Colin Reeves

Modelling Patient Flow in a Radiotherapy Department

OR Insight, Jul 1, 2007

This paper reports the development of a simulation model of the radiotherapy department of Walsgr... more This paper reports the development of a simulation model of the radiotherapy department of Walsgrave Hospital and shows the results of experiments conducted using the model. In the radiotherapy department a key target is the number of days from the time that the consultant refers the patient to the department to the date that the patient receives their first treatment. Many factors can affect this time and this project has attempted to identify and quantify the effects of these factors. Initial discussions were held to provide a framework for the study. These discussions were followed by a series of visits to the department to observe the way in which it operates and to interview staff in each of the main areas of work. Following this a flow diagram of the department was produced. This was used as a basis for the development of a computer simulation model which represents the way in which a patient moves through the department, from referral by a consultant, to the planning of the treatment, to the treatment itself, and finally discharge from the hospital. A series of experiments was used to evaluate the effects of changes to the input to the model, the number of resources in the model and the way in which the department operates. Finally, recommendations are made for future work to develop the model further and suggestions are made for its application.

Radial basis function artificial neural networks for the inference process in fuzzy logic based control

Computing, Jun 1, 1995

ABSTRACT This paper illustrates the fuzzy logic based approach to the control of a plant or a sys... more ABSTRACT This paper illustrates the fuzzy logic based approach to the control of a plant or a system, and discusses some of the possible shortcomings of the usual inference mechanisms. Radial basis function artificial neural networks have been shown to be effective in a number of applications, and have the advantage that network training is a very rapid process due to their structure. In fact, this is usually accomplished by the solution of a system of linear equations, a process for which fast and reliable algorithms are available. Radial basis function networks are shown to provide a means of constructing an inference engine capable of handling a rule base in which plant state and control actions are specified in terms of fuzzy sets. The resulting inference mechanism is shown to avoid the phenomena of rule overlap which can be a feature of fuzzy control algorithms. It is interesting to note that in this application of radial basis function networks, the usual problems on the number and location of centres do not arise. The paper concludes with a brief discussion of some experimental results achieved.Dieser Artikel illustriert den auf Fuzzy-Logik basierenden Ansatz zur Steuerung eines Systems and diskutiert einige der mglichen Nachteile der blichen Inferenzmechanismen. Es wurde gezeigt, da neuronale Netzwerke mit radialen Basisfunktionen fr viele Anwendungen sehr effektiv sind und den Vorteil haben, da das Trainieren des Netzwerkes wegen seiner Struktur ein sehr schneller Proze ist. Praktisch wird dies fr gewhnlich durch das Lsen eines linearen Gleichungssystems durchgefhrt, ein Schritt fr den schnelle und robuste Verfahren verfgbar sind. Es wird gezeigt, da neuronale Netzwerke mit radialen Basisfunktionen ein Mittel zur Konstruktion einer Inferenzmaschine sind, wobei eine Regel-Basis zur Steuerung von Systemzustnden und Systemnderungen durch Fuzzy-Logik dargestellt wird. Der resultierende Inferenzmechanismus vermeidet das Phnomen der Regelberlappung, das bei Fuzzy-Logic-Steueralgorithmen auftreten kann. Es ist interessant, da bei dieser Anwendung von neuronalen Netzwerken mit radialen Basisfunktionen die blichen Probleme bei der Anzahl und Plazierung der Zentren nicht auftreten. Der Artikel schliet mit einer zusammenfassenden Diskussion und einigen experimentellen Ergebnissen.

Genetic Algorithms

Kluwer Academic Publishers eBooks, Feb 2, 2006

Genetic algorithms (GAs) have become popular as a means of solving hard combinatorial optimizatio... more Genetic algorithms (GAs) have become popular as a means of solving hard combinatorial optimization problems. The first part of this chapter briefly traces their history, explains the basic concepts and discusses some of their theoretical aspects. It also references a number of sources for further research into their applications. The second part concentrates on the detailed implementation of a GA. It discusses the fundamentals of encoding a 'genotype' in different circumstances and describes the mechanics of population selection and management and the choice of genetic 'operators' for generating new populations. In closing, some specific guidelines for using GAs in practice are provided.

Download

An Improved Heuristic for the

A technique is described whereby the computational efficiency of the Lashkari-Jaisingh heuristic ... more A technique is described whereby the computational efficiency of the Lashkari-Jaisingh heuristic for the quadratic assignment problem is greatly enhanced. Results for the modified heuristic are presented which demonstrate that it provides solutions of consistently high quality at relatively small computational cost.

Genetic Algorithms—Principles and Perspectives

Operations research, computer science. Interface series, 2002

Unlike some specialist books, Genetic Algorithms-Principles and Perspectives, does not fall into ... more Unlike some specialist books, Genetic Algorithms-Principles and Perspectives, does not fall into the common trap of expounding at length the authors' own work. While the authors certainly do include mention of their own research, GAPP is a very balanced read. This is nicely conveyed by the subtitle, A Guide to GA Theory. All the theoretical topics one would expect are included and are well described in a non-emotional style. We start with topics such as selection intensity. Then relate this to the speed at which every bit string in the population becomes identical (or nearly so). Various diversity maintenance schemes, which prevent or slow such convergence, then are described. Later chapters explain, without undue mathematics, schema theorems, Markov models, Walsh analysis, deception and the ever popular gray versus binary coding, No Free Lunch (NFL) and building block controversies. In addition many specialist GAs are summarised. It is nice to have them and their associated theory gather together in one place. In addition to the references (and index) at the back of the book, each chapter finishes with a small Bibliographic Notes section, which criticises the literature covered by the chapter and (for the unsatiated) indicating further reading. Many of us may delay this on first reading. Instead these notes may be more helpful when using GAPP as a reference work. To this end, it is a book which every self respecting computer science library should have. The emphasis is entirely on using genetic algorithms for optimisation. Related evolutionary computation techniques (evolution strategies, genetic programming, etc.) get little mention. (There are already specialists books on the theory of these areas .) Similarly GAPP does not cover non-optimisation uses of evolutionary computation such as: artificial life, evolutionary art, design, invention or co-evolution. Later in the book the authors also analyse population based search both as a dynamical system and by using statistical mechanics and other approximation schemes. Essentially, like experimental design, these hope to capture the bulk behaviour of the population with mathematical models that use low order cumulants (such as the mean and variance) and ignore higher order interactions. This is similar to approximations successfully used in other fields. Cf. Fourier analysis and Principle Component Analysis (PCA). However while ignoring high frequencies or "higher order effects" may make the maths feasible, it is still dif-

Download

Genetic Algorithms: Principles and Perspectives: A Guide to GA Theory

Unlike some specialist books, Genetic Algorithms-Principles and Perspectives, does not fall into ... more Unlike some specialist books, Genetic Algorithms-Principles and Perspectives, does not fall into the common trap of expounding at length the authors' own work. While the authors certainly do include mention of their own research, GAPP is a very balanced read. This is nicely conveyed by the subtitle, A Guide to GA Theory. All the theoretical topics one would expect are included and are well described in a non-emotional style. We start with topics such as selection intensity. Then relate this to the speed at which every bit string in the population becomes identical (or nearly so). Various diversity maintenance schemes, which prevent or slow such convergence, then are described. Later chapters explain, without undue mathematics, schema theorems, Markov models, Walsh analysis, deception and the ever popular gray versus binary coding, No Free Lunch (NFL) and building block controversies. In addition many specialist GAs are summarised. It is nice to have them and their associated theory gather together in one place. In addition to the references (and index) at the back of the book, each chapter finishes with a small Bibliographic Notes section, which criticises the literature covered by the chapter and (for the unsatiated) indicating further reading. Many of us may delay this on first reading. Instead these notes may be more helpful when using GAPP as a reference work. To this end, it is a book which every self respecting computer science library should have. The emphasis is entirely on using genetic algorithms for optimisation. Related evolutionary computation techniques (evolution strategies, genetic programming, etc.) get little mention. (There are already specialists books on the theory of these areas .) Similarly GAPP does not cover non-optimisation uses of evolutionary computation such as: artificial life, evolutionary art, design, invention or co-evolution. Later in the book the authors also analyse population based search both as a dynamical system and by using statistical mechanics and other approximation schemes. Essentially, like experimental design, these hope to capture the bulk behaviour of the population with mathematical models that use low order cumulants (such as the mean and variance) and ignore higher order interactions. This is similar to approximations successfully used in other fields. Cf. Fourier analysis and Principle Component Analysis (PCA). However while ignoring high frequencies or "higher order effects" may make the maths feasible, it is still dif-

Download

Foundations of Genetic Algorithms 6

Elsevier eBooks, 2001

Genetic Algorithms, Path Relinking, the Flowshop Sequencing Problem and

In a previous paper, a simple genetic algorithm (GA) was developed for finding (approximately) th... more In a previous paper, a simple genetic algorithm (GA) was developed for finding (approximately) the minimum makespan of the n-job, m-machine permutation flowshop sequencing problem (PFSP). The performance of the algorithm was comparable to that of a naive neighborhood search technique and a proven simulated annealing algorithm. However, recent results have demonstrated the superiority of a tabu search method in solving the PFSP. In this paper, we reconsider the implementation of a GA for this problem and show that by taking into account the features of the landscape generated by the operators used, we are able to improve its performance significantly.

Activation Functions

Artificial Neural Nets and Genetic Algorithms, 2001

Measuring the Robustness of Airline Fleet Schedules

Multidisciplinary Scheduling: Theory and Applications

Constructing good quality fleet schedules is essential for an airline to operate in an effective ... more Constructing good quality fleet schedules is essential for an airline to operate in an effective and efficient way in order to accomplish high levels of consumer satisfaction and to maximise profits. The robustness of an airline schedule is an indicative measure of how good the schedule is because a robust plan allows the airline to cope with the unexpected disturbances which normally occur on a daily basis. This paper describes a method to measure the robustness of schedules for aircraft fleet scheduling within KLM airlines. The method is based on the 'Aircraft on Ground (ACOG)' measure, it employs statistical methods (although alternative methods were also considered) and it is shown to provide a good estimation of the robustness of a given schedule.

Download

Structure of a potassium salt of Lasalocid A and an investigation of solid–state conformational variance of the Lasalocid A backbone in known complexes

Journal of Molecular Structure, 2021

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Download

Finding routeways in airframe design using genetic algorithms

Artificial Neural Nets and Genetic Algorithms, 2003

Routing of wires and piping in airframe design is an arduous process. Current processes attempt t... more Routing of wires and piping in airframe design is an arduous process. Current processes attempt to wire bundles of wires individually, resulting in a lengthy iterative process as attempts are made to satisfy the many constraints for each type of wire or bundle. This paper describes a new approach to this problem, in which pre defined routeways are established at an early stage of the design, so as to satisfy the constraints of the wiring and piping to be placed within. The work described here provides for automatic optimization of these routeways using genetic algorithms. Solutions produced this way are compared with those produced by a maze solver, and found to offer better use of the available space. Variations of the detail design of the genetic algorithm used have been prototyped and evaluated.

Genetic Algorithms

Encyclopedia of Database Systems, 2016

A Critical Evaluation of Statistical Baraminology: Part 2—Alternatives and Conceptual and Practical Issues

ISSN: 1937-9056 Copyright © 2021 Answers in Genesis, Inc. All content is owned by Answers in Gene... more ISSN: 1937-9056 Copyright © 2021 Answers in Genesis, Inc. All content is owned by Answers in Genesis (“AiG”) unless otherwise indicated. AiG consents to unlimited copying and distribution of print copies of Answers Research Journal articles for non-commercial, non-sale purposes only, provided the following conditions are met: the author of the article is clearly identified; Answers in Genesis is acknowledged as the copyright owner; Answers Research Journal and its website, www.answersresearchjournal.org, are acknowledged as the publication source; and the integrity of the work is not compromised in any way. For website and other electronic distribution and publication, AiG consents to republication of article abstracts with direct links to the full papers on the ARJ website. All rights reserved. For more information write to: Answers in Genesis, PO Box 510, Hebron, KY 41048, Attn: Editor, Answers Research Journal. The views expressed are those of the writer(s) and not necessarily th...

Download

Statistical analysis of the effect of a single O H hydrogen-bonding interaction on carbonyl bond lengths

Journal of Molecular Structure, 2018

A statistical analysis of carbonyl bond lengths both with and without O-H hydrogen-bonding intera... more A statistical analysis of carbonyl bond lengths both with and without O-H hydrogen-bonding interactions has been undertaken using data from the Cambridge Structural Database. Only structures with Csp 3-C(=O)-Csp 3 were considered to rule out any resonant or inductive effects. All structures were subdivided into five groups based on the carbon ring structure supporting the carbonyl bond. The carbon ring structures involved 4-, 5-, 6-, and 7-membered rings with the fifth sub-category being 8-membered rings or higher out to alkyl chains. It was found that carbonyl bond lengths from the 4-membered rings were statistically shorter than the remainder but in all cases the carbonyl bond length increased with involvement of a single O-H hydrogen-bonding interaction. The overall average of carbonyl bond length was 1.210 Å whereas the overall average carbonyl bond length involved in a hydrogen bond was 1.217 Å.

format_quoteIn dicoumarols, C=O bond elongation due to hydrogen bonding was significantly noted, showcasing environmental effects.format_quote

Download

Foundations of Genetic Algorithms

format_quoteFOGA conferences focus on foundational theories in evolutionary computation, emphasizing the link between population genetics and evolutionary algorithms.format_quote

Download

Landscapes, Embedded Paths

Summary. been applied to scheduling problems. Whenever we apply such an algorithm, we implicitly ... more Summary. been applied to scheduling problems. Whenever we apply such an algorithm, we implicitly construct a landscape over which the search traverses. The nature of this landscape is not an invariant of the problem instance, but depends on a number of algorithmic choices—most obviously, the type of neighbourhood operator used as a means of exploring the search space. In this chapter, after discussing the basic ideas of a landscape, we show how this variation in the landscape of a particular instance manifests itself in terms of an important property—the number of local optima—and discuss ways in which local optima can be avoided. We then review evidence for a particular conformation of local optima in a variety of scheduling and other combinatorial problems—the ‘big valley’ property. We then turn to the question of how we can exploit such effects in terms of a fruitful search strategy—embedded path tracing—for flowshop scheduling problems. While many approaches could be taken, the ...

Download

In Modern Heuristic Techniques for Combinatorial Problems (edited by Reeves), The course aims to teach approximation methods and metaheuristic algorithms to solve

The job shop problem is among the class of NP- hard combinatorial problems. This Research paper a... more

Tabu Search Nds Global Optima of a Class of Ga-hard Problems

Tabu search (TS) is becoming increasingly recognised as an eecient way of nding high-quality solu... more Tabu search (TS) is becoming increasingly recognised as an eecient way of nding high-quality solutions to hard combinatorial problems. It may be described as an intelligent meta-heuristic for controlling simpler local search procedures by the incorporation of simulated memory. Much of the development has been experimentally driven, and there is little in the way of theory to explain its undeniably good performance. Another popular approach to optimization is the use of genetic algorithms (GAs). Like TS, GAs can also be interpreted as a development of traditional neighbourhood search methods. Unlike TS, GA research has seen some interesting theoretical work in an attempt to explain more precisely why and how they work. One area which has seen exensive development is the investigation of problems which can be expected to be either hard of easy for GAs to solve. Classes of`GA-hard' problems have been constructed using the concept of deception. In this paper we show that a particula...

Training Set Selection in Neural Network Applications

Artificial Neural Nets and Genetic Algorithms, 1995

In some applications of ANNs to classification problems, training can be inefficient simply becau... more

Uploads

Papers by Colin Reeves

Log In