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).

Role of cytokine gene polymorphisms in acute rejection and renal impairment after liver transplantation

Although immunosuppressive regimens are effective, rejection occurs in up to 50% of patients after orthotopic liver transplantation (OLT), and there is concern about side effects from long-term therapy. Knowledge of clinical and immunogenetic variables may allow tailoring of immunosuppressive therapy to patients according to their potential risks. We studied the association between transforming growth factor-beta, interleukin-10, and tumor necrosis factor alpha (TNF-alpha) gene polymorphisms and graft rejection and renal impairment in 121 white liver transplant recipients. Clinical variables were collected retrospectively, and creatinine clearance was estimated using the formula of Cockcroft and Gault. Biallelic polymorphisms were detected using polymerase chain reaction-based methods. Thirty-seven of 121 patients (30.6%) developed at least 1 episode of rejection. Multivariate analysis showed that Child-Pugh score (P =.001), immune-mediated liver disease (P =.018), normal pre-OLT creatinine clearance (P =.037), and fewer HLA class 1 mismatches (P =.038) were independently associated with rejection, Renal impairment occurred in 80% of patients and was moderate or severe in 39%, Clinical variables independently associated with renal impairment were female sex (P =.001), pre-OLT renal dysfunction (P =.0001), and a diagnosis of viral hepatitis (P =.0008), There was a significant difference in the frequency of TNF-alpha -308 alleles among the primary liver diseases. After adjustment for potential confounders and a Bonferroni correction, the association between the TNF-alpha -308 polymorphism and graft rejection approached significance (P =.06). Recipient cytokine genotypes do not have a major independent role in graft rejection or renal impairment after OLT, Additional studies of immunogenetic factors require analysis of large numbers of patients with appropriate phenotypic information to avoid population stratification, which may lead to inappropriate conclusions.

An investigation into effects of long-distance seed dispersal on organelle population genetic structure and colonization rate: a model analysis

A simulation-based modelling approach is used to examine the effects of stratified seed dispersal (representing the distribution of the majority of dispersal around the maternal parent and also rare long-distance dispersal) on the genetic structure of maternally inherited genomes and the colonization rate of expanding plant populations. The model is parameterized to approximate postglacial oak colonization in the UK, but is relevant to plant populations that exhibit stratified seed dispersal. The modelling approach considers the colonization of individual plants over a large area (three 500 km x 10 km rolled transects are used to approximate a 500 km x 300 km area). Our approach shows how the interaction of plant population dynamics with stratified dispersal can result in a spatially patchy haplotype structure. We show that while both colonization speeds and the resulting genetic structure are influenced by the characteristics of the dispersal kernel, they are robust to changes in the periodicity of long-distance events, provided the average number of long-distance dispersal events remains constant. We also consider the effects of additional physical and environmental mechanisms on plant colonization. Results show significant changes in genetic structure when the initial colonization of different haplotypes is staggered over time and when a barrier to colonization is introduced. Environmental influences on survivorship and fecundity affect both the genetic structure and the speed of colonization. The importance of these mechanisms in relation to the postglacial spread and genetic structure of oak in the UK is discussed.

Winding patterns for biplanar MRI shim coils with rectangular and circular target-field regions

A method is presented for calculating the winding patterns required to design independent zonal and tesseral biplanar shim coils for magnetic resonance imaging. Streamline, target-field, Fourier integral and Fourier series methods are utilized. For both Fourier-based methods, the desired target field is specified on the surface of the conducting plates. For the Fourier series method it is possible to specify the target field at additional depths interior to the two conducting plates. The conducting plates are confined symmetrically in the xy plane with dimensions 2a x 2b, and are separated by 2d in the z direction. The specification of the target field is symmetric for the Fourier integral method, but can be over some asymmetric portion pa < x < qa and sb < y < tb of the coil dimensions (-1 < p < q < 1 and -1 < s < t < 1) for the Fourier series method. Arbitrary functions are used in the outer sections to ensure continuity of the magnetic field across the entire coil face. For the Fourier series case, the entire field is periodically extended as double half-range sine or cosine series. The resultant Fourier coefficients are substituted into the Fourier series and integral expressions for the internal and external magnetic fields, and stream functions on both the conducting surfaces. A contour plot of the stream function directly gives the required coil winding patterns. Spherical harmonic analysis of field calculations from a ZX shim coil indicates that example designs and theory are well matched.

Modelling, nitrogen dynamics in sugarcane systems: Recent advances and applications

Substantial amounts of nitrogen (N) fertiliser are necessary for commercial sugarcane production because of the large biomass produced by sugarcane crops. Since this fertiliser is a substantial input cost and has implications if N is lost to the environment, there are pressing needs to optimise the supply of N to the crops' requirements. The complexity of the N cycle and the strong influence of climate, through its moderation of N transformation processes in the soil and its impact on N uptake by crops, make simulation-based approaches to this N management problem attractive. In this paper we describe the processes to be captured in modelling soil and plant N dynamics in sugarcane systems, and review the capability for modelling these processes. We then illustrate insights gained into improved management of N through simulation-based studies for the issues of crop residue management, irrigation management and greenhouse gas emissions. We conclude by identifying processes not currently represented in the models used for simulating N cycling in sugarcane production systems, and illustrate ways in which these can be partially overcome in the short term. (c) 2005 Elsevier B.V. All rights reserved.

Optimisation of poly-b-hydroxyalkanoate analysis using gas chromatography for enhanced biological phosphorus removal systems

Poly-beta-hydroxyalkanoate (PHA) is a polymer commonly used in carbon and energy storage for many different bacterial cells. Polyphosphate accumulating organisms (PAOs) and glycogen accumulating organisms (GAOs), store PHA anaerobically through metabolism of carbon substrates such as acetate and propionate. Although poly-beta-hydroxybutyrate (PHB)and poly-beta-hydroxyvalerate (PHV) are commonly quantified using a previously developed gas chromatography (GC) method, poly-beta-hydroxy-2-methyl valerate (PH2MV) is seldom quantified despite the fact that it has been shown to be a key PHA fraction produced when PAOs or GAOs metabolise propionate. This paper presents two GC-based methods modified for extraction and quantification of PHB, PHV and PH2MV from enhanced biological phosphorus removal (EBPR) systems. For the extraction Of PHB and PHV from acetate fed PAO and GAO cultures, a 3% sulfuric acid concentration and a 2-20 h digestion time is recommended, while a 10% sulfuric acid solution digested for 20 h is recommended for PHV and PH2MV analysis from propionate fed EBPR systems. (c) 2005 Elsevier B.V. All rights reserved.

Using extreme value theory to measure value-at-risk for daily electricity spot prices

The recent deregulation in electricity markets worldwide has heightened the importance of risk management in energy markets. Assessing Value-at-Risk (VaR) in electricity markets is arguably more difficult than in traditional financial markets because the distinctive features of the former result in a highly unusual distribution of returns-electricity returns are highly volatile, display seasonalities in both their mean and volatility, exhibit leverage effects and clustering in volatility, and feature extreme levels of skewness and kurtosis. With electricity applications in mind, this paper proposes a model that accommodates autoregression and weekly seasonals in both the conditional mean and conditional volatility of returns, as well as leverage effects via an EGARCH specification. In addition, extreme value theory (EVT) is adopted to explicitly model the tails of the return distribution. Compared to a number of other parametric models and simple historical simulation based approaches, the proposed EVT-based model performs well in forecasting out-of-sample VaR. In addition, statistical tests show that the proposed model provides appropriate interval coverage in both unconditional and, more importantly, conditional contexts. Overall, the results are encouraging in suggesting that the proposed EVT-based model is a useful technique in forecasting VaR in electricity markets. (c) 2005 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.

Predicting residue-wise contact orders in proteins by support vector regression

Background: The residue-wise contact order (RWCO) describes the sequence separations between the residues of interest and its contacting residues in a protein sequence. It is a new kind of one-dimensional protein structure that represents the extent of long-range contacts and is considered as a generalization of contact order. Together with secondary structure, accessible surface area, the B factor, and contact number, RWCO provides comprehensive and indispensable important information to reconstructing the protein three-dimensional structure from a set of one-dimensional structural properties. Accurately predicting RWCO values could have many important applications in protein three-dimensional structure prediction and protein folding rate prediction, and give deep insights into protein sequence-structure relationships. Results: We developed a novel approach to predict residue-wise contact order values in proteins based on support vector regression (SVR), starting from primary amino acid sequences. We explored seven different sequence encoding schemes to examine their effects on the prediction performance, including local sequence in the form of PSI-BLAST profiles, local sequence plus amino acid composition, local sequence plus molecular weight, local sequence plus secondary structure predicted by PSIPRED, local sequence plus molecular weight and amino acid composition, local sequence plus molecular weight and predicted secondary structure, and local sequence plus molecular weight, amino acid composition and predicted secondary structure. When using local sequences with multiple sequence alignments in the form of PSI-BLAST profiles, we could predict the RWCO distribution with a Pearson correlation coefficient (CC) between the predicted and observed RWCO values of 0.55, and root mean square error (RMSE) of 0.82, based on a well-defined dataset with 680 protein sequences. Moreover, by incorporating global features such as molecular weight and amino acid composition we could further improve the prediction performance with the CC to 0.57 and an RMSE of 0.79. In addition, combining the predicted secondary structure by PSIPRED was found to significantly improve the prediction performance and could yield the best prediction accuracy with a CC of 0.60 and RMSE of 0.78, which provided at least comparable performance compared with the other existing methods. Conclusion: The SVR method shows a prediction performance competitive with or at least comparable to the previously developed linear regression-based methods for predicting RWCO values. In contrast to support vector classification (SVC), SVR is very good at estimating the raw value profiles of the samples. The successful application of the SVR approach in this study reinforces the fact that support vector regression is a powerful tool in extracting the protein sequence-structure relationship and in estimating the protein structural profiles from amino acid sequences.

Methicillin-resistant Staphylococcus aureus genotyping using a small set of polymorphisms

The aim of this study was to identify a set of genetic polymorphisms that efficiently divides methicillin-resistant Staphylococcus aureus (MRSA) strains into groups consistent with the population structure. The rationale was that such polymorphisms could underpin rapid real-time PCR or low-density array-based methods for monitoring MRSA dissemination in a cost-effective manner. Previously, the authors devised a computerized method for identifying sets of single nucleoticle polymorphisms (SNPs) with high resolving power that are defined by multilocus sequence typing (MLST) databases, and also developed a real-time PCR method for interrogating a seven-member SNP set for genotyping S. aureus. Here, it is shown that these seven SNPs efficiently resolve the major MRSA lineages and define 27 genotypes. The SNP-based genotypes are consistent with the MRSA population structure as defined by eBURST analysis. The capacity of binary markers to improve resolution was tested using 107 diverse MRSA isolates of Australian origin that encompass nine SNP-based genotypes. The addition of the virulence-associated genes cna, pvl and bbplsdrE, and the integrated plasmids pT181, p1258 and pUB110, resolved the nine SNP-based genotypes into 21 combinatorial genotypes. Subtyping of the SCCmec locus revealed new SCCmec types and increased the number of combinatorial genotypes to 24. It was concluded that these polymorphisms provide a facile means of assigning MRSA isolates into well-recognized lineages.

An atomistic simulation of solid state sintering using Monte Carlo methods

This paper presents results on the simulation of the solid state sintering of copper wires using Monte Carlo techniques based on elements of lattice theory and cellular automata. The initial structure is superimposed onto a triangular, two-dimensional lattice, where each lattice site corresponds to either an atom or vacancy. The number of vacancies varies with the simulation temperature, while a cluster of vacancies is a pore. To simulate sintering, lattice sites are picked at random and reoriented in terms of an atomistic model governing mass transport. The probability that an atom has sufficient energy to jump to a vacant lattice site is related to the jump frequency, and hence the diffusion coefficient, while the probability that an atomic jump will be accepted is related to the change in energy of the system as a result of the jump, as determined by the change in the number of nearest neighbours. The jump frequency is also used to relate model time, measured in Monte Carlo Steps, to the actual sintering time. The model incorporates bulk, grain boundary and surface diffusion terms and includes vacancy annihilation on the grain boundaries. The predictions of the model were found to be consistent with experimental data, both in terms of the microstructural evolution and in terms of the sintering time. (C) 2002 Elsevier Science B.V. All rights reserved.

Laboratory-based simulation of freezing profiles of beef trim for Escherichia coli O157 survival determinations

This study was undertaken to develop a simple laboratory-based method for simulating the freezing profiles of beef trim so that their effect on E. coli 0157 survival could be better assessed. A commercially available apparatus of the type used for freezing embryos, together with an associated temperature logger and software, was used for this purpose with a -80 degrees C freezer as a heat sink. Four typical beef trim freezing profiles, of different starting temperatures or lengths, were selected and modelled as straight lines for ease of manipulation. A further theoretical profile with an extended freezing plateau was also developed. The laboratory-based setup worked well and the modelled freezing profiles fitted closely to the original data. No change in numbers of any of the strains was apparent for the three simulated profiles of different lengths starting at 25 degrees C. Slight but significant (P < 0.05) decreases in numbers (similar to 0.2 log cfu g(-1)) of all strains were apparent for a profile starting at 12 degrees C. A theoretical version of this profile with a freezing plateau phase extended from 11 h to 17 h resulted in significant (P < 0.05) decreases in numbers (similar to 1.2 log cfu g(-1)) of all strains. Results indicated possible avenues for future research in controlling this pathogen. The method developed in this study proved a useful and cost-effective way for simulating freezing profiles of beef trim. (c) 2005 Elsevier B.V. All rights reserved.

Erosion/productivity modelling of maize farming in the Philippine uplands part II: Simulation of alternative farming methods

A version of the Agricultural Production Systems Simulator (APSIM) capable of simulating the key agronomic aspects of intercropping maize between legume shrub hedgerows was described and parameterised in the first paper of this series (Nelson et al., this issue). In this paper, APSIM is used to simulate maize yields and soil erosion from traditional open-field farming and hedgerow intercropping in the Philippine uplands. Two variants of open-field farming were simulated using APSIM, continuous and fallow, for comparison with intercropping maize between leguminous shrub hedgerows. Continuous open-field maize farming was predicted to be unsustainable in the long term, while fallow open-field farming was predicted to slow productivity decline by spreading the effect of erosion over a larger cropping area. Hedgerow intercropping was predicted to reduce erosion by maintaining soil surface cover during periods of intense rainfall, contributing to sustainable production of maize in the long term. In the third paper in this series, Nelson et al. (this issue) use cost-benefit analysis to compare the economic viability of hedgerow intercropping relative to traditional open-field farming of maize in relatively inaccessible upland areas. (C) 1998 Elsevier Science Ltd. All rights reserved.

Predicting energy requirements in the clinical setting: Are current methods evidence based?

Estimating energy requirements is necessary in clinical practice when indirect calorimetry is impractical. This paper systematically reviews current methods for estimating energy requirements. Conclusions include: there is discrepancy between the characteristics of populations upon which predictive equations are based and current populations; tools are not well understood, and patient care can be compromised by inappropriate application of the tools. Data comparing tools and methods are presented and issues for practitioners are discussed. (C) 2003 International Life Sciences Institute.

Assessing cost-effectiveness - Mental health: introduction to the study and methods

Objective: The Assessing Cost-Effectiveness - Mental Health (ACE-MH) study aims to assess from a health sector perspective, whether there are options for change that could improve the effectiveness and efficiency of Australia's current mental health services by directing available resources toward 'best practice' cost-effective services. Method: The use of standardized evaluation methods addresses the reservations expressed by many economists about the simplistic use of League Tables based on economic studies confounded by differences in methods, context and setting. The cost-effectiveness ratio for each intervention is calculated using economic and epidemiological data. This includes systematic reviews and randomised controlled trials for efficacy, the Australian Surveys of Mental Health and Wellbeing for current practice and a combination of trials and longitudinal studies for adherence. The cost-effectiveness ratios are presented as cost (A$) per disability-adjusted life year (DALY) saved with a 95% uncertainty interval based on Monte Carlo simulation modelling. An assessment of interventions on 'second filter' criteria ('equity', 'strength of evidence', 'feasibility' and 'acceptability to stakeholders') allows broader concepts of 'benefit' to be taken into account, as well as factors that might influence policy judgements in addition to cost-effectiveness ratios. Conclusions: The main limitation of the study is in the translation of the effect size from trials into a change in the DALY disability weight, which required the use of newly developed methods. While comparisons within disorders are valid, comparisons across disorders should be made with caution. A series of articles is planned to present the results.