Abstract. In previous work, we have investigated real coded genetic algorithms with several types of multi-parent recombination operators and found evidence that multi-parent recombination with center of mass crossover (CMX) seems a good choice for real coded GAs. But CMX does not work well on functions which have their optimum on the corner of the search space. In this paper, we propose a method named boundary extension by mirroring (BEM) to cope with this problem. Applying BEM to CMX, the performance of CMX on the test functions which have their optimum on the corner of the search space was much improved. Further, by applying BEM, we observed clear improvement in performance of two-parent recombination on the functions which have their optimum on the corner of the search space. Thus, we suggest that BEM is a good general technique to improve the efficiency of crossover operators in real-coded GAs for a wide range of functions. 1.

k.matthews, a.r.sibbald @ mluri.sari.ac.uk This paper explores the application of multiobjective Genetic Algorithms (mGAs) to rural land use planning, a spatial allocation problem. Two mGAs are proposed. Both share an underlying structure of: fitness assignment using Pareto-dominance ranking, niche induction and an individual replacement strategy. They are differentiated by their representations: a fixedlength genotype composed of genes that map directly to a land parcel's use and a variablelength, order-dependent representation making allocations indirectly via a greedy algorithm. The latter representation requires additional breeding operators to be defined and post-processing of the genotype structure to identify and remove duplicate genotypes. The two mGAs are compared on a real land use planning problem and the strengths and weaknesses of the underlying framework and each representation are identified. 1

In real-coded genetic algorithms, some crossover operators do not work well on functions which have their optimum at the corner of the search space. To cope with this problem, we have proposed a boundary extension methods which allows individuals to be located within a limited space beyond the boundary of the search space. In this paper, we give an analysis of the boundary extension methods from the view point of sampling bias and perform a comparative study on the effect of applying two boundary extension methods, namely the boundary extension by mirroring BEM) and the boundary extension with extended selection (BES). We were able to confirm that to use sampling methods which have smaller sampling bias had good performance on both functions which have their optimum at or near the boundaries of the search space, and functions which have their optimum at the center of the search space. The BES/SD/A (BES by shortest distance selection with aging) had good performance on functions which have their optimum at or near the boundaries of the search space. We also confirmed that applying the BES/SD/A did not cause any performance degradation on functions which have their optimum at the center of the search space. 1.

Unit commitment is a complex decision-making process because of multiple constraints which must not be violated while finding the optimal or a near-optimal commitment schedule. This paper discusses the application of genetic algorithms for determining short-term commitment of thermal units in power generation. The objective of the optimal commitment is to determine the on/off states of the units in the system to meet the load demand and spinning-reserve requirement at each time period such that the overall cost of generation is minimum, while satisfying various operational constraints. The paper examines the feasibility of using genetic algorithms, and reports preliminary results in determining a near-optimal commitment order of thermal units in studied power systems. INTRODUCTION In power industries, fuel expenses constitute a significant part of the overall generation costs. In general, there exist different types of thermal power units based on the fuel used (e.g coal, natural gas,...

Neural networks are a computational paradigm modeled on the human brain that has become popular in

We use a Generalized Hough transform (GHT) to detect and track instances of a class of sonar signals. This class consists of a four-dimensional set of curves and hence requires a four-dimensional transform space for the GHT. Many of the signals we need to detect are very weak. Such signals yield peaks in the transform space which are both very narrow and not too far above the random background variations. Finding such peaks is difficult. Exhaustive search over a predetermined discretization of the transform space will yield a nearly optimal point for a sufficiently fine discretization. However, even with an intelligently chosen discretization, exhaustive search requires searching over (and hence evaluating) many points in the transform space. We have therefore developed a genetic algorithm to more efficiently search the transform space. Designing the genetic algorithm to work properly has required experimentation with a number of its parameters. The most important of these are (i) the representation, (ii) the population size, and (iii) the number of runs.

We have developed an algorithm to detect the presence of narrowband signals and track the time evolution of their center frequencies. This algorithm has 35 parameters whose optimal values depend on (among other things): (1) the expected dynamics of the signals, (ii) the background statistics, and (iii) the clutter (i.e., the number of simultaneous signals). Manually optimizing these parameters is a difficult task not only because of the large number of parameters but also because of the interdependence of their effects on performance. We have therefore devised an automated method for optimizing the parameters. It has three basic components: (i) a ”truth ” database with a graphical interface for easy manual entry of ”truth”, (ii) a scoring function which is a linear combination of six subscores (three evaluating detection performance and three evaluating tracking performance), and (iii) a distributed genetic algorithm which optimizes the parameter values for a particular truth database. We have used this procedure to optimize the parameter values to a variety of signal types and environmental conditions. The results have been improved performance as well as the ability to make the algorithm adaptive: as the system detects changes in the environmental conditions, it can switch to a different set of parameters. 1.1 Detection and tracking of narrowband signals 1.

Abstract--Recombination operator plays a very important role in genetic algorithms. In this paper, we present binary coded genetic algorithms in which more than two parents are involved in recombination operation. We propose two types of multi-parent recombination operators, the multi-cut (MX) and seed crossover (SX). Each of these operators is a natural generalization of two parents recombination operator. These operators are evaluated on the De Jong standard test functions. The results showed clearly that the multi-parent recombinations lead to better performance, although the performance improvement for different techniques were found to be dependent on problems. 1.

This article presents two hybrid strategies for the modeling and optimization of the glucose to gluconic acid batch bioprocess. In the hybrid approaches, first a novel artificial intelligence formalism, namely, genetic programming (GP), is used to develop a process model solely from the historic process input-output data. In the next step, the input space of the GP-based model, representing process operating conditions, is optimized using two stochastic optimization (SO) formalisms, viz., genetic algorithms (GAs) and simultaneous perturbation stochastic approximation (SPSA). These SO formalisms possess certain unique advantages over the commonly used gradient-based optimization techniques. The principal advantage of the GP-GA and GP-SPSA hybrid techniques is that process modeling and optimization can be performed exclusively from the process input-output data without invoking the detailed knowledge of the process phenomenology. The GP-GA and GP-SPSA techniques have been employed for modeling and optimization of the glucose to gluconic acid bioprocess, and the optimized process operating conditions obtained thereby have been compared with those obtained using two other hybrid modeling-optimization paradigms integrating artificial neural networks (ANNs) and GA/SPSA formalisms. Finally, the overall optimized operating conditions given by the GP-GA method, when verified experimentally resulted in a significant improvement in the gluconic acid yield. The hybrid strategies presented here are generic in nature and can be employed for modeling and optimization of a wide variety of batch and continuous bioprocesses. 1.

There are many people I would like to thank for their support. Principally I thank my family, Sue, Nick, Katie and William, and my Supervisor Larry Bull. All have shown tolerance, forbearance, support and inspiration well beyond the call of duty. In addition Dave Wyatt and Praminda Caleb-Solly have been very knowledgeable, approachable and helpful, I owe them a lot. The UWE LCSG has been a key source of ideas, knowledge and inspiration. Books and papers cannot provide such a level of understanding and debate about fundamental issues. Amongst the key players Larry Bull, Alwyn Barry, Dave Wyatt, Matt Studley, Chris Stone, Tony Pipe, Brian Carse and Rob Smith have always provided difficult and thought provoking questions, and sometimes even answers. Lastly thanks to Paul Lewis, Joe Mackenzie both of BT, Terry Fogarty, and Roger Miles who in there own ways facilitated the move from being a competent project manager to entering the (from Huxley) “brave new world that hath such people in’t ” of evolutionary and neural computing. This thesis investigates a hybrid of evolutionary computing and neural computing which long has been a goal of machine learning. X-NCS is a neural and hence a more complex version of XCS (Wilson 1995), the pre-eminent accuracy based Learning Classifier System (LCS) (Holland, 1986). XCS differs from other