Medical image classification using an efficient data mining technique

Data mining refers to extracting or "mining" knowledge from large amounts of data. It is an increasingly popular field that uses statistical, visualization, machine learning, and other data manipulation and knowledge extraction techniques aimed at gaining an insight into the relationships and patterns hidden in the data. Availability of digital data within picture archiving and communication systems raises a possibility of health care and research enhancement associated with manipulation, processing and handling of data by computers.That is the basis for computer-assisted radiology development. Further development of computer-assisted radiology is associated with the use of new intelligent capabilities such as multimedia support and data mining in order to discover the relevant knowledge for diagnosis. It is very useful if results of data mining can be communicated to humans in an understandable way. In this paper, we present our work on data mining in medical image archiving systems. We investigate the use of a very efficient data mining technique, a decision tree, in order to learn the knowledge for computer-assisted image analysis. We apply our method to the classification of x-ray images for lung cancer diagnosis. The proposed technique is based on an inductive decision tree learning algorithm that has low complexity with high transparency and accuracy. The results show that the proposed algorithm is robust, accurate, fast, and it produces a comprehensible structure, summarizing the knowledge it induces.

God, gratuitous evil, and van Inwagen's attempt to reconcile the two

Both critics and advocates of evidential arguments from evil often assume that theistic belief is not compatible with gratuitous evil. It is often assumed, in other words, that an omniscient, omnipotent, perfectly good being would not permit an evil unless he had a morally sufcient reason to permit it. However, this cornerstone of evidential arguments from evil has come under increasing re of late, in particular by Peter van Inwagen. The aim of this paper is to outline and then assess van Inwagen's attempt to reconcile theism with gratuitous evil.

Does hard determinism render the problem of evil even harder?

Hard determinism, in theological dress, holds that there is no human free will since God is the sufficient active cause of everything that happens in creation. It is surprising that, in the ever-growing literature on the problem of evil, very little attention has been paid to theodicies that adopt a hard determinist outlook. It is commonly assumed that without free will the theodical project is a non-starter. I challenge this long-held assumption by, firstly, developing a cumulative-style theodicy from within a hard determinist framework, and secondly, comparing the merits of such a theodicy with two libertarian rivals, specifically, Molinism and open theism. The hard determinist model of divine providence is, I argue, in no worse shape than the principal models developed by libertarians.

Meta-philosophy of religion : the analytic-continental divide in philosophy of religion

How is the philosophical study of religion best pursued? Responses to this meta-philosophical question tend to recapitulate the analytic-Continental divide in philosophy in general. My aim is to examine the nature of this divide, particularly as it has manifested itself in the philosophy of religion. I begin with a comparison of the stylistic differences in the language of the two traditions, taking the work of Alvin Plantinga and John Caputo as exemplars of the analytic and Continental schools respectively. In order to account for these stylistic divergences, however, it is necessary to delve further into meta-philosophy. I go on to show how each philosophical school models itself on different theoretical practices, the analytic school mimicking the scientific style of inquiry, while in Continental philosophy it is the arts and humanities rather than the sciences that provide the model for philosophical discourse. By situating themselves in such different genres,  analytic and Continental philosophers have developed contrasting, if not mutually exclusive, methods for pursuing the philosophy of religion.

A method for examining corporate social responsibility descriptions on SME websites

There is growing IS research concerning SME use of websites and limited but growing research on corporate social responsibility (CSR) by SMEs. However, to-date these two bodies of literature have remained largely separate. This paper links these fields by presenting an SME website content analysis method. Melville in his seminal MIS Quarterly article called for such methods which provide a nexus of IS, organisations and environment (which we extend to CSR). The method involves four steps: 1) identifying sources of SME websites; 2) determining if websites are describing CSR (based on the literature CSR by SMEs); 3) archiving website content for analysis; and 4) coding the website content using a structured framework (combining the literature on IS and CSR in an SME context). The paper also provides suggestions on how IS researchers can apply the method for quantitative and qualitative/exploratory objectives for future research.

Improving biodiversity monitoring

Effective biodiversity monitoring is critical to evaluate, learn from, and ultimately improve conservation practice. Well conceived, designed and implemented monitoring of biodiversity should: (i) deliver information on trends in key aspects of biodiversity (e.g. population changes); (ii) provide early warning of problems that might otherwise be difficult or expensive to reverse; (iii) generate quantifiable evidence of conservation successes (e.g. species recovery following management) and conservation failures; (iv) highlight ways to make management more effective; and (v) provide information on return on conservation investment. The importance of effective biodiversity monitoring is widely recognized (e.g. Australian Biodiversity Strategy). Yet, while everyone thinks biodiversity monitoring is a good idea, this has not translated into a culture of sound biodiversity monitoring, or widespread use of monitoring data. We identify four barriers to more effective biodiversity monitoring in Australia. These are: (i) many conservation programmes have poorly articulated or vague objectives against which it is difficult to measure progress contributing to design and implementation problems; (ii) the case for long-term and sustained biodiversity monitoring is often poorly developed and/or articulated; (iii) there is often a lack of appropriate institutional support, co-ordination, and targeted funding for biodiversity monitoring; and (iv) there is often a lack of appropriate standards to guide monitoring activities and make data available from these programmes. To deal with these issues, we suggest that policy makers, resource managers and scientists better and more explicitly articulate the objectives of biodiversity monitoring and better demonstrate the case for greater investments in biodiversitymonitoring. There is an urgent need for improved institutional support for biodiversity monitoring in Australia, for improved monitoring standards, and for improved archiving of, and access to, monitoring data. We suggest that more strategic financial, institutional and intellectual investments in monitoring will lead to more efficient use of the resources available for biodiversity conservation and ultimately better conservation outcomes.

Biomedical time series analysis based on bag-of-words model

This research proposes a number of new methods for biomedical time series classification and clustering based on a novel Bag-of-Words (BoW) representation. It is anticipated that the objective and automatic biomedical time series clustering and classification technologies developed in this work will potentially benefit a wide range of applications, such as biomedical data management, archiving, retrieving, and disease diagnosis and prognosis in the future.

Publishing choreographic ideas

A growing collection of self-determined reflections on dance practice are being published by choreographers in a variety of formats. Often working in collaboration with researchers, editors and designers, these heterogeneous publication projects make use of text, moving image and more open-ended digital tools and platforms. Many of these projects are either newly available or are in the process of development. In addition to offering practice led contributions to the discourse on dance, they point towards the artist's role in developing alternative forms of documenting, analyzing, notating and archiving contemporary dance.

Jondi Keane, Alan Prohm, Erin Manning (2014): organisers and curators

Keane, Prohm and Manning organised performative process for collecting and assembling materials for a publication. The event/process focused on work related to and inspired by the work of Arakawa and Madeline Gins. the festival will be held over 4 days at the Glasshouse in Brooklyn (4-7 June, 12-5pm). The publication, planned for release in 2015/16, is being imagined as a print + digital document an/archiving this moment of movement around – and going forward with – the work of Arakawa and Madeline Gins. This book will be dedicated to Arakawa and Madeline, with special tribute to Madeline, whose own last book, "Alive forerever, not if but when", will be coming out in 2015/6.

Multichannel biomedical time series clustering via hierarchical probabilistic latent semantic analysis

Biomedical time series clustering that automatically groups a collection of time series according to their internal similarity is of importance for medical record management and inspection such as bio-signals archiving and retrieval. In this paper, a novel framework that automatically groups a set of unlabelled multichannel biomedical time series according to their internal structural similarity is proposed. Specifically, we treat a multichannel biomedical time series as a document and extract local segments from the time series as words. We extend a topic model, i.e., the Hierarchical probabilistic Latent Semantic Analysis (H-pLSA), which was originally developed for visual motion analysis to cluster a set of unlabelled multichannel time series. The H-pLSA models each channel of the multichannel time series using a local pLSA in the first layer. The topics learned in the local pLSA are then fed to a global pLSA in the second layer to discover the categories of multichannel time series. Experiments on a dataset extracted from multichannel Electrocardiography (ECG) signals demonstrate that the proposed method performs better than previous state-of-the-art approaches and is relatively robust to the variations of parameters including length of local segments and dictionary size. Although the experimental evaluation used the multichannel ECG signals in a biometric scenario, the proposed algorithm is a universal framework for multichannel biomedical time series clustering according to their structural similarity, which has many applications in biomedical time series management.

Editors’ introduction: archives and archivists

Today, questions about online access to media history, digital research infrastructure, and cultural and political pedagogy have come to the fore. A host of related questions has acquired a new urgency: What is lost and gained in the shift from physical to digital archiving? What and how do archives preserve, and how do they curate public access? How do we search for digital material? Which tools are used to modify and limit our search options, and what does this tell us about digital networks and our relationships to them?