Browsing by Subject "Genetic algorithms"

Now showing 1 - 15 of 15

Open Access
Approximating the stochastic growth model with neural networks trained by genetic algorithms
(2006) Kıykaç, Cihan
In this thesis study, we present a direct numerical solution methodology for the onesector nonlinear stochastic growth model. Rather than parameterizing or dealing with the Euler equation, like other methods do, our method directly parameterizes the policy function with a neural network trained by a genetic algorithm. Since genetic algorithms are derivative free and the policy function is directly parameterized, there is no need for taking derivatives. While other methods are bounded by the existence of required derivatives in higher dimensional state spaces, our method preserves its functionality. As genetic algorithms are global search algorithms, our method’s results are robust whatever the search space is. In addition to the stochastic growth model, to observe the performance of the method under real conditions, we tested the method by adding capital adjustment costs to the model. Under all parameter configurations, the method performs quite well.
Open Access
Assembly line balancing using genetic algorithms
(Kluwer Academic Publishers, 2000) Sabuncuoğlu İ.; Erel, E.; Tanyer, M.
Assembly Line Balancing (ALB) is one of the important problems of production/operations management area. As small improvements in the performance of the system can lead to significant monetary consequences, it is of utmost importance to develop practical solution procedures that yield high-quality design decisions with minimal computational requirements. Due to the NP-hard nature of the ALB problem, heuristics are generally used to solve real life problems. In this paper, we propose an efficient heuristic to solve the deterministic and single-model ALB problem. The proposed heuristic is a Genetic Algorithm (GA) with a special chromosome structure that is partitioned dynamically through the evolution process. Elitism is also implemented in the model by using some concepts of Simulated Annealing (SA). In this context, the proposed approach can be viewed as a unified framework which combines several new concepts of AI in the algorithmic design. Our computational experiments with the proposed algorithm indicate that it outperforms the existing heuristics on several test problems.
Open Access
Circular arrays of log-periodic antennas for broadband applications
(IEEE, 2006) Ergül, Özgür; Gürel, Levent
Circular arrays of log-periodic (LP) antennas are designed for broadband applications. A sophisticated electromagnetic simulation environment involving integral equations and fast solvers is developed to analyze the LP arrays both accurately and efficienuy. The resulting matrix equation obtained by the discretization of the electric field integral equation is solved iteratively via the multilevel fast multipole algorithm (MLFMA). Genetic algorithms interacting with MLFMA is employed to optimize the excitations of the array elements to increase the frequency independence and also to add the beam-steering ability to the arrays.
Open Access
Customer order scheduling problem: a comparative metaheuristics study
(Springer, 2007) Hazır, Ö.; Günalay, Y.; Erel, E.
The customer order scheduling problem (COSP) is defined as to determine the sequence of tasks to satisfy the demand of customers who order several types of products produced on a single machine. A setup is required whenever a product type is launched. The objective of the scheduling problem is to minimize the average customer order flow time. Since the customer order scheduling problem is known to be strongly NP-hard, we solve it using four major metaheuristics and compare the performance of these heuristics, namely, simulated annealing, genetic algorithms, tabu search, and ant colony optimization. These are selected to represent various characteristics of metaheuristics: nature-inspired vs. artificially created, population-based vs. local search, etc. A set of problems is generated to compare the solution quality and computational efforts of these heuristics. Results of the experimentation show that tabu search and ant colony perform better for large problems whereas simulated annealing performs best in small-size problems. Some conclusions are also drawn on the interactions between various problem parameters and the performance of the heuristics.
Open Access
Design of dual-frequency probe-fed microstrip antennas with genetic optimization algorithm
(IEEE, 2003) Ozgun, O.; Mutlu, S.; Aksun, M. I.; Alatan, L.
Dual-frequency operation of antennas has become a necessity for many applications in recent wireless communication systems, such as GPS, GSM services operating at two different frequency bands, and services of PCS and IMT-2000 applications. Although there are various techniques to achieve dual-band operation from various types of microstrip antennas, there is no efficient design tool that has been incorporated with a suitable optimization algorithm. In this paper, the cavity-model based simulation tool along with the genetic optimization algorithm is presented for the design of dual-band microstrip antennas, using multiple slots in the patch or multiple shorting strips between the patch and the ground plane. Since this approach is based on the cavity model, the multiport approach is efficiently employed to analyze the effects of the slots and shorting strips on the input impedance. Then, the optimization of the positions of slots and shorting strips is performed via a genetic optimization algorithm, to achieve an acceptable antenna operation over the desired frequency bands. The antennas designed by this efficient design procedure were realized experimentally, and the results are compared. In addition, these results are also compared to the results obtained by the commercial electromagnetic simulation tool, the FEM-based software HFSS by ANSOFT.
Open Access
Diagnosis of gastric carcinoma by classification on feature projections
(Elsevier, 2004) Güvenir, H. A.; Emeksiz, N.; İkizler, N.; Örmeci, N.
A new classification algorithm, called benefit maximizing classifier on feature projections (BCFP), is developed and applied to the problem of diagnosis of gastric carcinoma. The domain contains records of patients with known diagnosis through gastroscopy results. Given a training set of such records, the BCFP classifier learns how to differentiate a new case in the domain. BCFP represents a concept in the form of feature projections on each feature dimension separately. Classification in the BCFP algorithm is based on a voting among the individual predictions made on each feature. In the gastric carcinoma domain, a lesion can be an indicator of one of nine different levels of gastric carcinoma, from early to late stages. The benefit of correct classification of early levels is much more than that of late cases. Also, the costs of wrong classifications are not symmetric. In the training phase, the BCFP algorithm learns classification rules that maximize the benefit of classification. In the querying phase, using these rules, the BCFP algorithm tries to make a prediction maximizing the benefit. A genetic algorithm is applied to select the relevant features. The performance of the BCFP algorithm is evaluated in terms of accuracy and running time. The rules induced are verified by experts of the domain. © 2004 Elsevier B.V. All rights reserved.
Open Access
Feedback approximation of the stochastic growth model by genetic neural networks
(Springer New York LLC, 2006) Sirakaya, S.; Turnovsky, S.; Alemdar, M. N.
A direct numerical optimization method is developed to approximate the one-sector stochastic growth model. The feedback investment policy is parameterized as a neural network and trained by a genetic algorithm to maximize the utility functional over the space of time-invariant investment policies. To eliminate the dependence of training on the initial conditions, at any generation, the same stationary investment policy (the same network) is used to repeatedly solve the problem from differing initial conditions. The fitness of a given policy rule is then computed as the sum of payoffs over all initial conditions. The algorithm performs quite well under a wide set of parameters. Given the general purpose nature of the method, the flexibility of neural network parametrization and the global nature of the genetic algorithm search, it can be easily extended to tackle problems with higher dimensional nonlinearities, state spaces and/or discontinuities. © Springer Science+Business Media, Inc. 2006.
Open Access
A genetic game of trade, growth and externalities
(1997) Özyıldırım, Süheyla
This dissertation introduces a new adaptive search algorithm, Genetic Algorithm (GA), for dynamic game applications. Since GAs require little knowledge of the problem itself, computations based on these algorithms are very attractive for optimizing complex dynamic structures. Part one discusses GA in general, and dynamic game applications in particular. Part two is comprised of three essays on computational economics. In Chapter one, a genetic algorithm is developed to approximate open-loop Nash equilibria in non-linear difference games of fixed duration. Two sample problems are provided to verify the success of the algorithm. Chapter two covers discrete-time dynamic games with more than two conflicting parties. In games with more than two players, there arises the possibility of coalitions among groups of players. A three-country, two-bloc trade model analyzes the impact of coalition formation on optimal policies. Chapter three extends GA further to solve open-loop differential games of infinite duration. In a dynamic North/South trade game with transboundary knowledge spillover and local pollution optimal policies are searched. Cooperative and noncooperative modes of behavior are considered to address the welfare effects of pollution and knowledge externalities.
Open Access
A genetic game of trade, growth and externalities
(Elsevier BV, 1998) Alemdar, N. M.; Özyıldırım, S.
A genetic algorithm is introduced to search for optimal policies in the presence of knowledge spillovers and local pollution in a dynamic North/South trade game. Non-cooperative trade compounds inefficiencies stemming from externalities. Cooperative trade policies are efficient and yet not credible. Short of a joint maximization of the global welfare, transfer of knowledge remains as a viable route to improve world welfare. © 1998 Elsevier Science B.V. All rights reserved.
Open Access
Heterogeneous network-on-chip design through evolutionary computing
(Taylor & Francis, 2010) Ozturk, O.; Demirbas, D.
This article explores the use of biologically inspired evolutionary computational techniques for designing and optimising heterogeneous network-on-chip (NoC) architectures, where the nodes of the NoC-based chip multiprocessor exhibit different properties such as performance, energy, temperature, area and communication bandwidth. Focusing primarily on array-dominated applications and heterogeneous execution environments, the proposed approach tries to optimise the distribution of the nodes for a given NoC area under the constraints present in the environment. This article is the first one, to our knowledge, that explores the possibility of employing evolutionary computational techniques for optimally placing the heterogeneous nodes in an NoC. We also compare our approach with an optimal integer linear programming (ILP) approach using a commercial ILP tool. The results collected so far are very encouraging and indicate that the proposed approach generates close results to the ILP-based approach with minimal execution latencies. © 2010 Taylor & Francis.
Open Access
Multi-population parallel genetic algorithm using a new genetic representation for the euclidean traveling salesman problem
(İstanbul Technical University, 2005) Kapanoğlu, M.; Koç, İ. O.; Kara, İ.; Aktürk, Mehmet Selim
This paper introduces a multi-population genetic algorithm (M-PPGA) using a new genetic representation, the kth-nearest neighbor representation, for Euclidean Traveling Salesman Problems. The proposed M-PPGA runs M greedy genetic algorithms on M separate populations, each with two new operators, intersection repairing and cheapest insert. The M-PPGA finds optimal or near optimal solutions by using a novel communication operator among individually converged populations. The algorithm generates high quality building blocks within each population; then, combines these blocks to build the optimal or near optimal solutions by means of the communication operator. The proposed M-PPGA outperforms the GAs that we know of as competitive with respect to running times and solution quality, over the considered test problems including the Turkey81.
Open Access
Non-incremental classification learning algorithms based on voting feature intervals
(1997-08) Demiröz, Gülşen
Learning is one of the necessary abilities of an intelligent agent. This thesis proposes several learning algorithms for multi-concept descriptions in the form of feature intervals, called Voting Feature Intervals (VFI) algorithms. These algorithms are non-incremental classification learning algorithms, and use feature projection based knowledge representation for the classification knowledge induced from a set of preclassified examples. The concept description learned is a set of intervals constructed separately for each feature. Each interval carries classification information for all classes. The classification of an unseen instance is based on a voting scheme, where each feature distributes its vote among all classes. Empirical evaluation of the VFI algorithms has shown that they are the best performing algorithms among other previously developed feature projection based methods in term of classification accuracy. In order to further improve the accuracy, genetic algorithms are developed to learn the optimum feature weights for any given classifier. Also a new crossover operator, called continuous uniform crossover, to be used in this weight learning genetic algorithm is proposed and developed during this thesis. Since the explanation ability of a learning system is as important as its accuracy, VFI classifiers are supplemented with a facility to convey what they have learned in a comprehensible way to humans.
Open Access
A problem space algorithm for single machine weighted tardiness problems
(Taylor & Francis Inc., 2003) Avcı, S.; Aktürk, M. S.; Storer, R. H.
We propose a problem space genetic algorithm to solve single machine total weighted tardiness scheduling problems. The proposed algorithm utilizes global and time-dependent local dominance rules to improve the neighborhood structure of the search space. They are also a powerful exploitation (intensifying) tool since the global optimum is one of the local optimum solutions. Furthermore, the problem space search method significantly enhances the exploration (diversification) capability of the genetic algorithm. In summary, we can improve both solution quality and robustness over the other local search algorithms reported in the literature.
Open Access
A problem space genetic algorithm in multiobjective optimization
(Springer New York LLC, 2003) Türkcan, A.; Aktürk, M. S.
In this study, a problem space genetic algorithm (PSGA) is used to solve bicriteria tool management and scheduling problems simultaneously in flexible manufacturing systems. The PSGA is used to generate approximately efficient solutions minimizing both the manufacturing cost and total weighted tardiness. This is the first implementation of PSGA to solve a multiobjective optimization problem (MOP). In multiobjective search, the key issues are guiding the search towards the global Pareto-optimal set and maintaining diversity. A new fitness assignment method, which is used in PSGA, is proposed to find a well-diversified, uniformly distributed set of solutions that are close to the global Pareto set. The proposed fitness assignment method is a combination of a nondominated sorting based method which is most commonly used in multiobjective optimization literature and aggregation of objectives method which is popular in the operations research literature. The quality of the Pareto-optimal set is evaluated by using the performance measures developed for multiobjective optimization problems.
Open Access
Using genetic algorithms to select architecture of a feedforward artificial neural network
(Elsevier BV, 2001) Arifovic, J.; Gençay, R.
This paper proposes a model selection methodology for feedforward network models based on the genetic algorithms and makes a number of distinct but inter-related contributions to the model selection literature for the feedforward networks. First, we construct a genetic algorithm which can search for the global optimum of an arbitrary function as the output of a feedforward network model. Second, we allow the genetic algorithm to evolve the type of inputs, the number of hidden units and the connection structure between the inputs and the output layers. Third, we study how introduction of a local elitist procedure which we call the election operator affects the algorithm's performance. We conduct a Monte Carlo simulation to study the sensitiveness of the global approximation properties of the studied genetic algorithm. Finally, we apply the proposed methodology to the daily foreign exchange returns.