Classification of cancer-related death certificates using machine learning

Background Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. Aims In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. Method A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Results Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall F-measure of 0.9866 when evaluated on a set of 5,000 free-text death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. Conclusion The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

An attack-localizing watermarking scheme for natural language documents

We present a text watermarking scheme that embeds a bitstream watermark Wi in a text document P preserving the meaning, context, and flow of the document. The document is viewed as a set of paragraphs, each paragraph being a set of sentences. The sequence of paragraphs and sentences used to embed watermark bits is permuted using a secret key. Then, English language sentence transformations are used to modify sentence lengths, thus embedding watermarking bits in the Least Significant Bits (LSB) of the sentences’ cardinalities. The embedding and extracting algorithms are public, while the secrecy and security of the watermark depends on a secret key K. The probability of False Positives is extremely small, hence avoiding incidental occurrences of our watermark in random text documents. Majority voting provides security against text addition, deletion, and swapping attacks, further reducing the probability of False Positives. The scheme is secure against the general attacks on text watermarks such as reproduction (photocopying, FAX), reformatting, synonym substitution, text addition, text deletion, text swapping, paragraph shuffling and collusion attacks.

Injury narrative text classification : a preliminary study

Description of a patient's injuries is recorded in narrative text form by hospital emergency departments. For statistical reporting, this text data needs to be mapped to pre-defined codes. Existing research in this field uses the Naïve Bayes probabilistic method to build classifiers for mapping. In this paper, we focus on providing guidance on the selection of a classification method. We build a number of classifiers belonging to different classification families such as decision tree, probabilistic, neural networks, and instance-based, ensemble-based and kernel-based linear classifiers. An extensive pre-processing is carried out to ensure the quality of data and, in hence, the quality classification outcome. The records with a null entry in injury description are removed. The misspelling correction process is carried out by finding and replacing the misspelt word with a soundlike word. Meaningful phrases have been identified and kept, instead of removing the part of phrase as a stop word. The abbreviations appearing in many forms of entry are manually identified and only one form of abbreviations is used. Clustering is utilised to discriminate between non-frequent and frequent terms. This process reduced the number of text features dramatically from about 28,000 to 5000. The medical narrative text injury dataset, under consideration, is composed of many short documents. The data can be characterized as high-dimensional and sparse, i.e., few features are irrelevant but features are correlated with one another. Therefore, Matrix factorization techniques such as Singular Value Decomposition (SVD) and Non Negative Matrix Factorization (NNMF) have been used to map the processed feature space to a lower-dimensional feature space. Classifiers with these reduced feature space have been built. In experiments, a set of tests are conducted to reflect which classification method is best for the medical text classification. The Non Negative Matrix Factorization with Support Vector Machine method can achieve 93% precision which is higher than all the tested traditional classifiers. We also found that TF/IDF weighting which works well for long text classification is inferior to binary weighting in short document classification. Another finding is that the Top-n terms should be removed in consultation with medical experts, as it affects the classification performance.

Government grants - an abrogation or management of risks?

New public management (NPFM), with its hands-on, private sector-style performance measurement, output control, parsimonious use of resources, disaggreation of public sector units and greater competition in the public sector, has significantly affected charitable and nonprofit organisations delivering community services (Hood, 1991; Dunleavy, 1994; George & Wilding, 2002). The literature indicates that nonprofit organisations under NPM believe they are doing more for less: while administration is increasing, core costs are not being met; their dependence on government funding comes at the expense of other funding strategies; and there are concerns about proportionality and power asymmetries in the relationship (Kerr & Savelsberg, 2001; Powell & Dalton, 2011; Smith, 2002, p. 175; Morris, 1999, 2000a). Government agencies are under increased pressure to do more with less, demonstrate value for money, measure social outcomes, not merely outputs and minimise political risk (Grant, 2008; McGreogor-Lowndes, 2008). Government-community service organisation relationships are often viewed as 'uneasy alliances' characterised by the pressures that come with the parties' differing roles and expectations and the pressures that come with the parties' differing roles and expectations and the pressurs of funding and security (Productivity Commission, 2010, p. 308; McGregor-Lowndes, 2008, p. 45; Morris, 200a). Significant community services are now delivered to citizens through such relationships, often to the most disadvantaged in the community, and it is important for this to be achieved with equity, efficiently and effectively. On one level, the welfare state was seen as a 'risk management system' for the poor, with the state mitigating the risks of sickness, job loss and old age (Giddens, 1999) with the subsequent neoliberalist outlook shifting this risk back to households (Hacker, 2006). At the core of this risk shift are written contracts. Vincent-Jones (1999,2006) has mapped how NPM is characterised by the use of written contracts for all manner of relations; e.g., relgulation of dealings between government agencies, between individual citizens and the state, and the creation of quais-markets of service providers and infrastructure partners. We take this lens of contracts to examine where risk falls in relation to the outsourcing of community services. First we examine the concept of risk. We consider how risk might be managed and apportioned between governments and community serivce organisations (CSOs) in grant agreements, which are quasiy-market transactions at best. This is informed by insights from the law and economics literature. Then, standard grant agreements covering several years in two jurisdictions - Australia and the United Kingdom - are analysed, to establish the risk allocation between government and CSOs. This is placed in the context of the reform agenda in both jurisdictions. In Australia this context is th enonprofit reforms built around the creation of a national charities regulator, and red tape reduction. In the United Kingdom, the backdrop is the THird Way agenda with its compacts, succeed by Big Society in a climate of austerity. These 'case studies' inform a discussion about who is best placed to bear and manage the risks of community service provision on behalf of government. We conclude by identifying the lessons to be learned from our analysis and possible pathways for further scholarship.

Navigating uncertainty in Australia : fostering informed citizenship through teaching controversial issues with pre-service teachers

Australia is a multicultural immigrant society created by public policy and direct state action over a period of two hundred years. It is now one of the world’s most diverse societies. However, like many nations, Australia faces challenges to managing ‘unauthorized arrivals’ who claim to be refugees. The issue of how to deal with unauthorized arrivals is controversial and highly emotive as it challenges public policy and government capacity to manage the multicultural ‘mix’ of Australia’s population. It also raises questions about border security. Given that it is impossible to discern beforehand who is a ‘proper’ refugee and who is not, claims to refugee status by unauthorised arrivals in Australia need to be tested against international convention criteria devised by the United Nations High Commissioner for Refugees (UNHCR). There are no simple solutions to controversial questions such as how and where should unauthorised arrivals, and the children accompanying them, be housed whilst their claims are investigated? Moreover, as this issue continues to prompt division and heated debate in Australian society, teachers new to the profession are often reluctant to explore it in the classroom. However, there are opportunities in national and state curriculum documents for the values dimensions of curriculum inquiries into controversial issues such as this to be addressed. For example, the most recent national statement on the goals for schooling in Australia, the Melbourne Declaration (MCEETYA, 2008), makes clear that Australian students need to be prepared for the challenges of the 21st century and to develop the capacity for innovation and complex problem-solving. The Melbourne Declaration informs the first national curriculum to be implemented in the Australian states and territories, and all other national and state initiatives. Its focus on developing active and informed citizens who can contribute to a socially cohesive society implies a capacity to deal with a range of issues associated with cultural diversity, This chapter explores the ways in which pre-service and early career teachers in one Australian state reflect upon curriculum opportunities to address controversial issues in the social sciences and history classroom. As part of their pre-service education, all the participants in this study completed a final year social science curriculum method unit that embedded a range of controversial issues, including the placement of children in Australian Immigration Detention Centres (IDCs), for investigation. By drawing from interviews and focus groups conducted with different cohorts of pre-service teachers in their final year of university study and beginning years of teaching, this chapter analyses the range of perceptions about how controversial issues can be examined in the secondary classroom as part of fostering informed citizenship. The discussion and analysis of the qualitative data in this study makes no claims for the representativeness of its findings, rather, a range of beginner teacher insights into a complex and important facet of teaching in a period of change and uncertainty is offered.

Decision boundary setting and classifier combination for text classification

This thesis presents a promising boundary setting method for solving challenging issues in text classification to produce an effective text classifier. A classifier must identify boundary between classes optimally. However, after the features are selected, the boundary is still unclear with regard to mixed positive and negative documents. A classifier combination method to boost effectiveness of the classification model is also presented. The experiments carried out in the study demonstrate that the proposed classifier is promising.

Information Security and Privacy : Proceedings of the 9th Australasian Conference, ACISP 2004, Sydney, Australia, July 13-15, 2004.

Preface The 9th Australasian Conference on Information Security and Privacy (ACISP 2004) was held in Sydney, 13–15 July, 2004. The conference was sponsored by the Centre for Advanced Computing – Algorithms and Cryptography (ACAC), Information and Networked Security Systems Research (INSS), Macquarie University and the Australian Computer Society. The aims of the conference are to bring together researchers and practitioners working in areas of information security and privacy from universities, industry and government sectors. The conference program covered a range of aspects including cryptography, cryptanalysis, systems and network security. The program committee accepted 41 papers from 195 submissions. The reviewing process took six weeks and each paper was carefully evaluated by at least three members of the program committee. We appreciate the hard work of the members of the program committee and external referees who gave many hours of their valuable time. Of the accepted papers, there were nine from Korea, six from Australia, five each from Japan and the USA, three each from China and Singapore, two each from Canada and Switzerland, and one each from Belgium, France, Germany, Taiwan, The Netherlands and the UK. All the authors, whether or not their papers were accepted, made valued contributions to the conference. In addition to the contributed papers, Dr Arjen Lenstra gave an invited talk, entitled Likely and Unlikely Progress in Factoring. This year the program committee introduced the Best Student Paper Award. The winner of the prize for the Best Student Paper was Yan-Cheng Chang from Harvard University for his paper Single Database Private Information Retrieval with Logarithmic Communication. We would like to thank all the people involved in organizing this conference. In particular we would like to thank members of the organizing committee for their time and efforts, Andrina Brennan, Vijayakrishnan Pasupathinathan, Hartono Kurnio, Cecily Lenton, and members from ACAC and INSS.

Governing civil society: How literacy, education and security were brought together

This study questions how the categories of security, education and literacy were brought together as related elements of a whole-of-government strategy in the production of civil society. Drawing on an analysis of key political texts, the study argues that the categories of education and literacy have been used in diverse ways in the production of national, social, economic and geopolitical security interests. As dialogue about security has intensified, rationalisations about the national interest have engaged notions of security leading to the legitimation of a diverse set of policy instruments, strategically used to contain the rise of complex social forces and protect homogenous cultural values.

Submission to the Queensland Government inquiry into "The adequacy of existing financial protections for Queensland's seniors"

This submission covers the following terms of reference: • the current levels of financial literacy of seniors and how that can be improved, for example by education programs; • what support and advice is available to assist seniors with their independent financial decision-making; • online and internet based vulnerabilities and the prevalence and vulnerability of seniors to scams; • agencies and organisations that provide advice and support to seniors requiring financial protection; and • the role of the financial sector in ensuring adequate safeguards for seniors in relation to financial decision-making.

Sustainability at the Australian local government level: Is there room for Strategic Environmental Assessment (SEA)?

Recent calls in Australia have addressed the need for better integration of planning processes. The consequent effort made by government has been, and still is, reshaping the way urban and regional planning and sustainability are managed. Focusing on planning practices at the local and regional levels, we investigate how environmental sustainability is pursued from an institutional perspective. Specifically, we analyse the way that planning in Australian cities aims to achieve sustainable strategies and reflect on the relationship with ‘Strategic Environmental Assessment’. This paper has four goals. First, sustainable planning practices at the local and regional levels are analysed considering the legislative and organizational frameworks of each state. The goal is to identify through an analysis of planning documents how much discretion is given to local councils to address sustainable strategies. Second, we focus on two regional and four cities in Queensland, to outline strengths and weaknesses of current legislative and practical frameworks. We use analytical criteria from the SEA literature to investigate these plans in more detail. Third, we examine the relationship between strategic and statutory plans, to see how sustainability is actually implemented. Finally we compare emerging issues about sustainable planning in Australia with countries overseas with different planning and SEA traditions. Considering that SEA is evolving and there are considerable international experiences, we offer recommendations on how Australia might achieve a more integrated and sustainable approach to planning.

Regulation beyond government: Weber, Foucault and the liberal governance of media content

This paper steps back from the question of how regulation of digital media content occurs, and whether it can be effective, to consider the rationales that inform regulation, and the ethics and practices associated with content regulation. It will be argued that Max Weber's account of bureaucratic expertise remains relevant to such discussions, particularly insofar as it intersects with Michel Foucault's concept of governmentality, and contemporary applications of the notion of 'governing at a distance'. The nature of the challenges to media regulators presented by online environments, and by digital and social media, are considered in depth, but it is argued that the significance of regulatory innovations that respond to such challenges should not be underestimated, nor should the continuing national foundations of media regulation. It will also discuss the relevance of the concept of 'soft law' to contemporary regulatory practice.

Creating healthy food environments in NSW: A knowledge and evidence synthesis to inform advocacy and action. Seven separate documents across the domains: Food promotion

Reviews and synthesizes evidence to make recommendations on policy actions improve food environments in the area of food promotion for NSW Health

Creating healthy food environments in NSW: A knowledge and evidence synthesis to inform advocacy and action. Seven separate documents across the domains: Food retail

Reviews and synthesizes nutrition policy actions to improve food retail for NSW Health

Creating healthy food environments in NSW: A knowledge and evidence synthesis to inform advocacy and action. Seven separate documents across the domains: Overview

Summaries evidence across seven domains of potential food policy action to improve food environments and food supply to prevent obesity for NSW Health