious manual work and expensive computation. They also rely heavily on designers' experiences. This paper explores how to use genetic algorithms to correct the reflection lines under user-specified constraints. This approach has the potential to alleviate these drawbacks. A method of measuring fitness is also devised which indicates how well the reflection lines comply with physical and aesthetic constraints. Two encoding schemes are proposed and experiments based on these schemes are analysed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An entropy-based adaptive genetic algorithm for learning classification rules

    Page(s): 790 - 796 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (648 KB) |  | HTML iconHTML  

    The genetic algorithm is one of the commonly used approaches to data mining. We propose a genetic algorithm approach for classification problems. Binary coding is adopted in which an individual in a population consists of a fixed number of rules that stand for a solution candidate. The evaluation function considers four important factors which are error rate, entropy measure, rule consistency and hole ratio, respectively. Adaptive asymmetric mutation is applied by the self-adaptation of mutation inversion probability from 1-0 (0-1). The generated rules are not disjoint but can overlap. The final conclusion for prediction is based on the voting of rules and the classifier gives all rules equal weight for their votes. Based on three databases, we compared our approach with several other traditional data mining techniques including decision trees, neural networks and naive bayes learning. The results show that our approach outperformed others in both prediction accuracy and the standard deviation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive control of partial functions in genetic programming

    Page(s): 895 - 901 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB) |  | HTML iconHTML  

    The paper investigates the use of partial functions in genetic programming. Previous work (R.I. McKay, 2000), has shown that the convergent behaviour of populations of partial functions is very similar to that of populations of total functions. However the convergence rates of populations of partial functions have been slower. The results presented demonstrate a significant improvement in the rate of convergence of populations of partial functions, and indicate that partial functions represent a realistic alternative to total functions for a range of problems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coevolutionary GA with schema extraction by machine learning techniques and its application to knapsack problems

    Page(s): 1213 - 1219 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (528 KB) |  | HTML iconHTML  

    The authors introduce a novel coevolutionary genetic algorithm with schema extraction by machine learning techniques. Our CGA consists of two GA populations: the first GA (H-GA) searches for the solutions in the given problems and the second GA (P-GA) searches for effective schemata of the H-GA. We aim to improve the search ability of our CGA by extracting more efficiently useful schemata from the H-GA population, and then incorporating those extracted schemata in a natural manner into the P-GA. Several computational simulations on multidimensional knapsack problems confirm the effectiveness of the proposed method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel quantum-inspired genetic algorithm for combinatorial optimization problem

    Page(s): 1422 - 1429 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (568 KB) |  | HTML iconHTML  

    This paper proposes a new parallel evolutionary algorithm called parallel quantum-inspired genetic algorithm (PQGA). Quantum-inspired genetic algorithm (QGA) is based on the concept and principles of quantum computing such as qubits and superposition of states. Instead of binary, numeric, or symbolic representation, by adopting the qubit chromosome as a representation, QGA can represent a linear superposition of solutions due to its probabilistic representation. QGA is suitable for parallel structures because of rapid convergence and good global search capability. That is, QGA is able to possess the two characteristics of exploration and exploitation simultaneously. The effectiveness and the applicability of PQGA are demonstrated by experimental results on the knapsack problem, which is a well-known combinatorial optimization problem. The results show that PQGA is superior to QGA as well as other conventional genetic algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolving bipedal locomotion with genetic programming - a preliminary report

    Page(s): 1025 - 1032 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB) |  | HTML iconHTML  

    Shows how genetic programming can be applied to the task of evolving the neural oscillators that produce the coordinated movements of human-like bipedal locomotion. In biomechanical engineering research, robotics and neurophysiology, it is of major interest to clarify the mechanism of human bipedal walking. This serves as the basis for developing several applications, such as rehabilitation tools and humanoid robots. Nevertheless, because of the complexity of the neuronal system that interacts with the body dynamics system to make walking movements, much is left unknown about the details of the locomotion mechanism. Researchers have previously been looking for the optimal model of the neuronal system by trial and error. In this paper, we apply genetic programming to induce the model of the nervous system automatically and show its effectiveness by simulating a human bipedal gait with the obtained model. Our experimental results are preliminary but they show some promising evidence for further improvements View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study of population diversity of multiobjective evolutionary algorithm based on immune and entropy principles

    Page(s): 1316 - 1321 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (340 KB) |  | HTML iconHTML  

    A key problem in a multiobjective evolutionary system is how to take measures to preserve diversity in the population. The mechanism of natural immune system and entropy principle are applied in a multiobjective evolutionary process to solve this problem and a strategy of preserving diversity in the population of a multiobjective evolutionary algorithm based on immune and entropy principles is introduced. The detailed design method is shown. Finally, we describe the computer simulation of implementing several two-objective flow shop scheduling problems and compare the computing results of the new method with the multiobjective genetic algorithm. Experimental results show that this strategy can effectively preserve population diversity and it has good search performance View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient genetic algorithm with less fitness evaluation by clustering

    Page(s): 887 - 894 vol. 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (512 KB) |  | HTML iconHTML  

    To solve a general problem with genetic algorithms, it is desirable to maintain the population size as large as possible. In some cases, however, the cost to evaluate each individual is relatively high, and it is difficult to maintain a large population. To solve this problem, we propose a hybrid GA based on clustering, which considerably reduces the evaluation number without any loss of performance. The algorithm divides the whole population into several clusters, and evaluates only one representative for each cluster. The fitness values of other individuals are estimated from the representative fitness values indirectly, which can maintain a large population with less number of evaluations. Several benchmark tests have been conducted and the results show that the proposed GA is very efficient View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.