Fitting a mixture model to three-mode three-way data with missing information

When the data consist of certain attributes measured on the same set of items in different situations, they would be described as a three-mode three-way array. A mixture likelihood approach can be implemented to cluster the items (i.e., one of the modes) on the basis of both of the other modes simultaneously (i.e,, the attributes measured in different situations). In this paper, it is shown that this approach can be extended to handle three-mode three-way arrays where some of the data values are missing at random in the sense of Little and Rubin (1987). The methodology is illustrated by clustering the genotypes in a three-way soybean data set where various attributes were measured on genotypes grown in several environments.

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD

Public reporting of hospital outcomes based on administrative data: risks and opportunities

In the wake of findings from the Bundaberg Hospital and Forster inquiries in Queensland, periodic public release of hospital performance reports has been recommended. A process for developing and releasing such reports is being established by Queensland Health, overseen by an independent expert panel. This recommendation presupposes that public reports based on routinely collected administrative data are accurate; that the public can access, correctly interpret and act upon report contents; that reports motivate hospital clinicians and managers to improve quality of care; and that there are no unintended adverse effects of public reporting. Available research suggests that primary data sources are often inaccurate and incomplete, that reports have low predictive value in detecting outlier hospitals, and that users experience difficulty in accessing and interpreting reports and tend to distrust their findings.

IJDWM Special Issue: Advances in Data Mining Applications

This special issue is a collection of the selected papers published on the proceedings of the First International Conference on Advanced Data Mining and Applications (ADMA) held in Wuhan, China in 2005. The articles focus on the innovative applications of data mining approaches to the problems that involve large data sets, incomplete and noise data, or demand optimal solutions.

Migrating eprints.org data to a Fez repository

This document records the process of migrating eprints.org data to a Fez repository. Fez is a Web-based digital repository and workflow management system based on Fedora (http://www.fedora.info/). At the time of migration, the University of Queensland Library was using EPrints 2.2.1 [pepper] for its ePrintsUQ repository. Once we began to develop Fez, we did not upgrade to later versions of eprints.org software since we knew we would be migrating data from ePrintsUQ to the Fez-based UQ eSpace. Since this document records our experiences of migration from an earlier version of eprints.org, anyone seeking to migrate eprints.org data into a Fez repository might encounter some small differences. Moving UQ publication data from an eprints.org repository into a Fez repository (hereafter called UQ eSpace (http://espace.uq.edu.au/) was part of a plan to integrate metadata (and, in some cases, full texts) about all UQ research outputs, including theses, images, multimedia and datasets, in a single repository. This tied in with the plan to identify and capture the research output of a single institution, the main task of the eScholarshipUQ testbed for the Australian Partnership for Sustainable Repositories project (http://www.apsr.edu.au/). The migration could not occur at UQ until the functionality in Fez was at least equal to that of the existing ePrintsUQ repository. Accordingly, as Fez development occurred throughout 2006, a list of eprints.org functionality not currently supported in Fez was created so that programming of such development could be planned for and implemented.

A simple data logger for student-designed rocket experiments.

The final-year project for Mechanical & Space Engineering students at UQ often involves the design and flight testing of an experiment. This report describes the design and use of a simple data logger that should be suitable for collecting data from the students' flight experiments. The exercise here was taken as far as the construction of a prototype device that is suitable for ground-based testing, say, the static firing of a hybrid rocket motor.

A class of compact dwarf galaxies from disruptive processes in galaxy clusters

Dwarf galaxies have attracted increased attention in recent years, because of their susceptibility to galaxy transformation processes within rich galaxy clusters. Direct evidence for these processes, however, has been difficult to obtain, with a small number of diffuse light trails and intra-cluster stars, being the only signs of galaxy disruption. Furthermore, our current knowledge of dwarf galaxy populations may be very incomplete, because traditional galaxy surveys are insensitive to extremely diffuse or compact galaxies. Aware of these concerns, we recently undertook an all-object survey of the Fornax galaxy cluster. This revealed a new population of compact members, overlooked in previous conventional surveys. Here we demonstrate that these 'ultra-compact' dwarf galaxies are structurally and dynamically distinct from both globular star clusters and known types of dwarf galaxy, and thus represent a new class of dwarf galaxy. Our data are consistent with the interpretation that these are the remnant nuclei of disrupted dwarf galaxies, making them an easily observed tracer of galaxy disruption.

Equational Reasoning as a Tool for Data Analysis

A combination of deductive reasoning, clustering, and inductive learning is given as an example of a hybrid system for exploratory data analysis. Visualization is replaced by a dialogue with the data.

Leadership Attributes and Cultural Values in Australia and New Zealand Compared: An Initial Report Based on GLOBE Data.

This paper reports a comparative study of Australian and New Zealand leadership attributes, based on the GLOBE (Global Leadership and Organizational Behavior Effectiveness) program. Responses from 344 Australian managers and 184 New Zealand managers in three industries were analyzed using exploratory and confirmatory factor analysis. Results supported some of the etic leadership dimensions identified in the GLOBE study, but also found some emic dimensions of leadership for each country. An interesting finding of the study was that the New Zealand data fitted the Australian model, but not vice versa, suggesting asymmetric perceptions of leadership in the two countries.

Selection bias in gene extraction on the basis of microarray gene-expression data

In the context of cancer diagnosis and treatment, we consider the problem of constructing an accurate prediction rule on the basis of a relatively small number of tumor tissue samples of known type containing the expression data on very many (possibly thousands) genes. Recently, results have been presented in the literature suggesting that it is possible to construct a prediction rule from only a few genes such that it has a negligible prediction error rate. However, in these results the test error or the leave-one-out cross-validated error is calculated without allowance for the selection bias. There is no allowance because the rule is either tested on tissue samples that were used in the first instance to select the genes being used in the rule or because the cross-validation of the rule is not external to the selection process; that is, gene selection is not performed in training the rule at each stage of the cross-validation process. We describe how in practice the selection bias can be assessed and corrected for by either performing a cross-validation or applying the bootstrap external to the selection process. We recommend using 10-fold rather than leave-one-out cross-validation, and concerning the bootstrap, we suggest using the so-called. 632+ bootstrap error estimate designed to handle overfitted prediction rules. Using two published data sets, we demonstrate that when correction is made for the selection bias, the cross-validated error is no longer zero for a subset of only a few genes.

Special issue on advances in data mining and its applications

Data mining is the process to identify valid, implicit, previously unknown, potentially useful and understandable information from large databases. It is an important step in the process of knowledge discovery in databases, (Olaru & Wehenkel, 1999). In a data mining process, input data can be structured, seme-structured, or unstructured. Data can be in text, categorical or numerical values. One of the important characteristics of data mining is its ability to deal data with large volume, distributed, time variant, noisy, and high dimensionality. A large number of data mining algorithms have been developed for different applications. For example, association rules mining can be useful for market basket problems, clustering algorithms can be used to discover trends in unsupervised learning problems, classification algorithms can be applied in decision-making problems, and sequential and time series mining algorithms can be used in predicting events, fault detection, and other supervised learning problems (Vapnik, 1999). Classification is among the most important tasks in the data mining, particularly for data mining applications into engineering fields. Together with regression, classification is mainly for predictive modelling. So far, there have been a number of classification algorithms in practice. According to (Sebastiani, 2002), the main classification algorithms can be categorized as: decision tree and rule based approach such as C4.5 (Quinlan, 1996); probability methods such as Bayesian classifier (Lewis, 1998); on-line methods such as Winnow (Littlestone, 1988) and CVFDT (Hulten 2001), neural networks methods (Rumelhart, Hinton & Wiliams, 1986); example-based methods such as k-nearest neighbors (Duda & Hart, 1973), and SVM (Cortes & Vapnik, 1995). Other important techniques for classification tasks include Associative Classification (Liu et al, 1998) and Ensemble Classification (Tumer, 1996).

A framework for electricity price spike analysis with advanced data mining methods

There are many techniques for electricity market price forecasting. However, most of them are designed for expected price analysis rather than price spike forecasting. An effective method of predicting the occurrence of spikes has not yet been observed in the literature so far. In this paper, a data mining based approach is presented to give a reliable forecast of the occurrence of price spikes. Combined with the spike value prediction techniques developed by the same authors, the proposed approach aims at providing a comprehensive tool for price spike forecasting. In this paper, feature selection techniques are firstly described to identify the attributes relevant to the occurrence of spikes. A simple introduction to the classification techniques is given for completeness. Two algorithms: support vector machine and probability classifier are chosen to be the spike occurrence predictors and are discussed in details. Realistic market data are used to test the proposed model with promising results.

Using household survey data to inform policy decisions regarding the delivery of evidence-based parenting interventions.

Background: This study used household survey data on the prevalence of child, parent and family variables to establish potential targets for a population-level intervention to strengthen parenting skills in the community. The goals of the intervention include decreasing child conduct problems, increasing parental self-efficacy, use of positive parenting strategies, decreasing coercive parenting and increasing help-seeking, social support and participation in positive parenting programmes. Methods: A total of 4010 parents with a child under the age of 12 years completed a statewide telephone survey on parenting. Results: One in three parents reported that their child had a behavioural or emotional problem in the previous 6 months. Furthermore, 9% of children aged 2–12 years meet criteria for oppositional defiant disorder. Parents who reported their child's behaviour to be difficult were more likely to perceive parenting as a negative experience (i.e. demanding, stressful and depressing). Parents with greatest difficulties were mothers without partners and who had low levels of confidence in their parenting roles. About 20% of parents reported being stressed and 5% reported being depressed in the 2 weeks prior to the survey. Parents with personal adjustment problems had lower levels of parenting confidence and their child was more difficult to manage. Only one in four parents had participated in a parent education programme. Conclusions: Implications for the setting of population-level goals and targets for strengthening parenting skills are discussed.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.