Object-centric process models and the design of flexible processes

Mainstream business process modelling techniques promote a design paradigm wherein the activities to be performed within a case, together with their usual execution order, form the backbone of a process model, on top of which other aspects are anchored. This paradigm, while eective in standardised and production-oriented domains, shows some limitations when confronted with processes where case-by-case variations and exceptions are the norm. In this thesis we develop the idea that the eective design of exible process models calls for an alternative modelling paradigm, one in which process models are modularised along key business objects, rather than along activity decompositions. The research follows a design science method, starting from the formulation of a research problem expressed in terms of requirements, and culminating in a set of artifacts that have been devised to satisfy these requirements. The main contributions of the thesis are: (i) a meta-model for object-centric process modelling incorporating constructs for capturing exible processes; (ii) a transformation from this meta-model to an existing activity-centric process modelling language, namely YAWL, showing the relation between object-centric and activity-centric process modelling approaches; and (iii) a Coloured Petri Net that captures the semantics of the proposed meta-model. The meta-model has been evaluated using a framework consisting of a set of work ow patterns. Moreover, the meta-model has been embodied in a modelling tool that has been used to capture two industrial scenarios.

Simulation and enhancement of a cardiovascular device test rig

Cardiovascular assist devices are tested in mock circulation loops (MCLs) prior to animal and clinical testing. These MCLs rely on characteristics such as pneumatic parameters to create pressure and flow, and pipe dimensions to replicate the resistance, compliance and fluid inertia of the natural cardiovascular system. A mathematical simulation was developed in SIMULINK to simulate an existing MCL. Model validation was achieved by applying the physical MCL characteristics to the simulation and comparing the resulting pressure traces. These characteristics were subsequently altered to improve and thus predict the performance of a more accurate physical system. The simulation was successful in simulating the physical mock circulation loop, and proved to be a useful tool in the development of improved cardiovascular device test rigs.

Robust real time multi-layer foreground segmentation

Many surveillance applications (object tracking, abandoned object detection) rely on detecting changes in a scene. Foreground segmentation is an effective way to extract the foreground from the scene, but these techniques cannot discriminate between objects that have temporarily stopped and those that are moving. We propose a series of modifications to an existing foreground segmentation system\cite{Butler2003} so that the foreground is further segmented into two or more layers. This yields an active layer of objects currently in motion and a passive layer of objects that have temporarily ceased motion which can itself be decomposed into multiple static layers. We also propose a variable threshold to cope with variable illumination, a feedback mechanism that allows an external process (i.e. surveillance system) to alter the motion detectors state, and a lighting compensation process and a shadow detector to reduce errors caused by lighting inconsistencies. The technique is demonstrated using outdoor surveillance footage, and is shown to be able to effectively deal with real world lighting conditions and overlapping objects.

Abandoned object detection using multi-layer motion detection

Abandoned object detection (AOD) systems are required to run in high traffic situations, with high levels of occlusion. Systems rely on background segmentation techniques to locate abandoned objects, by detecting areas of motion that have stopped. This is often achieved by using a medium term motion detection routine to detect long term changes in the background. When AOD systems are integrated into person tracking system, this often results in two separate motion detectors being used to handle the different requirements. We propose a motion detection system that is capable of detecting medium term motion as well as regular motion. Multiple layers of medium term (static) motion can be detected and segmented. We demonstrate the performance of this motion detection system and as part of an abandoned object detection system.

Object tracking using multiple motion modalities

This paper presents an object tracking system that utilises a hybrid multi-layer motion segmentation and optical flow algorithm. While many tracking systems seek to combine multiple modalities such as motion and depth or multiple inputs within a fusion system to improve tracking robustness, current systems have avoided the combination of motion and optical flow. This combination allows the use of multiple modes within the object detection stage. Consequently, different categories of objects, within motion or stationary, can be effectively detected utilising either optical flow, static foreground or active foreground information. The proposed system is evaluated using the ETISEO database and evaluation metrics and compared to a baseline system utilising a single mode foreground segmentation technique. Results demonstrate a significant improvement in tracking results can be made through the incorporation of the additional motion information.

Dynamic Performance Measures for Object Tracking Systems

Performance evaluation of object tracking systems is typically performed after the data has been processed, by comparing tracking results to ground truth. Whilst this approach is fine when performing offline testing, it does not allow for real-time analysis of the systems performance, which may be of use for live systems to either automatically tune the system or report reliability. In this paper, we propose three metrics that can be used to dynamically asses the performance of an object tracking system. Outputs and results from various stages in the tracking system are used to obtain measures that indicate the performance of motion segmentation, object detection and object matching. The proposed dynamic metrics are shown to accurately indicate tracking errors when visually comparing metric results to tracking output, and are shown to display similar trends to the ETISEO metrics when comparing different tracking configurations.

Improved simultaneous computation of motion detection and optical flow for object tracking

Object tracking systems require accurate segmentation of the objects from the background for effective tracking. Motion segmentation or optical flow can be used to segment incoming images. Whilst optical flow allows multiple moving targets to be separated based on their individual velocities, optical flow techniques are prone to errors caused by changing lighting and occlusions, both common in a surveillance environment. Motion segmentation techniques are more robust to fluctuating lighting and occlusions, but don't provide information on the direction of the motion. In this paper we propose a combined motion segmentation/optical flow algorithm for use in object tracking. The proposed algorithm uses the motion segmentation results to inform the optical flow calculations and ensure that optical flow is only calculated in regions of motion, and improve the performance of the optical flow around the edge of moving objects. Optical flow is calculated at pixel resolution and tracking of flow vectors is employed to improve performance and detect discontinuities, which can indicate the location of overlaps between objects. The algorithm is evaluated by attempting to extract a moving target within the flow images, given expected horizontal and vertical movement (i.e. the algorithms intended use for object tracking). Results show that the proposed algorithm outperforms other widely used optical flow techniques for this surveillance application.

FPGA implementation of dual-microphone delay-and-sum beamforming for in-car speech enhancement and recognition

In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone delay-and-sum beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

EUAustralia Online : News & Information from the Capitals of Europe to Australia (www.euaustralia.com)

Experimental / pilot online journalistic publication. EUAustralia Online (www.euaustralia.com) is a pilot niche publication identifying and demonstrating dynamics of online journalism. The editor, an experienced and senior journalist and academic, specialist in European studies, commenced publication on 28.8.06 during one year’s “industry immersion” -- with media accreditation to the European Commission, Brussels. Reporting now is from Australia and from Europe on field trip exercises. Student editors participate making it partly a training operation. EUAustralia demonstrates adaptation of conventional, universal, “Western” liberal journalistic practices. Its first premise is to fill a knowledge gap in Australia about the European Union -- institutions, functions and directions. The second premise is to test the communications capacity of the online format, where the publication sets a strong standard of journalistic credibility – hence its transparency with sourcing or signposting of “commentary” or ”opinion”. EUAustralia uses modified, enhanced weblog software allowing for future allocation of closed pages to subscribers. An early exemplar of its kind, with modest upload rate (2010-13 average, 16 postings monthly), esteemed, it commands over 180000 site visits p.a. (half as unique visitors; AWB Statistics); strongly rated by search engines, see page one Googlr placements for “EU Australia”. Comment by the ISP (SeventhVision, Broadbeach, Queensland): “The site has good search engine recognition because seen as credible; can be used to generate revenue”. This journalistic exercise has been analysed in theoretical context twice, in published refereed conference proceedings (Communication and Media Policy Forum, Sydney; 2007, 2009).

Using Ownership to Reason About Inherent Parallelism in Object-Oriented Programs

With the emergence of multi-cores into the mainstream, there is a growing need for systems to allow programmers and automated systems to reason about data dependencies and inherent parallelismin imperative object-oriented languages. In this paper we exploit the structure of object-oriented programs to abstract computational side-effects. We capture and validate these effects using a static type system. We use these as the basis of sufficient conditions for several different data and task parallelism patterns. We compliment our static type system with a lightweight runtime system to allow for parallelization in the presence of complex data flows. We have a functioning compiler and worked examples to demonstrate the practicality of our solution.

Contrasting scenarios : embracing speech recognition

The purpose of this chapter is to describe the use of caricatured contrasting scenarios (Bødker, 2000) and how they can be used to consider potential designs for disruptive technologies. The disruptive technology in this case is Automatic Speech Recognition (ASR) software in workplace settings. The particular workplace is the Magistrates Court of the Australian Capital Territory.----- Caricatured contrasting scenarios are ideally suited to exploring how ASR might be implemented in a particular setting because they allow potential implementations to be “sketched” quickly and with little effort. This sketching of potential interactions and the emphasis of both positive and negative outcomes allows the benefits and pitfalls of design decisions to become apparent.----- A brief description of the Court is given, describing the reasons for choosing the Court for this case study. The work of the Court is framed as taking place in two modes: Front of house, where the courtroom itself is, and backstage, where documents are processed and the business of the court is recorded and encoded into various systems.----- Caricatured contrasting scenarios describing the introduction of ASR to the front of house are presented and then analysed. These scenarios show that the introduction of ASR to the court would be highly problematic.----- The final section describes how ASR could be re-imagined in order to make it useful for the court. A final scenario is presented that describes how this re-imagined ASR could be integrated into both the front of house and backstage of the court in a way that could strengthen both processes.

Adiabatic compression testing - part II : background and approach to estimating severity of test methodology

Adiabatic compression testing of components in gaseous oxygen is a test method that is utilized worldwide and is commonly required to qualify a component for ignition tolerance under its intended service. This testing is required by many industry standards organizations and government agencies; however, a thorough evaluation of the test parameters and test system influences on the thermal energy produced during the test has not yet been performed. This paper presents a background for adiabatic compression testing and discusses an approach to estimating potential differences in the thermal profiles produced by different test laboratories. A “Thermal Profile Test Fixture” (TPTF) is described that is capable of measuring and characterizing the thermal energy for a typical pressure shock by any test system. The test systems at Wendell Hull & Associates, Inc. (WHA) in the USA and at the BAM Federal Institute for Materials Research and Testing in Germany are compared in this manner and some of the data obtained is presented. The paper also introduces a new way of comparing the test method to idealized processes to perform system-by-system comparisons. Thus, the paper introduces an “Idealized Severity Index” (ISI) of the thermal energy to characterize a rapid pressure surge. From the TPTF data a “Test Severity Index” (TSI) can also be calculated so that the thermal energies developed by different test systems can be compared to each other and to the ISI for the equivalent isentropic process. Finally, a “Service Severity Index” (SSI) is introduced to characterizing the thermal energy of actual service conditions. This paper is the second in a series of publications planned on the subject of adiabatic compression testing.

Quality issues for the National Bowel Cancer Screening Program (NBCSP)

Purpose: This two-part research project was undertaken as part of the planning process by Queensland Health (QH), Cancer Screening Services Unit (CSSU), Queensland Bowel Cancer Screening Program (QBCSP), in partnership with the National Bowel Cancer Screening Program (NBCSP), to prepare for the implementation of the NBCSP in public sector colonoscopy services in QLD in late 2006. There was no prior information available on the quality of colonoscopy services in Queensland (QLD) and no prior studies that assessed the quality of colonoscopy training in Australia. Furthermore, the NBCSP was introduced without extra funding for colonoscopy service improvement or provision for increases in colonoscopic capacity resulting from the introduction of the NBCSP. The main purpose of the research was to record baseline data on colonoscopy referral and practice in QLD and current training in colonoscopy Australia-wide. It was undertaken from a quality improvement perspective. Implementation of the NBCSP requires that all aspects of the screening pathway, in particular colonoscopy services for the assessment of positive Faecal Occult Blood Tests (FOBTs), will be effective, efficient, equitable and evidence-based. This study examined two important aspects of the continuous quality improvement framework for the NBCSP as they relate to colonoscopy services: (1) evidence-based practice, and (2) quality of colonoscopy training. The Principal Investigator was employed as Senior Project Officer (Training) in the QBCSP during the conduct of this research project. Recommendations from this research have been used to inform the development and implementation of quality improvement initiatives for provision of colonoscopy in the NBCSP, its QLD counterpart the QBCSP and colonoscopy services in QLD, in general. Methods – Part 1 Chart audit of evidence-based practice: The research was undertaken in two parts from 2005-2007. The first part of this research comprised a retrospective chart audit of 1484 colonoscopy records (some 13% of all colonoscopies conducted in public sector facilities in the year 2005) in three QLD colonoscopy services. Whilst some 70% of colonoscopies are currently conducted in the private sector, only public sector colonoscopy facilities provided colonoscopies under the NBCSP. The aim of this study was to compare colonoscopy referral and practice with explicit criteria derived from the National Health & Medical Research Council (NHMRC) (1999) Clinical Practice Guidelines for the Prevention, Early Detection and Management of Colorectal Cancer, and describe the nature of variance with the guidelines. Symptomatic presentations were the most common indication for colonoscopy (60.9%). These comprised per rectal bleeding (31.0%), change of bowel habit (22.1%), abdominal pain (19.6%), iron deficiency anaemia (16.2%), inflammatory bowel disease (8.9%) and other symptoms (11.4%). Surveillance and follow-up colonoscopies accounted for approximately one-third of the remaining colonoscopy workload across sites. Gastroenterologists (GEs) performed relatively more colonoscopies per annum (59.9%) compared to general surgeons (GS) (24.1%), colorectal surgeons (CRS) (9.4%) and general physicians (GPs) (6.5%). Guideline compliance varied with the designation of the colonoscopist. Compliance was lower for CRS (62.9%) compared to GPs (76.0%), GEs (75.0%), GSs (70.9%, p<0.05). Compliance with guideline recommendations for colonoscopic surveillance for family history of colorectal cancer (23.9%), polyps (37.0%) and a past history of bowel cancer (42.7%), was by comparison significantly lower than for symptomatic presentations (94.4%), (p<0.001). Variation with guideline recommendations occurred more frequently for polyp surveillance (earlier than guidelines recommend, 47.9%) and follow-up for past history of bowel cancer (later than recommended, 61.7%, p<0.001). Bowel cancer cases detected at colonoscopy comprised 3.6% of all audited colonoscopies. Incomplete colonoscopies occurred in 4.3% of audited colonoscopies and were more common among women (76.6%). For all colonoscopies audited, the rate of incomplete colonoscopies for GEs was 1.6% (CI 0.9-2.6), GPs 2.0% (CI 0.6-7.2), GS 7.0% (CI 4.8-10.1) and CRS 16.4% (CI 11.2-23.5). 18.6% (n=55) of patients with a documented family history of bowel cancer had colonoscopy performed against guidelines recommendations (for general (category 1) population risk, for reasons of patient request or family history of polyps, rather than for high risk status for colorectal cancer). In general, family history was inadequately documented and subsequently applied to colonoscopy referral and practice. Methods - Part 2 Surveys of quality of colonoscopy training: The second part of the research consisted of Australia-wide anonymous, self-completed surveys of colonoscopy trainers and their trainees to ascertain their opinions on the current apprenticeship model of colonoscopy in Australia and to identify any training needs. Overall, 127 surveys were received from colonoscopy trainers (estimated response rate 30.2%). Approximately 50% of trainers agreed and 27% disagreed that current numbers of training places were adequate to maintain a skilled colonoscopy workforce in preparation for the NBCSP. Approximately 70% of trainers also supported UK-style colonoscopy training within dedicated accredited training centres using a variety of training approaches including simulation. A collaborative approach with the private sector was seen as beneficial by 65% of trainers. Non-gastroenterologists (non-GEs) were more likely than GEs to be of the opinion that simulators are beneficial for colonoscopy training (χ2-test = 5.55, P = 0.026). Approximately 60% of trainers considered that the current requirements for recognition of training in colonoscopy could be insufficient for trainees to gain competence and 80% of those indicated that ≥ 200 colonoscopies were needed. GEs (73.4%) were more likely than non-GEs (36.2%) to be of the opinion that the Conjoint Committee standard is insufficient to gain competence in colonoscopy (χ2-test = 16.97, P = 0.0001). The majority of trainers did not support training either nurses (73%) or GPs in colonoscopy (71%). Only 81 (estimated response rate 17.9%) surveys were received from GS trainees (72.1%), GE trainees (26.3%) and GP trainees (1.2%). The majority were males (75.9%), with a median age 32 years and who had trained in New South Wales (41.0%) or Victoria (30%). Overall, two-thirds (60.8%) of trainees indicated that they deemed the Conjoint Committee standard sufficient to gain competency in colonoscopy. Between specialties, 75.4% of GS trainees indicated that the Conjoint Committee standard for recognition of colonoscopy was sufficient to gain competence in colonoscopy compared to only 38.5% of GE trainees. Measures of competency assessed and recorded by trainees in logbooks centred mainly on caecal intubation (94.7-100%), complications (78.9-100%) and withdrawal time (51-76.2%). Trainees described limited access to colonoscopy training lists due to the time inefficiency of the apprenticeship model and perceived monopolisation of these by GEs and their trainees. Improvements to the current training model suggested by trainees included: more use of simulation, training tools, a United Kingdom (UK)-style training course, concentration on quality indicators, increased access to training lists, accreditation of trainers and interdisciplinary colonoscopy training. Implications for the NBCSP/QBCSP: The introduction of the NBCSP/QBCSP necessitates higher quality colonoscopy services if it is to achieve its ultimate goal of decreasing the incidence of morbidity and mortality associated with bowel cancer in Australia. This will be achieved under a new paradigm for colonoscopy training and implementation of evidence-based practice across the screening pathway and specifically targeting areas highlighted in this thesis. Recommendations for improvement of NBCSP/QBCSP effectiveness and efficiency include the following: 1. Implementation of NBCSP and QBCSP health promotion activities that target men, in particular, to increase FOBT screening uptake. 2. Improved colonoscopy training for trainees and refresher courses or retraining for existing proceduralists to improve completion rates (especially for female NBCSP/QBCSP participants), and polyp and adenoma detection and removal, including newer techniques to detect flat and depressed lesions. 3. Introduction of colonoscopy training initiatives for trainees that are aligned with NBCSP/QBCSP colonoscopy quality indicators, including measurement of training outcomes using objective quality indicators such as caecal intubation, withdrawal time, and adenoma detection rate. 4. Introduction of standardised, interdisciplinary colonoscopy training to reduce apparent differences between specialties with regard to compliance with guideline recommendations, completion rates, and quality of polypectomy. 5. Improved quality of colonoscopy training by adoption of a UK-style training program with centres of excellence, incorporating newer, more objective assessment methods, use of a variety of training tools such as simulation and rotations of trainees between metropolitan, rural, and public and private sector training facilities. 6. Incorporation of NHMRC guidelines into colonoscopy information systems to improve documentation, provide guideline recommendations at the point of care, use of gastroenterology nurse coordinators to facilitate compliance with guidelines and provision of guideline-based colonoscopy referral letters for GPs. 7. Provision of information and education about the NBCSP/QBCSP, bowel cancer risk factors, including family history and polyp surveillance guidelines, for participants, GPs and proceduralists. 8. Improved referral of NBCSP/QBCSP participants found to have a high-risk family history of bowel cancer to appropriate genetics services.

Robust speech recognition using speech enhancement

Automatic Speech Recognition (ASR) has matured into a technology which is becoming more common in our everyday lives, and is emerging as a necessity to minimise driver distraction when operating in-car systems such as navigation and infotainment. In “noise-free” environments, word recognition performance of these systems has been shown to approach 100%, however this performance degrades rapidly as the level of background noise is increased. Speech enhancement is a popular method for making ASR systems more ro- bust. Single-channel spectral subtraction was originally designed to improve hu- man speech intelligibility and many attempts have been made to optimise this algorithm in terms of signal-based metrics such as maximised Signal-to-Noise Ratio (SNR) or minimised speech distortion. Such metrics are used to assess en- hancement performance for intelligibility not speech recognition, therefore mak- ing them sub-optimal ASR applications. This research investigates two methods for closely coupling subtractive-type enhancement algorithms with ASR: (a) a computationally-efficient Mel-filterbank noise subtraction technique based on likelihood-maximisation (LIMA), and (b) in- troducing phase spectrum information to enable spectral subtraction in the com- plex frequency domain. Likelihood-maximisation uses gradient-descent to optimise parameters of the enhancement algorithm to best fit the acoustic speech model given a word se- quence known a priori. Whilst this technique is shown to improve the ASR word accuracy performance, it is also identified to be particularly sensitive to non-noise mismatches between the training and testing data. Phase information has long been ignored in spectral subtraction as it is deemed to have little effect on human intelligibility. In this work it is shown that phase information is important in obtaining highly accurate estimates of clean speech magnitudes which are typically used in ASR feature extraction. Phase Estimation via Delay Projection is proposed based on the stationarity of sinusoidal signals, and demonstrates the potential to produce improvements in ASR word accuracy in a wide range of SNR. Throughout the dissertation, consideration is given to practical implemen- tation in vehicular environments which resulted in two novel contributions – a LIMA framework which takes advantage of the grounding procedure common to speech dialogue systems, and a resource-saving formulation of frequency-domain spectral subtraction for realisation in field-programmable gate array hardware. The techniques proposed in this dissertation were evaluated using the Aus- tralian English In-Car Speech Corpus which was collected as part of this work. This database is the first of its kind within Australia and captures real in-car speech of 50 native Australian speakers in seven driving conditions common to Australian environments.

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.