Simple supervised dissimilarity measure : bolstering iForest-induced similarity with class information without learning
- Authors: Wells, Jonathan , Aryal, Sunil , Ting, Kai
- Date: 2020
- Type: Text , Journal article
- Relation: Knowledge and Information Systems Vol. 62, no. 8 (2020), p. 3203-3216
- Full Text: false
- Reviewed:
- Description: Existing distance metric learning methods require optimisation to learn a feature space to transform data—this makes them computationally expensive in large datasets. In classification tasks, they make use of class information to learn an appropriate feature space. In this paper, we present a simple supervised dissimilarity measure which does not require learning or optimisation. It uses class information to measure dissimilarity of two data instances in the input space directly. It is a supervised version of an existing data-dependent dissimilarity measure called me. Our empirical results in k-NN and LVQ classification tasks show that the proposed simple supervised dissimilarity measure generally produces predictive accuracy better than or at least as good as existing state-of-the-art supervised and unsupervised dissimilarity measures. © 2020, Springer-Verlag London Ltd., part of Springer Nature.
Applying anatomical therapeutic chemical (ATC) and critical term ontologies to Australian drug safety data for association rules and adverse event signalling
- Authors: Saunders, Gary , Ivkovic, Sasha , Ghosh, Ranadhir , Yearwood, John
- Date: 2005
- Type: Text , Journal article
- Relation: Conferences in Research and Practice in Information Technology, Advances in Ontologies 2005: Proceedings of the Australasian Ontology Workshop AOW 2005 Vol. 58, no. (2005), p. 93-98
- Full Text:
- Reviewed:
- Description: C1
- Description: 2003001450
Why do good accountants do bad things? Conversations with inmate accountants
- Authors: Dellaportas, Steven
- Date: 2007
- Type: Text , Conference paper
- Relation: Paper presented at 2007 AFAANZ Conference, The Gold Coast, Queensland : 1st-3rd July 2007
- Full Text: false
- Description: The extent of fraud in large organistations is an increasing phenomenon. The implications of fraud are well known, in addition to the moneys lost from the fraudulent act, fraud has adverse effects arising from the negative publicity relating to the fraud. Responding to fraud represents a major challenge for business and the professions with considerable resources being devoted annually to fraud risk management and prevention.
- Description: 2003005171
Being smart and being green : Entrepreneurial innovation in challenging times
- Authors: Braun, Patrice , Lowe, Julian
- Date: 2009
- Type: Text , Conference paper
- Relation: Paper presented at 32nd Institute for Small Business & Entrepreneurship Conference, ISBE 2009, Liverpool, UK : 3rd-6th November 2009
- Full Text:
- Description: In difficult times business operators are looking for clever and affordable ways to grow their enterprises. This paper seeks to make a contribution to a better understanding of proactive environmental and innovation strategies for SMEs and the interaction between demand and supply towards sustainable and innovative business practices. The paper discusses the combined outcomes of the exit survey of a greening small business 2008 pilot program and the entry survey for the 2009 online training and networking version of the program, which fuses environmental, business and ICT- enabled skilling to enhance both SME entrepreneurship and innovation. The study suggests that SME business sustainability cannot be reduced to an oversimplified business case and that pro-environmental strategy adoption and behaviour, and particularly behavioural change, is highly complex. The outcomes of this research are expected to contribute to good practice in environmental and innovation skilling for SMEs, especially skilling that differentiates between supply and demand side skilling and brings together the two sides in a proactive resource acquisition, knowledge transfer and networking environment.
- Description: 2003007572
The impact of semantic class identification and semantic role labeling on natural language answer extraction
- Authors: Ofoghi, Bahadorreza , Yearwood, John , Ma, Liping
- Date: 2008
- Type: Text , Conference paper
- Relation: Paper presented at 30th European Conference on IR Research, ECIR 2008, Glasgow, UK : 30th March - 3rd April 2008 p. 430-437
- Full Text: false
- Description: In satisfying an information need by a Question Answering (QA) system, there are text understanding approaches which can enhance the performance of final answer extraction. Exploiting the FrameNet lexical resource in this process inspires analysis of the levels of semantic representation in the automated practice where the task of semantic class and role labeling takes place. In this paper, we analyze the impact of different levels of semantic parsing on answer extraction with respect to the individual sub-tasks of frame evocation and frame element assignment.
- Description: 2003006587
Barriers to purchasing on the internet
- Authors: Van Beveren, John , Wilson, Robyn
- Date: 2002
- Type: Text , Journal article
- Relation: Journal of E-Business Vol. 2, no. (2002), p. 1-4
- Full Text: false
- Reviewed:
- Description: A tremendous amount of work and effort has been devoted to securing financial transactions over the Internet. However the amount of effort is not reflected in the number of people who are purchasing on the Web. This paper provides a conceptual model and framework for future empirical investigations as to why people are still apprehensive to purchasing on the Internet. The model is based on the development of perceptions of risk related to purchasing on the Internet and incorporates, product class, prior experiences with the product and purchasing online, and word of mouth (media reports) as determinants for risk. The model then provides Website design, with technology and information provided as moderators of the effect of perceptions of risk to the purchasing decision.
- Description: C1
- Description: 2003000234
Firm Performance, corporate governance, and CEO turnover : An empirical study from China
- Authors: Pi, Lili , Lowe, Julian , Zhao, Chao
- Date: 2009
- Type: Text , Conference paper
- Relation: Paper presented at 23rd ANZAM Conference 2009: Sustainable Management and Marketing, Melbourne, Victoria : 1st-4th December 2009
- Full Text: false
- Description: This study examines the impacts of firm performance and mechanisms of corporate governance on CEO turnover by using a sample of 325 companies listed on the Chinese stock markets over the ten-year period 1997-2006. A negative relationship between CEO turnover and firm performance has been found in this study. For mechanisms of corporate governance, the proportion of independent directors is negatively associated with CEO turnover. Similarly, serving as the representative of the largest shareholder in the company significantly reduces the likelihood of CEO turnover, While CEO turnover is unrelated to whether CEOs are representatives of any other top ten largest shareholders. Moreover, neither CEOs’ shareholdings nor state shareholdings influence CEO turnover.
- Description: 2003007599
An efficient algorithm for the incremental construction of a piecewise linear classifier
- Authors: Bagirov, Adil , Ugon, Julien , Webb, Dean
- Date: 2011
- Type: Text , Journal article
- Relation: Information Systems Vol. 36, no. 4 (2011), p. 782-790
- Relation: http://purl.org/au-research/grants/arc/DP0666061
- Full Text: false
- Reviewed:
- Description: In this paper the problem of finding piecewise linear boundaries between sets is considered and is applied for solving supervised data classification problems. An algorithm for the computation of piecewise linear boundaries, consisting of two main steps, is proposed. In the first step sets are approximated by hyperboxes to find so-called "indeterminate" regions between sets. In the second step sets are separated inside these "indeterminate" regions by piecewise linear functions. These functions are computed incrementally starting with a linear function. Results of numerical experiments are reported. These results demonstrate that the new algorithm requires a reasonable training time and it produces consistently good test set accuracy on most data sets comparing with mainstream classifiers. © 2010 Elsevier B.V. All rights reserved.
A global optimisation approach to classification in medical diagnosis and prognosis
- Authors: Bagirov, Adil , Rubinov, Alex , Yearwood, John , Stranieri, Andrew
- Date: 2001
- Type: Text , Conference paper
- Relation: Paper presented at 34th Hawaii International Conference on System Sciences, HICSS-34, Maui, Hawaii, USA : 3rd-6th January 2001
- Full Text:
- Description: In this paper global optimisation-based techniques are studied in order to increase the accuracy of medical diagnosis and prognosis with FNA image data from the Wisconsin Diagnostic and Prognostic Breast Cancer databases. First we discuss the problem of determining the most informative features for the classification of cancerous cases in the databases under consideration. Then we apply a technique based on convex and global optimisation to breast cancer diagnosis. It allows the classification of benign cases and malignant ones and the subsequent diagnosis of patients with very high accuracy. The third application of this technique is a method that calculates centres of clusters to predict when breast cancer is likely to recur in patients for which cancer has been removed. The technique achieves higher accuracy with these databases than reported elsewhere in the literature.
- Description: 2003003950
Motives, money and microfinance – Are we measuring the right subsidy variable?
- Authors: Langton, Jonathan
- Date: 2007
- Type: Text , Conference paper
- Relation: Paper presented at 2007 AFAANZ Conference, The Gold Coast, Queensland : 1st-3rd July 2007
- Full Text: false
- Description: In the next ten years, society will spend $20 billion U.S. on Microfinance Institutions (MFIs). Previous research on the impact of subsidies suggests that there is little if any consensus on an effective method to measure the impact of subsidies with considerable doubt existing that a financial variable is the most appropriate method. Findings suggest that in order for the impact of subsidies to be fully reconciled, some consideration must be given to the initial objectives and underlying motives of MFIs and subsidy providers as this has an intrinsic bearing on any result they are attempting to achieve. I have attempted to shed light on a significant failure of the microfinance movement to date, in that we still have not clearly articulated by what qualitative measure we are to determine the success of MFI’s. Identifying what is the priority issue, even if it is a combination of factors requires willingness on behalf of both pro and anti- subsidy lobbies to concede that their approach may not be the most important. In order to transcend this discord a retrospective approach is taken to the impact of subsidies, whereby they are analysed from an initial substantive view in regard to underlying motive. I use this framework to assess microfinance in general and then apply my findings to a policy framework for microfinance institutions (MFIs) and subsidy providers.
- Description: 2003005169
An intelligent learning environment for traditional Chinese medicine practitioners and students
- Authors: Jia, Long , Stranieri, Andrew , Shen, J
- Date: 2008
- Type: Text , Conference paper
- Relation: Paper presented at HIC 2008 Australia's Health Informatics Conference; The Person in the Centre, Brunswick East, Victoria : 31st August - 2nd September 2008
- Full Text:
- Description: Objectives: This study aims to support the training of Traditional Chinese Medicine practitioners by embedding an expert diagnostic model for arthritis into an Intelligent Interactive Learning Environment (IILE). Background: The increasing prevalence of Traditional Chinese Medicine (TCM) outside China is characterised by the emergence of university level practitioner training and stringent regulatory requirements. TCM differential diagnosis is a difficult task that was traditionally taught by exposure to large numbers of patients in a master-apprentice context. In university degree programs, students and novice diagnosticians cannot have the exposure to cases possible in the traditional context. An online system that engages students in the interactive construction of a virtual case and provides immediate feedback on the appropriateness of student actions and the accuracy of diagnostic conclusions can enhance student learning. The system, an Intelligent Interactive Learning Environment (IILE) is based on an approach that has been shown to improve learning outcomes in intensive care nurse training. Methods: An expert model of diagnostic reasoning elicited from TCM expert practitioners lies at the core of the IILE. The knowledge acquisition is performed using an argumentation tree representation that has been shown to be effective in structuring complex knowledge and facilitating engineer - expert interactions. Problems associated with keeping knowledge bases up to date are mitigated with the use of a knowledge model known as ripple down rules permits dynamic updating of knowledge so that knowledge bases evolve over time. A simple narrative model builds up the virtual case study as user interaction proceeds. Results and discussion: This article reports preliminary results in the study that includes an overview of TCM differential diagnosis, the argument tree, the ripple down rule representation and the narrative based IILE. Segments of the knowledge model based solely on TCM literature are illustrated.
- Description: 2003006755
Automated opinion detection : Implications of the level of agreement between human raters
- Authors: Osman, Deanna , Yearwood, John , Vamplew, Peter
- Date: 2010
- Type: Text , Journal article
- Relation: Information Processing and Management Vol. 46, no. 3 (2010), p. 331-342
- Full Text: false
- Reviewed:
- Description: The ability to agree with the TREC Blog06 opinion assessments was measured for seven human assessors and compared with the submitted results of the Blog06 participants. The assessors achieved a fair level of agreement between their assessments, although the range between the assessors was large. It is recommended that multiple assessors are used to assess opinion data, or a pre-test of assessors is completed to remove the most dissenting assessors from a pool of assessors prior to the assessment process. The possibility of inconsistent assessments in a corpus also raises concerns about training data for an automated opinion detection system (AODS), so a further recommendation is that AODS training data be assembled from a variety of sources. This paper establishes an aspirational value for an AODS by determining the level of agreement achievable by human assessors when assessing the existence of an opinion on a given topic. Knowing the level of agreement amongst humans is important because it sets an upper bound on the expected performance of AODS. While the AODSs surveyed achieved satisfactory results, none achieved a result close to the upper bound. © 2009 Elsevier Ltd. All rights reserved.
Data mining with combined use of optimization techniques and self-organizing maps for improving risk grouping rules : Application to prostate cancer patients
- Authors: Churilov, Leonid , Bagirov, Adil , Schwartz, Daniel , Smith, Kate , Dally, Michael
- Date: 2005
- Type: Text , Journal article
- Relation: Journal of Management Information Systems Vol. 21, no. 4 (2005), p. 85-100
- Full Text:
- Reviewed:
- Description: Data mining techniques provide a popular and powerful tool set to generate various data-driven classification systems. In this paper, we investigate the combined use of self-organizing maps (SOM) and nonsmooth nonconvex optimization techniques in order to produce a working case of a data-driven risk classification system. The optimization approach strengthens the validity of SOM results, and the improved classification system increases both the quality of prediction and the homogeneity within the risk groups. Accurate classification of prostate cancer patients into risk groups is important to assist in the identification of appropriate treatment paths. We start with the existing rules and aim to improve classification accuracy by identifying inconsistencies utilizing self-organizing maps as a data visualization tool. Then, we progress to the study of assigning prostate cancer patients into homogenous groups with the aim to support future clinical treatment decisions. Using the case of prostate cancer patients grouping, we demonstrate strong potential of data-driven risk classification schemes for addressing the risk grouping issues in more general organizational settings. © 2005 M.E. Sharpe, Inc.
- Description: C1
- Description: 2003001265
Re-consider : The integration of online dispute resolution and decision support systems
- Authors: Muecke, Nial , Stranieri, Andrew , Miller, Charlynn
- Date: 2008
- Type: Text , Conference paper
- Relation: Paper presented at 5th International Workshop on Online Dispute Resolution, in conjunction with the 21st International Conference on Legal Knowledge and Information Systems (JURIX 2008), Firenze, Italy : 13th December 2008
- Full Text:
- Description: Current approaches for the design of Online Dispute Resolution (ODR) systems involve the replication of Alternative Dispute Resolution practices such as mediation and negotiation. Though such systems have been found to be popular, there are concerns that these systems fail to take into account judicial practices. In this paper a system that supports disputants' decisions making when engaged in an online dispute is advanced. The system, Re-Consider, is an Australia Family Law ODR system, that is based on judicial reasoning modelled with Bayesian belief networks and provides disputants with decision support in the dispute. It is believed that this approach provides disputants with an online resolution process that will help them to reach outcomes that take judicial practices into account and presents a step toward more deliberative form of online dispute resolution.
- Description: 2003006782
Going green : Women entrepreneurs and the environment
- Authors: Braun, Patrice
- Date: 2009
- Type: Text , Conference paper
- Relation: Paper presented at 32nd Institute for Small Business & Entrepreneurship Conference, ISBE 2009, Liverpool, UK : 3rd-6th November 2009
- Full Text:
- Description: In economically challenging times business operators are looking for clever and affordable ways to grow their enterprises. This paper discusses the role of women entrepreneurs’ in proactively greening their small business. The paper highlights the combined outcomes of the exit survey of a greening small business 2008 pilot program and the entry survey for the 2009 online version of the training and networking program, which fuses environmental, business and ICT-enabled skilling to enhance both SME entrepreneurship and innovation. The study suggests that while reported environmental attitudes between male and female entrepreneurs do not differ significantly, women’s motivations differ from male entrepreneurs in terms of greening their business; and women are more proactive in pursuing green networking opportunities, where they can interact with like-minded businesses, access more clients, source alternative resources and expand their green business networks.
- Description: 2003007573
A fuzzy-neural approach for interpretation and fusion of colour and texture features for CBIR systems
- Authors: Verma, Brijesh , Kulkarni, Siddhivinayak
- Date: 2004
- Type: Text , Journal article
- Relation: Journal of Applied Soft Computing Vol. 5, no. 1 (2004), p. 119-130
- Full Text:
- Reviewed:
- Description: This paper presents a fuzzy-neural approach for interpretation and fusion of colour and texture features for CBIR systems. The presented approach uses fuzzy logic to interpret queries expressed in natural language such as mostly red, many green, few red for colour feature. Tamura feature is used to represent the texture of an image in the database. A term set on each Tamura feature is generated using a fuzzy clustering algorithm to pose a query in terms of natural language. The query can be expressed as a logic combination of natural language terms and Tamura feature values. A fusion of multiple queries is incorporated into the proposed approach. The performance of the technique was evaluated on Brodatz texture benchmark database and it was noticed that there was a prominent increase in the confidence factor for the images. Fusion experiments were conducted using neurofuzzy, fuzzy AND and binary AND techniques. A comparative analysis showed that fuzzy-neural approach has significantly improved the performance of CBIR system.
- Description: C1
- Description: 2003002798
Human resource management in TAFE institutes in Australia
- Authors: Smith, Andy
- Date: 2009
- Type: Text , Conference paper
- Relation: Paper presented at 23rd ANZAM Conference 2009: Sustainable Management and Marketing, Melbourne, Victoria : 1st-4th December 2009
- Full Text: false
- Description: This paper reports the results of a national research project into the impact of human resource management practices on teaching and learning performance in TAFE Institutes in Australia. The research and literature on human resource management and, more recently, on high performance work systems has suggested strongly that the implementation of more sophisticated policies of human resource management will result in higher levels of organisational performance. This research project tests this theory in the context of vocational education and training (VET). The research examines the formulation and implementation of human resource management practices in TAFE institutes. The project involved a survey of TAFE institutes which established the form and extent of human resource management and a series of case studies investigating the impact of human resource management on teaching and learning and other aspects of organisational performance.
- Description: 2003007598
Networking tourism SMEs : E-commerce and e-marketing issues in regional Australia
- Authors: Braun, Patrice
- Date: 2002
- Type: Text , Journal article
- Relation: Information Technology and Tourism Vol. 5, no. 1 (2002), p. 13-23
- Full Text:
- Reviewed:
- Description: Networks, knowledge, and relationships have become crucial assets to business survival in the new economy. Research indicates that network building is a major new source of competitive advantage and an essential regional and indeed global management requirement. Because regional policies encourage interfirm alliances and the development of regional economic communities, the fostering of a culture of connectivity, networking, learning, and trust between regional Australian small and medium- size tourism enterprises (SMTEs) may offer a potential solution to the possible loss of competitive advantage for Australian tourism enterprises. It is suggested that SMTEs would benefit from increased information flow through regional networking and cooperative e-marketing campaigns to enhance market visibility, global positioning, and strategic leverage in the new economy.
- Description: C1
- Description: 2003000256
Adding thermal information to multisensory input in simulated environments
- Authors: Van Doorn, George , Richardson, Barry , Symmons, Mark , Wells, Jonathan
- Date: 2009
- Type: Text , Journal article
- Relation: International Journal of Intelligent Defence Support Systems Vol. 2, no. 4 (2009 2009), p. 350-362
- Full Text: false
- Reviewed:
- Description: Although simulated environments are improved by adding sensory information, temperature is one input that has rarely featured in them. Here we report findings from experiments that examine the efficacy of adding temperature information to the multimodal complex known to be of benefit in simulations. In the first experiment, Peltier tiles added thermal information to the kinesthetic feedback given by a hand-worn exoskeletal device and this increased ratings for 'presence' during interactions with simulated objects. In an experiment in which exploratory movements across surfaces of differing temperatures were either active or passive-guided, the degree of 'coldness' felt at the fingertip was reported as less intense when movement was active, suggesting that intentionality of movement plays a role in the attenuation of the thermal stimulus. Other work reported here suggests that the perception of temperature is not influenced by a simultaneously presented colour. For example, the perception of coldness is not enhanced when it is processed in conjunction with a blue colour. We discuss the potential value of thermal information within the context of the hypothesis that presence in simulated environments is enhanced by multisensory inputs that include redundant information.
Probabilistic neural networks based network security management
- Authors: Wu, Zhiyou , Liu, W , Wu, Jian-ping , Duan, Hai-xin
- Date: 2008
- Type: Text , Journal article
- Relation: Journal Communication and Computer Vol. 5, no. 2 (2008), p. 19-24
- Full Text: false
- Reviewed:
- Description: Intrusion Detection System (IDS) is one of the main tools in computer and network management, we consider intrusion detection using probabilistic neural networks. An ensemble of Probabilistic Neural Networks (PNN) is trained with Adaptive Boost to classify the detected event as normal or intrusive. We use Hamming distance kernels for PNN and find them superior to Euclidean distance kernels for this kind of detected event