Showing papers by "Enrique Alba published in 2004"

Solving the Vehicle Routing Problem by Using Cellular Genetic Algorithms

Abstract: Cellular Genetic Algorithms (cGAs) are a subclass of Genetic Algorithms (GAs) in which the population diversity and exploration are enhanced thanks to the existence of small overlapped neighborhoods. Such a kind of structured algorithms is specially well suited for complex problems. In this paper we propose the utilization of some cGAs with and without including local search techniques for solving the vehicle routing problem (VRP). A study on the behavior of these algorithms has been performed in terms of the quality of the solutions found, execution time, and number of function evaluations (effort). We have selected the benchmark of Christofides, Mingozzi and Toth for testing the proposed cGAs, and compare them with some other heuristics in the literature. Our conclusions are that cGAs with an added local search operator are able of always locating the optimum of the problem at low times and reasonable effort for the tested instances.

Training Neural Networks with GA Hybrid Algorithms

Abstract: Training neural networks is a complex task of great importance in the supervised learning field of research. In this work we tackle this problem with five algorithms, and try to offer a set of results that could hopefully foster future comparisons by following a kind of standard evaluation of the results (the Prechelt approach). To achieve our goal of studying in the same paper population based, local search, and hybrid algorithms, we have selected two gradient descent algorithms: Backpropagation and Levenberg-Marquardt, one population based heuristic such as a Genetic Algorithm, and two hybrid algorithms combining this last with the former local search ones. Our benchmark is composed of problems arising in Medicine, and our conclusions clearly establish the advantages of the proposed hybrids over the pure algorithms.

Parallel heterogeneous genetic algorithms for continuous optimization

Abstract: In this paper we address the physical parallelization of a very efficient genetic algorithm (GA) known as gradual distributed real-coded GA (GD-RCGA). This search model naturally provides a set of eight subpopulations residing in a cube topology having two faces for promoting exploration and exploitation. The resulting technique has been shown to yield very accurate results in continuous optimization by using crossover operators tuned to explore and exploit the solutions inside each subpopulation. Here, we encompass the actual parallelization of the technique, and get deeper into the importance of running a synchronous versus an asynchronous version of the basic GD-RCGA model. We also present the evaluation of the parallel execution of GD-RCGA over two local area networks, a Fast-Ethernet network and a Myrinet network. Our results indicate that the GD-RCGA model maintains a very high level of accuracy for continuous optimization when run in parallel, and we also demonstrate the relative advantages of each algorithm version over the two networks. Finally, we show that the async parallelization scales better than the sync one, what suggests future research lines for WAN execution and new models of search based on the original two-faced cube.

Modeling selection intensity for toroidal cellular evolutionary algorithms

Abstract: We present quantitative models for the selection pressure of cellular evolutionary algorithms structured in two dimensional regular lattices. We derive models based on probabilistic difference equations for synchronous and several asynchronous cell update policies. Theoretical results are in agreement with experimental values and show that the selection intensity can be controlled by using different update methods.

Advances in parallel heterogeneous genetic algorithms for continuous optimization

Abstract: In this paper we address an extension of a very efficient genetic algorithm (GA) known as Hy3, a physical parallelization of the gradual distributed real-coded GA (GD-RCGA) This search model relies on a set of eight subpopulations residing in a cube topology having two faces for promoting exploration and exploitation The resulting technique has been shown to yield very accurate results in continuous optimization by using crossover operators tuned to explore and exploit the solutions inside each subpopulation We introduce here a further extension of Hy3, called Hy4, that uses 16 islands arranged in a hypercube of four dimensions Thus, two new faces with different exploration/exploitation search capabilities are added to the search performed by Hy3 We analyze the importance of running a synchronous versus an asynchronous version of the models considered The results indicate that the proposed Hy4 model overcomes the Hy3 performance because of its improved balance between exploration and exploitation that enhances the search Finally, we also show that the async Hy4 model scales better than the sync one

Evolutionary algorithms for optimal placement of antennae in radio network design

Abstract: Summary form only given. Evolutionary algorithms (EAs) are applied to solve the radio network design problem (RND). The task is to find the best set of transmitter locations in order to cover a given geographical region at an optimal cost. Usually, parallel EAs are needed in order to cope with the high computational requirements of such a problem. Here, we try to develop and evaluate a set of sequential and parallel genetic algorithms (GAs) in order to solve efficiently the RND problem. The results show that our distributed steady state GA is an efficient and accurate tool for solving RND that even outperforms existing parallel solutions. The sequential algorithm performs very efficiently from a numerical point of view, although the distributed version is much faster, with an observed linear speedup.

The influence of grid shape and asynchronicity on cellular evolutionary algorithms

Abstract: In This work we study cellular evolutionary algorithms, a kind of decentralized heuristics, and the importance of the induced exploration/exploitation balance on different problems. It is shown that, by choosing synchronous or asynchronous update policies, the selection pressure, and thus the exploration/exploitation tradeoff, can be influenced directly, without using additional ad hoc parameters. Synchronous algorithms of different neighborhood-to-topology ratio, and asynchronous update policies are applied to a set of benchmark problems. Our conclusions show that the update methods of the asynchronous versions, as well as the ratio of the decentralized algorithm, have a marked influence on its convergence and on its accuracy.

Growth Curves and Takeover Time in Distributed Evolutionary Algorithms

Abstract: This paper presents a study of different models for the gro- wth curves and takeover time in a distributed EA (dEA). The calculation of the takeover time and the dynamical growth curves is a common analy- tical approach to measure the selection pressure of an EA. This work is a first step to mathematically unify and describe the roles of the migra- tion rate and the migration frequency in the selection pressure induced by the dynamics of dEAs. In order to achieve these goals we evaluate the appropriateness of the well-known logistic model and of a hypergraph model for dEAs. After that, we propose a corrected hypergraph model and two new models based in an extension of the logistic one. Our results show that accurate models for growth curves can be defined for dEAs, and explain analytically the migration rate and frequency effects.

Solving the error correcting code problem with parallel hybrid heuristics

Abstract: Some telecommunication systems can not afford the cost of repeating a corrupted message. Instead, the message should be somewhat "corrected" by the receiver. In these cases an error correcting code is suitable. The problem of finding an error correcting code of n bits and M codewords that corrects a given maximum number of errors is NP-hard. For this reason the problem has been solved in the literature with heuristic techniques such as Simulated Annealing and Genetic Algorithms. In this paper we present a new local search algorithm for the problem: the Repulsion Algorithm. We further use a hybrid between Parallel Genetic Algorithm and this new algorithm to solve the problem, and we compare it against a pure Parallel Genetic Algorithm. The results show that an important improvement is achieved with the inclusion of the Repulsion Algorithm and the parallelism.

A neuro-fuzzy decision model for prognosis of breast cancer relapse

Abstract: The prediction of clinical outcome of patients after breast cancer surgery plays an important role in medical tasks like diagnosis and treatment planning. These kinds of estimations are currently performed by clinicians using non-numerical techniques. Artificial neural networks are shown to be a powerful tool for analyse data sets where there are complicated non-linear interactions between the input data and the information to be predicted, and fuzzy logic appears as an useful tool to perform decision making in real life problems. In this paper, we present an hybrid neuro-fuzzy prognosis system for the prediction of patients relapse probability using clinical-pathological data (tumor size, patient age, estrogens receptors, etc.) from the Medical Oncology Service of the Hospital Clinical University of Malaga. Results show the classification accuracy improvement obtained by the proposed model in comparison with an approach based on exclusively on artificial neural networks proposed in our previous work.

Metaheuristics for Natural Language Tagging

Abstract: This work compares different metaheuristics techniques applied to an important problem in natural language: tagging. Tagging amounts to assigning to each word in a text one of its possible lexical categories (tags) according to the context in which the word is used (thus it is a disambiguation task). Specifically, we have applied a classic genetic algorithm (GA), a CHC algorithm, and a Simulated Annealing (SA). The aim of the work is to determine which one is the most accurate algorithm (GA, CHC or SA), which one is the most appropriate encoding for the problem (integer or binary) and also to study the impact of parallelism on each considered method. The work has been highly simplified by the use of MALLBA, a library of search techniques which provides generic optimization software skeletons able to run in sequential, LAN and WAN environments. Experiments show that the GA with the integer encoding provides the more accurate results. For the CHC algorithm, the best results are obtained with binary coding and a parallel implementation. SA provides less accurate results than any of the evolutionary algorithms.

A Globus-Based Distributed Enumerative Search Algorithm for Multi-objective Optimization

Abstract: Enumerative search is a technique to solve multi- objective optimization problems based on evaluating each pos- sible solution from a given finite set The technique is simple and computationally expensive, but it is the only way at present to compute exact Pareto fronts in multi-objective problems In this context, Grid computing systems offer a potentially large amount of computing power that can be used to overcome the mentioned drawback to some extent In this paper, we analyze several practical and technical issues concerning the use of the Globus Toolkit, a de facto standard system for Grid computing, to implement a distributed enumerative search algorithm We have solved a benchmark of multi-objective problems in a cluster of computers and we have analyzed issues such as the parallel efficiency, mean CPU use, and network bandwidth utilization Furthermore, we also use Globus to develop a new technique named grid-"GA, an extension of the micro-GA algorithm The results indicate that using Globus is a promising choice to solve multi-objective problems in Grid computing systems

Parallel LAN/WAN heuristics for optimization

Abstract: We present in this work a wide spectrum of results on analyzing the behavior of parallel heuristics (both pure and hybrid) for solving optimization problems. We focus on several evolutionary algorithms as well as on simulated annealing. Our goal is to offer a first study on the possible changes in the search mechanics that the algorithms suffer when shifting from a LAN network to a WAN environment. We will address six optimization tasks of considerable complexity. The results show that, despite their expected slower execution time, the WAN versions of our algorithms consistently solve the problems. We report also some interesting results in which WAN algorithms outperform LAN ones. Those results are further extended to analyze the behavior of the heuristics in WAN with a larger number of processors and different connectivities.

Solving the vehicle routing problem by using cellular genetic algorithms

Abstract: Cellular Genetic Algorithms (cGAs) are a subclass of Genetic Algorithms (GAs) in which the population diversity and exploration are enhanced thanks to the existence of small overlapped neighborhoods. Such a kind of structured algorithms is specially well suited for complex problems. In this paper we propose the utilization of some cGAs with and without including local search techniques for solving the vehicle routing problem (VRP). A study on the behavior of these algorithms has been performed in terms of the quality of the solutions found, execution time, and number of function evaluations (effort). We have selected the benchmark of Christofides, Mingozzi and Toth for testing the proposed cGAs, and compare them with some other heuristics in the literature. Our conclusions are that cGAs with an added local search operator are able of always locating the optimum of the problem at low times and reasonable effort for the tested instances.

Actuarial science at itam

Abstract: The Instituto Tecnologico Autonomo de Mexico (ITAM) is a private university founded in 1946 by a group of Mexican businessmen. It is a small institution of higher education, specializing in the management and social sciences and related disciplines. It is recognized in Mexico for its programs in Economics and Business. It was recently ranked number one among universities in Mexico City by the Newspaper “Reforma” (July 29, 2001). Our Business School has consistently been ranked among the top programs in Latin America; we were ranked number 5 for 2001. We also are one of only two business programs in Mexico that have AACSB accreditation. The Mexican magazine “EXP” ranked ITAM as number two in management and number one in finance. We are also a member of the Program in International Management (PIM) since 1997; again, we are one of only two universities in Mexico that belong to this network.