Interestingness Measures for Multi-Level Association Rules

Association rule mining is one technique that is widely used when querying databases, especially those that are transactional, in order to obtain useful associations or correlations among sets of items. Much work has been done focusing on efficiency, effectiveness and redundancy. There has also been a focusing on the quality of rules from single level datasets with many interestingness measures proposed. However, with multi-level datasets now being common there is a lack of interestingness measures developed for multi-level and cross-level rules. Single level measures do not take into account the hierarchy found in a multi-level dataset. This leaves the Support-Confidence approach,which does not consider the hierarchy anyway and has other drawbacks, as one of the few measures available. In this paper we propose two approaches which measure multi-level association rules to help evaluate their interestingness. These measures of diversity and peculiarity can be used to help identify those rules from multi-level datasets that are potentially useful.

ERP systems in the higher education sector : a descriptive study

In response to a range of contextual drivers, the worldwide adoption of ERP Systems in Higher Education Institutions (HEIs) has increased substantially over the past decade. Though this demand continues to grow, with HEIs now a main target market for ERP vendors, little has been published on the topic. This paper reports a sub-study of a larger research effort that aims to contribute to understanding the phenomenon of ERP adoption and evaluation in HEIs in the Australasian region. It presents a descriptive case study conducted at Queensland University of Technology (QUT) in Australia, with emphasis on challenges with ERP adoption. The case study provides rich contextual details about ERP system selection, customisation, integration and evaluation, and insights into the role of consultants in the HE sector. Through this analysis, the paper (a) provides evidence of the dearth of ERP literature pertaining to the HE sector; (b) yields insights into differentiating factors in the HE sector that warrants specific research attention, and (c) offers evidence of how key ERP decisions such as systems selection, customisation, integration, evaluation, and consultant engagement are influenced by the specificities of the HE sector.

Trends in demographic, health behaviour factors, and self-perceived weight status : influences on obesity in Australia from 1995 to 2005

Overweight and obesity are two of the most important emerging public health issues in our time and regarded by the World Health Organisation [WHO] (1998) as a worldwide epidemic. The prevalence of obesity in the USA is the highest in the world, and Australian obesity rates fall into second place. Currently, about 60% of Australian adults are overweight (BMI „d 25kg/m2). The socio-demographic factors associated with overweight and/or obesity have been well demonstrated, but many of the existing studies only examined these relationships at one point of time, and did not examine whether significant relationships changed over time. Furthermore, only limited previous research has examined the issue of the relationship between perception of weight status and actual weight status, as well as factors that may impact on people¡¦s perception of their body weight status. Aims: The aims of the proposed research are to analyse the discrepancy between perceptions of weight status and actual weight status in Australian adults; to examine if there are trends in perceptions of weight status in adults between 1995 to 2004/5; and to propose a range of health promotion strategies and furth er research that may be useful in managing physical activity, healthy diet, and weight reduction. Hypotheses: Four alternate hypotheses are examined by the research: (1) there are associations between independent variables (e.g. socio -demographic factors, physical activity and dietary habits) and overweight and/or obesity; (2) there are associations between the same independent variables and the perception of overweight; (3) there are associations between the same independent variables and the discrepancy between weight status and perception of weight status; and (4) there are trends in overweight and/or obesity, perception of overweight, and the discrepancy in Australian adults from 1995 to 2004/5. Conceptual Framework and Methods: A conceptual framework is developed that shows the associations identified among socio -demographic factors, physical activity and dietary habits with actual weight status, as well as examining perception of weight status. The three latest National Health Survey data bases (1995 , 2001 and 2004/5) were used as the primary data sources. A total of 74,114 Australian adults aged 20 years and over were recruited from these databases. Descriptive statistics, bivariate analyses (One -Way ANOVA tests, unpaired t-tests and Pearson chi-square tests), and multinomial logistic regression modelling were used to analyse the data. Findings: This research reveals that gender, main language spoken at home, occupation status, household structure, private health insurance status, and exercise are related to the discrepancy between actual weight status and perception of weight status, but only gender and exercise are related to the discrepancy across the three time point s. The current research provides more knowledge about perception of weight status independently. Factors which affect perception of overweight are gender, age, language spoken at home, private health insurance status, and diet ary habits. The study also finds that many factors that impact overweight and/or obesity also have an effect on perception of overweight, such as age, language spoken at home, household structure, and exercise. However, some factors (i.e. private health insurance status and milk consumption) only impact on perception of overweight. Furthermore, factors that are rel ated to people’s overweight are not totally related to people’s underestimation of their body weight status in the study results. Thus, there are unknown factors which can affect people’s underestimation of their body weight status. Conclusions: Health promotion and education activities should provide education about population health education and promotion and education for particular at risk sub -groups. Further research should take the form of a longitudinal study design ed to examine the causal relationship between overweight and/or obesity and underestimation of body weight status, it should also place more attention on the relationships between overweight and/or obesity and dietary habits, with a more comprehensive representation of SES. Moreover, further research that deals with identification of characteristics about perception of weight status, in particular the underestimation of body weight status should be undertaken.

Beyond the user : use and non-use in HCI

For many, an interest in Human-Computer Interaction is equivalent to an interest in usability. However, using computers is only one way of relating to them, and only one topic from which we can learn about interactions between people and technology. Here, we focus on not using computers – ways not to use them, aspects of not using them, what not using them might mean, and what we might learn by examining non-use as seriously as we examine use.

The impact of health information technology on the quality of medical and health care : a systematic review

Objective: To systematically review the published evidence of the impact of health information technology (HIT) on the quality of medical and health care specifically clinicians’ adherence to evidence-based guidelines and the corresponding impact this had on patient clinical outcomes. In order to be as inclusive as possible the research examined literature discussing the use of health information technologies and systems in both medical care such as clinical and surgical, and other health care such as allied health and preventive services.----- Design: Systematic review----- Data Sources: Relevant literature was systematically searched on English language studies indexed in MEDLINE and CINAHL(1998 to 2008), Cochrane Library, PubMed, Database of Abstracts of Review of Effectiveness (DARE), Google scholar and other relevant electronic databases. A search for eligible studies (matching the inclusion criteria) was also performed by searching relevant conference proceedings available through internet and electronic databases, as well as using reference lists identified from cited papers.----- Selection criteria: Studies were included in the review if they examined the impact of Electronic Health Record (EHR), Computerised Provider Order-Entry (CPOE), or Decision Support System (DS); and if the primary outcomes of the studies were focused on the level of compliance with evidence-based guidelines among clinicians. Measures could be either changes in clinical processes resulting from a change of the providers’ behaviour or specific patient outcomes that demonstrated the effectiveness of a particular treatment given by providers. ----- Methods: Studies were reviewed and summarised in tabular and text form. Due to heterogeneity between studies, meta-analysis was not performed.----- Results: Out of 17 studies that assessed the impact of health information technology on health care practitioners’ performance, 14 studies revealed a positive improvement in relation to their compliance with evidence-based guidelines. The primary domain of improvement was evident from preventive care and drug ordering studies. Results from the studies that included an assessment for patient outcomes however, were insufficient to detect either clinically or statistically important improvements as only a small proportion of these studies found benefits. For instance, only 3 studies had shown positive improvement, while 5 studies revealed either no change or adverse outcomes.----- Conclusion: Although the number of included studies was relatively small for reaching a conclusive statement about the effectiveness of health information technologies and systems on clinical care, the results demonstrated consistency with other systematic reviews previously undertaken. Widescale use of HIT has been shown to increase clinician’s adherence to guidelines in this review. Therefore, it presents ongoing opportunities to maximise the uptake of research evidence into practice for health care organisations, policy makers and stakeholders.

Towards an automatic road lane marks extraction based on ISODATA segmentation and shadow detection from large-scale aerial images

The automatic extraction of road features from remote sensed images has been a topic of great interest within the photogrammetric and remote sensing communities for over 3 decades. Although various techniques have been reported in the literature, it is still challenging to efficiently extract the road details with the increasing of image resolution as well as the requirement for accurate and up-to-date road data. In this paper, we will focus on the automatic detection of road lane markings, which are crucial for many applications, including lane level navigation and lane departure warning. The approach consists of four steps: i) data preprocessing, ii) image segmentation and road surface detection, iii) road lane marking extraction based on the generated road surface, and iv) testing and system evaluation. The proposed approach utilized the unsupervised ISODATA image segmentation algorithm, which segments the image into vegetation regions, and road surface based only on the Cb component of YCbCr color space. A shadow detection method based on YCbCr color space is also employed to detect and recover the shadows from the road surface casted by the vehicles and trees. Finally, the lane marking features are detected from the road surface using the histogram clustering. The experiments of applying the proposed method to the aerial imagery dataset of Gympie, Queensland demonstrate the efficiency of the approach.

Creative Commons & Data

This guide is relevant to anyone who owns copyright in data compilations or databases and wants to share their data openly, or to anyone who wants to use data under an open content licence. ANDS Guides are available at http://ands.org.au/guides/index.html.

Evaluating information systems

The book within which this chapter appears is published as a research reference book (not a coursework textbook) on Management Information Systems (MIS) for seniors or graduate students in Chinese universities. It is hoped that this chapter, along with the others, will be helpful to MIS scholars and PhD/Masters research students in China who seek understanding of several central Information Systems (IS) research topics and related issues. The subject of this chapter - ‘Evaluating Information Systems’ - is broad, and cannot be addressed in its entirety in any depth within a single book chapter. The chapter proceeds from the truism that organizations have limited resources and those resources need to be invested in a way that provides greatest benefit to the organization. IT expenditure represents a substantial portion of any organization’s investment budget and IT related innovations have broad organizational impacts. Evaluation of the impact of this major investment is essential to justify this expenditure both pre- and post-investment. Evaluation is also important to prioritize possible improvements. The chapter (and most of the literature reviewed herein) admittedly assumes a blackbox view of IS/IT1, emphasizing measures of its consequences (e.g. for organizational performance or the economy) or perceptions of its quality from a user perspective. This reflects the MIS emphasis – a ‘management’ emphasis rather than a software engineering emphasis2, where a software engineering emphasis might be on the technical characteristics and technical performance. Though a black-box approach limits diagnostic specificity of findings from a technical perspective, it offers many benefits. In addition to superior management information, these benefits may include economy of measurement and comparability of findings (e.g. see Part 4 on Benchmarking IS). The chapter does not purport to be a comprehensive treatment of the relevant literature. It does, however, reflect many of the more influential works, and a representative range of important writings in the area. The author has been somewhat opportunistic in Part 2, employing a single journal – The Journal of Strategic Information Systems – to derive a classification of literature in the broader domain. Nonetheless, the arguments for this approach are believed to be sound, and the value from this exercise real. The chapter drills down from the general to the specific. It commences with a highlevel overview of the general topic area. This is achieved in 2 parts: - Part 1 addressing existing research in the more comprehensive IS research outlets (e.g. MISQ, JAIS, ISR, JMIS, ICIS), and Part 2 addressing existing research in a key specialist outlet (i.e. Journal of Strategic Information Systems). Subsequently, in Part 3, the chapter narrows to focus on the sub-topic ‘Information Systems Success Measurement’; then drilling deeper to become even more focused in Part 4 on ‘Benchmarking Information Systems’. In other words, the chapter drills down from Parts 1&2 Value of IS, to Part 3 Measuring Information Systems Success, to Part 4 Benchmarking IS. While the commencing Parts (1&2) are by definition broadly relevant to the chapter topic, the subsequent, more focused Parts (3 and 4) admittedly reflect the author’s more specific interests. Thus, the three chapter foci – value of IS, measuring IS success, and benchmarking IS - are not mutually exclusive, but, rather, each subsequent focus is in most respects a sub-set of the former. Parts 1&2, ‘the Value of IS’, take a broad view, with much emphasis on ‘the business Value of IS’, or the relationship between information technology and organizational performance. Part 3, ‘Information System Success Measurement’, focuses more specifically on measures and constructs employed in empirical research into the drivers of IS success (ISS). (DeLone and McLean 1992) inventoried and rationalized disparate prior measures of ISS into 6 constructs – System Quality, Information Quality, Individual Impact, Organizational Impact, Satisfaction and Use (later suggesting a 7th construct – Service Quality (DeLone and McLean 2003)). These 6 constructs have been used extensively, individually or in some combination, as the dependent variable in research seeking to better understand the important antecedents or drivers of IS Success. Part 3 reviews this body of work. Part 4, ‘Benchmarking Information Systems’, drills deeper again, focusing more specifically on a measure of the IS that can be used as a ‘benchmark’3. This section consolidates and extends the work of the author and his colleagues4 to derive a robust, validated IS-Impact measurement model for benchmarking contemporary Information Systems (IS). Though IS-Impact, like ISS, has potential value in empirical, causal research, its design and validation has emphasized its role and value as a comparator; a measure that is simple, robust and generalizable and which yields results that are as far as possible comparable across time, across stakeholders, and across differing systems and systems contexts.

Age-related maculopathy : linking aetiology and pathophysiological changes to the ischaemia hypothesis

Age-related maculopathy (ARM) has remained a challenging topic with respect to its aetiology, pathomechanisms, early detection and treatment since the late 19th century when it was first described as its own entity. ARM was previously considered an inflammatory disease, a degenerative disease, a tumor and as the result of choroidal hemodynamic disturbances and ischaemia. The latter processes have been repeatedly suggested to have a key role in its development and progression. In vivo experiments under hypoxic conditions could be models for the ischaemic deficits in ARM. Recent research has also linked ARM with gene polymorphisms. It is however unclear what triggers a person's gene susceptibility. In this manuscript, a linking hypothesis between aetiological factors including ischaemia and genetics and the development of early clinicopathological changes in ARM is proposed. New clinical psychophysical and electrophysiological tests are introduced that can detect ARM at an early stage. Models of early ARM based upon hemodynamic, photoreceptor and post-receptoral deficits are described and the mechanisms by which ischaemia may be involved as a final common pathway are considered. In neovascular age-related macular degeneration (neovascular AMD), ischaemia is thought to promote release of vascular endothelial growth factor (VEGF) which induces chorioretinal neovascularisation. VEGF is critical in the maintenance of the healthy choriocapillaris. In the final section of the manuscript the documentation of the effect of new anti-VEGF treatments on retinal function in neovascular AMD is critically viewed.

Recommending best answer in a collaborative question answering system

The World Wide Web has become a medium for people to share information. People use Web-based collaborative tools such as question answering (QA) portals, blogs/forums, email and instant messaging to acquire information and to form online-based communities. In an online QA portal, a user asks a question and other users can provide answers based on their knowledge, with the question usually being answered by many users. It can become overwhelming and/or time/resource consuming for a user to read all of the answers provided for a given question. Thus, there exists a need for a mechanism to rank the provided answers so users can focus on only reading good quality answers. The majority of online QA systems use user feedback to rank users’ answers and the user who asked the question can decide on the best answer. Other users who didn’t participate in answering the question can also vote to determine the best answer. However, ranking the best answer via this collaborative method is time consuming and requires an ongoing continuous involvement of users to provide the needed feedback. The objective of this research is to discover a way to recommend the best answer as part of a ranked list of answers for a posted question automatically, without the need for user feedback. The proposed approach combines both a non-content-based reputation method and a content-based method to solve the problem of recommending the best answer to the user who posted the question. The non-content method assigns a score to each user which reflects the users’ reputation level in using the QA portal system. Each user is assigned two types of non-content-based reputations cores: a local reputation score and a global reputation score. The local reputation score plays an important role in deciding the reputation level of a user for the category in which the question is asked. The global reputation score indicates the prestige of a user across all of the categories in the QA system. Due to the possibility of user cheating, such as awarding the best answer to a friend regardless of the answer quality, a content-based method for determining the quality of a given answer is proposed, alongside the non-content-based reputation method. Answers for a question from different users are compared with an ideal (or expert) answer using traditional Information Retrieval and Natural Language Processing techniques. Each answer provided for a question is assigned a content score according to how well it matched the ideal answer. To evaluate the performance of the proposed methods, each recommended best answer is compared with the best answer determined by one of the most popular link analysis methods, Hyperlink-Induced Topic Search (HITS). The proposed methods are able to yield high accuracy, as shown by correlation scores: Kendall correlation and Spearman correlation. The reputation method outperforms the HITS method in terms of recommending the best answer. The inclusion of the reputation score with the content score improves the overall performance, which is measured through the use of Top-n match scores.

Structuring free-form tagging in online news

Tagging has become one of the key activities in next generation websites which allow users selecting short labels to annotate, manage, and share multimedia information such as photos, videos and bookmarks. Tagging does not require users any prior training before participating in the annotation activities as they can freely choose any terms which best represent the semantic of contents without worrying about any formal structure or ontology. However, the practice of free-form tagging can lead to several problems, such as synonymy, polysemy and ambiguity, which potentially increase the complexity of managing the tags and retrieving information. To solve these problems, this research aims to construct a lightweight indexing scheme to structure tags by identifying and disambiguating the meaning of terms and construct a knowledge base or dictionary. News has been chosen as the primary domain of application to demonstrate the benefits of using structured tags for managing the rapidly changing and dynamic nature of news information. One of the main outcomes of this work is an automatically constructed vocabulary that defines the meaning of each named entity tag, which can be extracted from a news article (including person, location and organisation), based on experts suggestions from major search engines and the knowledge from public database such as Wikipedia. To demonstrate the potential applications of the vocabulary, we have used it to provide more functionalities in an online news website, including topic-based news reading, intuitive tagging, clipping and sharing of interesting news, as well as news filtering or searching based on named entity tags. The evaluation results on the impact of disambiguating tags have shown that the vocabulary can help to significantly improve news searching performance. The preliminary results from our user study have demonstrated that users can benefit from the additional functionalities on the news websites as they are able to retrieve more relevant news, clip and share news with friends and families effectively.

Statistical analysis and reduction of multiple access interference in MC-CDMA systems

Multicarrier code division multiple access (MC-CDMA) is a very promising candidate for the multiple access scheme in fourth generation wireless communi- cation systems. During asynchronous transmission, multiple access interference (MAI) is a major challenge for MC-CDMA systems and significantly affects their performance. The main objectives of this thesis are to analyze the MAI in asyn- chronous MC-CDMA, and to develop robust techniques to reduce the MAI effect. Focus is first on the statistical analysis of MAI in asynchronous MC-CDMA. A new statistical model of MAI is developed. In the new model, the derivation of MAI can be applied to different distributions of timing offset, and the MAI power is modelled as a Gamma distributed random variable. By applying the new statistical model of MAI, a new computer simulation model is proposed. This model is based on the modelling of a multiuser system as a single user system followed by an additive noise component representing the MAI, which enables the new simulation model to significantly reduce the computation load during computer simulations. MAI reduction using slow frequency hopping (SFH) technique is the topic of the second part of the thesis. Two subsystems are considered. The first sub- system involves subcarrier frequency hopping as a group, which is referred to as GSFH/MC-CDMA. In the second subsystem, the condition of group hopping is dropped, resulting in a more general system, namely individual subcarrier frequency hopping MC-CDMA (ISFH/MC-CDMA). This research found that with the introduction of SFH, both of GSFH/MC-CDMA and ISFH/MC-CDMA sys- tems generate less MAI power than the basic MC-CDMA system during asyn- chronous transmission. Because of this, both SFH systems are shown to outper- form MC-CDMA in terms of BER. This improvement, however, is at the expense of spectral widening. In the third part of this thesis, base station polarization diversity, as another MAI reduction technique, is introduced to asynchronous MC-CDMA. The com- bined system is referred to as Pol/MC-CDMA. In this part a new optimum com- bining technique namely maximal signal-to-MAI ratio combining (MSMAIRC) is proposed to combine the signals in two base station antennas. With the applica- tion of MSMAIRC and in the absents of additive white Gaussian noise (AWGN), the resulting signal-to-MAI ratio (SMAIR) is not only maximized but also in- dependent of cross polarization discrimination (XPD) and antenna angle. In the case when AWGN is present, the performance of MSMAIRC is still affected by the XPD and antenna angle, but to a much lesser degree than the traditional maximal ratio combining (MRC). Furthermore, this research found that the BER performance for Pol/MC-CDMA can be further improved by changing the angle between the two receiving antennas. Hence the optimum antenna angles for both MSMAIRC and MRC are derived and their effects on the BER performance are compared. With the derived optimum antenna angle, the Pol/MC-CDMA system is able to obtain the lowest BER for a given XPD.

Transforming Queensland VET : Challenges and Opportunities (Volume 1)

The volume is a collection of papers that address issues associated with change in the delivery of VET programs in Queensland, foreshadowed by the release of The Queensland Skill Plan in 2006. Issues that relate to the implementation of the Actions identified in the Queensland Skills Plan are the focus of the collection. In particular, the incorporation of Information Communication Technologies (ICTs) and e-learning approaches in the delivery of training packages is a key topic, how such change can be managed in the delivery of training programs, as well as broader professional development issues for VET practitioners. Change at an organisational level is the focus of two papers. Lyn Ambrose uses ideas from Diffusion of Innovations Theory to consider how the adoption eLearning in a TAFE community can be addressed. The paper by Susan Todhunter also discusses the organisational challenges in change initiatives in TAFE Institutes. Specific issues related to in the professional development of VET teachers are the focus of the papers by Mary Campbell, Sharon Altena, and Judy Gronold. Mary Campbell discusses the importance of building staff capabilities within the TAFE system and how this might be managed. Sharon Altena considers how professional development programs are currently delivered and how new approaches to professional development for TAFE teachers are needed to ensure changes can be sustained in teaching practice. The paper by Judy Gronold takes up a specific challenge for VET practitioners in the Queensland Skills Plan. She addresses issues related to embedding employability skills into training delivery in order to address industries’ need for flexible, multi-skilled productive workers. Mark Driver discusses the issues resulting from increased number of mature-aged learners in VET programs and how this change in the demographic profile of students presents challenges to the VET system. In the paper by David McKee, implications in the incorporation of ICTs into trade training are discussed and the need for effective change management strategies to ensure a smooth transition to new ways of delivering trade training. Finally, in the paper by David Roberts, the potential of Problem-Based Learning (PBL) approaches in VET training and the role of ICTs within such approaches are discussed. David uses horticulture training as an example to discuss the issues in implementing PBL effectively in VET programs. These papers were completed by the authors as a part of their postgraduate studies at QUT. The views reported are those of the authors and should not be attributed to the Queensland Department of Education, Training and the Arts.

A shameful spectacle

The linguistics of violence in film and on television is a hotly debated topic, especially whenever outrageously violent crimes are committed in the community. The debate tends to proceed thus: was the perpetrator addicted to watching violent films and videos, and if so, did the language of mediated violence translate into the language of everyday action, blurring the boundaries between fantasy and reality? The cause—effect relationship between fantasies enacted on screen and horrific real-life crimes has never been proven scientifically, despite endless governmental inquiries and many attempts by academics to discover a causation formula. I will not be looking so much at the vexed question of the relationship between stylized violence on celluloid and real violence in a community. Rather, I wish to explore the nature of a particular form of mediated, gendered violence through an analysis of the language of several key films made in the past decade focusing on the violent crime of rape: Hollywood films The Accused (1988), Casualties of War (1989), Thelma and Louise (1991), Strange Days (1996), and the Australian films Shame (1988) and The Boys (1998). In this way, I wish to show how rape is depicted linguistically in film, and how such films may actually give solutions to this abhorrent kind of violence rather than thrill the viewer vicariously, or, in a worst case scenario, stimulate people to further violence.

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.