Using Agents for Mining Maintenance Data while interacting in 3D Objectoriented Virtual Environments

This report demonstrates the development of: (a) object-oriented representation to provide 3D interactive environment using data provided by Woods Bagot; (b) establishing basis of agent technology for mining building maintenance data, and (C) 3D interaction in virtual environments using object-oriented representation. Applying data mining over industry maintenance database has been demonstrated in the previous report.

Intelligent prognostics of machinery health utilising suspended condition monitoring data

The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models for forecasting machinery health based on condition data. Although these models have aided the advancement of the discipline, they have made only a limited contribution to developing an effective machinery health prognostic system. The literature review indicates that there is not yet a prognostic model that directly models and fully utilises suspended condition histories (which are very common in practice since organisations rarely allow their assets to run to failure); that effectively integrates population characteristics into prognostics for longer-range prediction in a probabilistic sense; which deduces the non-linear relationship between measured condition data and actual asset health; and which involves minimal assumptions and requirements. This work presents a novel approach to addressing the above-mentioned challenges. The proposed model consists of a feed-forward neural network, the training targets of which are asset survival probabilities estimated using a variation of the Kaplan-Meier estimator and a degradation-based failure probability density estimator. The adapted Kaplan-Meier estimator is able to model the actual survival status of individual failed units and estimate the survival probability of individual suspended units. The degradation-based failure probability density estimator, on the other hand, extracts population characteristics and computes conditional reliability from available condition histories instead of from reliability data. The estimated survival probability and the relevant condition histories are respectively presented as “training target” and “training input” to the neural network. The trained network is capable of estimating the future survival curve of a unit when a series of condition indices are inputted. Although the concept proposed may be applied to the prognosis of various machine components, rolling element bearings were chosen as the research object because rolling element bearing failure is one of the foremost causes of machinery breakdowns. Computer simulated and industry case study data were used to compare the prognostic performance of the proposed model and four control models, namely: two feed-forward neural networks with the same training function and structure as the proposed model, but neglected suspended histories; a time series prediction recurrent neural network; and a traditional Weibull distribution model. The results support the assertion that the proposed model performs better than the other four models and that it produces adaptive prediction outputs with useful representation of survival probabilities. This work presents a compelling concept for non-parametric data-driven prognosis, and for utilising available asset condition information more fully and accurately. It demonstrates that machinery health can indeed be forecasted. The proposed prognostic technique, together with ongoing advances in sensors and data-fusion techniques, and increasingly comprehensive databases of asset condition data, holds the promise for increased asset availability, maintenance cost effectiveness, operational safety and – ultimately – organisation competitiveness.

Granule-based knowledge representation for intra and inter transaction association mining

Abstract With the phenomenal growth of electronic data and information, there are many demands for the development of efficient and effective systems (tools) to perform the issue of data mining tasks on multidimensional databases. Association rules describe associations between items in the same transactions (intra) or in different transactions (inter). Association mining attempts to find interesting or useful association rules in databases: this is the crucial issue for the application of data mining in the real world. Association mining can be used in many application areas, such as the discovery of associations between customers’ locations and shopping behaviours in market basket analysis. Association mining includes two phases. The first phase, called pattern mining, is the discovery of frequent patterns. The second phase, called rule generation, is the discovery of interesting and useful association rules in the discovered patterns. The first phase, however, often takes a long time to find all frequent patterns; these also include much noise. The second phase is also a time consuming activity that can generate many redundant rules. To improve the quality of association mining in databases, this thesis provides an alternative technique, granule-based association mining, for knowledge discovery in databases, where a granule refers to a predicate that describes common features of a group of transactions. The new technique first transfers transaction databases into basic decision tables, then uses multi-tier structures to integrate pattern mining and rule generation in one phase for both intra and inter transaction association rule mining. To evaluate the proposed new technique, this research defines the concept of meaningless rules by considering the co-relations between data-dimensions for intratransaction-association rule mining. It also uses precision to evaluate the effectiveness of intertransaction association rules. The experimental results show that the proposed technique is promising.

Modeling videokeratoscopic height data with spherical harmonics

Purpose: All currently considered parametric models used for decomposing videokeratoscopy height data are viewercentered and hence describe what the operator sees rather than what the surface is. The purpose of this study was to ascertain the applicability of an object-centered representation to modeling of corneal surfaces. Methods: A three-dimensional surface decomposition into a series of spherical harmonics is considered and compared with the traditional Zernike polynomial expansion for a range of videokeratoscopic height data. Results: Spherical harmonic decomposition led to significantly better fits to corneal surfaces (in terms of the root mean square error values) than the corresponding Zernike polynomial expansions with the same number of coefficients, for all considered corneal surfaces, corneal diameters, and model orders. Conclusions: Spherical harmonic decomposition is a viable alternative to Zernike polynomial decomposition. It achieves better fits to videokeratoscopic height data and has the advantage of an object-centered representation that could be particularly suited to the analysis of multiple corneal measurements.

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.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

A statistical framework for natural feature representation

This paper presents a robust stochastic framework for the incorporation of visual observations into conventional estimation, data fusion, navigation and control algorithms. The representation combines Isomap, a non-linear dimensionality reduction algorithm, with expectation maximization, a statistical learning scheme. The joint probability distribution of this representation is computed offline based on existing training data. The training phase of the algorithm results in a nonlinear and non-Gaussian likelihood model of natural features conditioned on the underlying visual states. This generative model can be used online to instantiate likelihoods corresponding to observed visual features in real-time. The instantiated likelihoods are expressed as a Gaussian mixture model and are conveniently integrated within existing non-linear filtering algorithms. Example applications based on real visual data from heterogenous, unstructured environments demonstrate the versatility of the generative models.

A stochastic model for natural feature representation

This paper presents a robust stochastic model for the incorporation of natural features within data fusion algorithms. The representation combines Isomap, a non-linear manifold learning algorithm, with Expectation Maximization, a statistical learning scheme. The representation is computed offline and results in a non-linear, non-Gaussian likelihood model relating visual observations such as color and texture to the underlying visual states. The likelihood model can be used online to instantiate likelihoods corresponding to observed visual features in real-time. The likelihoods are expressed as a Gaussian Mixture Model so as to permit convenient integration within existing nonlinear filtering algorithms. The resulting compactness of the representation is especially suitable to decentralized sensor networks. Real visual data consisting of natural imagery acquired from an Unmanned Aerial Vehicle is used to demonstrate the versatility of the feature representation.

Decentralised Data Fusion with Parzen Density Estimates

Decentralised sensor networks typically consist of multiple processing nodes supporting one or more sensors. These nodes are interconnected via wireless communication. Practical applications of Decentralised Data Fusion have generally been restricted to using Gaussian based approaches such as the Kalman or Information Filter This paper proposes the use of Parzen window estimates as an alternate representation to perform Decentralised Data Fusion. It is required that the common information between two nodes be removed from any received estimates before local data fusion may occur Otherwise, estimates may become overconfident due to data incest. A closed form approximation to the division of two estimates is described to enable conservative assimilation of incoming information to a node in a decentralised data fusion network. A simple example of tracking a moving particle with Parzen density estimates is shown to demonstrate how this algorithm allows conservative assimilation of network information.

Rich probabilistic representations for bearing only decentralised data fusion

The aim of this paper is to demonstrate the validity of using Gaussian mixture models (GMM) for representing probabilistic distributions in a decentralised data fusion (DDF) framework. GMMs are a powerful and compact stochastic representation allowing efficient communication of feature properties in large scale decentralised sensor networks. It will be shown that GMMs provide a basis for analytical solutions to the update and prediction operations for general Bayesian filtering. Furthermore, a variant on the Covariance Intersect algorithm for Gaussian mixtures will be presented ensuring a conservative update for the fusion of correlated information between two nodes in the network. In addition, purely visual sensory data will be used to show that decentralised data fusion and tracking of non-Gaussian states observed by multiple autonomous vehicles is feasible.

Bridging the representation and interaction challenges of mobile context-aware computing: designing agile ridesharing

The increasing capability of mobile devices and social networks to gather contextual and social data has led to increased interest in context-aware computing for mobile applications. This paper explores ways of reconciling two different viewpoints of context, representational and interactional, that have arisen respectively from technical and social science perspectives on context-aware computing. Through a case study in agile ridesharing, the importance of dynamic context control, historical context and broader context is discussed. We build upon earlier work that has sought to address the divide by further explicating the problem in the mobile context and expanding on the design approaches.

Impact of a data warehouse model for improved decision-making process in healthcare

The health system is one sector dealing with a deluge of complex data. Many healthcare organisations struggle to utilise these volumes of health data effectively and efficiently. Also, there are many healthcare organisations, which still have stand-alone systems, not integrated for management of information and decision-making. This shows, there is a need for an effective system to capture, collate and distribute this health data. Therefore, implementing the data warehouse concept in healthcare is potentially one of the solutions to integrate health data. Data warehousing has been used to support business intelligence and decision-making in many other sectors such as the engineering, defence and retail sectors. The research problem that is going to be addressed is, "how can data warehousing assist the decision-making process in healthcare". To address this problem the researcher has narrowed an investigation focusing on a cardiac surgery unit. This research used the cardiac surgery unit at the Prince Charles Hospital (TPCH) as the case study. The cardiac surgery unit at TPCH uses a stand-alone database of patient clinical data, which supports clinical audit, service management and research functions. However, much of the time, the interaction between the cardiac surgery unit information system with other units is minimal. There is a limited and basic two-way interaction with other clinical and administrative databases at TPCH which support decision-making processes. The aims of this research are to investigate what decision-making issues are faced by the healthcare professionals with the current information systems and how decision-making might be improved within this healthcare setting by implementing an aligned data warehouse model or models. As a part of the research the researcher will propose and develop a suitable data warehouse prototype based on the cardiac surgery unit needs and integrating the Intensive Care Unit database, Clinical Costing unit database (Transition II) and Quality and Safety unit database [electronic discharge summary (e-DS)]. The goal is to improve the current decision-making processes. The main objectives of this research are to improve access to integrated clinical and financial data, providing potentially better information for decision-making for both improved from the questionnaire and by referring to the literature, the results indicate a centralised data warehouse model for the cardiac surgery unit at this stage. A centralised data warehouse model addresses current needs and can also be upgraded to an enterprise wide warehouse model or federated data warehouse model as discussed in the many consulted publications. The data warehouse prototype was able to be developed using SAS enterprise data integration studio 4.2 and the data was analysed using SAS enterprise edition 4.3. In the final stage, the data warehouse prototype was evaluated by collecting feedback from the end users. This was achieved by using output created from the data warehouse prototype as examples of the data desired and possible in a data warehouse environment. According to the feedback collected from the end users, implementation of a data warehouse was seen to be a useful tool to inform management options, provide a more complete representation of factors related to a decision scenario and potentially reduce information product development time. However, there are many constraints exist in this research. For example the technical issues such as data incompatibilities, integration of the cardiac surgery database and e-DS database servers and also, Queensland Health information restrictions (Queensland Health information related policies, patient data confidentiality and ethics requirements), limited availability of support from IT technical staff and time restrictions. These factors have influenced the process for the warehouse model development, necessitating an incremental approach. This highlights the presence of many practical barriers to data warehousing and integration at the clinical service level. Limitations included the use of a small convenience sample of survey respondents, and a single site case report study design. As mentioned previously, the proposed data warehouse is a prototype and was developed using only four database repositories. Despite this constraint, the research demonstrates that by implementing a data warehouse at the service level, decision-making is supported and data quality issues related to access and availability can be reduced, providing many benefits. Output reports produced from the data warehouse prototype demonstrated usefulness for the improvement of decision-making in the management of clinical services, and quality and safety monitoring for better clinical care. However, in the future, the centralised model selected can be upgraded to an enterprise wide architecture by integrating with additional hospital units’ databases.

XML data clustering: An overview

In the last few years we have observed a proliferation of approaches for clustering XML docu- ments and schemas based on their structure and content. The presence of such a huge amount of approaches is due to the different applications requiring the XML data to be clustered. These applications need data in the form of similar contents, tags, paths, structures and semantics. In this paper, we first outline the application contexts in which clustering is useful, then we survey approaches so far proposed relying on the abstract representation of data (instances or schema), on the identified similarity measure, and on the clustering algorithm. This presentation leads to draw a taxonomy in which the current approaches can be classified and compared. We aim at introducing an integrated view that is useful when comparing XML data clustering approaches, when developing a new clustering algorithm, and when implementing an XML clustering compo- nent. Finally, the paper moves into the description of future trends and research issues that still need to be faced.

Representation of assertions in clinical free-­text using SNOMED CT

Information retrieval (IR) by clinicians in the healthcare setting is critical for informing clinical decision-making. However, a large part of this information is in the form of free-text and inhibits clinical decision support and effective healthcare services. This makes meaningful use of clinical free-­text in electronic health records (EHRs) for patient care a difficult task. Within the context of IR, given a repository of free-­text clinical reports, one might want to retrieve and analyse data for patients who have a known clinical finding.

The minority report : disproportionate representation in Australia’s largest education system

The overrepresentation of students from minority ethnic groups in separate special education settings has been extensively documented in North America, yet little research exists for Australian school systems. To address this gap, we systematically analyzed 13 years of enrolment data from the state of New South Wales. Stark differences are seen in patterns of enrolment between Indigenous students, students from a Language Background Other than English (LBOTE), and non-Indigenous English speaking students. Moreover, these differences are increasing. While enrollments of Indigenous students in separate settings increased faster across time than did enrollments of Indigenous students in mainstream, enrollments of LBOTE students in mainstream increased faster than did enrollments of LBOTE students in separate settings.