2013.bib

@COMMENT{{Automatically generated - DO NOT MODIFY!}}

@INPROCEEDINGS{puurula13:_integ_instan_class_gener_model_text_class,
  AUTHOR = {Antti Puurula and Sung-Hyon Myaeng},
  TITLE = {Integrated Instance- and Class-based Generative Modeling for Text Classification},
  BOOKTITLE = {Proc 18th Australasian Document Computing Symposium},
  PAGES = {66--73},
  YEAR = 2013,
  PUBLISHER = {ACM},
  ABSTRACT = {Statistical methods for text classification are predominantly based on the paradigm of class-based learning that associates class variables with features, discarding the instances of data after model training. This results in efficient models, but neglects the fine-grained information present in individual documents. Instance-based learning uses this information, but suffers from data sparsity with text data. In this paper, we propose a generative model called Tied Document Mixture (TDM) for extending Multinomial Naive Bayes (MNB) with mixtures of hierarchically smoothed models for documents. Alternatively, TDM can be viewed as a Kernel Density Classifier using class-smoothed Multinomial kernels. TDM is evaluated for classification accuracy on 14 different datasets for multi-label, multi-class and binary-class text classification tasks and compared to instance- and class-based learning baselines. The comparisons to MNB demonstrate a substantial improvement in accuracy as a function of available training documents per class, ranging up to average error reductions of over 26\% in sentiment clas- sification and 65\% in spam classification. On average TDM is as accurate as the best discriminative classifiers, but retains the linear time complexities of instance-based learning methods, with exact algorithms for both model estimation and inference.},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/Puurula_13.pdf}
}

@INPROCEEDINGS{puurula13:_cumul_progr_languag_model_infor_retriev,
  AUTHOR = {Antti Puurula},
  TITLE = {Cumulative Progress in Language Models for Information Retrieval},
  BOOKTITLE = {Proc 11th Australasian Language Technology Workshop},
  PAGES = {96--100},
  YEAR = 2013,
  SERIES = {Brisbane, Australia},
  PUBLISHER = {ACL},
  ABSTRACT = {The improvements to ad-hoc IR systems over the last decades have been recently criticized as illusionary and based on incorrect baseline comparisons. In this paper several improvements to the LM approach to IR are combined and evaluated: Pitman-Yor Process smoothing, TF-IDF feature weighting and modelbased feedback. The increases in ranking quality are significant and cumulative over the standard baselines of Dirichlet Prior and 2-stage Smoothing, when evaluated across 13 standard ad-hoc retrieval datasets. The combination of the improvements is shown to improve the Mean Average Precision over the datasets by 17.1\% relative. Furthermore, the considered improvements can be easily implemented with little additional computation to existing LM retrieval systems. On the basis of the results it is suggested that LM research for IR should move towards using stronger baseline models.},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/Puurula_13b.pdf}
}

@INPROCEEDINGS{geilke13:_onlin_estim_of_discr_densit,
  AUTHOR = {Michael Geilke and Eibe Frank and Andreas Karwath and Stefan Kramer},
  TITLE = {Online Estimation of Discrete Densities},
  BOOKTITLE = {Proc 13th IEEE International Conference on Data Mining},
  SERIES = {Dallas, Texas},
  YEAR = 2013,
  PUBLISHER = {IEEE},
  ABSTRACT = {We address the problem of estimating a discrete joint density online, that is, the algorithm is only provided the current example and its current estimate. The proposed online estimator of discrete densities, EDDO (Estimation of Discrete Densities Online), uses classifier chains to model dependencies among features. Each classifier in the chain estimates the probability of one particular feature. Because a single chain may not provide a reliable estimate, we also consider ensembles of classifier chains and ensembles of weighted classifier chains. For all density estimators, we provide consistency proofs and propose algorithms to perform certain inference tasks. The empirical evaluation of the estimators is conducted in several experiments and on data sets of up to several million instances: We compare them to density estimates computed from Bayesian structure learners, evaluate them under the influence of noise, measure their ability to deal with concept drift, and measure the run-time performance. Our experiments demonstrate that, even though designed to work online, EDDO delivers estimators of competitive accuracy compared to batch Bayesian structure learners and batch variants of EDDO.},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/icdm2013_ieee.pdf}
}

@INPROCEEDINGS{frank13:_propos_of_multi_instan_data,
  AUTHOR = {Eibe Frank and Bernhard Pfahringer},
  TITLE = {Propositionalisation of Multi-instance Data using Random Forests},
  BOOKTITLE = {Proc 26th Australasian Conference on Artificial Intelligence},
  PAGES = {362-373},
  YEAR = 2013,
  SERIES = {Otago, New Zealand},
  PUBLISHER = {Springer},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/Frank_and_Pfahringer_CR_AI_13.pdf},
  ABSTRACT = {Multi-instance learning is a generalisation of attribute-value learning where examples for learning consist of labeled bags (i.e. multi-sets) of instances. This learning setting is more computationally challenging than attribute-value learning and a natural fit for important application areas of machine learning such as classification of molecules and image classification. One approach to solve multi-instance learning problems is to apply propositionalisation, where bags of data are converted into vectors of attribute-value pairs so that a standard propositional (i.e. attribute-value) learning algorithm can be applied. This approach is attractive because of the large number of propositional learning algorithms that have been developed and can thus be applied to the propositionalised data. In this paper, we empirically investigate a variant of an existing propositionalisation method called TLC. TLC uses a single decision tree to obtain propositionalised data. Our variant applies a random forest instead and is motivated by the potential increase in robustness that this may yield. We present results on synthetic and real-world data from the above two application domains showing that it indeed yields increased classification accuracy when applying boosting and support vector machines to classify the propositionalised data.}
}

@INPROCEEDINGS{durrant13:_random_projec_regul,
  AUTHOR = {Robert J. Durrant and Ata Kab{\'a}n},
  TITLE = {Random Projections as Regularizers: Learning a Linear Discriminant Ensemble from Fewer Observations than Dimensions},
  BOOKTITLE = {Proc 5th Asian Conference on Machine Learning},
  PUBLISHER = {JMLR},
  YEAR = 2013,
  SERIES = {Canberra, Australia},
  ABSTRACT = {We examine the performance of an ensemble of randomly-projected Fisher Linear Discriminant classifiers, focusing on the case when there are fewer training observations than data
dimensions. Our ensemble is learned from a sequence of randomly-projected representations of the original high dimensional data and therefore for this approach data can be
collected, stored and processed in such a compressed form.
The specific form and simplicity of this ensemble permits a direct and much more detailed
analysis than existing generic tools in previous works. In particular, we are able to derive the exact form of the generalization error of our ensemble, conditional on the training
set, and based on this we give theoretical guarantees which directly link the performance
of the ensemble to that of the corresponding linear discriminant learned in the full data
space. To the best of our knowledge these are the first theoretical results to prove such
an explicit link for any classifier and classifier ensemble pair. Furthermore we show that
the randomly-projected ensemble is equivalent to implementing a sophisticated regularization scheme to the linear discriminant learned in the original data space and this prevents
overfitting in conditions of small sample size where pseudo-inverse FLD learned in the data
space is provably poor.
We confirm theoretical findings with experiments, and demonstrate the utility of our approach on several datasets from the bioinformatics domain where fewer observations than
dimensions are the norm.},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/ACML_2013_RPENS.pdf}
}

@INPROCEEDINGS{kaban13:_dimen_adapt_bound_compr_fld_class,
  AUTHOR = {Ata Kab{\'a}n and
               Robert J. Durrant},
  TITLE = {Dimension-Adaptive Bounds on Compressive FLD Classification},
  BOOKTITLE = {Proc 24th International Conference on Algorithmic Learning Theory},
  YEAR = 2013,
  PAGES = {294-308},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-40935-6_21},
  PUBLISHER = SPRINGER,
  SERIES = {Singapore},
  ABSTRACT = {Efficient dimensionality reduction by random projections (RP) gains popularity, hence the learning guarantees achievable in RP spaces are of great interest. In finite dimensional setting, it has been shown for the compressive Fisher Linear Discriminant (FLD) classifier that for good generalisation the required target dimension grows only as the log of the number of classes and is not adversely affected by the number of projected data points. However these bounds depend on the dimensionality d of the original data space. In this paper we give further guarantees that remove d from the bounds under certain conditions of regularity on the data density structure. In particular, if the data density does not fill the ambient space then the error of compressive FLD is independent of the ambient dimension and depends only on a notion of ‘intrinsic dimension’.},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/alt13_v3.pdf}
}

@INPROCEEDINGS{ienco13:_clust_based_activ_learn_for,
  AUTHOR = {Dino Ienco and
               Albert Bifet and
               Indre Zliobaite and
               Bernhard Pfahringer},
  TITLE = {Clustering Based Active Learning for Evolving Data Streams},
  BOOKTITLE = {Proc 16th International Conference on Discovery Science},
  YEAR = 2013,
  PAGES = {79-93},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-40897-7_6},
  PUBLISHER = SPRINGER,
  SERIES = {Singapore},
  ABSTRACT = {Data labeling is an expensive and time-consuming task. Choosing which labels to use is increasingly becoming important. In the active learning setting, a classifier is trained by asking for labels for only a small fraction of all instances. While many works exist that deal with this issue in non-streaming scenarios, few works exist in the data stream setting. In this paper we propose a new active learning approach for evolving data streams based on a pre-clustering step, for selecting the most informative instances for labeling. We consider a batch incremental setting: when a new batch arrives, first we cluster the examples, and then, we select the best instances to train the learner. The clustering approach allows to cover the whole data space avoiding to oversample examples from only few areas. We compare our method w.r.t. state of the art active learning strategies over real datasets. The results highlight the improvement in performance of our proposal. Experiments on parameter sensitivity are also reported.}
}

@ARTICLE{sun13:_pairw_meta_rules_for_better,
  AUTHOR = {Quan Sun and
               Bernhard Pfahringer},
  TITLE = {Pairwise meta-rules for better meta-learning-based algorithm
               ranking},
  JOURNAL = {Machine Learning},
  VOLUME = 93,
  NUMBER = 1,
  YEAR = 2013,
  PAGES = {141-161},
  HTTP = {http://dx.doi.org/10.1007/s10994-013-5387-y},
  ABSTRACT = {In this paper, we present a novel meta-feature generation method in the context of meta-learning, which is based on rules that compare the performance of individual base learners in a one-against-one manner. In addition to these new meta-features, we also introduce a new meta-learner called Approximate Ranking Tree Forests (ART Forests) that performs very competitively when compared with several state-of-the-art meta-learners. Our experimental results are based on a large collection of datasets and show that the proposed new techniques can improve the overall performance of meta-learning for algorithm ranking significantly. A key point in our approach is that each performance figure of any base learner for any specific dataset is generated by optimising the parameters of the base learner separately for each dataset.}
}

@INPROCEEDINGS{bifet13:_pitfal_in_bench_data_stream,
  AUTHOR = {Albert Bifet and
               Jesse Read and
               Indre Zliobaite and
               Bernhard Pfahringer and
               Geoff Holmes},
  TITLE = {Pitfalls in Benchmarking Data Stream Classification and
               How to Avoid Them},
  BOOKTITLE = {Proc European Conference on Machine Learning and Knowledge Discovery in Databases},
  YEAR = 2013,
  PAGES = {465-479},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-40988-2_30},
  PUBLISHER = SPRINGER,
  SERIES = {Prague, Czech Republic},
  ABSTRACT = {Data stream classification plays an important role in modern data analysis, where data arrives in a stream and needs to be mined in real time. In the data stream setting the underlying distribution from which this data comes may be changing and evolving, and so classifiers that can update themselves during operation are becoming the state-of-the-art. In this paper we show that data streams may have an important temporal component, which currently is not considered in the evaluation and benchmarking of data stream classifiers. We demonstrate how a naive classifier considering the temporal component only outperforms a lot of current state-of-the-art classifiers on real data streams that have temporal dependence, i.e. data is autocorrelated. We propose to evaluate data stream classifiers taking into account temporal dependence, and introduce a new evaluation measure, which provides a more accurate gauge of data stream classifier performance. In response to the temporal dependence issue we propose a generic wrapper for data stream classifiers, which incorporates the temporal component into the attribute space.}
}

@INPROCEEDINGS{torgo13:_smote_for_regres,
  AUTHOR = {Lu\'{\i}s Torgo and
               Rita P. Ribeiro and
               Bernhard Pfahringer and
               Paula Branco},
  TITLE = {SMOTE for Regression},
  BOOKTITLE = {Proc 16th Portuguese Conference on Artificial Intelligence},
  YEAR = 2013,
  PAGES = {378-389},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-40669-0_33},
  PUBLISHER = SPRINGER,
  SERIES = {Angra do Hero\'{\i}smo, Azores, Portugal},
  ABSTRACT = {Several real world prediction problems involve forecasting rare values of a target variable. When this variable is nominal we have a problem of class imbalance that was already studied thoroughly within machine learning. For regression tasks, where the target variable is continuous, few works exist addressing this type of problem. Still, important application areas involve forecasting rare extreme values of a continuous target variable. This paper describes a contribution to this type of tasks. Namely, we propose to address such tasks by sampling approaches. These approaches change the distribution of the given training data set to decrease the problem of imbalance between the rare target cases and the most frequent ones. We present a modification of the well-known Smote algorithm that allows its use on these regression tasks. In an extensive set of experiments we provide empirical evidence for the superiority of our proposals for these particular regression tasks. The proposed SmoteR method can be used with any existing regression algorithm turning it into a general tool for addressing problems of forecasting rare extreme values of a continuous target variable}
}

@ARTICLE{kamphuis13:_apply_addit_logis_regres_to,
  AUTHOR = {Claudia Kamphuis and Eibe Frank and Jennie K. Burke and Gwyn Verkerk and Jenny Jago},
  TITLE = {Applying additive logistic regression to data derived from sensors monitoring behavioral and physiological characteristics of dairy cows to detect lameness},
  JOURNAL = {Dairy Science},
  YEAR = 2013,
  HTTP = {http://dx.doi.org/10.3168/jds.2013-6993},
  ABSTRACT = {The hypothesis was that sensors currently available on farm that monitor behavioral and physiological characteristics have potential for the detection of lameness in dairy cows. This was tested by applying additive logistic regression to variables derived from sensor data. Data were collected between November 2010 and June 2012 on 5 commercial pasture-based dairy farms. Sensor data from weigh scales (liveweight), pedometers (activity), and milk meters (milking order, unadjusted and adjusted milk yield in the first 2 min of milking, total milk yield, and milking duration) were collected at every milking from 4,904 cows. Lameness events were recorded by farmers who were trained in detecting lameness before the study commenced. A total of 318 lameness events affecting 292 cows were available for statistical analyses. For each lameness event, the lame cow's sensor data for a time period of 14 d before observation date were randomly matched by farm and date to 10 healthy cows (i.e., cows that were not lame and had no other health event recorded for the matched time period). Sensor data relating to the 14-d time periods were used for developing univariable (using one source of sensor data) and multivariable (using multiple sources of sensor data) models. Model development involved the use of additive logistic regression by applying the LogitBoost algorithm with a regression tree as base learner. The model's output was a probability estimate for lameness, given the sensor data collected during the 14-d time period. Models were validated using leave-one-farm-out cross-validation and, as a result of this validation, each cow in the data set (318 lame and 3,180 nonlame cows) received a probability estimate for lameness. Based on the area under the curve (AUC), results indicated that univariable models had low predictive potential, with the highest AUC values found for liveweight (AUC = 0.66), activity (AUC = 0.60), and milking order (AUC = 0.65). Combining these 3 sensors improved AUC to 0.74. Detection performance of this combined model varied between farms but it consistently and significantly outperformed univariable models across farms at a fixed specificity of 80\%. Still, detection performance was not high enough to be implemented in practice on large, pasture-based dairy farms. Future research may improve performance by developing variables based on sensor data of liveweight, activity, and milking order, but that better describe changes in sensor data patterns when cows go lame.}
}

@INPROCEEDINGS{sun13:_towar_framew_for_desig_full,
  AUTHOR = {Quan Sun and
               Bernhard Pfahringer and
               Michael Mayo},
  TITLE = {Towards a Framework for Designing Full Model Selection and
               Optimization Systems},
  BOOKTITLE = {Proc 11th International Workshop on Multiple Classifier Systems},
  YEAR = 2013,
  PAGES = {259-270},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-38067-9_23},
  PUBLISHER = {Springer},
  SERIES = {Nanjing, China},
  ABSTRACT = {People from a variety of industrial domains are beginning to realise that appropriate use of machine learning techniques for their data mining projects could bring great benefits. End-users now have to face the new problem of how to choose a combination of data processing tools and algorithms for a given dataset. This problem is usually termed the Full Model Selection (FMS) problem. Extended from our previous work [10], in this paper, we introduce a framework for designing FMS algorithms. Under this framework, we propose a novel algorithm combining both genetic algorithms (GA) and particle swarm optimization (PSO) named GPS (which stands for GA-PSO-FMS), in which a GA is used for searching the optimal structure for a data mining solution, and PSO is used for searching optimal parameters for a particular structure instance. Given a classification dataset, GPS outputs a FMS solution as a directed acyclic graph consisting of diverse data mining operators that are available to the problem. Experimental results demonstrate the benefit of the algorithm. We also present, with detailed analysis, two model-tree-based variants for speeding up the GPS algorithm.}
}

@INPROCEEDINGS{mayo13:_predic_regres_test_failur_using,
  AUTHOR = {Michael Mayo and
               Simon A. Spacey},
  TITLE = {Predicting Regression Test Failures Using Genetic Algorithm-Selected
               Dynamic Performance Analysis Metrics},
  BOOKTITLE = {Proc 5th International Symposium on Search Based Software Engineering},
  YEAR = 2013,
  PAGES = {158-171},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-39742-4_13},
  PUBLISHER = SPRINGER,
  SERIES = {St. Petersburg, Russia},
  ABSTRACT = {A novel framework for predicting regression test failures is proposed. The basic principle embodied in the framework is to use performance analysis tools to capture the runtime behaviour of a program as it executes each test in a regression suite. The performance information is then used to build a dynamically predictive model of test outcomes. Our framework is evaluated using a genetic algorithm for dynamic metric selection in combination with state-of-the-art machine learning classifiers. We show that if a program is modified and some tests subsequently fail, then it is possible to predict with considerable accuracy which of the remaining tests will also fail which can be used to help prioritise tests in time constrained testing environments.}
}

@ARTICLE{medelyan13:_autom_const_of_lexic_taxon,
  AUTHOR = {Olena Medelyan and
               Ian H. Witten and
               Anna Divoli and
               Jeen Broekstra},
  TITLE = {Automatic construction of lexicons, taxonomies, ontologies,
               and other knowledge structures},
  JOURNAL = {Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery},
  VOLUME = 3,
  NUMBER = 4,
  YEAR = 2013,
  PAGES = {257-279},
  HTTP = {http://dx.doi.org/10.1002/widm.1097},
  ABSTRACT = {Abstract, structured, representations of knowledge such as lexicons, taxonomies, and ontologies have proven to be powerful resources not only for the systematization of knowledge in general, but to support practical technologies of document organization, information retrieval, natural language understanding, and question-answering systems. These resources are extremely time consuming for people to create and maintain, yet demand for them is growing, particularly in specialized areas ranging from legacy documents of large enterprises to rapidly changing domains such as current affairs and celebrity news. Consequently, researchers are investigating methods of creating such structures automatically from document collections, calling on the proliferation of interlinked resources already available on the web for background knowledge and general information about the world. This review surveys what is possible, and also outlines current research directions.}
}

@INPROCEEDINGS{kaban13:_towar_eda,
  AUTHOR = {Ata Kab{\'a}n and
               Jakramate Bootkrajang and
               Robert John Durrant},
  TITLE = {Towards large scale continuous EDA: a random matrix theory
               perspective},
  BOOKTITLE = {Proc Genetic and Evolutionary Computation Conference},
  YEAR = 2013,
  PAGES = {383-390},
  HTTP = {http://doi.acm.org/10.1145/2463372.2463423},
  PDF = {http://www.cms.waikato.ac.nz/~ml/publications/2013/eda.pdf},
  PUBLISHER = ACM,
  SERIES = {Amsterdan, The Netherlands},
  ABSTRACT = {Estimation of distribution algorithms (EDA) are a major branch of evolutionary algorithms (EA) with some unique advantages in principle. They are able to take advantage of correlation structure to drive the search more efficiently, and they are able to provide insights about the structure of the search space. However, model building in high dimensions is extremely challenging and as a result existing EDAs lose their strengths in large scale problems.
Large scale continuous global optimisation is key to many real world problems of modern days. Scaling up EAs to large scale problems has become one of the biggest challenges of the field.
This paper pins down some fundamental roots of the problem and makes a start at developing a new and generic framework to yield effective EDA-type algorithms for large scale continuous global optimisation problems. Our concept is to introduce an ensemble of random projections of the set of fittest search points to low dimensions as a basis for developing a new and generic divide-and-conquer methodology. This is rooted in the theory of random projections developed in theoretical computer science, and will exploit recent advances of non-asymptotic random matrix theory.}
}

@INPROCEEDINGS{durrant13:_sharp_gener_error_bound_random_class,
  AUTHOR = {Robert J. Durrant and Ata Kab{\'a}n},
  TITLE = {Sharp Generalization Error Bounds for Randomly-projected Classifiers},
  BOOKTITLE = {Proc 30th International Conference on Machine Learning},
  PUBLISHER = {JMLR},
  YEAR = 2013,
  SERIES = {Atlanta, Georgia},
  PAGES = {693-701},
  ABSTRACT = {We derive sharp bounds on the generalization error of a generic linear classifier trained by empirical risk minimization on randomly-projected data. We make no restrictive assumptions (such as sparsity or separability) on the data: Instead we use the fact that, in a classification setting, the question of interest is really ‘what is the effect of random projection on the predicted class labels?’ and we therefore derive the exact probability of ‘label flipping’ under Gaussian random projection in order to quantify this effect precisely in our bounds.},
  HTTP = {http://jmlr.org/proceedings/papers/v28/durrant13.pdf}
}

@INPROCEEDINGS{medelyan13:_const_focus_taxon_from_docum_collec,
  AUTHOR = {Olena Medelyan and
               Steve Manion and
               Jeen Broekstra and
               Anna Divoli and
               Anna-Lan Huang and
               Ian H. Witten},
  TITLE = {Constructing a Focused Taxonomy from a Document Collection},
  BOOKTITLE = {Proc 10th European Semantic Web Conference},
  YEAR = 2013,
  PAGES = {367-381},
  SERIES = {Montpellier, France},
  PUBLISHER = {Springer},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-38288-8_25},
  ABSTRACT = {We describe a new method for constructing custom taxonomies from document collections. It involves identifying relevant concepts and entities in text; linking them to knowledge sources like Wikipedia, DBpedia, Freebase, and any supplied taxonomies from related domains; disambiguating conflicting concept mappings; and selecting semantic relations that best group them hierarchically. An RDF model supports interoperability of these steps, and also provides a flexible way of including existing NLP tools and further knowledge sources. From 2000 news articles we construct a custom taxonomy with 10,000 concepts and 12,700 relations, similar in structure to manually created counterparts. Evaluation by 15 human judges shows the precision to be 89\% and 90\% for concepts and relations respectively; recall was 75\% with respect to a manually generated taxonomy for the same domain.}
}

@ARTICLE{rajanayagam13:_artif_neural_networ_is_highl,
  AUTHOR = {Jeremy Rajanayagam and Eibe Frank and Ross W. Shepherd and Peter J. Lewindon},
  TITLE = {Artificial neural network is highly predictive of outcome in paediatric acute liver failure},
  JOURNAL = {Pediatric Transplantation},
  YEAR = 2013,
  HTTP = {http://dx.doi.org/10.1111/petr.12100},
  ABSTRACT = {Current prognostic models in PALF are unreliable, failing to account for complex, non-linear relationships existing between multiple prognostic factors. A computational approach using ANN should provide superior modelling to PELD-MELD scores. We assessed the prognostic accuracy of PELD-MELD scores and ANN in PALF in children presenting to the QLTS, Australia. A comprehensive registry-based data set was evaluated in 54 children (32M, 22F, median age 17 month) with PALF. PELD-MELD scores calculated at (i) meeting PALF criteria and (ii) peak. ANN was evaluated using stratified 10-fold cross-validation. Outcomes were classified as good (transplant-free survival) or poor (death or LT) and predictive accuracy compared using AUROC curves. Mean PELD-MELD scores were significantly higher in non-transplanted non-survivors (i) 37 and (ii) 46 and transplant recipients (i) 32 and (ii) 43 compared to transplant-free survivors (i) 26 and (ii) 30. Threshold PELD-MELD scores ≥27 and ≥42, at meeting PALF criteria and peak, gave AUROC 0.71 and 0.86, respectively, for poor outcome. ANN showed superior prediction for poor outcome with AUROC 0.96, sensitivity 82.6\%, specificity 96\%, PPV 96.2\% and NPV 85.7\% (cut-off 0.5). ANN is superior to PELD-MELD for predicting poor outcome in PALF. }
}

@INPROCEEDINGS{mayo13:_ident_market_price_level_using_differ_evolut,
  AUTHOR = {Michael Mayo},
  TITLE = {Identifying Market Price Levels Using Differential Evolution},
  BOOKTITLE = {Proc 16th European Conference on Applications of Evolutionary Computation},
  YEAR = 2013,
  PAGES = {203-212},
  HTTP = {http://dx.doi.org/10.1007/978-3-642-37192-9_21},
  PUBLISHER = SPRINGER,
  SERIES = {Vienna, Austria},
  ABSTRACT = {Evolutionary data mining is used in this paper to investigate the concept of support and resistance levels in financial markets. Specifically, Differential Evolution is used to learn support/resistance levels from price data. The presence of these levels is then tested in out-of-sample data. Our results from a set of experiments covering five years worth of daily data across nine different US markets show that there is statistical evidence for price levels in certain markets, and that Differential Evolution can uncover them.}
}

@PHDTHESIS{sarjant13:_direc_polic_searc_algor_for,
  AUTHOR = {Samuel Sarjant},
  TITLE = {A direct policy-search algorithm for relational reinforcement learning},
  SCHOOL = {Department of Computer Science, University of Waikato},
  YEAR = 2013,
  HTTP = {http://hdl.handle.net/10289/7671},
  ABSTRACT = {Relational Reinforcement Learning (RRL) is a subfield of machine learning in which a learning agent seeks to maximise a numerical reward within an environment, represented as collections of objects and relations, by performing actions that interact with the environment. The relational representation allows more dynamic environment states than an attribute-based representation of reinforcement learning, but this flexibility also creates new problems such as a potentially infinite number of states.
This thesis describes an RRL algorithm named Cerrla that creates policies directly from a set of learned relational condition-action rules using the Cross-Entropy Method (CEM) to control policy creation. The CEM assigns each rule a sampling probability and gradually modifies these probabilities such that the randomly sampled policies consist of ‘better’ rules, resulting in larger rewards received. Rule creation is guided by an inferred partial model of the environment that defines: the minimal conditions needed to take an action, the possible specialisation conditions per rule, and a set of simplification rules to remove redundant and illegal rule conditions, resulting in compact, efficient, and comprehensible policies.
Cerrla is evaluated on four separate environments, where each environment has several different goals. Results show that compared to existing RRL algorithms, Cerrla is able to learn equal or better behaviour in less time on the standard RRL environment. On other larger, more complex environments, it can learn behaviour that is competitive to specialised approaches. The simplified rules and CEM’s bias towards compact policies result in comprehensive and effective relational policies created in a relatively short amount of time.
}
}

@INPROCEEDINGS{seeland13:_model_selec_based_produc_kernel,
  AUTHOR = {Madeleine Seeland and
               Stefan Kramer and
               Bernhard Pfahringer},
  TITLE = {Model selection based product kernel learning for regression
               on graphs},
  BOOKTITLE = {Proc 28th Annual ACM Symposium on Applied Computing},
  YEAR = 2013,
  PAGES = {136-143},
  HTTP = {http://doi.acm.org/10.1145/2480362.2480391},
  PUBLISHER = {ACM},
  SERIES = {Coimbra, Portugal},
  ABSTRACT = {The choice of a suitable graph kernel is intrinsically hard and often cannot be made in an informed manner for a given dataset. Methods for multiple kernel learning offer a possible remedy, as they combine and weight kernels on the basis of a labeled training set of molecules to define a new kernel. Whereas most methods for multiple kernel learning focus on learning convex linear combinations of kernels, we propose to combine kernels in products, which theoretically enables higher expressiveness. In experiments on ten publicly available chemical QSAR datasets we show that product kernel learning is on no dataset significantly worse than any of the competing kernel methods and on average the best method available. A qualitative analysis of the resulting product kernels shows how the results vary from dataset to dataset.}
}

@INPROCEEDINGS{bifet13:_effic_data_stream_class_via,
  AUTHOR = {Albert Bifet and
               Bernhard Pfahringer and
               Jesse Read and
               Geoff Holmes},
  TITLE = {Efficient data stream classification via probabilistic adaptive
               windows},
  BOOKTITLE = {Proc 28th Annual ACM Symposium on Applied Computing},
  YEAR = 2013,
  PUBLISHER = {ACM},
  SERIES = {Coimbra, Portugal},
  PAGES = {801-806},
  HTTP = {http://doi.acm.org/10.1145/2480362.2480516},
  ABSTRACT = {In the context of a data stream, a classifier must be able to learn from a theoretically-infinite stream of examples using limited time and memory, while being able to predict at any point. Many methods deal with this problem by basing their model on a window of examples. We introduce a probabilistic adaptive window (PAW) for data-stream learning, which improves this windowing technique with a mechanism to include older examples as well as the most recent ones, thus maintaining information on past concept drifts while being able to adapt quickly to new ones. We exemplify PAW with lazy learning methods in two variations: one to handle concept drift explicitly, and the other to add classifier diversity using an ensemble. Along with the standard measures of accuracy and time and memory use, we compare classifiers against state-of-the-art classifiers from the data-stream literature.}
}

@ARTICLE{milne13:_open_sourc_toolk_for_minin_wikip,
  AUTHOR = {David N. Milne and Ian H. Witten},
  TITLE = {An open-source toolkit for mining Wikipedia},
  JOURNAL = {Artificial Intelligence},
  VOLUME = 194,
  YEAR = 2013,
  PAGES = {222-239},
  HTTP = {http://dx.doi.org/10.1016/j.artint.2012.06.007},
  ABSTRACT = {The online encyclopedia Wikipedia is a vast, constantly evolving tapestry of interlinked articles. For developers and researchers it represents a giant multilingual database of concepts and semantic relations, a potential resource for natural language processing and many other research areas. This paper introduces the Wikipedia Miner toolkit, an open-source software system that allows researchers and developers to integrate Wikipedia's rich semantics into their own applications. The toolkit creates databases that contain summarized versions of Wikipedia's content and structure, and includes a Java API to provide access to them. Wikipedia's articles, categories and redirects are represented as classes, and can be efficiently searched, browsed, and iterated over. Advanced features include parallelized processing of Wikipedia dumps, machine-learned semantic relatedness measures and annotation features, and XML-based web services. Wikipedia Miner is intended to be a platform for sharing data mining techniques.}
}