Improved damage detectability in a wind turbine blade by optimal selection of vibration signal correlation coefficients

Piotr Omenzetter and Simon Hoell’s work within the Lloyd’s Register Foundation Centre for Safety and Reliability Engineering at the University of Aberdeen is supported by Lloyd’s Register Foundation. The Foundation helps to protect life and property by supporting engineering-related education, public engagement and the application of research.

Advanced Techniques for Image Quality Assessment of Modern X-ray Computed Tomography Systems

X-ray computed tomography (CT) imaging constitutes one of the most widely used diagnostic tools in radiology today with nearly 85 million CT examinations performed in the U.S in 2011. CT imparts a relatively high amount of radiation dose to the patient compared to other x-ray imaging modalities and as a result of this fact, coupled with its popularity, CT is currently the single largest source of medical radiation exposure to the U.S. population. For this reason, there is a critical need to optimize CT examinations such that the dose is minimized while the quality of the CT images is not degraded. This optimization can be difficult to achieve due to the relationship between dose and image quality. All things being held equal, reducing the dose degrades image quality and can impact the diagnostic value of the CT examination.

A recent push from the medical and scientific community towards using lower doses has spawned new dose reduction technologies such as automatic exposure control (i.e., tube current modulation) and iterative reconstruction algorithms. In theory, these technologies could allow for scanning at reduced doses while maintaining the image quality of the exam at an acceptable level. Therefore, there is a scientific need to establish the dose reduction potential of these new technologies in an objective and rigorous manner. Establishing these dose reduction potentials requires precise and clinically relevant metrics of CT image quality, as well as practical and efficient methodologies to measure such metrics on real CT systems. The currently established methodologies for assessing CT image quality are not appropriate to assess modern CT scanners that have implemented those aforementioned dose reduction technologies.

Thus the purpose of this doctoral project was to develop, assess, and implement new phantoms, image quality metrics, analysis techniques, and modeling tools that are appropriate for image quality assessment of modern clinical CT systems. The project developed image quality assessment methods in the context of three distinct paradigms, (a) uniform phantoms, (b) textured phantoms, and (c) clinical images.

The work in this dissertation used the “task-based” definition of image quality. That is, image quality was broadly defined as the effectiveness by which an image can be used for its intended task. Under this definition, any assessment of image quality requires three components: (1) A well defined imaging task (e.g., detection of subtle lesions), (2) an “observer” to perform the task (e.g., a radiologists or a detection algorithm), and (3) a way to measure the observer’s performance in completing the task at hand (e.g., detection sensitivity/specificity).

First, this task-based image quality paradigm was implemented using a novel multi-sized phantom platform (with uniform background) developed specifically to assess modern CT systems (Mercury Phantom, v3.0, Duke University). A comprehensive evaluation was performed on a state-of-the-art CT system (SOMATOM Definition Force, Siemens Healthcare) in terms of noise, resolution, and detectability as a function of patient size, dose, tube energy (i.e., kVp), automatic exposure control, and reconstruction algorithm (i.e., Filtered Back-Projection– FPB vs Advanced Modeled Iterative Reconstruction– ADMIRE). A mathematical observer model (i.e., computer detection algorithm) was implemented and used as the basis of image quality comparisons. It was found that image quality increased with increasing dose and decreasing phantom size. The CT system exhibited nonlinear noise and resolution properties, especially at very low-doses, large phantom sizes, and for low-contrast objects. Objective image quality metrics generally increased with increasing dose and ADMIRE strength, and with decreasing phantom size. The ADMIRE algorithm could offer comparable image quality at reduced doses or improved image quality at the same dose (increase in detectability index by up to 163% depending on iterative strength). The use of automatic exposure control resulted in more consistent image quality with changing phantom size.

Based on those results, the dose reduction potential of ADMIRE was further assessed specifically for the task of detecting small (<=6 mm) low-contrast (<=20 HU) lesions. A new low-contrast detectability phantom (with uniform background) was designed and fabricated using a multi-material 3D printer. The phantom was imaged at multiple dose levels and images were reconstructed with FBP and ADMIRE. Human perception experiments were performed to measure the detection accuracy from FBP and ADMIRE images. It was found that ADMIRE had equivalent performance to FBP at 56% less dose.

Using the same image data as the previous study, a number of different mathematical observer models were implemented to assess which models would result in image quality metrics that best correlated with human detection performance. The models included naïve simple metrics of image quality such as contrast-to-noise ratio (CNR) and more sophisticated observer models such as the non-prewhitening matched filter observer model family and the channelized Hotelling observer model family. It was found that non-prewhitening matched filter observers and the channelized Hotelling observers both correlated strongly with human performance. Conversely, CNR was found to not correlate strongly with human performance, especially when comparing different reconstruction algorithms.

The uniform background phantoms used in the previous studies provided a good first-order approximation of image quality. However, due to their simplicity and due to the complexity of iterative reconstruction algorithms, it is possible that such phantoms are not fully adequate to assess the clinical impact of iterative algorithms because patient images obviously do not have smooth uniform backgrounds. To test this hypothesis, two textured phantoms (classified as gross texture and fine texture) and a uniform phantom of similar size were built and imaged on a SOMATOM Flash scanner (Siemens Healthcare). Images were reconstructed using FBP and a Sinogram Affirmed Iterative Reconstruction (SAFIRE). Using an image subtraction technique, quantum noise was measured in all images of each phantom. It was found that in FBP, the noise was independent of the background (textured vs uniform). However, for SAFIRE, noise increased by up to 44% in the textured phantoms compared to the uniform phantom. As a result, the noise reduction from SAFIRE was found to be up to 66% in the uniform phantom but as low as 29% in the textured phantoms. Based on this result, it clear that further investigation was needed into to understand the impact that background texture has on image quality when iterative reconstruction algorithms are used.

To further investigate this phenomenon with more realistic textures, two anthropomorphic textured phantoms were designed to mimic lung vasculature and fatty soft tissue texture. The phantoms (along with a corresponding uniform phantom) were fabricated with a multi-material 3D printer and imaged on the SOMATOM Flash scanner. Scans were repeated a total of 50 times in order to get ensemble statistics of the noise. A novel method of estimating the noise power spectrum (NPS) from irregularly shaped ROIs was developed. It was found that SAFIRE images had highly locally non-stationary noise patterns with pixels near edges having higher noise than pixels in more uniform regions. Compared to FBP, SAFIRE images had 60% less noise on average in uniform regions for edge pixels, noise was between 20% higher and 40% lower. The noise texture (i.e., NPS) was also highly dependent on the background texture for SAFIRE. Therefore, it was concluded that quantum noise properties in the uniform phantoms are not representative of those in patients for iterative reconstruction algorithms and texture should be considered when assessing image quality of iterative algorithms.

The move beyond just assessing noise properties in textured phantoms towards assessing detectability, a series of new phantoms were designed specifically to measure low-contrast detectability in the presence of background texture. The textures used were optimized to match the texture in the liver regions actual patient CT images using a genetic algorithm. The so called “Clustured Lumpy Background” texture synthesis framework was used to generate the modeled texture. Three textured phantoms and a corresponding uniform phantom were fabricated with a multi-material 3D printer and imaged on the SOMATOM Flash scanner. Images were reconstructed with FBP and SAFIRE and analyzed using a multi-slice channelized Hotelling observer to measure detectability and the dose reduction potential of SAFIRE based on the uniform and textured phantoms. It was found that at the same dose, the improvement in detectability from SAFIRE (compared to FBP) was higher when measured in a uniform phantom compared to textured phantoms.

The final trajectory of this project aimed at developing methods to mathematically model lesions, as a means to help assess image quality directly from patient images. The mathematical modeling framework is first presented. The models describe a lesion’s morphology in terms of size, shape, contrast, and edge profile as an analytical equation. The models can be voxelized and inserted into patient images to create so-called “hybrid” images. These hybrid images can then be used to assess detectability or estimability with the advantage that the ground truth of the lesion morphology and location is known exactly. Based on this framework, a series of liver lesions, lung nodules, and kidney stones were modeled based on images of real lesions. The lesion models were virtually inserted into patient images to create a database of hybrid images to go along with the original database of real lesion images. ROI images from each database were assessed by radiologists in a blinded fashion to determine the realism of the hybrid images. It was found that the radiologists could not readily distinguish between real and virtual lesion images (area under the ROC curve was 0.55). This study provided evidence that the proposed mathematical lesion modeling framework could produce reasonably realistic lesion images.

Based on that result, two studies were conducted which demonstrated the utility of the lesion models. The first study used the modeling framework as a measurement tool to determine how dose and reconstruction algorithm affected the quantitative analysis of liver lesions, lung nodules, and renal stones in terms of their size, shape, attenuation, edge profile, and texture features. The same database of real lesion images used in the previous study was used for this study. That database contained images of the same patient at 2 dose levels (50% and 100%) along with 3 reconstruction algorithms from a GE 750HD CT system (GE Healthcare). The algorithms in question were FBP, Adaptive Statistical Iterative Reconstruction (ASiR), and Model-Based Iterative Reconstruction (MBIR). A total of 23 quantitative features were extracted from the lesions under each condition. It was found that both dose and reconstruction algorithm had a statistically significant effect on the feature measurements. In particular, radiation dose affected five, three, and four of the 23 features (related to lesion size, conspicuity, and pixel-value distribution) for liver lesions, lung nodules, and renal stones, respectively. MBIR significantly affected 9, 11, and 15 of the 23 features (including size, attenuation, and texture features) for liver lesions, lung nodules, and renal stones, respectively. Lesion texture was not significantly affected by radiation dose.

The second study demonstrating the utility of the lesion modeling framework focused on assessing detectability of very low-contrast liver lesions in abdominal imaging. Specifically, detectability was assessed as a function of dose and reconstruction algorithm. As part of a parallel clinical trial, images from 21 patients were collected at 6 dose levels per patient on a SOMATOM Flash scanner. Subtle liver lesion models (contrast = -15 HU) were inserted into the raw projection data from the patient scans. The projections were then reconstructed with FBP and SAFIRE (strength 5). Also, lesion-less images were reconstructed. Noise, contrast, CNR, and detectability index of an observer model (non-prewhitening matched filter) were assessed. It was found that SAFIRE reduced noise by 52%, reduced contrast by 12%, increased CNR by 87%. and increased detectability index by 65% compared to FBP. Further, a 2AFC human perception experiment was performed to assess the dose reduction potential of SAFIRE, which was found to be 22% compared to the standard of care dose.

In conclusion, this dissertation provides to the scientific community a series of new methodologies, phantoms, analysis techniques, and modeling tools that can be used to rigorously assess image quality from modern CT systems. Specifically, methods to properly evaluate iterative reconstruction have been developed and are expected to aid in the safe clinical implementation of dose reduction technologies.

The O stars in the VLT-FLAMES Tarantula Survey

The VLT-FLAMES Tarantula Survey (VFTS) has secured mid-resolution spectra of over 300 O-type stars in the 30 Doradus region of the Large Magellanic Cloud. A homogeneous analysis of such a large sample requires automated techniques, an approach that will also be needed for the upcoming analysis of the Gaia surveys of the Northern and Southern Hemisphere supplementing the Gaia measurements. We point out the importance of Gaia for the study of O stars, summarize the O star science case of VFTS and present a test of the automated modeling technique using synthetically generated data. This method employs a genetic algorithm based optimization technique in combination with fastwind model atmospheres. The method is found to be robust and able to recover the main photospheric parameters accurately. Precise wind parameters can be obtained as well, however, as expected, for dwarf stars the rate of acceleration of the ow is poorly constrained.

GRASP and statistical bounds for heuristic solutions to combinatorial problems

The quality of a heuristic solution to a NP-hard combinatorial problem is hard to assess. A few studies have advocated and tested statistical bounds as a method for assessment. These studies indicate that statistical bounds are superior to the more widely known and used deterministic bounds. However, the previous studies have been limited to a few metaheuristics and combinatorial problems and, hence, the general performance of statistical bounds in combinatorial optimization remains an open question. This work complements the existing literature on statistical bounds by testing them on the metaheuristic Greedy Randomized Adaptive Search Procedures (GRASP) and four combinatorial problems. Our findings confirm previous results that statistical bounds are reliable for the p-median problem, while we note that they also seem reliable for the set covering problem. For the quadratic assignment problem, the statistical bounds has previously been found reliable when obtained from the Genetic algorithm whereas in this work they found less reliable. Finally, we provide statistical bounds to four 2-path network design problem instances for which the optimum is currently unknown.

Dimensionality hyper-reduction and machine learning for dynamical systems with varying parameters

Thesis (Ph.D.)--University of Washington, 2016-08

Application of battery energy storage in the Québec interconnection

Le Système Stockage de l’Énergie par Batterie ou Batterie de Stockage d’Énergie (BSE) offre de formidables atouts dans les domaines de la production, du transport, de la distribution et de la consommation d’énergie électrique. Cette technologie est notamment considérée par plusieurs opérateurs à travers le monde entier, comme un nouveau dispositif permettant d’injecter d’importantes quantités d’énergie renouvelable d’une part et d’autre part, en tant que composante essentielle aux grands réseaux électriques. De plus, d’énormes avantages peuvent être associés au déploiement de la technologie du BSE aussi bien dans les réseaux intelligents que pour la réduction de l’émission des gaz à effet de serre, la réduction des pertes marginales, l’alimentation de certains consommateurs en source d’énergie d’urgence, l’amélioration de la gestion de l’énergie, et l’accroissement de l’efficacité énergétique dans les réseaux. Cette présente thèse comprend trois étapes à savoir : l’Étape 1 - est relative à l’utilisation de la BSE en guise de réduction des pertes électriques ; l’Étape 2 - utilise la BSE comme élément de réserve tournante en vue de l’atténuation de la vulnérabilité du réseau ; et l’Étape 3 - introduit une nouvelle méthode d’amélioration des oscillations de fréquence par modulation de la puissance réactive, et l’utilisation de la BSE pour satisfaire la réserve primaire de fréquence. La première Étape, relative à l’utilisation de la BSE en vue de la réduction des pertes, est elle-même subdivisée en deux sous-étapes dont la première est consacrée à l’allocation optimale et le seconde, à l’utilisation optimale. Dans la première sous-étape, l’Algorithme génétique NSGA-II (Non-dominated Sorting Genetic Algorithm II) a été programmé dans CASIR, le Super-Ordinateur de l’IREQ, en tant qu’algorithme évolutionniste multiobjectifs, permettant d’extraire un ensemble de solutions pour un dimensionnement optimal et un emplacement adéquat des multiple unités de BSE, tout en minimisant les pertes de puissance, et en considérant en même temps la capacité totale des puissances des unités de BSE installées comme des fonctions objectives. La première sous-étape donne une réponse satisfaisante à l’allocation et résout aussi la question de la programmation/scheduling dans l’interconnexion du Québec. Dans le but de réaliser l’objectif de la seconde sous-étape, un certain nombre de solutions ont été retenues et développées/implantées durant un intervalle de temps d’une année, tout en tenant compte des paramètres (heure, capacité, rendement/efficacité, facteur de puissance) associés aux cycles de charge et de décharge de la BSE, alors que la réduction des pertes marginales et l’efficacité énergétique constituent les principaux objectifs. Quant à la seconde Étape, un nouvel indice de vulnérabilité a été introduit, formalisé et étudié ; indice qui est bien adapté aux réseaux modernes équipés de BES. L’algorithme génétique NSGA-II est de nouveau exécuté (ré-exécuté) alors que la minimisation de l’indice de vulnérabilité proposé et l’efficacité énergétique représentent les principaux objectifs. Les résultats obtenus prouvent que l’utilisation de la BSE peut, dans certains cas, éviter des pannes majeures du réseau. La troisième Étape expose un nouveau concept d’ajout d’une inertie virtuelle aux réseaux électriques, par le procédé de modulation de la puissance réactive. Il a ensuite été présenté l’utilisation de la BSE en guise de réserve primaire de fréquence. Un modèle générique de BSE, associé à l’interconnexion du Québec, a enfin été proposé dans un environnement MATLAB. Les résultats de simulations confirment la possibilité de l’utilisation des puissances active et réactive du système de la BSE en vue de la régulation de fréquence.

A survey of intrusion detection system technologies

This paper provides an overview of IDS types and how they work as well as configuration considerations and issues that affect them. Advanced methods of increasing the performance of an IDS are explored such as specification based IDS for protecting Supervisory Control And Data Acquisition (SCADA) and Cloud networks. Also by providing a review of varied studies ranging from issues in configuration and specific problems to custom techniques and cutting edge studies a reference can be provided to others interested in learning about and developing IDS solutions. Intrusion Detection is an area of much required study to provide solutions to satisfy evolving services and networks and systems that support them. This paper aims to be a reference for IDS technologies other researchers and developers interested in the field of intrusion detection.

Modeling of burden distribution in the blast furnace

The blast furnace is the main ironmaking production unit in the world which converts iron ore with coke and hot blast into liquid iron, hot metal, which is used for steelmaking. The furnace acts as a counter-current reactor charged with layers of raw material of very different gas permeability. The arrangement of these layers, or burden distribution, is the most important factor influencing the gas flow conditions inside the furnace, which dictate the efficiency of the heat transfer and reduction processes. For proper control the furnace operators should know the overall conditions in the furnace and be able to predict how control actions affect the state of the furnace. However, due to high temperatures and pressure, hostile atmosphere and mechanical wear it is very difficult to measure internal variables. Instead, the operators have to rely extensively on measurements obtained at the boundaries of the furnace and make their decisions on the basis of heuristic rules and results from mathematical models. It is particularly difficult to understand the distribution of the burden materials because of the complex behavior of the particulate materials during charging. The aim of this doctoral thesis is to clarify some aspects of burden distribution and to develop tools that can aid the decision-making process in the control of the burden and gas distribution in the blast furnace. A relatively simple mathematical model was created for simulation of the distribution of the burden material with a bell-less top charging system. The model developed is fast and it can therefore be used by the operators to gain understanding of the formation of layers for different charging programs. The results were verified by findings from charging experiments using a small-scale charging rig at the laboratory. A basic gas flow model was developed which utilized the results of the burden distribution model to estimate the gas permeability of the upper part of the blast furnace. This combined formulation for gas and burden distribution made it possible to implement a search for the best combination of charging parameters to achieve a target gas temperature distribution. As this mathematical task is discontinuous and non-differentiable, a genetic algorithm was applied to solve the optimization problem. It was demonstrated that the method was able to evolve optimal charging programs that fulfilled the target conditions. Even though the burden distribution model provides information about the layer structure, it neglects some effects which influence the results, such as mixed layer formation and coke collapse. A more accurate numerical method for studying particle mechanics, the Discrete Element Method (DEM), was used to study some aspects of the charging process more closely. Model charging programs were simulated using DEM and compared with the results from small-scale experiments. The mixed layer was defined and the voidage of mixed layers was estimated. The mixed layer was found to have about 12% less voidage than layers of the individual burden components. Finally, a model for predicting the extent of coke collapse when heavier pellets are charged over a layer of lighter coke particles was formulated based on slope stability theory, and was used to update the coke layer distribution after charging in the mathematical model. In designing this revision, results from DEM simulations and charging experiments for some charging programs were used. The findings from the coke collapse analysis can be used to design charging programs with more stable coke layers.

Multi-objective ant colony optimization for requirements selection

The selection of a set of requirements between all the requirements previously defined by customers is an important process, repeated at the beginning of each development step when an incremental or agile software development approach is adopted. The set of selected requirements will be developed during the actual iteration. This selection problem can be reformulated as a search problem, allowing its treatment with metaheuristic optimization techniques. This paper studies how to apply Ant Colony Optimization algorithms to select requirements. First, we describe this problem formally extending an earlier version of the problem, and introduce a method based on Ant Colony System to find a variety of efficient solutions. The performance achieved by the Ant Colony System is compared with that of Greedy Randomized Adaptive Search Procedure and Non-dominated Sorting Genetic Algorithm, by means of computational experiments carried out on two instances of the problem constructed from data provided by the experts.

O problema de alocação de berços: um estudo das heurísticas simulated annealing e algoritmo genético

Este trabalho apresenta um estudo de caso das heurísticas Simulated Annealing e Algoritmo Genético para um problema de grande relevância encontrado no sistema portuário, o Problema de Alocação em Berços. Esse problema aborda a programação e a alocação de navios às áreas de atracação ao longo de um cais. A modelagem utilizada nesta pesquisa é apresentada por Mauri (2008) [28] que trata do problema como uma Problema de Roteamento de Veículos com Múltiplas Garagens e sem Janelas de Tempo. Foi desenvolvido um ambiente apropriado para testes de simulação, onde o cenário de análise foi constituido a partir de situações reais encontradas na programação de navios de um terminal de contêineres. Os testes computacionais realizados mostram a performance das heurísticas em relação a função objetivo e o tempo computacional, a m de avaliar qual das técnicas apresenta melhores resultados.

Uma metodologia heurística para minimizar o roteiro nos serviços de leitura de hidrômetros

Este trabalho tem por objetivo propor uma metodologia heurística para o Problema de Cobertura de Arcos aplicado aos serviços de saneamento, em específico na leitura de hidrômetros. Dentro deste contexto desenvolveu-se um aplicativo que permite o planejamento de rotas de maneira que os custos em distância percorrida sejam reduzidos e mantenham-se aproximadamente os mesmos em todos os percursos. A metodologia foi dividida em etapas. Na primeira etapa, para compreender melhor o problema, fez-se uma pesquisa de campo organizando os dados disponibilizados por uma empresa de saneamento. A segunda etapa foi caracterizada pela determinação de pontos em cada metade de trechos de quadra e nas interseções de ruas, os quais foram cadastrados, em um mapa georeferenciado. Este mapa contemplou a região escolhida para o estudo e os pontos cadastrados serviram para determinar e consequentemente, designar as medianas relacionadas, o que constitui a terceira etapa. Para isso utilizou-se respectivamente o algoritmo de Teitz Bart Modificado por CADP e o algoritmo de designação de Gillet e Johnson adaptado. Ao final desta etapa formaram-se subsetores dentro de um setor específico. Na última etapa encontrou-se as rotas de cada subsetor através do algoritmo genético. O aplicativo desenvolvido permitiu flexibilidade de ações, dando autonomia para o usuário na escolha das opções de cálculo. Sua interface gráfica possibilitou a elaboração de mapas e a visualização das rotas em cada subsetor. Além disso o aplicativo minimizou os percursos e distribuiu os subsetores com distâncias aproximadas. A eficiência das heurísticas que embasaram o aplicativo desenvolvido, foi comprovada através dos testes realizados, os quais obtiveram resultados de boa qualidade.

Uma abordagem evolucionária para o planejamento online de rotas para múltiplos robôs móveis em ambiente multiagente

O problema de planejamento de rotas de robôs móveis consiste em determinar a melhor rota para um robô, em um ambiente estático e/ou dinâmico, que seja capaz de deslocá-lo de um ponto inicial até e um ponto final, também em conhecido como estado objetivo. O presente trabalho emprega o uso de uma abordagem baseada em Algoritmos Genéticos para o planejamento de rotas de múltiplos robôs em um ambiente complexo composto por obstáculos fixos e obstáculos moveis. Através da implementação do modelo no software do NetLogo, uma ferramenta utilizada em simulações de aplicações multiagentes, possibilitou-se a modelagem de robôs e obstáculos presentes no ambiente como agentes interativos, viabilizando assim o desenvolvimento de processos de detecção e desvio de obstáculos. A abordagem empregada busca pela melhor rota para robôs e apresenta um modelo composto pelos operadores básicos de reprodução e mutação, acrescido de um novo operador duplo de refinamento capaz de aperfeiçoar as melhores soluções encontradas através da eliminação de movimentos inúteis. Além disso, o calculo da rota de cada robô adota um método de geração de subtrechos, ou seja, não calcula apenas uma unica rota que conecta os pontos inicial e final do cenário, mas sim várias pequenas subrotas que conectadas formam um caminho único capaz de levar o robô ao estado objetivo. Neste trabalho foram desenvolvidos dois cenários, para avaliação da sua escalabilidade: o primeiro consiste em um cenário simples composto apenas por um robô, um obstáculo movel e alguns obstáculos fixos; já o segundo, apresenta um cenário mais robusto, mais amplo, composto por múltiplos robôs e diversos obstáculos fixos e moveis. Ao final, testes de desempenho comparativos foram efetuados entre a abordagem baseada em Algoritmos Genéticos e o Algoritmo A*. Como critério de comparação foi utilizado o tamanho das rotas obtidas nas vinte simulações executadas em cada abordagem. A analise dos resultados foi especificada através do Teste t de Student.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

'Bayesian Optimisation for Nurse Scheduling'

A Bayesian optimisation algorithm for a nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse's assignment. When a human scheduler works, he normally builds a schedule systematically following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not yet completed, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this paper, we design a more human-like scheduling algorithm, by using a Bayesian optimisation algorithm to implement explicit learning from past solutions. A nurse scheduling problem from a UK hospital is used for testing. Unlike our previous work that used Genetic Algorithms to implement implicit learning [1], the learning in the proposed algorithm is explicit, i.e. we identify and mix building blocks directly. The Bayesian optimisation algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, new rule strings have been obtained. Sets of rule strings are generated in this way, some of which will replace previous strings based on fitness. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. For clarity, consider the following toy example of scheduling five nurses with two rules (1: random allocation, 2: allocate nurse to low-cost shifts). In the beginning of the search, the probabilities of choosing rule 1 or 2 for each nurse is equal, i.e. 50%. After a few iterations, due to the selection pressure and reinforcement learning, we experience two solution pathways: Because pure low-cost or random allocation produces low quality solutions, either rule 1 is used for the first 2-3 nurses and rule 2 on remainder or vice versa. In essence, Bayesian network learns 'use rule 2 after 2-3x using rule 1' or vice versa. It should be noted that for our and most other scheduling problems, the structure of the network model is known and all variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus, learning can amount to 'counting' in the case of multinomial distributions. For our problem, we use our rules: Random, Cheapest Cost, Best Cover and Balance of Cost and Cover. In more detail, the steps of our Bayesian optimisation algorithm for nurse scheduling are: 1. Set t = 0, and generate an initial population P(0) at random; 2. Use roulette-wheel selection to choose a set of promising rule strings S(t) from P(t); 3. Compute conditional probabilities of each node according to this set of promising solutions; 4. Assign each nurse using roulette-wheel selection based on the rules' conditional probabilities. A set of new rule strings O(t) will be generated in this way; 5. Create a new population P(t+1) by replacing some rule strings from P(t) with O(t), and set t = t+1; 6. If the termination conditions are not met (we use 2000 generations), go to step 2. Computational results from 52 real data instances demonstrate the success of this approach. They also suggest that the learning mechanism in the proposed approach might be suitable for other scheduling problems. Another direction for further research is to see if there is a good constructing sequence for individual data instances, given a fixed nurse scheduling order. If so, the good patterns could be recognized and then extracted as new domain knowledge. Thus, by using this extracted knowledge, we can assign specific rules to the corresponding nurses beforehand, and only schedule the remaining nurses with all available rules, making it possible to reduce the solution space. Acknowledgements The work was funded by the UK Government's major funding agency, Engineering and Physical Sciences Research Council (EPSRC), under grand GR/R92899/01. References [1] Aickelin U, "An Indirect Genetic Algorithm for Set Covering Problems", Journal of the Operational Research Society, 53(10): 1118-1126,

'Investigating Artificial Immune Systems For Job Shop Rescheduling In Changing Environments'

ABSTRACT Artificial immune system can be used to generate schedules in changing environments and it has been proven to be more robust than schedules developed using a genetic algorithm. Good schedules can be produced especially when the number of the antigens is increased. However, an increase in the range of the antigens had somehow affected the fitness of the immune system. In this research, we are trying to improve the result of the system by rescheduling the same problem using the same method while at the same time maintaining the robustness of the schedules.