Showing 1 to 31 of 31 matching Articles
Results per page:
Export (CSV)
By
KuriMorales, Angel; CortésArce, Iván
Post to Citeulike
Computer Networks are usually balanced appealing to personal experience and heuristics, without taking advantage of the behavioral patterns embedded in their operation. In this work we report the application of tools of computational intelligence to find such patterns and take advantage of them to improve the network’s performance. The traditional traffic flow for Computer Network is improved by the concatenated use of the following “tools”: a) Applying intelligent agents, b) Forecasting the traffic flow of the network via MultiLayer Perceptrons (MLP) and c) Optimizing the forecasted network’s parameters with a genetic algorithm. We discuss the implementation and experimentally show that every consecutive new tool introduced improves the behavior of the network. This incremental improvement can be explained from the characterization of the network’s dynamics as a set of emerging patterns in time.
more …
By
RosalesPérez, Alejandro; ReyesGarcía, Carlos A.; Gonzalez, Jesus A.; ArchTirado, Emilio
Show all (4)
Post to Citeulike
3 Citations
In the last years, infant cry recognition has been of particular interest because it contains useful information to determine if the infant is hungry, has pain, or a particular disease. Several studies have been performed in order to differentiate between these kinds of cries. In this work, we propose to use Genetic Selection of a Fuzzy Model (GSFM) for classification of infant cry. GSFM selects a combination of feature selection methods, type of fuzzy processing, learning algorithm, and its associated parameters that best fit to the data. The experiments demonstrate the feasibility of this technique in the classification task. Our experimental results reach up to 99.42% accuracy.
more …
By
Sánchez, Daniela; Melin, Patricia; Castillo, Oscar
Post to Citeulike
In this paper we propose a new model of a Modular Neural Network (MNN) with fuzzy integration based on granular computing. The topology and parameters of the model are optimized with a Hierarchical Genetic Algorithm (HGA). The model was applied to the case of human recognition to illustrate its applicability. The proposed method is able to divide the data automatically into sub modules, to work with a percentage of images and select which images will be used for training. We considered, to test this method, the problem of human recognition based on ear, and we used a database with 77 persons (with 4 images each person for this task).
more …
By
PazRamos, Marco Antonio; TorresJimenez, Jose; QuinteroMarmolMarquez, Enrique; EstradaEsquivel, Hugo
Show all (4)
Post to Citeulike
2 Citations
During the last years the use of intelligent strategies for tuning ProportionalIntegralDerivative (PID) controllers has been growing. The evolutionary strategies have won an important place thanks to their flexibility. In this paper, the automatic tuning of systems with stable and unstable dynamics, through a genetic approach is presented. The advantages of the proposed approach ere highlighted through the comparison with the ZieglerNichols modified closed loop method, and the Visioli genetic approach. The proposed methodology goal is to expand the intelligent tuning application to a wider range of processes (covering systems with oscillatory or unstable modes).
more …
By
PazRamos, Marco Antonio; TorresJimenez, Jose; QuinteroMarmolMarquez, Enrique
Post to Citeulike
1 Citations
During the last years the use of intelligent strategies for tuning ProportionalIntegralDerivative (PID) controllers has been growing. The evolutionary strategies have won an important place thanks to their flexibility. In this paper, the automatic tuning of systems with scarce initial information and integrative and unstable dynamics, through a genetic approach is presented. The advantages of the proposed approach were highlighted through the comparison with the ZieglerNichols modified closed loop method, and the Visioli genetic approach. The proposed methodology goal is to expand the intelligent tuning application to a wider range of processes (covering systems with oscillatory or unstable modes).
more …
By
Pérez, Jesús Fabián López
Post to Citeulike
Our problem is about a routing of a vehicle with product pickup and delivery and with time window constraints. This problem requires to be attended with instances of medium scale (nodes ≥ 100). A strong active time window exists (≥90%) with a large factor of amplitude (≥75%). This problem is NPhard and for such motive the application of an exact method is limited by the computational time. This paper proposes a specialized genetic algorithm. We report good solutions in computational times below 5 minutes.
more …
By
RodriguezTello, Eduardo; Hao, JinKao; TorresJimenez, Jose
Post to Citeulike
1 Citations
This paper introduces a refined evaluation function, called Φ, for the Minimum Linear Arrangement problem (MinLA). Compared with the classical evaluation function (LA), Φ integrates additional information contained in an arrangement to distinguish arrangements with the same LA value. The main characteristics of Φ are analyzed and its practical usefulness is assessed within both a Steepest Descent (SD) algorithm and a Memetic Algorithm (MA). Experiments show that the use of Φ allows to boost the performance of SD and MA, leading to the improvement on some previous best known solutions.
more …
By
Cueva, Victor; Ramos, Fernando
Post to Citeulike
1 Citations
We are presenting in this work a method to calculate collision free paths, for redundant and non redundant robots, through an adaptation of the Messy Genetic Algorithm with a fitness function weakly defined. The adaptation consists in replacing the two crossing operators (cut and splice) traditionally used by a mechanism similar to that one used in the simple genetic algorithm. Nevertheless, the mechanism presented in this work was designed to work with variable length strings. The main advantages of this method are: even though the fitness function is weakly defined good solutions can be obtained; it does not need a previous discretization of the work space; and it works directly within such space without needing any transformation as in the Cspace method. In this work, the fitness function is defined as a linear combination of values which are easily calculated.
more …
By
RodriguezMaya, Noel E.; Graff, Mario; Flores, Juan J.
Post to Citeulike
1 Citations
Modelling the behaviour of algorithms is the realm of Evolutionary Algorithm theory. From a practitioner’s point of view, theory must provide some guidelines regarding which algorithm/parameters to use in order to solve a particular problem. Unfortunately, most theoretical models of evolutionary algorithms are difficult to apply to realistic situations. Recently, there have been works that addressed this problem by proposing models of performance of different Genetic Programming Systems. In this work, we complement previous approaches by proposing a scheme capable of classifying the hardness of optimization problems based on different difficulty measures such as Negative Slope Coefficient, Fitness Distance Correlation, Neutrality, Ruggedness, Basins of Attraction, and Epistasis. The results indicate that this procedure is able to accurately classify the performance of the GA over a set of benchmark problems.
more …
By
KuriMorales, Angel; LopezPeña, Ignacio
Post to Citeulike
1 Citations
A method to determine the position of a mobile robot using machine learning strategies was introduced in [1]. The method raises the possibility to decrease the size of database that holds the images that describe an area where a robot will localize itself. The present work does a statistical validation of the approach by calculating the Hamming and Euclidean distances between all the images using on the one hand all their pixels and on the other hand the reduced set of pixels obtained by the GA as described in [1]. To perform the analysis, a new series of images were taken from a specific position at several angles in both horizontal (pan) and vertical (tilt). These images were compared using two different measures: a) the Hamming distance and b) the Euclidean distance to determine how similar are one from another.
more …
By
QuixtianoXicohténcatl, Rocío; ReyesGalaviz, Orion Fausto; FloresPulido, Leticia; ReyesGarcía, Carlos Alberto
Show all (4)
Post to Citeulike
One of the speaker authentication problems consists on identifying a person only by means of his/her voice. To obtain the best authentication results, it is very important to select the most relevant features from the speech samples, this because we think that not all of the characteristics are relevant for the authentication process and also that many of these data might be redundant. This work presents the design and implementation of a GeneticNeural algorithm for feature selection used on a speaker authentication task. We extract acoustic features such as Mel Frequency Cepstral Coefficients, on a database composed by 150 recorded voice samples, and a genetic feature selection system combined with a time delay feedforward neural network trained by scaled conjugate gradient back propagation, to classify/authenticate the speaker. We also show that after the hybrid system finds the best solution, it almost never looses it, even when the search space changes. The design and implementation process, the performed experiments, as well as some results are shown.
more …
By
Gómez, Juan Carlos; Hernández, Fernando; Coello, Carlos A. Coello; Ronquillo, Guillermo; Trejo, Antonio
Show all (5)
Post to Citeulike
1 Citations
This paper introduces a Genetic Algorithm (GA) for training Artificial Neural Networks (ANNs) using the electromagnetic spectrum signal of a combustion process for flame pattern classification. Combustion requires identification systems that provide information about the state of the process in order to make combustion more efficient and clean. Combustion is complex to model using conventional deterministic methods thus motivate the use of heuristics in this domain. ANNs have been successfully applied to combustion classification systems; however, traditional ANN training methods get often trapped in local minima of the error function and are inefficient in multimodal and nondifferentiable functions. A GA is used here to overcome these problems. The proposed GA finds the weights of an ANN than best fits the training pattern with the highest classification rate.
more …
By
GuevaraSouza, Mauricio; Vallejo, Edgar E.
Post to Citeulike
This paper introduces a new evolutionary algorithm for solving multiobjective optimization problems. The proposed algorithm simulates the infection of the endosymbiotic bacteria Wolbachia to improve the evolutionary search. We conducted a series of experiments to compare the results of the proposed algorithm to those obtained by state of the art multiobjective evolutionary algorithms (MOEAs) at solving the ZDT test suite. Our experimental results show that the proposed model outperforms established MOEAs at solving most of the test problems.
more …
By
KuriMorales, Angel Fernando
Post to Citeulike
1 Citations
When designing neural networks (NNs) one has to consider the ease to determine the best architecture under the selected paradigm. One possible choice is the socalled multilayer perceptron network (MLP). MLPs have been theoretically proven to be universal approximators. However, a central issue is that the architecture of the MLPs, in general, is not known and has to be determined heuristically. In the past, several such approaches have been taken but none has been shown to be applicable in general, while others depend on complex parameter selection and finetuning. In this paper we present a method which allows us to determine the said architecture from basic theoretical considerations: namely, the information content of the sample and the number of variables. From these we derive a closed analytic formulation. We discuss the theory behind our formula and illustrate its application by solving a set of problems (both for classification and regression) from the University of California at Irvine (UCI) data base repository.
more …
By
MontesGonzalez, Fernando; AldanaFranco, Fernando
Post to Citeulike
3 Citations
In this paper we report our experiments with the epuck robots for developing a communication system using evolutionary robotics. In order to do the latter we follow the evolutionary approach by using Neural Networks and Genetic Algorithms. The robots develop a communication scheme for solving tasks like: locating food areas, avoiding obstacles, approaching light sources and locating soundsources (other robots emitting sounds). Evorobot* and Webots simulators are used as tools for computing the evolutionary process and optimization of the weights of neural controllers. As a consequence, two different kinds of neural controllers emerge. On one hand, one controller is used for robot movement; on the other hand the second controller process sound signals.
more …
By
CaballeroMorales, Santiago Omar; TrujilloRomero, Felipe
Post to Citeulike
A field of research in Automatic Speech Recognition (ASR) is the development of assistive technology, particularly for people with speech disabilities. Diverse techniques have been proposed to accomplish accurately this task, among them the use of Metamodels. In this paper we present an approach to improve the performance of Metamodels which consists in using a speaker’s phoneme confusion matrix to model the pronunciation patterns of this speaker. In contrast with previous confusionmatrix approaches, where the confusionmatrix is only estimated with fixed settings for language model, here we explore on the response of the ASR for different language model restrictions. A Genetic Algorithm (GA) was applied to further balance the contribution of each confusionmatrix estimation, and thus, to provide more reliable patterns. When incorporating these estimates into the ASR process with the Metamodels, consistent improvement in accuracy was accomplished when tested with speakers of mild to severe dysarthria which is a common speech disorder.
more …
By
RodriguezMaya, Noel; Flores, Juan J.; Graff, Mario
Post to Citeulike
The University Course Timetabling Problem (UCTP) is a well known optimization problem. Literature reports different methods and techniques to solve it, being Evolutionary Algorithms (EA) one of the most successful. In the EA field, the selection of the best algorithm and its parameters to solve a particular problem, is a difficult problem; would be helpful to know a priori the performance related to that algorithm. Fitness Landscape Analysis (FLA) is a set of tools to describe optimization problems and for the prediction of the performance related with EA. FLA uses a set of metrics to characterize the landscape depicted by a cost function, aiming to understand the behaviour of search algorithms. This work presents an empirical study to characterize some instances of UCTP, and for the prediction of difficulty exhibited by RealCoded Genetic Algorithms (RCGA) to solve the instances. We used FLA as characterization schema; neutrality, ruggedness, and negative slope coefficient are the metrics used in the analysis. To test and validate the proposal, we use three UCTP instances based on Mexican universities. Incipient results suggest an correlation between the negative slope coefficient and the difficulty exhibited by RCGA in the solution of UCTP instances. Ruggedness and neutrality provide the global structure of the instances’s landscape.
more …
By
CruzCortés, Nareli
Post to Citeulike
5 Citations
Artificial Immune Systems (AIS) are computational intelligent systems inspired by some processes or theories observed in the biological immune system. They have been applied to solve a wide range of machine learning and optimization problems. In this chapter the main AISbased proposals for solving constrained numerical optimization problems are shown. Although the first works were hybrid solutions partially based on Genetic Algorithms, the most recent proposals are algorithms completely based on immune features.We show that these algorithms represent viable alternatives to the penalty functions and other similar mechanisms to handle constraints in numerical optimization problems.
more …
By
Ezin, Eugène C.; ReyesGalaviz, Orion Fausto; ReyesGarcía, Carlos A.
Post to Citeulike
Character classification is known to be one of many basic applications in the field of artificial neural networks (ANN), while data transmission with low size is important in the field of source coding. In this paper, we constructed an alphabet of 36 letters which are encoded with the Huffman algorithm and then classified with a backpropagation Feed Forward artificial neural network. Since an ANN is initialized with random weights, the performance is not always optimal. Therefore, we designed a simple genetic algorithm (SGA) that choses an ANN and optimizes its architecture to improve the recognition accuracy. The performance evaluation is given to show the effectiveness of the procedure used, where we reached an accuracy of 100%.
more …
By
Hidalgo, Denisse; Melin, Patricia; Licea, Guillerrno; Castillo, Oscar
Show all (4)
Post to Citeulike
4 Citations
We describe in this paper a new evolutionary method for the optimization of a modular neural network for multimodal biometry The proposed evolutionary method produces the best architecture of the modular neural network (number of modules, layers and neurons) and fuzzy inference systems (memberships functions and rules) as fuzzy integration methods. The integration of responses in the modular neural network is performed by using type1 and type2 fuzzy inference systems.
more …
By
HerbertAcero, JoséFrancisco; FrancoAcevedo, JorgeRodolfo; ValenzuelaRendón, Manuel; ProbstOleszewski, Oliver
Show all (4)
Post to Citeulike
3 Citations
The optimal positioning of wind turbines, even in one dimension, is a problem with no analytical solution. This article describes the application of computational intelligence techniques to solve this problem. A systematic analysis of the optimal positioning of wind turbines on a straight line, on flat terrain, and considering wake effects has been conducted using both simulated annealing and genetic algorithms. Free parameters were the number of wind turbines, the distances between wind turbines and wind turbine hub heights. Climate and terrain characteristics were varied, like incoming wind speed, wind direction, air density, and surface roughness length, producing different patterns of positioning. Analytical functions were used to model wake effects quantifying the reduction in speed after the wind passes through a wind turbine. Conclusions relevant to the placement of wind turbines for several cases are presented.
more …
By
MartinezSoto, Ricardo; Castillo, Oscar; Aguilar, Luis T.; Melin, Patricia
Show all (4)
Post to Citeulike
10 Citations
In this paper we apply to Bioinspired and evolutionary optimization methods to design fuzzy logic controllers (FLC) to minimize the steady state error of linear systems. We test the optimal FLC obtained by the genetic algorithms and the PSO applied on linear systems using benchmark plants. The bioinspired and the evolutionary methods are used to find the parameters of the membership functions of the FLC to obtain the optimal controller. Simulation results are obtained with Simulink showing the feasibility of the proposed approach.
more …
By
Hidalgo, Denisse; Melin, Patricia; Castillo, Oscar
Post to Citeulike
1 Citations
In this paper we describe a method for the optimization of type2 fuzzy systems based on the level of uncertainty considering three different cases to reduce the complexity problem of searching the solution space. The proposed method produces the best fuzzy inference systems for particular applications based on a genetic algorithm. We apply a Genetic Algorithm to find the optimal type2 fuzzy system dividing the search space in three subspaces. We show the comparative results obtained for the benchmark problems.
more …
By
CuevasTello, Juan C.
Post to Citeulike
An evolutionary algorithm for parameter estimation of a kernel method for noisy and irregularly sampled time series is presented. We aim to estimate the time delay between time series coming from gravitational lensing in astronomy. The parameters to estimate include the delay, the width of kernels or smoothing, and a regularization parameter. We use mixed types to represent variables within the evolutionary algorithm. The algorithm is tested on several artificial data sets, and also on real astronomical observations. The performance of our method is compared with the most popular methods for time delay estimation. An statistical analysis of results is given, where the results of our approach are more accurate and significant than those of other methods.
more …
By
Figueroa, Fernando David Ramirez; Caeiros, Alfredo Victor Mantilla
Post to Citeulike
This paper presents a novel hybrid adaptive fuzzy controller for the regulation of speed on induction machines with direct torque control. The controller is based on a fuzzy system and PID control with decoupled gains. Genetic programming techniques are used for offline optimizations of the normalization constants of fuzzy membership function ranges. Fuzzy cluster means is introduced for online optimization on the limits of triangular fuzzy membership functions. Finally simulations in LabVIEW are presented validating the response of the controller with and without load on the machine; results and conclusions are discussed.
more …
By
Stephens, Christopher R.; Poli, Riccardo
Post to Citeulike
4 Citations
We present a personal overview of EC theory. In particular, we try to show that recent theoretical developments have pointed the way to a grand unification of different branches of EC, such as Genetic Algorithms and Genetic Programming, and also different theoretical models, such as the Vose model and Holland’s Schema theorem. We give a broad outline of this unification program showing how the different elements above are related to each other via changes of representation on the space of EC models. Based on our work we pose a series of challenges which if met, we believe, will lead to a much deeper understanding of EC and the various types of evolutionary algorithm.
more …
By
MontesGonzalez, Fernando
Post to Citeulike
The evolution of an effective central model of action selection and behavioral modules have already been revised in previous papers. The central model has been set to resolve a foraging task, where specific modules for exploring the environment and for handling the collection and delivery of cylinders have been developed. Evolution has been used to adjust the selection parameters of the model and the neural weights of the exploring behaviors. However, in this paper the focus is on the use of genetic algorithms for coevolving both the selection parameters and the exploring behaviors. The main goal of this study is to reduce the number of decisions made by the human designer.
more …
By
Téllez, Humberto Aguayo; Rovira, Noel León
Post to Citeulike
2 Citations
In this paper a method is described for determining the design unbalance of crankshafts and also the recommended procedure for a balanced design strategy. The use of a search tool for solutions is suggested based on Genetic Algorithms (GA). GAs have been used in different applications, one of them is the optimization of geometric shapes, a relatively recent area with high research potential. The interest towards this field is growing, and it is anticipated that in the future mechanical engineering will be an area where many applications of shape optimization will be widely applied.
more …
By
Hamzaoui, Y.El.; Rodriguez, J.A.; Puga, S.A.; Escalante Soberanis, M.A.; Bassam, A.
Show all (5)
Post to Citeulike
Genetics Algorithms (GAs) are based on the principles of Darwins evolution which are applied to the minimization complex function successfully. Codification is a very important issue when GAs are designed to dealing with a combinatorial problem. An effective crossed binary method is developed. The GAs have the advantages of no special demand for initial values of decision variables, lower computer storage, and less CPU time for computation. Better results are obtained in comparison the results of traditional Genetic Algorithms. The effectiveness of GAs with crossed binary coding in minimizing the complex function is demonstrated.
more …
By
Hernández Carreón, Carlos A.; Fraire Huacuja, Héctor J.; Fernandez, Karla Espriella; Valdez, Guadalupe Castilla; Mancilla Tolama, Juana E.
Show all (5)
Post to Citeulike
1 Citations
This paper presents an application of a genetic algorithm (GA) to the scheduling of hot rolling mills. The objective function used is based on earlier developments on flow stress modeling of steels. A hybrid twophase procedure was applied in order to calculate the optimal pass reductions, in terms of minimum total rolling time. In the first phase, a nonlinear optimization function was applied to evaluate the computational cost to the problem solution. For the second phase, a GA was applied. A comparison with twopoint and simulated binary (SBX) crossover operators was established. The results were validated with data of industrial schedules. A GA with SBX crossover operator is shown to be an efficient method to calculate the multipass schedules at reduced processing time.
more …
By
Albers, Albert; Rovira, Noel Leon; Aguayo, Humberto; Maier, Thomas
Show all (4)
Post to Citeulike
1 Citations
This paper describes the conceptual foundations to construct a method on Computer Aided Innovation for product development. It begins with a brief recap of the different methodologies and disciplines that build its bases. Evolutionary Design is presented and explained how the first activities in Genetic Algorithms (GAs) helped to produce computer shapes that resembled a creative behavior. A description of optimization processes based on Genetic Algorithms is presented, and some of the genetic operators are explained as a background of the creative operators that are intended to be developed. A summary of some Design Optimization Systems is also explained and its use of splined profiles to optimize mechanical structures. The approach to multiobjective optimization with Genetic Algorithms is analyzed from the point of view of Pareto diagrams. It is discussed how the transition from a multiobjective optimization conflict to a solution with the aim of an ideal result can be developed means the help of TRIZ (Theory of Inventive Problem Solving), complementing the discipline of Evolutionary Design. Similarities between Genetic Algorithms and TRIZ regarding ideality and evolution are identified and presented. Finally, a brief presentation of a case study about the design of engine crankshafts is used to explain the concepts and methods deployed. The authors have been working on strategies to optimize the balance of a crankshaft using CAD and CAE software, splines, Genetic Algorithms, and tools for its integration [1] [2].
more …
