Controlled automated discovery of collections of business process models

Automated process discovery techniques aim at extracting process models from information system logs. Existing techniques in this space are effective when applied to relatively small or regular logs, but generate spaghetti-like and sometimes inaccurate models when confronted to logs with high variability. In previous work, trace clustering has been applied in an attempt to reduce the size and complexity of automatically discovered process models. The idea is to split the log into clusters and to discover one model per cluster. This leads to a collection of process models – each one representing a variant of the business process – as opposed to an all-encompassing model. Still, models produced in this way may exhibit unacceptably high complexity and low fitness. In this setting, this paper presents a two-way divide-and-conquer process discovery technique, wherein the discovered process models are split on the one hand by variants and on the other hand hierarchically using subprocess extraction. Splitting is performed in a controlled manner in order to achieve user-defined complexity or fitness thresholds. Experiments on real-life logs show that the technique produces collections of models substantially smaller than those extracted by applying existing trace clustering techniques, while allowing the user to control the fitness of the resulting models.

Fault diagnosis of low speed bearing based on acoustic emission signal and multi-class relevance vector machine

This study presents an acoustic emission (AE) based fault diagnosis for low speed bearing using multi-class relevance vector machine (RVM). A low speed test rig was developed to simulate the various defects with shaft speeds as low as 10 rpm under several loading conditions. The data was acquired using anAEsensor with the test bearing operating at a constant loading (5 kN) andwith a speed range from20 to 80 rpm. This study is aimed at finding a reliable method/tool for low speed machines fault diagnosis based on AE signal. In the present study, component analysis was performed to extract the bearing feature and to reduce the dimensionality of original data feature. The result shows that multi-class RVM offers a promising approach for fault diagnosis of low speed machines.

A multi-genome analysis approach enables tracking of the invasion of a single Russian wheat aphid (Diuraphis noxia) clone throughout the New World

This study investigated the population genetics, demographic history and pathway of invasion of the Russian wheat aphid (RWA) from its native range in Central Asia, the Middle East and Europe to South Africa and the Americas. We screened microsatellite markers, mitochondrial DNA and endosymbiont genes in 504 RWA clones from nineteen populations worldwide. Following pathway analyses of microsatellite and endosymbiont data, we postulate that Turkey and Syria were the most likely sources of invasion to Kenya and South Africa, respectively. Furthermore, we found that one clone transferred between South Africa and the Americas was most likely responsible for the New World invasion. Finally, endosymbiont DNA was found to be a high resolution population genetic marker, extremely useful for studies of invasion over a relatively short evolutionary history time frame. This study has provided valuable insights into the factors that may have facilitated the recent global invasion by this damaging pest.

A multi-hierarchical motorway ramp signalling strategy

Ramp signalling is an access control for motorways, in which a traffic signal is placed at on-ramps to regulate the rate of vehicles entering the motorway and thus to preserve the motorway capacity. In general, ramp signalling algorithms fall into two categories: local control and coordinated control by their effective scope. Coordinated ramp signalling strategies make use of measurements from the entire motorway network to operate individual ramp signals for the optimal performances at the network level. This study proposes a multi-hierarchical strategy for coordinated ramp signalling. The strategy is structured in two layers. At the higher layer with a longer update interval, coordination group is assembled and disassembled based on the location of high-risk breakdown flow. At the lower layer with a shorter update interval, individual ramps are hired to serve the coordination and are also released based on the prevailing congestion level on the ramp. This strategy is modelled and applied to the northbound Pacific Motorway micro-simulation platform (AIMSUN). The simulation results show an effective congestion mitigation of the proposed strategy.

When should private property rights give way to the public interest?

Since Queensland Wire Industries Pty Ltd v Broken Hill Pty Co Ltd (1989) 167 CLR 177 it has been recognised that corporations with substantial market power are subject to special responsibilities and restraints that corporations without market power are not. In NT Power Generation Pty Ltd v Power and Water Authority (2004) 219 CLR 90 McHugh A-CJ, Gummow, Callinan and Heydon JJ in their joint reasons stated (at [76]), that s 46 of the Competition and Consumer Act 2010 (Cth) (CCA) can operate not only to prevent firms with substantial market power from doing prohibited things, but also compel them positively to do things they do not want to do. Their Honours also stated (at [126]) that the proposition that a private property owner who declines to permit competitors to use the property is immune from s 46 is “intrinsically unsound”. However, the circumstances in which a firm with substantial power must accommodate competitors, and private property rights give way to the public interest are uncertain. The purpose of this Note is to consider recent developments in two areas of the CCA where the law requires private property rights to give way to the public interest. The first part of the Note considers two recent cases which clarify the circumstances in which s 46 of the CCA can be used to compel a firm with substantial market power to accommodate a competitor and allow the competitor to make use of private property rights in the public interest. Secondly, on 12 February 2014 the Minister for Small Business, the Hon Bruce Billson,released the Productivity Commission’s Final Report, on the National Access Regime in Pt IIIA of the CCA (National Access Regime, Inquiry Report No 66, Canberra). Pt IIIA provides for the processes by which third parties may obtain access to infrastructure owned by others in the public interest. The Report recommends that Pt IIIA be retained but makes a number of suggestions for its reform, some of which will be briefly considered.

Proton-transfer and non-transfer compounds of the multi-purpose drug dapsone [4-(4-Aminophenylsulfonyl)aniline] with 3,5-dinitrosalicylic acid and 5-nitroisophthalic acid

The structures of the compounds from the reaction of the drug dapsone [4-(4-aminophenylsulfonyl)aniline] with 3,5-dinitrosalicylic acid, the salt hydrate [4-(4-aminohenylsulfonyl)anilinium 2-carboxy-4,6-dinitrophenolate monohydrate] (1) and the 1:1 adduct with 5-nitroisophthalic acid [4-(4-aminophenylsulfonyl)aniline 5-nitrobenzene-1,3-dicarboxylic acid] (2) have been determined. Crystals of 1 are triclinic, space group P-1, with unit cell dimensions a = 8.2043(3), b = 11.4000(6), c = 11.8261(6)Å, α = 110.891(5), β = 91.927(3), γ = 98.590(4)deg. and Z = 4. Compound 2 is orthorhombic, space group Pbcn, with unit cell dimensions a = 20.2662(6), b = 12.7161(4), c = 15.9423(5)Å and Z = 8. In 1, intermolecular analinium N-H…O and water O-H…O and O-H…N hydrogen-bonding interactions with sulfone, carboxyl, phenolate and nitro O-atom and aniline N-atom acceptors give a two-dimensional layered structure. With 2, the intermolecular interactions involve both aniline N-H…O and carboxylic acid O-H…O and O-H…N hydrogen bonds to sulfone, carboxyl, nitro and aniline acceptors, giving a three-dimensional network structure. In both structures π--π aromatic ring associations are present.

The IKBALS project: multi-modal reasoning in legal knowledge based systems

In attempting to build intelligent litigation support tools, we have moved beyond first generation, production rule legal expert systems. Our work integrates rule based and case based reasoning with intelligent information retrieval. When using the case based reasoning methodology, or in our case the specialisation of case based retrieval, we need to be aware of how to retrieve relevant experience. Our research, in the legal domain, specifies an approach to the retrieval problem which relies heavily on an extended object oriented/rule based system architecture that is supplemented with causal background information. We use a distributed agent architecture to help support the reasoning process of lawyers. Our approach to integrating rule based reasoning, case based reasoning and case based retrieval is contrasted to the CABARET and PROLEXS architectures which rely on a centralised blackboard architecture. We discuss in detail how our various cooperating agents interact, and provide examples of the system at work. The IKBALS system uses a specialised induction algorithm to induce rules from cases. These rules are then used as indices during the case based retrieval process. Because we aim to build legal support tools which can be modified to suit various domains rather than single purpose legal expert systems, we focus on principles behind developing legal knowledge based systems. The original domain chosen was theAccident Compensation Act 1989 (Victoria, Australia), which relates to the provision of benefits for employees injured at work. For various reasons, which are indicated in the paper, we changed our domain to that ofCredit Act 1984 (Victoria, Australia). This Act regulates the provision of loans by financial institutions. The rule based part of our system which provides advice on the Credit Act has been commercially developed in conjunction with a legal firm. We indicate how this work has lead to the development of a methodology for constructing rule based legal knowledge based systems. We explain the process of integrating this existing commercial rule based system with the case base reasoning and retrieval architecture.

ACE research vignette 031: Startups lead the way in creating a nanobiotechnology industry

This series of research vignettes is aimed at sharing current and interesting research findings from our team of international Entrepreneurship researchers. In this vignette, Dr Martin Bliemel and his research team explore the emergence and evolution of a new knowledge intensive industry, i.e. the nanobiotechnology industry.

Interpretation of association rules with multi-tier granule mining

This study was a step forward to improve the performance for discovering useful knowledge – especially, association rules in this study – in databases. The thesis proposed an approach to use granules instead of patterns to represent knowledge implicitly contained in relational databases; and multi-tier structure to interpret association rules in terms of granules. Association mappings were proposed for the construction of multi-tier structure. With these tools, association rules can be quickly assessed and meaningless association rules can be justified according to the association mappings. The experimental results indicated that the proposed approach is promising.

Characterising transiting exoplanets by way of differential photometry

This paper describes a simple activity for plotting and characterising the light curve from an exoplanet transit event by way of differential photometry analysis. Using free digital imaging software, participants analyse a series of telescope images with the goal of calculating various exoplanet parameters, including its size, orbital radius and habitability. The activity has been designed for a high-school or undergraduate university level and introduces fundamental concepts in astrophysics and an understanding of the basis for exoplanetary science, the transit method and digital photometry.

Matching image sets via adaptive multi convex hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

Physical activity recognition from accelerometer data using a multi-scale ensemble method

Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.

Multi-shot person re-identification via relational stein divergence

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.

Transmedia Practice : A Collective Approach

This volume introduces a collective approach that positions transmedia as a dynamic phenomenon which undergoes constant innovation as it absorbs current trends and advances in its constituent disciplines. The first section, 'Sustaining Future Practices', explores emerging models for defining stakeholder needs, understanding resource requirements and measuring the value and success of transmedia productions. The focus then shifts to 'Intersecting Contexts of Transmedia Practices', which uses the juxtaposition of a diverse collection of case studies to transcend not only the debates about how to define transmedia, but also the professional and disciplinary boundaries that impose artificial constraints upon the way transmedia projects are approached and understood. This inter-disciplinary dialogue aims to promote an ongoing conversation on the challenges and opportunities associated with sustaining this vital creative industry.