Synthesis of orchestrators from service choreographies

With service interaction modelling, it is customary to distinguish between two types of models: choreographies and orchestrations. A choreography describes interactions within a collection of services from a global perspective, where no service plays a privileged role. Instead, services interact in a peer-to-peer manner. In contrast, an orchestration describes the interactions between one particular service, the orchestrator, and a number of partner services. The main proposition of this work is an approach to bridge these two modelling viewpoints by synthesising orchestrators from choreographies. To start with, choreographies are defined using a simple behaviour description language based on communicating finite state machines. From such a model, orchestrators are initially synthesised in the form of state machines. It turns out that state machines are not suitable for orchestration modelling, because orchestrators generally need to engage in concurrent interactions. To address this issue, a technique is proposed to transform state machines into process models in the Business Process Modelling Notation (BPMN). Orchestrations represented in BPMN can then be augmented with additional business logic to achieve value-adding mediation. In addition, techniques exist for refining BPMN models into executable process definitions. The transformation from state machines to BPMN relies on Petri nets as an intermediary representation and leverages techniques from theory of regions to identify concurrency in the initial Petri net. Once concurrency has been identified, the resulting Petri net is transformed into a BPMN model. The original contributions of this work are: an algorithm to synthesise orchestrators from choreographies and a rules-based transformation from Petri nets into BPMN.

Rough set-based reasoning and pattern mining for information filtering

An information filtering (IF) system monitors an incoming document stream to find the documents that match the information needs specified by the user profiles. To learn to use the user profiles effectively is one of the most challenging tasks when developing an IF system. With the document selection criteria better defined based on the users’ needs, filtering large streams of information can be more efficient and effective. To learn the user profiles, term-based approaches have been widely used in the IF community because of their simplicity and directness. Term-based approaches are relatively well established. However, these approaches have problems when dealing with polysemy and synonymy, which often lead to an information overload problem. Recently, pattern-based approaches (or Pattern Taxonomy Models (PTM) [160]) have been proposed for IF by the data mining community. These approaches are better at capturing sematic information and have shown encouraging results for improving the effectiveness of the IF system. On the other hand, pattern discovery from large data streams is not computationally efficient. Also, these approaches had to deal with low frequency pattern issues. The measures used by the data mining technique (for example, “support” and “confidences”) to learn the profile have turned out to be not suitable for filtering. They can lead to a mismatch problem. This thesis uses the rough set-based reasoning (term-based) and pattern mining approach as a unified framework for information filtering to overcome the aforementioned problems. This system consists of two stages - topic filtering and pattern mining stages. The topic filtering stage is intended to minimize information overloading by filtering out the most likely irrelevant information based on the user profiles. A novel user-profiles learning method and a theoretical model of the threshold setting have been developed by using rough set decision theory. The second stage (pattern mining) aims at solving the problem of the information mismatch. This stage is precision-oriented. A new document-ranking function has been derived by exploiting the patterns in the pattern taxonomy. The most likely relevant documents were assigned higher scores by the ranking function. Because there is a relatively small amount of documents left after the first stage, the computational cost is markedly reduced; at the same time, pattern discoveries yield more accurate results. The overall performance of the system was improved significantly. The new two-stage information filtering model has been evaluated by extensive experiments. Tests were based on the well-known IR bench-marking processes, using the latest version of the Reuters dataset, namely, the Reuters Corpus Volume 1 (RCV1). The performance of the new two-stage model was compared with both the term-based and data mining-based IF models. The results demonstrate that the proposed information filtering system outperforms significantly the other IF systems, such as the traditional Rocchio IF model, the state-of-the-art term-based models, including the BM25, Support Vector Machines (SVM), and Pattern Taxonomy Model (PTM).

Improved GMM-based speaker verification using SVM-driven impostor dataset selection

The problem of impostor dataset selection for GMM-based speaker verification is addressed through the recently proposed data-driven background dataset refinement technique. The SVM-based refinement technique selects from a candidate impostor dataset those examples that are most frequently selected as support vectors when training a set of SVMs on a development corpus. This study demonstrates the versatility of dataset refinement in the task of selecting suitable impostor datasets for use in GMM-based speaker verification. The use of refined Z- and T-norm datasets provided performance gains of 15% in EER in the NIST 2006 SRE over the use of heuristically selected datasets. The refined datasets were shown to generalise well to the unseen data of the NIST 2008 SRE.

Data-driven impostor selection for T-norm score normalisation and the background dataset in SVM-based speaker verification

A data-driven background dataset refinement technique was recently proposed for SVM based speaker verification. This method selects a refined SVM background dataset from a set of candidate impostor examples after individually ranking examples by their relevance. This paper extends this technique to the refinement of the T-norm dataset for SVM-based speaker verification. The independent refinement of the background and T-norm datasets provides a means of investigating the sensitivity of SVM-based speaker verification performance to the selection of each of these datasets. Using refined datasets provided improvements of 13% in min. DCF and 9% in EER over the full set of impostor examples on the 2006 SRE corpus with the majority of these gains due to refinement of the T-norm dataset. Similar trends were observed for the unseen data of the NIST 2008 SRE.

Scatter difference NAP for SVM speaker recognition

This paper presents Scatter Difference Nuisance Attribute Projection (SD-NAP) as an enhancement to NAP for SVM-based speaker verification. While standard NAP may inadvertently remove desirable speaker variability, SD-NAP explicitly de-emphasises this variability by incorporating a weighted version of the between-class scatter into the NAP optimisation criterion. Experimental evaluation of SD-NAP with a variety of SVM systems on the 2006 and 2008 NIST SRE corpora demonstrate that SD-NAP provides improved verification performance over standard NAP in most cases, particularly at the EER operating point.

Scheduling trains as a blocking parallel-machine job shop scheduling problem

In this paper, the train scheduling problem is modelled as a blocking parallel-machine job shop scheduling (BPMJSS) problem. In the model, trains, single-track sections and multiple-track sections, respectively, are synonymous with jobs, single machines and parallel machines, and an operation is regarded as the movement/traversal of a train across a section. Due to the lack of buffer space, the real-life case should consider blocking or hold-while-wait constraints, which means that a track section cannot release and must hold the train until next section on the routing becomes available. Based on literature review and our analysis, it is very hard to find a feasible complete schedule directly for BPMJSS problems. Firstly, a parallel-machine job-shop-scheduling (PMJSS) problem is solved by an improved shifting bottleneck procedure (SBP) algorithm without considering blocking conditions. Inspired by the proposed SBP algorithm, feasibility satisfaction procedure (FSP) algorithm is developed to solve and analyse the BPMJSS problem, by an alternative graph model that is an extension of the classical disjunctive graph models. The proposed algorithms have been implemented and validated using real-world data from Queensland Rail. Sensitivity analysis has been applied by considering train length, upgrading track sections, increasing train speed and changing bottleneck sections. The outcomes show that the proposed methodology would be a very useful tool for the real-life train scheduling problems

An experiment in mixed compilation/interpretation

One of the classic forms of intermediate representation used for communication between compiler front-ends and back-ends are those based on abstract stack machines. It is possible to compile the stack machine instructions into machine code by means of an interpretive code generator, or to simulate the stack machine at runtime using an interpreter. This paper describes an approach intermediate between these two extremes. The front-end for a commercial Modula 2 compiler was ported to the "industry standard PC", and a partially compiling back-end written. The object code runs with the assistance of an interpreter, but may be linked with libraries which are fully compiled. The intent was to provide a programming environment on the PC which is identical to that of the same compilers on 32-bit UNIX machines. This objective has been met, and the compiler is available to educational institutions as free-ware. The design basis of the new compiler is described, and the performance critically evaluated.

Condition-based prognosis of machine health

Modern machines are complex and often required to operate long hours to achieve production targets. The ability to detect symptoms of failure, hence, forecasting the remaining useful life of the machine is vital to prevent catastrophic failures. This is essential to reducing maintenance cost, operation downtime and safety hazard. Recent advances in condition monitoring technologies have given rise to a number of prognosis models that attempt to forecast machinery health based on either condition data or reliability data. In practice, failure condition trending data are seldom kept by industries and data that ended with a suspension are sometimes treated as failure data. This paper presents a novel approach of incorporating historical failure data and suspended condition trending data in the prognostic model. The proposed model consists of a FFNN whose training targets are asset survival probabilities estimated using a variation of Kaplan-Meier estimator and degradation-based failure PDF estimator. The output survival probabilities collectively form an estimated survival curve. The viability of the model was tested using a set of industry vibration data.

Creative Industries

We are experiencing a period of profound social and economic transformation. This is a shift from an industrial economy to a knowledge economy (or a “creative economy”; or an “economy of the imagination”.) This new, emerging economic system is fundamentally organised around people (not machines or buildings); and around place. We heard Richard Florida argue that creative, talented people won’t go to where the job is, but vice versa, the job will come to them. So according to Florida, where we live is becoming the primary factor in global economic development. (Incidentally, it is worth contrasting this idea with the alternative proposition - put by speakers at this Forum - of “new nomadism”, that is, that creativity is nomadic and not bound by place.)

Decomposition of aggregated load : finding induction motor fraction in real load

The main contribution of this paper is decomposition/separation of the compositie induction motors load from measurement at a system bus. In power system transmission buses load is represented by static and dynamic loads. The induction motor is considered as the main dynamic loads and in the practice for major transmission buses there will be many and various induction motors contributing. Particularly at an industrial bus most of the load is dynamic types. Rather than traing to extract models of many machines this paper seeks to identify three groups of induction motors to represent the dynamic loads. Three groups of induction motors used to characterize the load. These are the small groups (4kw to 11kw), the medium groups (15kw to 180kw) and the large groups (above 630kw). At first these groups with different percentage contribution of each group is composite. After that from the composite models, each motor percentage contribution is decomposed by using the least square algorithms. In power system commercial and the residential buses static loads percentage is higher than the dynamic loads percentage. To apply this theory to other types of buses such as residential and commerical it is good practice to represent the total load as a combination of composite motor loads, constant impedence loads and constant power loads. To validate the theory, the 24hrs of Sydney West data is decomposed according to the three groups of motor models.

Metaheuristic approaches to the hybrid flow shop scheduling problem with a cost-related criterion

In the paper, the flow-shop scheduling problem with parallel machines at each stage (machine center) is studied. For each job its release and due date as well as a processing time for its each operation are given. The scheduling criterion consists of three parts: the total weighted earliness, the total weighted tardiness and the total weighted waiting time. The criterion takes into account the costs of storing semi-manufactured products in the course of production and ready-made products as well as penalties for not meeting the deadlines stated in the conditions of the contract with customer. To solve the problem, three constructive algorithms and three metaheuristics (based one Tabu Search and Simulated Annealing techniques) are developed and experimentally analyzed. All the proposed algorithms operate on the notion of so-called operation processing order, i.e. the order of operations on each machine. We show that the problem of schedule construction on the base of a given operation processing order can be reduced to the linear programming task. We also propose some approximation algorithm for schedule construction and show the conditions of its optimality.

Improving automatic speaker verification using SVM techniques

Automatic recognition of people is an active field of research with important forensic and security applications. In these applications, it is not always possible for the subject to be in close proximity to the system. Voice represents a human behavioural trait which can be used to recognise people in such situations. Automatic Speaker Verification (ASV) is the process of verifying a persons identity through the analysis of their speech and enables recognition of a subject at a distance over a telephone channel { wired or wireless. A significant amount of research has focussed on the application of Gaussian mixture model (GMM) techniques to speaker verification systems providing state-of-the-art performance. GMM's are a type of generative classifier trained to model the probability distribution of the features used to represent a speaker. Recently introduced to the field of ASV research is the support vector machine (SVM). An SVM is a discriminative classifier requiring examples from both positive and negative classes to train a speaker model. The SVM is based on margin maximisation whereby a hyperplane attempts to separate classes in a high dimensional space. SVMs applied to the task of speaker verification have shown high potential, particularly when used to complement current GMM-based techniques in hybrid systems. This work aims to improve the performance of ASV systems using novel and innovative SVM-based techniques. Research was divided into three main themes: session variability compensation for SVMs; unsupervised model adaptation; and impostor dataset selection. The first theme investigated the differences between the GMM and SVM domains for the modelling of session variability | an aspect crucial for robust speaker verification. Techniques developed to improve the robustness of GMMbased classification were shown to bring about similar benefits to discriminative SVM classification through their integration in the hybrid GMM mean supervector SVM classifier. Further, the domains for the modelling of session variation were contrasted to find a number of common factors, however, the SVM-domain consistently provided marginally better session variation compensation. Minimal complementary information was found between the techniques due to the similarities in how they achieved their objectives. The second theme saw the proposal of a novel model for the purpose of session variation compensation in ASV systems. Continuous progressive model adaptation attempts to improve speaker models by retraining them after exploiting all encountered test utterances during normal use of the system. The introduction of the weight-based factor analysis model provided significant performance improvements of over 60% in an unsupervised scenario. SVM-based classification was then integrated into the progressive system providing further benefits in performance over the GMM counterpart. Analysis demonstrated that SVMs also hold several beneficial characteristics to the task of unsupervised model adaptation prompting further research in the area. In pursuing the final theme, an innovative background dataset selection technique was developed. This technique selects the most appropriate subset of examples from a large and diverse set of candidate impostor observations for use as the SVM background by exploiting the SVM training process. This selection was performed on a per-observation basis so as to overcome the shortcoming of the traditional heuristic-based approach to dataset selection. Results demonstrate the approach to provide performance improvements over both the use of the complete candidate dataset and the best heuristically-selected dataset whilst being only a fraction of the size. The refined dataset was also shown to generalise well to unseen corpora and be highly applicable to the selection of impostor cohorts required in alternate techniques for speaker verification.

Data-driven background dataset selection for SVM-based speaker verification

The recently proposed data-driven background dataset refinement technique provides a means of selecting an informative background for support vector machine (SVM)-based speaker verification systems. This paper investigates the characteristics of the impostor examples in such highly-informative background datasets. Data-driven dataset refinement individually evaluates the suitability of candidate impostor examples for the SVM background prior to selecting the highest-ranking examples as a refined background dataset. Further, the characteristics of the refined dataset were analysed to investigate the desired traits of an informative SVM background. The most informative examples of the refined dataset were found to consist of large amounts of active speech and distinctive language characteristics. The data-driven refinement technique was shown to filter the set of candidate impostor examples to produce a more disperse representation of the impostor population in the SVM kernel space, thereby reducing the number of redundant and less-informative examples in the background dataset. Furthermore, data-driven refinement was shown to provide performance gains when applied to the difficult task of refining a small candidate dataset that was mis-matched to the evaluation conditions.

Exploiting multiple feature sets in data-driven impostor dataset selection for speaker verification

This study assesses the recently proposed data-driven background dataset refinement technique for speaker verification using alternate SVM feature sets to the GMM supervector features for which it was originally designed. The performance improvements brought about in each trialled SVM configuration demonstrate the versatility of background dataset refinement. This work also extends on the originally proposed technique to exploit support vector coefficients as an impostor suitability metric in the data-driven selection process. Using support vector coefficients improved the performance of the refined datasets in the evaluation of unseen data. Further, attempts are made to exploit the differences in impostor example suitability measures from varying features spaces to provide added robustness.