Category: Uncategorized

Nurse rostering is an important search problem with many constraints. In the literature, a number of approaches have been investigated including penalty function methods to tackle these constraints within genetic algorithm frameworks. In this paper, we investigate an extension of a previously proposed stochastic ranking method, which has demonstrated superior performance to other constraint handling techniques when tested against a set of constrained optimization benchmark problems. An initial experiment on nurse rostering problems demonstrates that the stochastic ranking method is better at finding feasible solutions, but fails to obtain good results with regard to the objective function. To improve the performance of the algorithm, we hybridize it with a recently proposed simulated annealing hyper-heuristic (SAHH) within a local search and genetic algorithm framework. Computational results show that the hybrid algorithm performs better than both the genetic algorithm with stochastic ranking and the SAHH alone. The hybrid algorithm also outperforms the methods in the literature which have the previously best known results.

A call center is a system used by companies to provide a number of services to customers, which may vary from providing simple information to gathering and dealing with complaints or more complex transactions. The design of this kind of system is an important task, since the trend is that companies and institutions choose call centers as the primary option for customer relationship management. This paper presents an evolutionary algorithm based on Dandelion encoding to obtain near-optimal service trees which represent the structure of the desired call center. We introduce several modifications to the original Dandelion encoding in order to adapt it to the specific problem of service tree design. Two search space size reduction procedures improve the performance of the algorithm. Systematic experiments have been tackled in order to show the performance of our approach: first, we tackle different synthetic instances, where we discuss and analyze several aspects of the proposed evolutionary algorithm, and second, we tackle a real application, the design of the call center of an Italian telecommunications company. In all the experiments carried out we compare our approach with a lower bound for the problem based on information theory, and also with the results of a Huffman algorithm we have used for reference.

We propose a unified data modeling approach that is equally applicable to supervised regression and classification applications, as well as to unsupervised probability density function estimation. A particle swarm optimization (PSO) aided orthogonal forward regression (OFR) algorithm based on leave-one-out (LOO) criteria is developed to construct parsimonious radial basis function (RBF) networks with tunable nodes. Each stage of the construction process determines the center vector and diagonal covariance matrix of one RBF node by minimizing the LOO statistics. For regression applications, the LOO criterion is chosen to be the LOO mean square error, while the LOO misclassification rate is adopted in two-class classification applications. By adopting the Parzen window estimate as the desired response, the unsupervised density estimation problem is transformed into a constrained regression problem. This PSO aided OFR algorithm for tunable-node RBF networks is capable of constructing very parsimonious RBF models that generalize well, and our analysis and experimental results demonstrate that the algorithm is computationally even simpler than the efficient regularization assisted orthogonal least square algorithm based on LOO criteria for selecting fixed-node RBF models. Another significant advantage of the proposed learning procedure is that it does not have learning hyperparameters that have to be tuned using costly cross validation. The effectiveness of the proposed PSO aided OFR construction procedure is illustrated using several examples taken from regression and classification, as well as density estimation applications.

We have developed a steady-state elitist evolutionary algorithm to approximate the Pareto-optimal frontiers of multiobjective decision making problems. The algorithms define a territory around each individual to prevent crowding in any region. This maintains diversity while facilitating the fast execution of the algorithm. We conducted extensive experiments on a variety of test problems and demonstrated that our algorithm performs well against the leading multiobjective evolutionary algorithms. We also developed a mechanism to incorporate preference information in order to focus on the regions that are appealing to the decision maker. Our experiments show that the algorithm approximates the Pareto-optimal solutions in the desired region very well when we incorporate the preference information.

This paper identifies five distinct mechanisms by which a population-based algorithm might have an advantage over a solo-search algorithm in classical optimization. These mechanisms are illustrated through a number of toy problems. Simulations are presented comparing different search algorithms on these problems. The plausibility of these mechanisms occurring in classical optimization problems is discussed. The first mechanism we consider relies on putting together building blocks from different solutions. This is extended to include problems containing critical variables. The second mechanism is the result of focusing of the search caused by crossover. Also discussed in this context is strong focusing produced by averaging many solutions. The next mechanism to be examined is the ability of a population to act as a low-pass filter of the landscape, ignoring local distractions. The fourth mechanism is a population’s ability to search different parts of the fitness landscape, thus hedging against bad luck in the initial position or the decisions it makes. The final mechanism is the opportunity of learning useful parameter values to balance exploration against exploitation.