Search

Trust is a major determinant of acceptance of an autonomous vehicle (AV), and a lack of appropriate trust could prevent drivers and society in general from taking advantage of such technology. This paper makes a new attempt to explore the effects of personalised AVs as a novel approach to the cognitive underpinnings of drivers’ trust in AVs. The personalised AV system is able to identify the driving behaviours of users and thus adapt the driving style of the AV accordingly. A prototype of a personalised AV was designed and evaluated in a lab-based experimental study of 36 human drivers, which investigated the impact of the personalised AV on user trust when compared with manual human driving and non-personalised AVs. The findings show that a personalised AV appears to be significantly more reliable through accepting and understanding each driver’s behaviour, which could thereby increase a user’s willingness to trust the system. Furthermore, a personalised AV brings a sense of familiarity by making the system more recognisable and easier for users to estimate the quality of the automated system. Personalisation parameters were also explored and discussed to support the design of AV systems to be more socially acceptable and trustworthy.

Saliency detection aims to automatically highlight the most important area in an image. Traditional saliency detection methods based on absorbing Markov chain only take into account boundary nodes and often lead to incorrect saliency detection when the boundaries have salient objects. In order to address this limitation and enhance saliency detection performance, this paper proposes a novel task-independent saliency detection method based on the bidirectional absorbing Markov chains that jointly exploits not only the boundary information but also the foreground prior and background prior cues. More specifically, the input image is first segmented into number of superpixels, and the four boundary nodes (duplicated as virtual nodes) are selected. Subsequently, the absorption time upon transition node’s random walk to the absorbing state is calculated to obtain the foreground possibility. Simultaneously, foreground prior (as the virtual absorbing nodes) is used to calculate the absorption time and get the background possibility. In addition, the two aforementioned results are fused to form a combined saliency map which is further optimized by using a cost function. Finally, the superpixel-level saliency results are optimized by a regularized random walks ranking model at multi-scale. The comparative experimental results on four benchmark datasets reveal superior performance of our proposed method over state-of-the-art methods reported in the literature. The experiments show that the proposed method is efficient and can be applicable to the bottom-up image saliency detection and other visual processing tasks.

The elasticity in cloud is essential to the effective management of computational resources as it enables readjustment at runtime to meet application demands. Over the years, researchers and practitioners have proposed many auto-scaling solutions using versatile techniques ranging from simple if-then-else based rules to sophisticated optimisation, control theory and machine learning based methods. However, despite an extensive range of existing elasticity research, the aim of implementing an efficient scaling technique that satisfies the actual demands is still a challenge to achieve. The existing methods suffer from issues like: (1) the lack of adaptability and static scaling behaviour whilst considering completely fixed approaches; (2) the burden of additional computational overhead, the inability to cope with the sudden changes in the workload behaviour and the preference of adaptability over reliability at runtime whilst considering the fully dynamic approaches; and (3) the lack of considering uncertainty aspects while designing auto-scaling solutions. In this paper, we aim to address these issues using a holistic biologically-inspired feedback switch controller. This method utilises multiple controllers and a switching mechanism, implemented using fuzzy system, that realises the selection of suitable controller at runtime. The fuzzy system also facilitates the design of qualitative elasticity rules. Furthermore, to improve the possibility of avoiding the oscillatory behaviour (a problem commonly associated with switch methodologies), this paper integrates a biologically-inspired computational model of action selection. Lastly, we identify seven different kinds of real workload patterns and utilise them to evaluate the performance of the proposed method against the state-of-the-art approaches. The obtained computational results demonstrate that the proposed method results in achieving better performance without incurring any additional cost in comparison to the state-of-the-art approaches.

The ABCD rule is a simple framework that physicians, novice dermatologists and non-physicians can use to learn about the features of melanoma in its early curable stage, enhancing thereby the early detection of melanoma. Since the interpretation of the ABCD rule traits is subjective, different solutions have been proposed in literature to tackle such subjectivity and provide objective evaluations to the different traits. This paper reviews the main contributions in literature towards automating asymmetry, border irregularity, color variegation and diameter, where the different methods involved have been highlighted. This survey could serve as an essential reference for researchers interested in automating the ABCD rule.

The main objective of this work is to improve the quality and transparency of the medical text classification solutions. Conventional text classification methods provide users with only a restricted mechanism (based on frequency) for selecting features. In this paper, a three-stage hybrid method combining the gated attention-based bi-directional Long Short-Term Memory (ABLSTM) and the regular expression based classifier is proposed for medical text classification tasks. The bi-directional Long Short-Term Memory (LSTM) architecture with an attention layer allows the network to weigh words according to their perceived importance and focus on crucial parts of a sentence. Feature words (or keywords) extracted by ABLSTM model are utilized to guide the regular expression rule construction. Our proposed approach leverages the advantages of both the interpretability of rule-based algorithms and the computational power of deep learning approaches for a production-ready scenario. Experimental results on real-world medical online query data clearly validate the superiority of our system in selecting domain-specific and topic-related features. Results show that the proposed approach achieves an accuracy of 0.89 and an F 1 -score of 0.92 respectively. Furthermore, our experimentation also illustrates the versatility of regular expressions as a user-level tool for focusing on desired patterns and providing interpretable solutions for human modification.

Skin lesion border irregularity, which represents the B feature in the ABCD rule, is considered one of the most significant factors in melanoma diagnosis. Since signs that clinicians rely on in melanoma diagnosis involve subjective judgment including visual signs such as border irregularity, this deems it necessary to develop an objective approach to finding border irregularity. Increased research in neural networks has been carried out in recent years mainly driven by the advances of deep learning. Artificial neural networks (ANNs) or multilayer perceptrons have been shown to perform well in supervised learning tasks. However, such networks usually don't incorporate information pertaining the ambiguity of the inputs when training the network, which in turn could affect how the weights are being updated in the learning process and eventually degrading the performance of the network when applied on test data. In this paper, we propose a fuzzy multilayer perceptron (F-MLP) that takes the ambiguity of the inputs into consideration and subsequently reduces the effects of ambiguous inputs on the learning process. A new optimization function, the fuzzy gradient descent, has been proposed to reflect those changes. Moreover, a type-II fuzzy sigmoid activation function has also been proposed which enables finding the range of performance the fuzzy neural network is able to attain. The fuzzy neural network was used to predict the skin lesion border irregularity, where the lesion was firstly segmented from the skin, the lesion border extracted, border irregularity measured using a proposed measure vector, and using the extracted border irregularity measures to train the neural network. The proposed approach outperformed most of the state-of-the-art classification methods in general and its standard neural network counterpart in particular. However, the proposed fuzzy neural network was more time-consuming when training the network.

Pneumoperitoneum, the presence of air within the peritoneal cavity, is a comparatively rare but potentially urgent critical finding in patients presenting with acute abdominal pain. When prior laparoscopic treatment can be ruled out as a cause, it can indicate perforation of the wall of a hollow organ, which typically necessitates immediate surgery. Computed tomography (CT) is the gold standard for detecting free intra-abdominal air, yet subtle cases are easy to miss. More crucially though, if there is no initial suspicion of pneumoperitoneum, the scans may not be read immediately as other emergency patients take precedence. Therefore, fully automatic detection would provide a direct clinical benefit. In this work, an algorithm for this purpose is proposed which follows a sliding-window approach and has a deep-learning based classifier at its core. In addition to the baseline method, variants that rely on multi-scale inputs and recurrent layers to increase robustness are presented. In a five-fold cross validation on the training data, consisting in abdominal CT scans of 110 affected patients and 29 controls, our method achieved an area under the receiver-operating characteristic curve of 89% for case-level classification. Due to its high specificity at reasonable detection rates, it shows potential for use in triage, where false alerts are considered particularly harmful as they may disrupt the clinical workflow.

Small angle X-ray scattering (SAXS) is widely used as an efficient method to analysis the structural changes. Thus, the aim of this mini-review was to summarize important information about performing SAXS technique. For more clarification, a brief introduction of the fundamental history, scattering theory, and essential structure of SAXS were presented at first. But the main focus was placed on the application of SAXS for structural analysis studies, including carbohydrate polymers, protein, and synthetic compounds. Additionally, the simultaneous performance of SAXS with other instruments was addressed to show the potential application value of SAXS technique in structural analysis field. Furthermore, the differences between SAXS and other similar techniques, including synchrotron X-ray diffraction (SXD), wide-angle X-ray scattering (WAXS), scanning Electronic Microscopy (SEM), and wide-angle X-ray diffraction (WAXD), were discussed to save time and money for studies on structural analysis. Moreover, the practical points and future perspectives of utilizing SAXS technique were put forwards based on the diagnostic vision on the development direction of SAXS technique.

The aim of the current work was to develop a novel method to model and quantitatively determine cooking doneness via integrating sensory evaluation and kinetics based on the maturity value (M value) which was redefined. The well-done food was first selected from a series of samples with different M values by sensory evaluation, the average termination maturity values (AMT values) were obtained in accordance with the weighted M values of the selected doneness samples. Among, the changes of M values were assumed to be accorded with the first-order reaction kinetic model and a specific zM value was set as well. The zM value was then obtained due to the rationality of the hypothesis, which was validated by rigorous data analysis. Results showed that maturity time values (MT values) were existing and stable for specific types of materials and a specific population. Quantitative determination of the degree of doneness has profound significance in industrial production.

Social media hold valuable, vast and unstructured information on public opinion that can be utilized to improve products and services. The automatic analysis of such data, however, requires a deep understanding of natural language. Current sentiment analysis approaches are mainly based on word co-occurrence frequencies, which are inadequate in most practical cases. In this work, we propose a novel hybrid framework for concept-level sentiment analysis in Persian language, that integrates linguistic rules and deep learning to optimize polarity detection. When a pattern is triggered, the framework allows sentiments to flow from words to concepts based on symbolic dependency relations. When no pattern is triggered, the framework switches to its subsymbolic counterpart and leverages deep neural networks (DNN) to perform the classification. The proposed framework outperforms state-of-the-art approaches (including support vector machine, and logistic regression) and DNN classifiers (long short-term memory, and Convolutional Neural Networks) with a margin of 10-15% and 3-4% respectively, using benchmark Persian product and hotel reviews corpora., Accepted in Neurocomputing, Demo available at: https://cogbid.napier.ac.uk/demo/persian-sentiment-analysis/

Lesion border detection is considered a crucial step in diagnosing skin cancer. However, performing such a task automatically is challenging due to the low contrast between the surrounding skin and lesion, ambiguous lesion borders, and the presence of artifacts such as hair. In this paper we propose a two-stage approach for skin lesion border detection: (i) segmenting the skin lesion dermoscopy image using U-Net, and (ii) extracting the edges from the segmented image using a novel approach we call FuzzEdge. The proposed approach is compared with another published skin lesion border detection approach, and the results show that our approach performs better in detecting the main borders of the lesion and is more robust to artifacts that might be present in the image. The approach is also compared with the manual border drawings of a dermatologist, resulting in an average Dice similarity of 87.7%.

Image segmentation is considered a crucial step in automatic dermoscopic image analysis as it affects the accuracy of subsequent steps. The huge progress in deep learning has recently revolutionized the image recognition and computer vision domains. In this paper, we compare a supervised deep learning based approach with an unsupervised deep learning based approach for the task of skin lesion segmentation in dermoscopy images. Results show that, by using the default parameter settings and network configurations proposed in the original approaches, although the unsupervised approach could detect fine structures of skin lesions in some occasions, the supervised approach shows much higher accuracy in terms of Dice coefficient and Jaccard index compared to the unsupervised approach, resulting in 77.7% vs. 40% and 67.2% vs. 30.4%, respectively. With a proposed modification to the unsupervised approach, the Dice and Jaccard values improved to 54.3% and 44%, respectively.

The robot detection and maintenance routine of high-voltage cables are of great significance to the normal operation of electrical power system. Aiming at the problems of poor obstacle-crossing capability and insufficient drive capability to the inspection robot at present, a three-module rotating-finger cable inspection robot is developed, which can move over a long distance on the cable. The robot is composed of three standard rotating-finger modules in series, each of which can cross obstacles via staggered rapid movement of the rotating-finger. According to the structure and movement characteristics of the modular robot, the static model of the robot under various obstacle-crossing attitudes is established, and the detailed static analysis of the movement process is carried out to obtain two relationships: the relationship among drive force, friction force, and permissible gradient, the relationship between robot configuration and obstacle-crossing attitude. The obstacle-crossing movement is optimized to realize the high-efficiency obstacle crossing. The correctness of the above analysis is verified by experiments and motion simulation.

Elasticity enables cloud customers to enrich their applications to dynamically adjust underlying cloud resources. Over the past, a plethora of techniques have been introduced to implement elasticity. Control theory is one such technique that offers a systematic method to design feedback controllers to perform elasticity. Many of the available such approaches utilise the single system model. However, for cloud applications that are subject to time varying workload conditions (e.g., e-commerce applications), it becomes difficult for such approaches to perform effectively at all times to achieve the desired performance goals. This paper exploits the novel use of a recently developed multi-controller based approach, where each controller is designed specifically for different operating conditions. Moreover, the use of fuzzy logic is exploited for the selection of a suitable controller at runtime. Initial results in comparison with the conventional feedback control approach demonstrate better achievement of the performance goals.

The lucrative features of cloud computing such as pay-as-you-go pricing model and dynamic resource provisioning (elasticity) attract clients to host their applications over the cloud to save up-front capital expenditure and to reduce the operational cost of the system. However, the efficient management of hired computational resources is a challenging task. Over the last decade, researchers and practitioners made use of various techniques to propose new methods to address cloud elasticity. Amongst many such techniques, control theory emerges as one of the popular methods to implement elasticity. A plethora of research has been undertaken on cloud elasticity including several review papers that summarise various aspects of elasticity. However, the scope of the existing review articles is broad and focused mostly on the high-level view of the overall research works rather than on the specific details of a particular implementation technique. While considering the importance, suitability and abundance of control theoretical approaches, this paper is a step forward towards a stand-alone review of control theoretic aspects of cloud elasticity. This paper provides a detailed taxonomy comprising of relevant attributes defining the following two perspectives, i.e., control-theory as an implementation technique as well as cloud elasticity as a target application domain. We carry out an exhaustive review of the literature by classifying the existing elasticity solutions using the attributes of control theoretic perspective. The summarized results are further presented by clustering them with respect to the type of control solutions, thus helping in comparison of the related control solutions. In last, a discussion summarizing the pros and cons of each type of control solutions are presented. This discussion is followed by the detail description of various open research challenges in the field.

Vehicle scheduling plays a profound role in public transit planning. Traditional approaches for the Vehicle Scheduling Problem (VSP) are based on a set of predetermined trips in a given timetable. Each trip contains a departure point/time and an arrival point/time whilst the trip time (i.e. the time duration of a trip) is fixed. Based on fixed durations, the resulting schedule is hard to comply with in practice due to the variability of traffic and driving conditions. To enhance the robustness of the schedule to be compiled, the VSP based on stochastic trip times instead of fixed ones is studied. The trip times follow the probability distributions obtained from the data captured by Automatic Vehicle Locating (AVL) systems. A network flow model featuring the stochastic trips is devised to better represent this problem, meanwhile the compatibility of any pair of trips is redefined based on trip time distributions instead of fixed values as traditionally done. A novel probabilistic model of the VSP is proposed with the objectives of minimizing the total cost and maximizing the on-time performance. Experiments show that the probabilistic model may lead to more robust schedules without increasing fleet size.

Skin lesion border irregularity is considered an important clinical feature for the early diagnosis of melanoma, representing the B feature in the ABCD rule. In this article we propose an automated approach for skin lesion border irregularity detection. The approach involves extracting the skin lesion from the image, detecting the skin lesion border, measuring the border irregularity, training a Convolutional Neural Network and Gaussian naive Bayes ensemble, to the automatic detection of border irregularity, which results in an objective decision on whether the skin lesion border is considered regular or irregular. The approach achieves outstanding results, obtaining an accuracy, sensitivity, specificity, and F-score of 93.6%, 100%, 92.5% and 96.1%, respectively.

Asymmetry, color variegation and diameter are considered strong indicators of malignant melanoma. The subjectivity inherent in the first two features and the fact that 10% of melanomas tend to be missed in the early diagnosis due to having a diameter less than 6mm, deem it necessary to develop an objective computer vision system to evaluate these criteria and aid in the early detection of melanoma which could eventually lead to a higher 5-year survival rate. This paper proposes an approach for evaluating the three criteria objectively, whereby we develop a measure to find asymmetry with the aid of a decision tree which we train on the extracted asymmetry measures and then use to predict the asymmetry of new skin lesion images. A range of colors that demonstrate the suspicious colors for the color variegation feature have been derived, and Feret’s diameter has been utilized to find the diameter of the skin lesion. The decision tree is 80% accurate in determining the asymmetry of skin lesions, and the number of suspicious colors and diameter values are objectively identified.

The successful usage of fuzzy systems can be seen in many application domains owing to their capabilities to model complex systems by exploiting knowledge of domain experts. Their accuracy and performance are, however, primarily dependent on the design of its membership functions and control rules. The commonly employed technique to design membership functions is to exploit the knowledge of domain experts. However, in certain application domains, the knowledge of domain experts are limited and therefore, cannot be relied upon. Alternatively, optimization techniques such as genetic algorithms are utilized to optimize the various design parameters of fuzzy systems. In this paper, we report a case study of optimizing the membership functions of a fuzzy system using genetic algorithm, which is an important part of our recently developed cloud elasticity framework. This work aims to improve the overall performance of the framework. Results obtained from this research work demonstrate performance improvement in comparison with our previous experimental settings.

This paper presents an adaptive evolutionary approach incorporating a hybrid genetic algorithm (GA) for public transport crew scheduling problems, which are well-known to be NP-hard. To ensure the search efficiency, a suitable chromosome representation has to be determined first. Unlike a canonical GA for crew scheduling where the chromosome length is fixed, the chromosome length in the proposed approach may vary adaptively during the iterative process, and its initial value is elaborately designated as the lower bound of the number of shifts to be used in an unachievable optimal solution. Next, the hybrid GA with such a short chromosome length is employed to find a feasible schedule. During the GA process, the adaptation on chromosome lengths is achieved by genetic operations of crossover and mutation with removal and replenishment strategies aided by a simple greedy algorithm. If a feasible schedule cannot be found when the GA’s termination condition is met, the GA will restart with one more gene added. The above process is repeated until a feasible solution is found. Computational experiments based on 11 real-world crew scheduling problems in China show that, compared to a fuzzy GA known to be well performed for crew scheduling, better solutions are found for all the testing problems. Moreover, the algorithm works fast, has achieved results close to the lower bounds obtained by a standard linear programming solver in terms of the number of shifts, and has much potential for future developments.

Cloud elasticity augments applications to dynamically adapt to changes in demand by acquiring or releasing computational resources on the fly. Recently, we developed a framework for cloud elasticity utilizing multiple feedback controllers simultaneously, wherein, each controller determines the scaling action with different intensity, and the selection of an appropriate controller is realized with a fuzzy inference system. In this paper, we aim to identify the similarities between cloud elasticity and action selection mechanism in the animal brain. We treat each controller in our previous framework as an action, and propose a novel bioinspired, soft switching approach. The proposed methodology integrates a basal ganglia computational model as an action selection mechanism. Initial experimental results demonstrate the improved potential of the basal ganglia-based approach by enhancing the overall system performance and stability.

For the purpose of investigating the effect of enzyme concentration (EC), barrel temperature (BT), moisture content (MC), and screw speed (SS) on processing parameters (product temperature, die pressure and special mechanical energy (SME)) and product responses (extent of gelatinization (GE), retention rate of total phenolic content (TPC-RR)), rice flour extruded with thermostable α-amylase was analyzed by response surface methodology. Stepwise regression models were computed to generate response surface and contour plots, revealing that both TPC-RR and GE increased as increasing MC while expressed different sensitivities to BT during enzymatic extrusion. Phenolics preservation was benefited from low SME. According to multiple-factor optimization, the conditions required to obtain the target SME (10kJ/kg), GE (100%) and TPC-RR (85%) were: EC=1.37‰, BT=93.01°C, MC=44.30%, and SS=171.66rpm, with the actual values (9.49kJ/kg, 99.96% and 87.10%, respectively) showing a good fit to the predicted values.

A hyper-heuristic often represents a heuristic search method that operates over a space of heuristic rules. It can be thought of as a high level search methodology to choose lower level heuristics. Nearly 200 papers on hyper-heuristics have recently appeared in the literature. A common theme in this body of literature is an attempt to solve the problems in hand in the following way: at each decision point, first employ the chosen heuristic(s) to generate a solution, then calculate the objective value of the solution by taking into account all the constraints involved. However, empirical studies from our previous research have revealed that, under many circumstances, there is no need to carry out this costly 2-stage determination and evaluation at all times. This is because many problems in the real world are highly constrained with the characteristic that the regions of feasible solutions are rather scattered and small. Motivated by this observation and with the aim of making the hyper-heuristic search more efficient and more effective, this paper investigates two fundamentally different data mining techniques, namely artificial neural networks and binary logistic regression. By learning from examples, these techniques are able to find global patterns hidden in large data sets and achieve the goal of appropriately classifying the data. With the trained classification rules or estimated parameters, the performance (i.e. the worth of acceptance or rejection) of a resulting solution during the hyper-heuristic search can be predicted without the need to undertake the computationally expensive 2-stage of determination and calculation. We evaluate our approaches on the solutions (i.e. the sequences of heuristic rules) generated by a graph-based hyper-heuristic proposed for exam timetabling problems. Time complexity analysis demonstrates that the neural network and the logistic regression method can speed up the search significantly. We believe that our work sheds light on the development of more advanced knowledge-based decision support systems.

Numerous papers based on various search methods across a wide variety of applications have appeared in the literature over recent years. Most of these methods apply the following same approach to address the problems at hand: at each iteration of the search, they first apply their search methods to generate new solutions, then they calculate the objective values (or costs) by taking some constraints into account, and finally they use some strategies to determine the acceptance or rejection of these solutions based upon the calculated objective values. However, the premise of this paper is that calculating the exact objective value of every resulting solution is not a must, particularly for highly constrained problems where such a calculation is costly and the feasible regions are small and disconnected. Furthermore, we believe that for newly-generated solutions, evaluating the quality purely by their objective values is sometimes not the most efficient approach. In many combinatorial problems, there are poor-cost solutions where possibly just one component is misplaced and all others work well. Although these poor-cost solutions can be the intermediate states towards the search of a high quality solution, any cost-oriented criteria for solution acceptance would deem them as inferior and consequently probably suggest a rejection. To address the above issues, we propose a pattern recognition-based framework with the target of designing more intelligent and more flexible search systems. The role of pattern recognition is to classify the quality of resulting solutions, based on the solution structure rather than the solution cost. Hence, the general contributions of this work are in the line of "insights" and recommendations. Two real-world cases of the assignment problem, i.e. the hospital personnel scheduling and educational timetabling, are used as the case studies. For each case, we apply neural networks as the tool for pattern recognition. In addition, we present our theoretical and experimental results in terms of runtime speedup.

In this paper we present a novel Case-Based Reasoning (CBR) system called CABAROST (CAsed-BAsed ROSTering) which was developed for personnel scheduling problems. CBR is used to capture and store examples of personnel manager behaviour which are then used to solve future problems. Previous examples of constraint violations in schedules and the repairs that were used to solve the violations are stored as cases. The sequence in which violations are repaired can have a great impact on schedule quality. A novel memetic algorithm is proposed which evolves good quality sequences of repairs generated by CABAROST. The algorithm was tested on instances of the real-world nurse rostering problem at the Queens Medical Centre NHS Trust in Nottingham.

Clinical Decision Support (CDS) aids in early diagnosis of liver cancer, a potentially fatal disease prevalent in both developed and developing countries. Our research aims to develop a robust and intelligent clinical decision support framework for disease management of cancer based on legacy Ultrasound (US) image data collected during various stages of liver cancer. The proposed intelligent CDS framework will automate real-time image enhancement, segmentation, disease classification and progression in order to enable efficient diagnosis of cancer patients at early stages. The CDS framework is inspired by the human interpretation of US images from the image acquisition stage to cancer progression prediction. Specifically, the proposed framework is composed of a number of stages where images are first acquired from an imaging source and pre-processed before running through an image enhancement algorithm. The detection of cancer and its segmentation is considered as the second stage in which different image segmentation techniques are utilized to partition and extract objects from the enhanced image. The third stage involves disease classification of segmented objects, in which the meanings of an investigated object are matched with the disease dictionary defined by physicians and radiologists. In the final stage; cancer progression, an array of US images is used to evaluate and predict the future stages of the disease. For experiment purposes, we applied the framework and classifiers to liver cancer dataset for 200 patients. Class distributions are 120 benign and 80 malignant in this dataset.

Service network design under uncertainty is fundamentally crucial for all freight transportation companies. The main challenge is to strike a balance between two conflicting objectives: low network setup costs and low expected operational costs. Together these have a significant impact on the quality of freight services. Increasing redundancy at crucial network links is a common way to improve network flexibility. However, in a highly uncertain environment, a single predefined network is unlikely to suit all possible future scenarios, unless it is prohibitively costly. Hence, rescheduling is often an effective alternative. In this paper, we proposed a new stochastic freight service network design model with vehicle rerouting options. The pro- posed model explicitly introduces a set of integer variables for vehicle rerouting in the second stage of the stochastic program. Although computationally more expensive, the resultant model provides more options (i.e. rerouting) and flexibility for planners to deal with uncertainties more effectively. The new model was tested on a set of instances adapted from the literature and its performance and characteristics are studied through both comparative studies and detailed analyses at the solution structure level. Implications for practical applications are discussed and further research directions are also provided.

Conditional value at risk (CVaR) is a widely used risk assessment technique. This paper proposes a new CVaR called credibilistic CVaR, which extend the tradition CVaR to fuzzy environment. The theoretical properties of credibilistic CVaR are given in this paper. Finally, trianguilar, trapezoidal and normal fuzzy variables are used to illustrate the applicability and feasibility of credibilistic CVaR.

Predicting the result of a football game is challenging due to the complexity and uncertainties of many possible influencing factors involved. Genetic Programming (GP) has been shown to be very successful at evolving novel and unexpected ways of solving problems. In this work, we apply GP to the problem of predicting the outcomes of English Premier League games with the result being either win, lose or draw. We select 25 features from each game as the inputs to our GP system, which will then generate a function to predict the result. The experimental test on the prediction accuracy of a single GP-generated function is promising. One advantage of our GP system is, by implementing different runs or using different settings, it can generate as many high quality functions as we want. It has been showed that combining the decisions of a number of classifiers can provide better results than a single one. In this work, we combine 43 different GP-generated functions together and achieve significantly improved system performance.

We show a frequency tunable perfect absorber in visible and near-infrared regimes based on the vanadium dioxide (VO2) phase transition with a wide tuning capability typical of asymmetric Fabry–Perot (FP) cavities, comprising only an unpatterned, ultrathin (∼λ/15) film of VO2 deposited on a metal-reflecting substrate. VO2 undergoes a structural transition from an insulating phase (i−VO2) to a metallic phase (m−VO2) at 68°C. A perfect absorption wavelength can be dynamically tuned over a wide wavelength range over 175 nm (from 905 to 730 nm in the measured spectrum) in visible and near-infrared regimes by controlling the temperature. More importantly, its absorption peaks become even stronger during the process of increasing temperature (from 96.8% at 905 nm to 98.4% at 730 nm). The frequency tunable absorption peaks were explained because both indices of i−VO2 and m−VO2 are very close to the maximum absorption point in n−k parameter space.

This paper presents a new class of intelligent systems, called Evolutionary Ruin and Stochastic Recreate, that can learn and adapt to the changing enviroment. It improves the original Ruin and Recreate principle’s performance by incorporating an Evolutionary Ruin step which implements evolution within a single solution. In the proposed approach, a cycle of Solution Decomposition, Evolutionary Ruin and Stochastic Recreate continues until stopping conditions are reached. The Solution Decomposition step first uses some domain knowledge to break a solution down into its components and assign a score to each. The Evolutionary Ruin step then applies two operators (namely Selection and Mutation) to destroy a certain fraction of the entire solution. After the above steps, an input solution becomes partial and thus the resulting partial solution needs to be repaired. The repair is carried out by using the Stochastic Recreate step to reintroduce the removed items in a specific way (somewhat stochastic in order to have a better chance to jump out of the local optima), and then ask the underlying improvement heuristic whether this move will be accepted. These three steps are executed in sequence until a specific stopping condition is reached. Therefore, optimisation is achieved by solution disruption, iterative improvement and a stochastic constructive repair process performed within. Encouraging experimental results on exam timetabling problems are reported.

Squeaky wheel optimization (SWO) is a relatively new metaheuristic that has been shown to be effective for many real-world problems. At each iteration SWO does a complete construction of a solution starting from the empty assignment. Although the construction uses information from previous iterations, the complete rebuilding does mean that SWO is generally effective at diversification but can suffer from a relatively weak intensification. Evolutionary SWO (ESWO) is a recent extension to SWO that is designed to improve the intensification by keeping the good components of solutions and only using SWO to reconstruct other poorer components of the solution. In such algorithms a standard challenge is to understand how the various parameters affect the search process. In order to support the future study of such issues, we propose a formal framework for the analysis of ESWO. The framework is based on Markov chains, and the main novelty arises because ESWO moves through the space of partial assignments. This makes it significantly different from the analyses used in local search (such as simulated annealing) which only move through complete assignments. Generally, the exact details of ESWO will depend on various heuristics; so we focus our approach on a case of ESWO that we call ESWO-II and that has probabilistic as opposed to heuristic selection and construction operators. For ESWO-II, we study a simple problem instance and explicitly compute the stationary distribution probability over the states of the search space. We find interesting properties of the distribution. In particular, we find that the probabilities of states generally, but not always, increase with their fitness. This nonmonotonocity is quite different from the monotonicity expected in algorithms such as simulated annealing.

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

Nurse rostering is a complex scheduling problem that affects hospital personnel on a daily basis all over the world. This paper presents a new component-based approach with evolutionary eliminations, for a nurse scheduling problem arising at a major UK hospital. The main idea behind this technique is to decompose a schedule into its components (i.e. the allocated shift pattern of each nurse), and then to implement two evolutionary elimination strategies mimicking natural selection and natural mutation process on these components respectively to iteratively deliver better schedules. The worthiness of all components in the schedule has to be continuously demonstrated in order for them to remain there. This demonstration employs an evaluation function which evaluates how well each component contributes towards the final objective. Two elimination steps are then applied: the first elimination eliminates a number of components that are deemed not worthy to stay in the current schedule; the second elimination may also throw out, with a low level of probability, some worthy components. The eliminated components are replenished with new ones using a set of constructive heuristics using local optimality criteria. Computational results using 52 data instances demonstrate the applicability of the proposed approach in solving real-world problems., Comment: 27 pages, 4 figures

This paper proposes a new memetic evolutionary algorithm to achieve explicit learning in rule-based nurse rostering, which involves applying a set of heuristic rules for each nurse’s assignment. The main framework of the algorithm is an estimation of distribution algorithm, in which an ant-miner methodology improves the individual solutions produced in each generation. Unlike our previous work (where learning is implicit), the learning in the memetic estimation of distribution algorithm is explicit, i.e. we are able to identify building blocks directly. The overall approach learns by building a probabilistic model, i.e. an estimation of the probability distribution of individual nurse-rule pairs that are used to construct schedules. The local search processor (i.e. the ant-miner) reinforces nurse-rule pairs that receive higher rewards. A challenging real world nurse rostering problem is used as the test problem. Computational results show that the proposed approach outperforms most existing approaches. It is suggested that the learning methodologies suggested in this paper may be applied to other scheduling problems where schedules are built systematically according to specific rules.

A novel algorithm named artificial fish swarm algorithm (AFSA) is discussed to solve the problem of routing optimization in computer communication networks. An improved AFSA (IAFSA) with the taboo table and a new parameter is proposed to increase the global optimum capability and the neighborhood search ability of AFSA. A mathematical model of routing optimization based on the minimal time delay is established. By description and analysis of AFSA, its principle and convergence capability are given. The experiment demonstrates that IAFSA has better capability and rapidity to search the global optimum. Summarization of AFSA's characteristics and ideas for improvement are presented according to the comparative result between AFSA and genetic algorithm.

Our research has shown that schedules can be built mimicking a human scheduler by using a set of rules that involve domain knowledge. This chapter presents a Bayesian Optimization Algorithm (BOA) for the nurse scheduling problem that chooses such suitable scheduling rules from a set for each nurse’s assignment. Based on the idea of using probabilistic models, the BOA builds a Bayesian network for the set of promising solutions and samples these networks to generate new candidate solutions. Computational results from 52 real data instances demonstrate the success of this approach. It is also suggested that the learning mechanism in the proposed algorithm may be suitable for other scheduling problems.

Two ideas taken from Bayesian optimization and classifier systems are presented for personnel scheduling based on choosing a suitable scheduling rule from a set for each person's assignment. Unlike our previous work of using genetic algorithms whose learning is implicit, the learning in both approaches is explicit, i.e. we are able to identify building blocks directly. To achieve this target, the Bayesian optimization algorithm builds a Bayesian network of the joint probability distribution of the rules used to construct solutions, while the adapted classifier system assigns each rule a strength value that is constantly updated according to its usefulness in the current situation. Computational results from 52 real data instances of nurse scheduling demonstrate the success of both approaches. It is also suggested that the learning mechanism in the proposed approaches might be suitable for other scheduling problems.

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