Search

In recent years, deep learning has rapidly become a method of choice for segmentation of medical images. Deep neural architectures such as UNet and FPN have achieved high performances on many medical datasets. However, medical image analysis algorithms are required to be reliable, robust, and accurate for clinical applications which can be difficult to achieve for some single deep learning methods. In this study, we introduce an ensemble of classifiers for semantic segmentation of medical images. The ensemble of classifiers here is a set of various deep learning-based classifiers, aiming to achieve better performance than using a single classifier. We propose a weighted ensemble method in which the weighted sum of segmentation outputs by classifiers is used to choose the final segmentation decision. We use a swarm intelligence algorithm namely Comprehensive Learning Particle Swarm Optimization to optimize the combining weights. Dice coefficient, a popular performance metric for image segmentation, is used as the fitness criteria. Experiments conducted on some medical datasets of the CAMUS competition on cardiographic image segmentation show that our method achieves better results than both the constituent segmentation models and the reported model of the CAMUS competition.

The application of finite element analysis is used to simulate the relative distribution and magnitude of stress–strain conditions during a geologically brief, NNW-SSE-oriented, extensional event (1595 Ma to 1590 Ma), co-incident with IOCG-hydrothermal fluid flow and mineralisation across the Mt Woods Inlier, Gawler Craton, South Australia. Differential stress and shear strain maps across the modelled terrane highlight regions that were predisposed to strain localization, extensional failure and fluid throughput during the simulated mineralisation event. These maps are integrated with other datasets and interpretation layers, one of which is a proposed structural–geometrical relationship apparent in many world-class IOCG deposits, including Prominent Hill, Olympic Dam, Sossego, Salobo, Cristalino and Candelaria. These deposits occur at steeply plunging, pipe-like intersections of conjugate extensional systems of faults, shears and/or contacts, wherein the obtuse angle may have been bisected by the maximum principal extensional axis (viz., σ3) during mineralisation. Several other layers are also used for the generation of targets, such as distance from major shear zones, favourable host lithologies, and proximity to tectonostratigraphic contacts of markedly contrasting competency. The result is an integrated target index or heat map for IOCG prospectively across the Mt. Woods Inlier.

Change detection of hyperspectral images is a very important subject in the field of remote sensing application. Due to the large number of bands and the high correlation between adjacent bands in the hyperspectral image cube, information redundancy is a big problem, which increases the computational complexity and brings negative factor to detection performance. To address this problem, the principal component analysis (PCA) has been widely used for dimension reduction. It has the capability of projecting the original multi-dimensional hyperspectral data into new eigenvector space which allows it to extract light but representative information. The difference image of the PCA components is obtained by subtracting the two dimensionality-reduced images, on which the change detection is considered as a binary classification problem. The first several principal components of each pixel are taken as a feature vector for data classification using k-means clustering with k=2, where the two classes are changed pixels and unchanged pixels, respectively. The centroids of two clusters are determined by iteratively finding the minimum Euclidean distance between pixel’s eigenvectors. Experiments on two publicly available datasets have been carried out and evaluated by overall accuracy. The results have validated the efficacy and efficiency of the proposed approach.

In this study, we introduce an ensemble selection method for deep ensemble systems called VEGAS. The deep ensemble models include multiple layers of the ensemble of classifiers (EoC). At each layer, we train the EoC and generates training data for the next layer by concatenating the predictions for training observations and the original training data. The predictions of the classifiers in the last layer are combined by a combining method to obtain the final collaborated prediction. We further improve the prediction accuracy of a deep ensemble model by searching for its optimal configuration, i.e., the optimal set of classifiers in each layer. The optimal configuration is obtained using the Variable-Length Genetic Algorithm (VLGA) to maximize the prediction accuracy of the deep ensemble model on the validation set. We developed three operators of VLGA: roulette wheel selection for breeding, a chunk-based crossover based on the number of classifiers to generate new offsprings, and multiple random points-based mutation on each offspring. The experiments on 20 datasets show that VEGAS outperforms selected benchmark algorithms, including two well-known ensemble methods (Random Forest and XgBoost) and three deep learning methods (Multiple Layer Perceptron, gcForest, and MULES).

In this study, we evolve an ensemble of detectors to check the presence of gross systematic errors on measurement data. We use the Fisher method to combine the output of different detectors and then test the hypothesis about the presence of gross errors based on the combined value. We further develop a detector selection approach in which a subset of detectors is selected for each sample. The selection is conducted by comparing the output of each detector to its associated selection threshold. The thresholds are obtained by minimizing the 0-1 loss function on training data using the Particle Swarm Optimization method. Experiments conducted on a simulated system confirm the advantages of ensemble and evolved ensemble approach.

In previous work, we proposed and studied a new dynamic formulation of the Location-allocation (LA) problem called the Dynamic-Customer Location-allocation (DC-LA) problem. DC-LA is based on the idea of changes in customer distribution over a defined period, and these changes have to be taken into account when establishing facilities to service changing customers distributions. This necessitated a dynamic stochastic evaluation function Which came with a high computational cost due to a large number of simulations required in the evaluation process.In this paper, we investigate the use of racing, an approach used in model selection, to reduce the high computational cost by employing the minimum number of simulations for solution selection. Our adaptation of racing uses the Friedman test to compare solutions statistically. Racing allows simulations to be performed iteratively, ensuring that the minimum number of simulations is performed to detect a statistical difference.We present experiments using Population-Based Incremental Learning (PBIL) to explore the savings achievable from using racing in this way. Our results show that racing achieves improved cost savings over the dynamic stochastic evaluation function. We also observed that on average, the computational cost of racing was about 4.5 times loWer than the computational cost of the full dynamic stochastic evaluation.

Text classification is one of the most important tasks in the field of Natural Language Processing. There are many approaches that focus on two main aspects: generating an effective representation; and selecting and refining algorithms to build the classification model. Traditional machine learning methods represent documents in vector space using features such as term frequencies, which have limitations in handling the order and semantics of words. Meanwhile, although achieving many successes, deep learning classifiers require substantial resources in terms of labelled data and computational complexity. In this work, a weighted ensemble of classifiers (WEC) is introduced to address the text classification problem. Instead of using majority vote as the combining method, we propose to associate each classifier’s prediction with a different weight when combining classifiers. The optimal weights are obtained by minimising a loss function on the training data with the Particle Swarm Optimisation algorithm. We conducted experiments on 5 popular datasets and report classification performance of algorithms with classification accuracy and macro F1 score. WEC was run with several different combinations of traditional machine learning and deep learning classifiers to show its flexibility and robustness. Experimental results confirm the advantage of WEC, especially on smaller datasets.

Deep Neural Networks have achieved many successes when applying to visual, text, and speech information in various domains. The crucial reasons behind these successes are the multi-layer architecture and the in-model feature transformation of deep learning models. These design principles have inspired other sub-fields of machine learning including ensemble learning. In recent years, there are some deep homogenous ensemble models introduced with a large number of classifiers in each layer. These models, thus, require a costly computational classification. Moreover, the existing deep ensemble models use all classifiers including unnecessary ones which can reduce the predictive accuracy of the ensemble. In this study, we propose a multi-layer ensemble learning framework called MUlti-Layer heterogeneous Ensemble System (MULES) to solve the classification problem. The proposed system works with a small number of heterogeneous classifiers to obtain ensemble diversity, therefore being efficiency in resource usage. We also propose an Evolutionary Algorithm-based selection method to select the subset of suitable classifiers and features at each layer to enhance the predictive performance of MULES. The selection method uses NSGA-II algorithm to optimize two objectives concerning classification accuracy and ensemble diversity. Experiments on 33 datasets confirm that MULES is better than a number of well-known benchmark algorithms.

We performed an investigation of how several data relationship discovery algorithms can be combined to improve performance. We investigated eight relationship discovery algorithms like Cosine similarity, Soundex similarity, Name similarity, Value range similarity, etc., to identify potential links between database tables in different ways using different categories of database information. We proposed voting system and hierarchical clustering ensemble methods to reduce the generalization error of each algorithm. Voting scheme uses a given weighting metric to combine the predictions of each algorithm. Hierarchical clustering groups predictions into clusters based on similarities and then combine a member from each cluster together. We run experiments to validate the performance of each algorithm and compare performance with our ensemble methods and the state-of-the-art algorithms (FaskFK, Randomness and HoPF) using Precision, Recall and F-Measure evaluation metrics over TPCH and AdvWork datasets. Results show that performance of each algorithm is limited, indicating the importance of combining them to consolidate their strengths.

We propose a new class of multi-objective benchmark problems on which we analyse the performance of four well established multi-objective evolutionary algorithms (MOEAs) – each implementing a different search paradigm – by comparing run-time convergence behaviour over a set of 1200 problem instances. The new benchmarks are created by fusing previously proposed single-objective interpolated continuous optimisation problems (ICOPs) via a common set of Pareto non-dominated seeds. They thus inherit the ICOP property of having tunable fitness landscape features. The benchmarks are of intrinsic interest as they derive from interpolation methods and so can approximate general problem instances. This property is revealed to be of particular importance as our extensive set of numerical experiments indicates that choices pertaining to (i) the weighting of the inverse distance interpolation function and (ii) the problem dimension can be used to construct problems that are challenging to all tested multi-objective search paradigms. This in turn means that the new multi-objective ICOPs problems (MO-ICOPs) can be used to construct well-balanced benchmark sets that discriminate well between the run-time convergence behaviour of different solvers.

In this study, we introduce an ensemble system by combining homogeneous ensemble and heterogeneous ensemble into a single framework. Based on the observation that the projected data is significantly different from the original data as well as each other after using random projections, we construct the homogeneous module by applying random projections on the training data to obtain the new training sets. In the heterogeneous module, several learning algorithms will train on the new training sets to generate the base classifiers. We propose four combining algorithms based on Sum Rule and Majority Vote Rule for the proposed ensemble. Experiments on some popular datasets confirm that the proposed ensemble method is better than several well-known benchmark algorithms proposed framework has great flexibility when applied to real-world applications. The proposed framework has great flexibility when applied to real-world applications by using any techniques that make rich training data for the homogeneous module, as well as using any set of learning algorithms for the heterogeneous module.

The field of object detection has witnessed great strides in recent years. With the wave of deep neural networks (DNN), many breakthroughs have achieved for the problems of object detection which previously were thought to be difficult. However, there exists a limitation with DNN-based approaches as some architectures are only suitable for particular types of object. Thus it would be desirable to combine the strengths of different methods to handle objects in different contexts. In this study, we propose an ensemble of object detectors in which individual detectors are adaptively combine for the collaborated decision. The combination is conducted on the outputs of detectors including the predicted label and location for each object. We proposed a detector selection method to select the suitable detectors and a weighted-based combining method to combine the predicted locations of selected detectors. The parameters of these methods are optimized by using Particle Swarm Optimization in order to maximize mean Average Precision (mAP) metric. Experiments conducted on VOC2007 dataset with six object detectors show that our ensemble method is better than each single detector.

Funding: This work was supported by the EU Horizon 2020 project, TeamPlay, Grant Number 779882, and UK EPSRC Discovery, Grant Number EP/P020631/1. This paper presents a new technique for introducing and tuning parallelism for heterogeneous shared-memory systems (comprising a mixture of CPUs and GPUs), using a combination of algorithmic skeletons (such as farms and pipelines), Monte–Carlo tree search for deriving mappings of tasks to available hardware resources, and refactoring tool support for applying the patterns and mappings in an easy and effective way. Using our approach, we demonstrate easily obtainable, significant and scalable speedups on a number of case studies showing speedups of up to 41 over the sequential code on a 24-core machine with one GPU. We also demonstrate that the speedups obtained by mappings derived by the MCTS algorithm are within 5–15% of the best-obtained manual parallelisation. Publisher PDF

In ensemble systems, the predictions of base classifiers are aggregated by a combining algorithm (meta-classifier) to achieve better classification accuracy than using a single classifier. Experiments show that the performance of ensembles significantly depends on the choice of meta-classifier. Normally, the classifier selection method applied to an ensemble usually removes all the predictions of a classifier if this classifier is not selected in the final ensemble. Here we present an idea to only remove a subset of each classifier's prediction thereby introducing a simultaneous meta-data and meta-classifier selection method for ensemble systems. Our approach uses Cross Validation on the training set to generate meta-data as the predictions of base classifiers. We then use Ant Colony Optimization to search for the optimal subset of meta-data and meta-classifier for the data. By considering each column of meta-data, we construct the configuration including a subset of these columns and a meta-classifier. Specifically, the columns are selected according to their corresponding pheromones, and the meta-classifier is chosen at random. The classification accuracy of each configuration is computed based on Cross Validation on meta-data. Experiments on UCI datasets show the advantage of proposed method compared to several classifier and feature selection methods for ensemble systems.

Benchmark sets and landscape features are used to test algorithms and to train models to perform algorithm selection or configuration. These approaches are based on the assumption that algorithms have similar performances on problems with similar feature sets. In this paper, we test different configurations of differential evolution (DE) against the BBOB set. We then use the landscape features of those problems and a case base reasoning approach for DE configuration selection. We show that, although this method obtains good results for BBOB problems, it fails to select the best configurations when facing a new set of optimisation problems with a distinct array of landscape features. This demonstrates the limitations of the BBOB set for algorithm selection. Moreover, by examination of the relationship between features and algorithm performance, we show that there is no correlation between the feature space and the performance space. We conclude by identifying some important open questions raised by this work.

In this paper, we introduce a new stochastic Location-Allocation Problem which assumes the movement of customers over time. We call this new problem Dynamic Customer Location-Allocation Problem (DC-LAP). The problem is based on the idea that customers will change locations over a defined horizon and these changes have to be taken into account when establishing facilities to service customers demands. We generate 1440 problem instances by varying the problem parameters of movement rate which determines the possible number of times a customer will change locations over the defined period, the number of facilities and the number of customers. We propose to analyse the characteristics of the instances generated by testing a search algorithm using the stochastic dynamic evaluation (based on the replication of customer movement scenarios) and a deterministic static evaluation (based on the assumption that customer will not move over time). We show that the dynamic approach obtains globally better results, but the performances are highly related to the parameters of the problem. Moreover, the dynamic approach involves a significantly high computational overhead.

We present a new variant of the Vehicle Routing Problem based on a real industrial scenario. This VRP is dynamic and heavily constrained and uses time-windows, a heterogeneous vehicle fleet and multiple types of job. A constructive solver is developed and tested using dynamic simulation of real-world data from a leading Scottish haulier. Our experiments establish the efficiency and reliability of the method for this problem. Additionally, a methodology for evaluating policy changes through simulation is presented, showing that our technique supports operations and management. We establish that fleet size can be reduced or more jobs handled by the company.

Designing an ensemble of classifiers is one of the popular research topics in machine learning since it can give better results than using each constituent member. Furthermore, the performance of ensemble can be improved using selection or adaptation. In the former, the optimal set of base classifiers, meta-classifier, original features, or meta-data is selected to obtain a better ensemble than using the entire classifiers and features. In the latter, the base classifiers or combining algorithms working on the outputs of the base classifiers are made to adapt to a particular problem. The adaptation here means that the parameters of these algorithms are trained to be optimal for each problem. In this study, we propose a novel evolving combining algorithm using the adaptation approach for the ensemble systems. Instead of using numerical value when computing the representation for each class, we propose to use the interval-based representation for the class. The optimal value of the representation is found through Particle Swarm Optimization. During classification, a test instance is assigned to the class with the interval-based representation that is closest to the base classifiers’ prediction. Experiments conducted on a number of popular dataset confirmed that the proposed method is better than the well-known ensemble systems using Decision Template and Sum Rule as combiner, L2-loss Linear Support Vector Machine, Multiple Layer Neural Network, and the ensemble selection methods based on GA-Meta-data, META-DES, and ACO.

In this paper, we aim to develop an effective combining algorithm for ensemble learning systems. The Decision Template method, one of the most popular combining algorithms for ensemble systems, does not perform well when working on certain datasets like those having imbalanced data. Moreover, point estimation by computing the average value on the outputs of base classifiers in the Decision Template method is sometimes not a good representation, especially for skewed datasets. Here we propose to search for an optimal decision template in the combining algorithm for a heterogeneous ensemble. To do this, we first generate the base classifier by training the pre-selected learning algorithms on the given training set. The meta-data of the training set is then generated via cross validation. Using the Artificial Bee Colony algorithm, we search for the optimal template that minimizes the empirical 0–1 loss function on the training set. The class label is assigned to the unlabeled sample based on the maximum of the similarity between the optimal decision template and the sample’s meta-data. Experiments conducted on the UCI datasets demonstrated the superiority of the proposed method over several benchmark algorithms.

Ensemble selection is one of the most studied topics in ensemble learning because a selected subset of base classifiers may perform better than the whole ensemble system. In recent years, a great many ensemble selection methods have been introduced. However, many of these lack flexibility: either a fixed subset of classifiers is pre-selected for all test samples (static approach), or the selection of classifiers depends upon the performance of techniques that define the region of competence (dynamic approach). In this paper, we propose an ensemble selection method that takes into account each base classifier's confidence during classification and the overall credibility of the base classifier in the ensemble. In other words, a base classifier is selected to predict for a test sample if the confidence in its prediction is higher than its credibility threshold. The credibility thresholds of the base classifiers are found by minimizing the empirical 0–1 loss on the entire training observations. In this way, our approach integrates both the static and dynamic aspects of ensemble selection. Experiments on 62 datasets demonstrate that the proposed method achieves much better performance in comparison to some ensemble methods.

Earlier diagnosis of hepatitis B virus (HBV) related hepatocellular carcinoma (HCC) increases treatment options and survival. The aim of this study is to evaluate which factors are associated with late presentation of HBV-related HCC.This is a retrospective review of all cases of HBV-related HCC diagnosed with late-stage/incurable HCC in New Zealand between 2003 and 2017. Cases were defined as patients with a positive hepatitis B surface antigen (HBsAg), and advanced (not amenable to potentially curable treatments) HCC at initial diagnosis. Patients were categorised into four groups according to potential reasons for late presentation: no previous diagnosis of HBV infection (Group A); known HBV diagnosis but not receiving HCC surveillance (Group B); known HBV diagnosis and receiving suboptimal HCC surveillance (Group C); and known HBV diagnosis and receiving optimised HCC surveillance (Group D).A total of 368 patients were reviewed. The average age at death was 59 years, and the majority of patients were Māori (39%), Pacific (34%) or Asian (20%). The incidence of patients presenting with HBV-related advanced HCC increased from 4.5 cases to 6.3 cases per million people over the review period. Of the cases, 40% were categorised into Group A, 26% into Group B, 12% into Group C and 23% in Group D. Overall, the median survival was 138 days, and this did not change during the study period. Patients receiving optimised surveillance (Group D) survived longer (mean 469 days) than patients in Group A (90 days), Group B (145 days) or Group C (152 days) (p0.05). Patients in Group D were more likely to be treated with transarterial chemoembolisation than patients in other groups (40% vs 15%, p0.05).This study has highlighted the need for improved rates of HBV diagnosis, better follow-up of those infected and the importance of optimal HCC surveillance. In New Zealand, HBV-related HCC disproportionately affects minority ethnic groups, and given the increasing incidence, provides a potential domain to reduce health inequities.

By incorporating domain knowledge, simple greedy procedures can be defined to generate reasonably good solutions to many optimisation problems. However, such solutions are unlikely to be optimal and their quality often depends on the way the decision variables are input to the greedy method. Indirect optimisation uses meta-heuristics to optimise the input of the greedy decoders. As the performance and the runtime differ across greedy methods and meta-heuristics, deciding how to split the computational effort between the two sides of the optimisation is not trivial and can significantly impact the search. In this paper, an artificial scheduling problem is presented along with five greedy procedures, using varying levels of domain information. A methodology to compare different indirect optimisation strategies is presented using a simple Hill Climber, a Genetic Algorithm and a population-based Local Search. By assessing all combinations of meta-heuristics and greedy procedures on a range of problem instances with different properties, experiments show that encapsulating problem knowledge within greedy decoders may not always prove successful and that simpler methods can lead to comparable results as advanced ones when combined with meta-heuristics that are adapted to the problem. However, the use of efficient greedy procedures reduces the relative difference between meta-heuristics.

The purpose of this paper is two fold. First, we present a set of benchmark problems for maintenance optimisation called VMELight. This model allows the user to define the number of components in the system to maintain and a number of customisable parameters such as the failure distribution of the components, the spare part stock level and every costs associated with the preventive and corrective maintenances, unavailability and spare parts. From this model, we create a benchmark of 175 optimisation problems across different dimensions. This benchmark allows us to test the idea of using an iterated racing algorithm called IRACE based on the Friedman statistical test, to reduce the number of simulations needed to compare solutions in the population. We assess different population size and truncation rate to show that those parameters can have a strong influence on the performance of the algorithm.

The Uncapacitated Location-Allocation problem (ULAP) is a major optimisation problem concerning the determination of the optimal location of facilities and the allocation of demand to them. In this paper, we present two novel problem variants of Non-Linear ULAP motivated by a real-world problem from the telecommunication industry: Uncapacitated Location-Allocation Resilience problem (ULARP) and Uncapacitated Location-Allocation Resilience problem with Restrictions (ULARPR). Problem sizes ranging from 16 to 100 facilities by 50 to 10000 demand points are considered. To solve the problems, we explore the components and configurations of four Genetic Algorithms [1]–[3] and [4] selected from the ULAP literature. We aim to understand the contribution each choice makes to the GA performance and so hope to design an Optimal GA configuration for the novel problems. We also conduct comparative experiments with Population-Based Incremental Learning (PBIL) Algorithm on ULAP. We show the effectiveness of PBIL and GA with parameter set: random and heuristic initialisation, tournament and fined_grained tournament selection, uniform crossover and bitflip mutation in solving the proposed problems.

The service chain planning process is a critical component in the operations of companies in the service industry, such as logistics, telecoms or utilities. This process involves looking ahead over various timescales to ensure that available capacity matches the required demand whilst maximizing revenues and minimizing costs. This problem is particularly complex for companies with large, multi-skilled workforces as matching these resources to the required demand can be done in a vast number of combinations. The vastness of the problem space combined with the criticality to the business is leading to an increasing move towards automation of the process in recent years. In this paper we focus on the tactical plan where planning is occurring daily for the coming weeks, matching the available capacity to demand, using capacity levers to flex capacity to keep backlogs within target levels whilst maintaining target levels for provision of new revenues. First we describe the tactical planning problem before defining a bi-level model to search for optimal solutions to it. We show, by comparing the model results to actual planners on real world examples, that the bi-level model produces good results that replicate the planners' process whilst keeping the backlogs closer to target levels, thus providing a strong case for its use in the automation of the tactical planning process.

In this paper, we introduce a dynamic variant of the Location-Allocation problem: Dynamic Location-Allocation Problem (DULAP). DULAP involves the location of facilities to service a set of customer demands over a defined horizon. To evaluate a solution to DULAP, we propose two holistic metric approaches: Static and Dynamic Approach. In the static approach, a solution is evaluated with the assumption that customer locations and demand remain constant over a defined horizon. In the dynamic approach, the assumption is made that customer demand, and demographic pattern may change over the defined horizon. We introduce a stochastic model to simulate customer population and distribution over time. We use a Genetic Algorithm and Population-Based Incremental Learning algorithm used in previous work to find robust and satisfactory solutions to DULAP. Results show the dynamic approach of evaluating a solution finds good and robust solutions.

Significance Filarial nematode infections, caused by Wuchereria bancrofti, Brugia malayi (elephantiasis), and Onchocerca volvulus (river blindness) infect 150 million of the world’s poorest populations and cause profound disability. Standard treatments require repetitive, long-term, mass drug administrations and have failed to interrupted transmission in certain sub-Saharan African regions. A drug cure using doxycycline, which targets the essential filarial endosymbiont Wolbachia, is clinically effective but programmatically challenging to implement due to long treatment durations and contraindications. Here we provide proof-of-concept of a radical improvement of targeting Wolbachia via identification of drug synergy between the anthelmintic albendazole and antibiotics. This synergy enables the shortening of treatment duration of macrofilaricidal anti-Wolbachia based treatments from 4 wk to 7 d with registered drugs ready for clinical testing., Elimination of filariasis requires a macrofilaricide treatment that can be delivered within a 7-day period. Here we have identified a synergy between the anthelmintic albendazole (ABZ) and drugs depleting the filarial endosymbiont Wolbachia, a proven macrofilaricide target, which reduces treatment from several weeks to 7 days in preclinical models. ABZ had negligible effects on Wolbachia but synergized with minocycline or rifampicin (RIF) to deplete symbionts, block embryogenesis, and stop microfilariae production. Greater than 99% Wolbachia depletion following 7-day combination of RIF+ABZ also led to accelerated macrofilaricidal activity. Thus, we provide preclinical proof-of-concept of treatment shortening using antibiotic+ABZ combinations to deliver anti-Wolbachia sterilizing and macrofilaricidal effects. Our data are of immediate public health importance as RIF+ABZ are registered drugs and thus immediately implementable to deliver a 1-wk macrofilaricide. They also suggest that novel, more potent anti-Wolbachia drugs under development may be capable of delivering further treatment shortening, to days rather than weeks, if combined with benzimidazoles.

Significance Filarial nematode infections, caused by Wuchereria bancrofti , Brugia malayi (elephantiasis), and Onchocerca volvulus (river blindness) infect 150 million of the world’s poorest populations and cause profound disability. Standard treatments require repetitive, long-term, mass drug administrations and have failed to interrupted transmission in certain sub-Saharan African regions. A drug cure using doxycycline, which targets the essential filarial endosymbiont Wolbachia , is clinically effective but programmatically challenging to implement due to long treatment durations and contraindications. Here we provide proof-of-concept of a radical improvement of targeting Wolbachia via identification of drug synergy between the anthelmintic albendazole and antibiotics. This synergy enables the shortening of treatment duration of macrofilaricidal anti- Wolbachia based treatments from 4 wk to 7 d with registered drugs ready for clinical testing.

In this paper, we introduce a new class of optimisation problems with tunable landscape features called Interpolated Continuous Optimisation Problems (ICOPs). ICOPs are defined by a search space, a set of solutions called seeds at selected positions, and their fitnesses. The rest of the fitness landscape is interpolated from the seeds using the inverse distance weighting interpolation function. We show that by evolving the position and the fitness of the seeds, we can generate extreme problems with respect to different fitness landscape measures.

Random Key (RK) is an alternative representation for permutation problems that enables application of techniques generally used for continuous optimisation. Although the benefit of RKs to permutation optimisation has been shown, its use within Estimation of Distribution Algorithms (EDAs) has been a challenge. Recent research proposing a RK-based EDA (RK-EDA) has shown that RKs can produce competitive results with state of the art algorithms. Following promising results on the Permutation Flowshop Scheduling Problem, this paper presents an analysis of RK-EDA for optimising the total flow time. Experiments show that RK-EDA outperforms other permutation-based EDAs on instances of large dimensions. The difference in performance between RK-EDA and the state of the art algorithms also decreases when the problem difficulty increases.

The Artificial Reaction Network (ARN) is an artificial chemistry inspired by Cell Signalling Networks. Its purpose is to represent chemical circuitry and to explore the computational properties responsible for generating emergent high-level behaviour. In this paper, the design and application of ARN-based cell-like agents termed "Cytobots" are explored. Such agents provide a facility to explore the dynamics and emergent properties of multicellular systems. The Cytobot ARN is constructed by combining functional motifs found in real biochemical networks. By instantiating this ARN, multiple Cytobots are created, each of which is capable of recognising environmental patterns, stigmergic communication with others and controlling its own trajectory. Applications in biological simulation and robotics are investigated by first applying the agents to model the life-cycle phases of the cellular slime mould D. discoideum and then to simulate an oil-spill clean-up operation. The results demonstrate that an ARN-based approach provides a powerful tool for modelling multi-agent biological systems and also has application in swarm robotics.

The National Emerging Infectious Diseases Laboratories (NEIDL), Boston University, is a globally unique biocontainment research facility housing biosafety level 2 (BSL-2), BSL-3, and BSL-4 laboratories. Located in the BioSquare area at the University's Medical Campus, it is part of a national network of secure facilities constructed to study infectious diseases of major public health concern. The NEIDL allows for basic, translational, and clinical phases of research to be carried out in a single facility with the overall goal of accelerating understanding, treatment, and prevention of infectious diseases. The NEIDL will also act as a center of excellence providing training and education in all aspects of biocontainment research. Within every detail of NEIDL operations is a primary emphasis on safety and security. The ultramodern NEIDL has required a new approach to communications technology solutions in order to ensure safety and security and meet the needs of investigators working in this complex building. This article discusses the implementation of secure wireless networks and private cloud computing to promote operational efficiency, biosecurity, and biosafety with additional energy-saving advantages. The utilization of a dedicated data center, virtualized servers, virtualized desktop integration, multichannel secure wireless networks, and a NEIDL-dedicated Voice over Internet Protocol (VoIP) network are all discussed.

This paper improves a recently developed multi-objective particle swarm optimizer ([Formula: see text]) that incorporates dominance with decomposition used in the context of multi-objective optimization. Decomposition simplifies a multi-objective problem (MOP) by transforming it to a set of aggregation problems, whereas dominance plays a major role in building the leaders’ archive. [Formula: see text] introduces a new archiving technique that facilitates attaining better diversity and coverage in both objective and solution spaces. The improved method is evaluated on standard benchmarks including both constrained and unconstrained test problems, by comparing it with three state of the art multi-objective evolutionary algorithms: MOEA/D, OMOPSO, and dMOPSO. The comparison and analysis of the experimental results, supported by statistical tests, indicate that the proposed algorithm is highly competitive, efficient, and applicable to a wide range of multi-objective optimization problems.

Fitness modeling has received growing interest from the evolutionary computation community in recent years. With a fitness model, one can improve evolutionary algorithm efficiency by directly sampling new solutions, developing hybrid guided evolutionary operators or using the model as a surrogate for an expensive fitness function. This paper addresses several issues on fitness modeling of discrete functions, particularly how modeling quality and efficiency can be improved. We define the Markov network fitness model in terms of Walsh functions. We explore the relationship between the Markov network fitness model and fitness in a number of discrete problems, showing how the parameters of the fitness model can identify qualitative features of the fitness function. We define the fitness prediction correlation, a metric to measure fitness modeling capability of local and global fitness models. We use this metric to investigate the effects of population size and selection on the tradeoff between model quality and complexity for the Markov network fitness model.

The Artificial Reaction Network (ARN) is a Cell Signalling Network inspired connectionist representation belonging to the branch of A-Life known as Artificial Chemistry. Its purpose is to represent chemical circuitry and to explore computational properties responsible for generating emergent high-level behaviour associated with cells. In this paper, the computational mechanisms involved in pattern recognition and spatio-temporal pattern generation are examined in robotic control tasks. The results show that the ARN has application in limbed robotic control and computational functionality in common with Artificial Neural Networks. Like spiking neural models, the ARN can combine pattern recognition and complex temporal control functionality in a single network, however it offers increased flexibility. Furthermore, the results illustrate parallels between emergent neural and cell intelligence.

In this paper we present a method to predict service levels in utility companies, giving them advanced visibility of expected service outcomes and helping them to ensure adherence to service level agreements made to their clients. Service level adherence is one of the key targets during the service chain planning process in service industries, such as telecoms or utility companies. These specify a time limit for successful completion of a certain percentage of tasks on that service level agreement. With the increasing use of automation within the planning process, the requirement for a method to evaluate the current plan decisions effects on service level outcomes has surfaced.

The Multi-mode Resource Constrained Project Scheduling Problem (MRCPSP) has been of research interest for over two decades. The problem is composed of two interacting sub problems: mode assignment and activity scheduling. These problems cannot be solved in isolation because of the interaction that exists between them. Many evolutionary algorithms have been applied to this problem most commonly the Genetic Algorithm (GA). It has been common practice to improve the performance of the GA with some local search techniques. The Bi-population Genetic Algorithm (BPGA) is one of the most competitive GAs for solving the MRCPSP. In this paper, we improve the BPGA by hybridising it with an Estimation of Distribution Algorithm that focuses on improving how modes are generated. We also suggest improvement to the existing experimental methodology.

Critical for successful operations of service industries, such as telecoms, utility companies and logistic companies, is the service chain planning process. This involves optimizing resources against expected demand to maximize the utilization and minimize the wastage, which in turn maximizes revenue whilst minimizing the cost. This is increasingly involving the automation of the planning process. However, due to unforeseen factors, the calculated optimal allocation of resources to complete tasks often does not match up with what is actually occurring on the day. This factor highlights a requirement for a method of predicting accurately the number of tasks that will be completed given a known amount of resources and demand in order to produce a more accurate plan.

Objectives: To construct new prostate cancer staging lookup tables based on a dataset collated by the British Association of Urological Surgeons (BAUS) and to validate them and compare their predictive power with Partin tables. Patients and methods: Complete data on 1701 patients was collated between 1999 and 2008 across 57 UK centres. Lookup tables were created for prediction of pathological stage (PS) using PSA level, biopsy Gleason score (GS) and clinical stage, replicating Partin's original approach. Tables were generated using logistic regression (LR) and bootstrap resampling methods and were internally validated and externally validated using concordance indices (CI) and area under the receiver operating characteristic curve (AUROC) respectively. Results: The CI and AUROC analyses indicate that Partin tables performed poorly on UK data in comparison with US data. The UK prostate cancer tables performed better than Partin tables but the predictive power of all models was relatively poor. Conclusion: The study shows that the predictive power of Partin tables is reduced when applied to the UK population. Models generated using LR methodology have fundamental limitations, and we suggest alternative modelling methods such as Bayesian networks.

Objectives: Prediction of prostate cancer pathological stage is an essential step in a patient's pathway. It determines the treatment that will be applied further. In current practice, urologists use the pathological stage predictions provided in Partin tables to support their decisions. However, Partin tables are based on logistic regression (LR) and built from US data. Our objective is to investigate a range of both predictive methods and of predictive variables for pathological stage prediction and assess them with respect to their predictive quality based on UK data. Methods and material: The latest version of Partin tables was applied to a large scale British dataset in order to measure their performances by mean of concordance index (c-index). The data was collected by the British Association of Urological Surgeons (BAUS) and gathered records from over 1700 patients treated with prostatectomy in 57 centers across UK. The original methodology was replicated using the BAUS dataset and evaluated using concordance index. In addition, a selection of classifiers, including, among others, LR, artificial neural networks and Bayesian networks (BNs) was applied to the same data and compared with each other using the area under the ROC curve (AUC). Subsets of the data were created in order to observe how classifiers perform with the inclusion of extra variables. Finally a local dataset prepared by the Aberdeen Royal Infirmary was used to study the effect on predictive performance of using different variables. Results: Partin tables have low predictive quality (c-index=0.602) when applied on UK data for comparison on patients with organ confined and extra prostatic extension conditions, patients at the two most frequently observed pathological stages. The use of replicate lookup tables built from British data shows an improvement in the classification, but the overall predictive quality remains low (c-index=0.610). Comparing a range of classifiers shows that BNs generally outperform other methods. Using the four variables from Partin tables, naive Bayes is the best classifier for the prediction of each class label (AUC=0.662 for OC). When two additional variables are added, the results of LR (0.675), artificial neural networks (0.656) and BN methods (0.679) are overall improved. BNs show higher AUCs than the other methods when the number of variables raises Conclusion: The predictive quality of Partin tables can be described as low to moderate on UK data. This means that following the predictions generated by Partin tables, many patients would received an inappropriate treatment, generally associated with a deterioration of their quality of life. In addition to demographic differences between UK and the original US population, the methodology and in particular LR present limitations. BN represents a promising alternative to LR from which prostate cancer staging can benefit. Heuristic search for structure learning and the inclusion of more variables are elements that further improve BN models quality.

Transient ischaemic attack (TIA) and stroke are clinical syndromes characterised by acute neurological deficits with vascular causes. People experiencing TIA or a first stroke are at significant risk of subsequent stroke. Risk factors have been identified and include factors associated with lifestyle such as tobacco use, diet, obesity, alcohol consumption, physical activity and stress. Targeted therapeutic interventions have the potential to reduce the burden of stroke substantially. The aim of this article is to provide an overview of the evidence relating to lifestyle risk factors for stroke. Health promotion theories and intervention techniques that nurses can use to address lifestyle behaviour change following stroke will also be discussed. Authors

The challenges of solving problems naturally represented as permutations by Estimation of Distribution Algorithms (EDAs) have been a recent focus of interest in the evolutionary computation community. One of the most common alternative representations for permutation based problems is the Random Key (RK), which enables the use of continuous approaches for this problem domain. However, the use of RK in EDAs have not produced competitive results to date and more recent research on permutation based EDAs have focused on creating superior algorithms with specially adapted representations. In this paper, we present RK-EDA; a novel RK based EDA that uses a cooling scheme to balance the exploration and exploitation of a search space by controlling the variance in its probabilistic model. Unlike the general performance of RK based EDAs, RK-EDA is actually competitive with the best EDAs on common permutation test problems: Flow Shop Scheduling, Linear Ordering, Quadratic Assignment, and Travelling Salesman Problems.

This paper presents a Markov random field (MRF) approach to estimating and sampling the probability distribution in populations of solutions. The approach is used to define a class of algorithms under the general heading distribution estimation using Markov random fields (DEUM). DEUM is a subclass of estimation of distribution algorithms (EDAs) where interaction between solution variables is represented as an undirected graph and the joint probability of a solution is factorized as a Gibbs distribution derived from the structure of the graph. The focus of this paper will be on describing the three main characteristics of DEUM framework, which distinguishes it from the traditional EDA. They are: 1) use of MRF models, 2) fitness modeling approach to estimating the parameter of the model and 3) Monte Carlo approach to sampling from the model.

The need to assess internet performance from the user’s perspective grows, as does the interest in deployment of Large-Scale Measurement Platforms (LMAPs). The potential of these platforms as a real-time network diagnostic tool is limited by the volume, velocity and variety of the data they generated. Fusing this data from multiple sources and generating a single piece of coherent information about the state of the network would increase the efficiency of network monitoring. The current practice of visually analysing LMAPs’ data stream would certainly benefit from having automatically generated notifications in a timely manner alerting human controllers to the network’s conditions of interest. This paper proposed a data fusion framework for LMAPs that makes use of mathematical distribution based sensors to generate probabilistic sensor outputs which are fused using a Dempster- Shafer Theory.

Hepatic venous outflow obstruction (HVOO) is a rare but serious complication in liver transplantation (LT).We conducted a retrospective analysis of HVOO with venography and gradient measurement in consecutive LT from a single centre.Five hundred and six LTs were performed in 486 patients with a median age of 49 years (range 3 months to 71 years). Nineteen (3.8%) cases of HVOO were identified. Diagnosis was confirmed at a median of 26 days post-LT (1-2312). The incidence fell from 5.5% in the first 253 LT, to 2.0% in the second 253 (P = 0.03). Seventeen were due to narrowing at the anastomosis and two cases were due to thrombosis. In adult patients, reconstruction of the supra-hepatic donor inferior vena cava (IVC) onto two veins versus modified 2-3 hepatic veins did not alter the likelihood of HVOO. 17/19 cases were managed successfully by stenting or venoplasty. Two paediatric patients with early onset HVOO had attempted surgical thrombectomy, one was successful and the other required retransplantation.The incidence of HVOO appears to fall with increasing experience and does not appear to be related to the number of veins the donor IVC is anastomosed to in adult recipients.

The Multi-mode Resource Constrained Project Scheduling Problem (MRCPSP) is composed of two interacting sub- problems which are the mode assignment problem and the scheduling problem. Solving these sub-problems in isola- tion pose a challenge due to the interaction that exists be- tween them. We present a unified approach for applying a combination of algorithms to the sub-problems of the MR- CPSP. The use of Genetic algorithms and Estimation of Distribution Algorithms aims to exploit efficiently and syn- chronously the distinct search spaces presented by the two sub-problems.

We present an approach to generating problems of variable difficulty based on the well-known Proximate Optimality Principle (POP), often paraphrased as "similar solutions have similar fitness". We explore definitions of this concept in terms of metrics in objective space and in representation space and define POP in terms of coherence of these metrics. We hypothesise that algorithms will perform well when the neighbourhoods they explore in representation space are coherent with the natural metric induced by fitness on objective space. We develop an explicit method of problem generation which creates bit string problems where the natural fitness metric is coherent or anti-coherent with Hamming neighbourhoods. We conduct experiments to show that coherent problems are easy whereas anti-coherent problems are hard for local hill climbers using the Hamming neighbourhoods.

Structural learning of Bayesian networks is a very expensive task even when sacrifying the optimality of the result. Because of that, there are some proposals aimed at obtaining relative-quality solutions in short times. One of them, namely Chain-ACO, searches an ordering among all variables with Ant Colony Optimization and a chain-structured surrogate model, and then uses this ordering to build a Bayesian network by means of the well-known K2 algorithm.This work is based on Chain-ACO. We evaluate the impact of using a tree-structured surrogate model instead of a chain to evaluate orderings during the search. Moreover, we propose a variation of the way K2 builds the network, which consists of allowing some changes in the positions of the variables whenever they such changes not produce a cycle. This modification of the process may improve the score of the final network, without (almost) any additional cost.

Metaheuristics assume some kind of coherence between decision and objective spaces. Estimation of Distribution algorithms approach this by constructing an explicit probabilistic model of high fitness solutions, the structure of which is intended to reflect the structure of the problem. In this context, “structure” means the dependencies or interactions between problem variables in a probabilistic graphical model. There are many approaches to discovering these dependencies, and existing work has already shown that often these approaches discover “unnecessary” elements of structure - that is, elements which are not needed to correctly rank solutions. This work performs an exhaustive analysis of all 2 and 3 bit problems, grouped into classes based on mononotic invariance. It is shown in [1] that each class has a minimal Walsh structure that can be used to solve the problem. We compare the structure discovered by different structure learning approaches to the minimal Walsh structure for each class, with summaries of which interactions are (in)correctly identified. Our analysis reveals a large number of symmetries that may be used to simplify problem solving. We show that negative selection can result in improved coherence between discovered and necessary structure, and conclude with some directions for a general programme of study building on this work.