Research Publications
All 2012 | |
| Narrow your search | 62 result(s) |
By Type
By Year By Research Group | Measuring cognitive load changes can contribute to better treatment of patients, can help design effective strategies to reduce medical errors among clinicians and can facilitate user evaluation of health care information systems. This paper proposes an ... Statistical learning and sequential prediction are two different but related formalisms to study the quality of predictions. Mapping out their relations and transferring ideas is an active area of investigation. We provide another piece of the puzzle ... Geolocation prediction is vital to geospatial applications like localised search and local event detection. Predominately, social media geolocation models are based on full text data, including common words with no geospatial dimension (e.g.\... We present a novel top modelling-based methodology to track emerging events in microblogs such as Twitter. Our topic model has an in-built update mechanism based on time slices and implements a dynamic vocabulary. We first show that the method is... Online discussion forums are a valuable means for users to resolve specific information needs, both interactively for the participants and statically for users who search/browse over historical thread data. However, the complex structure of forum... Automatically extracting terminology and index terms from scientific literature is useful for a variety of digital library, indexing and search applications. This task is non-trivial, complicated by domain-specific terminology and a steady ... We present a new formulation for attacking binary classification problems. Instead of relying on convex losses and regularisers such as in SVMs, logistic regression and boosting, or instead non-convex but continuous formulations such as those encountered ... The ALTA shared task ran for the third time in 2012 with the aim of bringing research students together to work on the same task and data set to program and compare their methods for a current research problem. The task was based on the recent study ... Clinical shift handover is the transfer of professional responsibility for patient care to another person. While verbal handover provides a good picture of care, after 3-5 shifts 100% of this information is lost or transferred incorrectly if notes are not... Partially-observable Markov decision processes (POMDPs) provide a powerful model for real-world sequential decision-making problems. In recent years, point- based value iteration methods have proven to be extremely effective techniques for finding (... We strengthen recent connections between prediction markets and learning by showing that a natural class of market makers can be understood as performing stochastic mirror descent when trader demands are sequentially drawn from a fixed distribution. This ... High cognitive load arises from complex time- and safety-critical tasks (e.g., mapping out flight paths, monitoring traffic, or even managing nuclear reactors), which cause stress, errors and diminished performance. Over the past five years, our research ... Health data includes all health-related content in all data formats, document types, information systems, publication media and languages from all specialties, organizations, regions, states and countries. Examples include private data on electronic ... One of the potentially most relevant pieces of metadata for filtering studies in environmental science is the geographic region in which the study took place (the ``study region''). In this paper, we apply support vector machines to the automatic ... We present a method to estimate word use similarity independent of an external sense inventory. This method utilizes a topic-modelling approach to compute the similarity in usage of a single word across a pair of sentences, and we evaluate our ... Galvanic Skin Response (GSR) has recently attracted researchers’ attention as a prospective physiological indicator of cognitive load and emotions. However, it has commonly been investigated through single or few measures and in one experimental scenario.... A key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is known to be scale-free. We show that in such cases it is natural to ... The process of finding the best locations for drilling in geothermal exploration requires the collection of vast amounts of information. Gravity, magnetism, seismicity, radiometric, magnetotellurics and drilling data are commonly used to infer specific ... Humans experience cognitive load during critical task activities and learning. Affective factors such as arousal and valence can be experienced at the same time, induced by the task in hand or by personal feelings. Identifying modalities or features that ... Microblog is a prominent information platform for sharing experiences, discussing current events, and exchanging ideas. Many events are first reported in social media, and increas- ing amounts of rich-media content are associated with the posts, making ... The promise of spectral clustering is that it can help detect complex shapes and intrinsic manifold structure in large and high dimensional spaces. The price for this promise is the computational cost O(n^3) for computing the eigen-decomposition of the ... We extend the Bayesian skill rating system of TrueSkill to accommodate score-based match outcomes. TrueSkill has proven to be a very effective algorithm for matchmaking --- the process of pairing competitors based on similar skill-level --- in ... Introduction More and more textual eHealth information is electronically available. Examples include scientific literature, care guidelines, health records, and social media. Language technologies (LTs) provide a way to analyse these documents for the... Introduction. Failures in information flow from clinical handover are the leading cause of sentinel events in the USA and associated with nearly half of all adverse events and over a tenth of preventable adverse events in Australia.1-3 Verbal clinical ... Introduction Invasive fungal diseases (IFDs) cause more than 1,000 deaths in hospitals and cost the health system more than AUD100m in Australia each year.1 The most common life-threatening IFD is aspergillosis and a patient with this IFD typically has ... CLEFeHealth2012 is the CLEF2012 workshop on cross-language evaluation of methods, applications, and resources for eHealth document analysis. Its focus is on written and spoken natural-language processing with the use scenario of people using ICT tools to ... Capabilities to share, integrate, and compare eHealth data, clinical trial results, and other evaluation outcomes together with eHealth applications are critical to accelerate discovery and its diffusion to clinical practice. However, the same ethical and... Classical mechanism design assumes that an agent's value of any determined outcome depends only on its private information. However in many situations, an agent's value of an outcome depends on the private information of other agents in addition to its ... The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. These annotations may be imperfect, in the sense that many images contain multiple objects belonging to the label vocabulary. In ... On the Mathematical Relationship between Expected n-call@k and the Relevance vs. Diversity Trade-off It has been previously noted that optimization of the ncall@k relevance objective (i.e., a set-based objective that is 1 if at least n documents in a set of k are relevant, otherwise 0) encourages more result set diversification for smaller n, but ... Introduction. We discuss three initiatives from the NICTA eHealth Business Team towards developing ICT techniques for improving healthcare via: 1. capturing more clinical data; 2. converting them to processable information; 3. recording this as ... Probabilistic reasoning in the real-world often requires inference in continuous variable graphical models, yet there are few methods for \emph{exact, closed-form} inference when joint distributions are non-Gaussian. To address this inferential ... Many real-world decision-theoretic planning problems are naturally modeled using both continuous state and action (CSA) spaces, yet little work has provided exact solutions for the case of continuous actions. In this work, we propose a symbolic ... Topic models are increasingly being used for text analysis tasks, often times replacing earlier semantic techniques such as latent seman- tic analysis. In this paper, we develop a novel adaptive topic model with the ability to adapt topics from both ... We propose an efficient algorithm for calculating hold-out and cross-validation (CV) type of estimates for sparse regularized least-squares predictors. Holding out H data points with our method requires O(min(nH^2,Hn^2)) time provided that a predictor ... Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of a user's rating on an item is then given by that rating of neighbouring... In this paper we investigate the performance of three different classification systems testing a range of acoustic features to find a system to classify speaker likeability. We introduce a Sparse Representation Classification for paralinguistic ... We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore their ... This paper presents an improvement to model learning when using multi-class LogitBoost for classification. Motivated by the statistical view, LogitBoost can be seen as additive tree regression. Two important factors in this setting are: 1) coupled ... We develop dependent hierarchical normalized random measures and apply them to dynamic topic modeling. The dependency arises via {\em superposition}, {\em subsampling} and {\em point transition} on the underlying Poisson processes of these measures. ... In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where an input datapoint is described by a set of feature vectors and its associated output may be given by soft labels indicating, for ... Background: Continuous prospective surveillance of invasive fungal diseases (IFDs) in hematology-oncology patients should be the standard of care but is unfeasible for many institutions due to resource limitations and an absence of, in the case of ... We study a natural generalisation of Csiszar's f-divergence to more than two distributions. By exploiting classical results from the comparison of experiments we prove the resulting divergence satisfi es all the same properties as the traditional binary... Learners experience a variety of emotions during learning sessions with Intelligent Tutoring Systems (ITS). The research community is building systems that are aware about these experiences, generally represented as a category or as a point in a ... We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter ... In this article we review the 2011 International Planning Competition. We give an overview of the history of the competition, discussing how it has developed since its first edition in 1998. The 2011 competition was run in three main separate tracks: ... We present langid.py, an off-the-shelf language identification tool. We discuss the design and implementation of langid.py, and provide an empirical comparison on 5 long-document datasets, and 2 datasets from the microblog domain. We find that ... This volume contains the papers presented at EWRL 2011: the 9th European Workshop on Reinforcement Learning held in Athens Greece, September 9-11, 2011. The workshop was co-located with the European Conference on Machine Learning and Principles and ... Online forums are rich sources of information about users' communication activity over time. Finding temporal patterns in communication records can advance our understanding of the dynamics of conversations. The main challenge of temporal analysis in ... Mixability of a loss governs the best possible performance when aggregating expert predictions with respect to that loss. The determination of the mixability constant for binary losses is straightforward but opaque. In the binary case we make this ... The problem of isometric point-pattern matching can be modeled as inference in small tree-width graphical models whose embeddings in the plane are said to be ‘globally rigid’. Although such graphical models lead to efficient and exact solutions, they ... Background: This work describes a system for identifying event mentions in bio-molecular research abstracts that are either speculative (e.g. analysis of IkappaBalpha phosphorylation, where it is not specified whether phosphorylation did or did not occur... This paper examines the problem of social collaborative filtering (CF) to recommend items of interest to users in a social network setting. Unlike standard CF algorithms using relatively simple user and item features, recommendation in social networks... We investigate the effects of adding semantic annotations including word sense hypernyms to the source text for use as an extra source of information in HPSG parse ranking for the English Resource Grammar. The semantic annotations are coarse semantic ... Given the high level description of a task, many different hardware modules may be generated while meeting its behavioral requirements. The characteristics of the generated hardware can be tailored to favor energy efficiency, performance, accuracy or die ... We begin with a brief review of Bayesian latent variable models such as Latent Dirichlet Allocation and Hierarchical Dirichlet Processes. We then extend the discussion to the more general case of directed graphical models (or Bayesian networks), ... Compressive sensing is an emerging field predicated upon the fact that, if a signal has a sparse representation in some basis, then it can be almost exactly reconstructed from very few random measurements. Many signals and natural images, for example ... The two parameter Poisson-Dirichlet Process (PDP), a generalisation of the Dirichlet Process, is increasingly being used for probabilistic modelling in discrete areas such as language technology, bioinformatics, and image analysis. There is a rich ... Multiple instance learning (MIL) which introduces label ambiguity by applying bag concept obtains increasing attentions in computer vision community. Due to its flexible labeling mechanism, MIL can be naturally utilized on a variety of computer vision... The performances of supervised learning techniques on image classification problems heavily rely on the quality of their training images. But the acquisition of high quality training images requires significant efforts from human annotators. In this paper... |