Towards a model-driven engineering approach of data mining

Nowadays, data mining is based on low-level specications of the employed techniques typically bounded to a specic analysis platform. Therefore, data mining lacks a modelling architecture that allows analysts to consider it as a truly software-engineering process. Here, we propose a model-driven approach based on (i) a conceptual modelling framework for data mining, and (ii) a set of model transformations to automatically generate both the data under analysis (via data-warehousing technology) and the analysis models for data mining (tailored to a specic platform). Thus, analysts can concentrate on the analysis problem via conceptual data-mining models instead of low-level programming tasks related to the underlying-platform technical details. These tasks are now entrusted to the model-transformations scaffolding.

On a resampling approach for tests on the number of clusters with mixture model-based clustering of tissue samples

We consider the problem of assessing the number of clusters in a limited number of tissue samples containing gene expressions for possibly several thousands of genes. It is proposed to use a normal mixture model-based approach to the clustering of the tissue samples. One advantage of this approach is that the question on the number of clusters in the data can be formulated in terms of a test on the smallest number of components in the mixture model compatible with the data. This test can be carried out on the basis of the likelihood ratio test statistic, using resampling to assess its null distribution. The effectiveness of this approach is demonstrated on simulated data and on some microarray datasets, as considered previously in the bioinformatics literature. (C) 2004 Elsevier Inc. All rights reserved.

Seven-membered Rings Through Metal-free Rearrangement Mediated By Hypervalent Iodine.

A versatile and metal-free approach for the synthesis of carbocycles and of heterocycles bearing seven- and eight-membered rings is described. The strategy is based on ring expansion of 1-vinylcycloalkanols (or the corresponding silyl or methyl ether) mediated by the hypervalent iodine reagent HTIB (PhI(OH)OTs). Reaction conditions can be easily adjusted to give ring expansion products bearing different functional groups. A route to medium-ring lactones was also developed.

Long-term survivor mixture model with random effects: application to a multi-centre clinical trial of carcinoma

A mixture model incorporating long-term survivors has been adopted in the field of biostatistics where some individuals may never experience the failure event under study. The surviving fractions may be considered as cured. In most applications, the survival times are assumed to be independent. However, when the survival data are obtained from a multi-centre clinical trial, it is conceived that the environ mental conditions and facilities shared within clinic affects the proportion cured as well as the failure risk for the uncured individuals. It necessitates a long-term survivor mixture model with random effects. In this paper, the long-term survivor mixture model is extended for the analysis of multivariate failure time data using the generalized linear mixed model (GLMM) approach. The proposed model is applied to analyse a numerical data set from a multi-centre clinical trial of carcinoma as an illustration. Some simulation experiments are performed to assess the applicability of the model based on the average biases of the estimates formed. Copyright (C) 2001 John Wiley & Sons, Ltd.

A zero-augmented gamma mixed model for longitudinal data with many zeros

In many occupational safety interventions, the objective is to reduce the injury incidence as well as the mean claims cost once injury has occurred. The claims cost data within a period typically contain a large proportion of zero observations (no claim). The distribution thus comprises a point mass at 0 mixed with a non-degenerate parametric component. Essentially, the likelihood function can be factorized into two orthogonal components. These two components relate respectively to the effect of covariates on the incidence of claims and the magnitude of claims, given that claims are made. Furthermore, the longitudinal nature of the intervention inherently imposes some correlation among the observations. This paper introduces a zero-augmented gamma random effects model for analysing longitudinal data with many zeros. Adopting the generalized linear mixed model (GLMM) approach reduces the original problem to the fitting of two independent GLMMs. The method is applied to evaluate the effectiveness of a workplace risk assessment teams program, trialled within the cleaning services of a Western Australian public hospital.

Integrable variant of the one-dimensional Hubbard model

A new integrable model which is a variant of the one-dimensional Hubbard model is proposed. The integrability of the model is verified by presenting the associated quantum R-matrix which satisfies the Yang-Baxter equation. We argue that the new model possesses the SO(4) algebra symmetry, which contains a representation of the eta-pairing SU(2) algebra and a spin SU(2) algebra. Additionally, the algebraic Bethe ansatz is studied by means of the quantum inverse scattering method. The spectrum of the Hamiltonian, eigenvectors, as well as the Bethe ansatz equations, are discussed. (C) 2002 American Institute of Physics.

Model-based clustering in gene expression microarrays: An application to breast cancer data

In microarray studies, the application of clustering techniques is often used to derive meaningful insights into the data. In the past, hierarchical methods have been the primary clustering tool employed to perform this task. The hierarchical algorithms have been mainly applied heuristically to these cluster analysis problems. Further, a major limitation of these methods is their inability to determine the number of clusters. Thus there is a need for a model-based approach to these. clustering problems. To this end, McLachlan et al. [7] developed a mixture model-based algorithm (EMMIX-GENE) for the clustering of tissue samples. To further investigate the EMMIX-GENE procedure as a model-based -approach, we present a case study involving the application of EMMIX-GENE to the breast cancer data as studied recently in van 't Veer et al. [10]. Our analysis considers the problem of clustering the tissue samples on the basis of the genes which is a non-standard problem because the number of genes greatly exceed the number of tissue samples. We demonstrate how EMMIX-GENE can be useful in reducing the initial set of genes down to a more computationally manageable size. The results from this analysis also emphasise the difficulty associated with the task of separating two tissue groups on the basis of a particular subset of genes. These results also shed light on why supervised methods have such a high misallocation error rate for the breast cancer data.

On performance of distributed model predictive control in power system frequency regulation

This paper describes the implementation of a distributed model predictive approach for automatic generation control. Performance results are discussed by comparing classical techniques (based on integral control) with model predictive control solutions (centralized and distributed) for different operational scenarios with two interconnected networks. These scenarios include variable load levels (ranging from a small to a large unbalance generated power to power consumption ratio) and simultaneously variable distance between the interconnected networks systems. For the two networks the paper also examines the impact of load variation in an island context (a network isolated from each other).

O futuro da liderança de topo na administração pública portuguesa. Forças motrizes e cenários possíveis.

Dissertação de mestrado em Administração Pública, orientada pelo Professor Doutor J. A. Oliveira Rocha apresentada na Escola de Economia e Gestão da Universidade do Minho, em 2006.

Relationship between ISO 9001 certification maturity and EFQM business excellence model results

Purpose: This exploratory research evaluates if there is a relationship between the number of years since an organization has achieved ISO 9001 certification and the highest level of recognition received by the same organization with the EFQM Business Excellence Model. Methodology/Approach: After state of the art review a detailed comparison between both models was made. Fifty two Portuguese organizations were considered and Correlation coefficient Spearman Rho was used to investigate the possible relationships. Findings: Conclusion is that there is indeed a moderate positive correlation between these two variables, the higher the number of years of ISO 9001 certification, the higher the results of the organization EFQM model evaluation and recognition. This supports the assumption that ISO 9001 International Standard by incorporating many of the principles present in the EFQM Business Excellence Model is consistent with this model and can be considered as a step towards that direction. Research Limitation/implication: Due to the dynamic nature of these models that might change over time and the possible time delays between implementation and results, more in-depth studies like experimental design or a longitudinal quasi-experimental design could be used to confirm the results of this investigation. Originality/Value of paper: This research gives additional insights on conjunct studies of both models. The use of external evaluation results carried out by the independent EFQM assessors minimizes the possible bias of previous studies accessing the value of ISO 9001 certification.

Relationship between imatinib population pharmacokinetics and alpha-1-acid glycoprotein

Objectives: Considering the large inter-individual differences in the function of the systems involved in imatinib disposition, exposure to this drug can be expected to vary widely among patients. Among those known systems is alpha-1-acid glycoprotein (AGP), a circulating protein that strongly binds imatinib. This observational study aimed to explore the influence of plasma AGP on imatinib pharmacokinetics. Methods: A population pharmacokinetic analysis was performed using NONMEM based on 278 plasma samples from 51 oncologic patients, for whom both total imatinib and AGP plasma concentrations were measured. The influence of this biological covariate on oral clearance and volume of distribution was examined. Results: A one-compartment model with first-order absorption appropriately described the data. A hyperbolic relationship between plasma AGP levels and oral clearance, as well as volume of distribution was observed. A mechanistic approach was built up, postulating that only the unbound imatinib concentration was able to undergo first-order elimination through an unbound clearance process, and integrating the dissociation constant as a parameter in the model. This approach allowed determining an average (± SEM) free clearance of 1310 (± 172) L/h and a volume of distribution of 301 (± 23) L. By comparison, the total clearance previously determined was 14 (± 1) L/h. Free clearance was affected by body weight and pathology diagnosis. Moreover, this model provided consistent estimates of the association constant between imatinib and AGP (5.5?106 L/mol) and of the average in vivo free fraction of imatinib (1.1%). The variability observed (17% for free clearance and 66% for volume of distribution) was less than the one previously reported without considering AGP impact. AGP explained indeed about one half of the variability observed in total imatinib disposition. Conclusion: Such findings clarify in part the in vivo impact of protein binding on imatinib disposition and might raise again the question whether high levels of AGP could represent a resistance factor to imatinib. This remains however questionable, as it is not expected to affect free drug concentrations. On the other hand, would imatinib be demonstrated as a drug requiring therapeutic drug monitoring, either the measurement of free concentration or the correction of the total concentration by the actual AGP plasma levels should be considered for accurate interpretation of the results.

Predictability of music descriptor time series and its application to cover song detection

Intuitively, music has both predictable and unpredictable components. In this work we assess this qualitative statement in a quantitative way using common time series models fitted to state-of-the-art music descriptors. These descriptors cover different musical facets and are extracted from a large collection of real audio recordings comprising a variety of musical genres. Our findings show that music descriptor time series exhibit a certain predictability not only for short time intervals, but also for mid-term and relatively long intervals. This fact is observed independently of the descriptor, musical facet and time series model we consider. Moreover, we show that our findings are not only of theoretical relevance but can also have practical impact. To this end we demonstrate that music predictability at relatively long time intervals can be exploited in a real-world application, namely the automatic identification of cover songs (i.e. different renditions or versions of the same musical piece). Importantly, this prediction strategy yields a parameter-free approach for cover song identification that is substantially faster, allows for reduced computational storage and still maintains highly competitive accuracies when compared to state-of-the-art systems.

Estimation of the viscoelastic properties of vessel walls using a computational model and Doppler ultrasound

Human arteries affected by atherosclerosis are characterized by altered wall viscoelastic properties. The possibility of noninvasively assessing arterial viscoelasticity in vivo would significantly contribute to the early diagnosis and prevention of this disease. This paper presents a noniterative technique to estimate the viscoelastic parameters of a vascular wall Zener model. The approach requires the simultaneous measurement of flow variations and wall displacements, which can be provided by suitable ultrasound Doppler instruments. Viscoelastic parameters are estimated by fitting the theoretical constitutive equations to the experimental measurements using an ARMA parameter approach. The accuracy and sensitivity of the proposed method are tested using reference data generated by numerical simulations of arterial pulsation in which the physiological conditions and the viscoelastic parameters of the model can be suitably varied. The estimated values quantitatively agree with the reference values, showing that the only parameter affected by changing the physiological conditions is viscosity, whose relative error was about 27% even when a poor signal-to-noise ratio is simulated. Finally, the feasibility of the method is illustrated through three measurements made at different flow regimes on a cylindrical vessel phantom, yielding a parameter mean estimation error of 25%.

Transfer entropy reconstruction and labeling of neuronal connections from simulated calcium imaging

Neuronal dynamics are fundamentally constrained by the underlying structural network architecture, yet much of the details of this synaptic connectivity are still unknown even in neuronal cultures in vitro. Here we extend a previous approach based on information theory, the Generalized Transfer Entropy, to the reconstruction of connectivity of simulated neuronal networks of both excitatory and inhibitory neurons. We show that, due to the model-free nature of the developed measure, both kinds of connections can be reliably inferred if the average firing rate between synchronous burst events exceeds a small minimum frequency. Furthermore, we suggest, based on systematic simulations, that even lower spontaneous inter-burst rates could be raised to meet the requirements of our reconstruction algorithm by applying a weak spatially homogeneous stimulation to the entire network. By combining multiple recordings of the same in silico network before and after pharmacologically blocking inhibitory synaptic transmission, we show then how it becomes possible to infer with high confidence the excitatory or inhibitory nature of each individual neuron.

Competence Development and Capacity Building of Sawmill Enterprises in Kenya – A Human Resources Development Approach

The Kenyan forestry and sawmilling industry have been subject to a changing environment since 1999 when the industrial forest plantations were closed down. This has lowered raw material supply and it has affected and reduced the sawmill operations and the viability of the sawmill enterprises. The capacity of the 276 registered sawmills is not sufficient to fulfill sawn timber demand in Kenya. This is because of the technological degradation and lack of a qualified labor force, which were caused because of non-existent sawmilling education and further training in Kenya. Lack of competent sawmill workers has led to low raw material recovery, under utilization of resources and loss of employment. The objective of the work was to suggest models, methods and approaches for the competence and capacity development of the Kenyan sawmilling industry, sawmills and their workers. A nationwide field survey, interviews, questionnaire and literature review was used for data collection to find out the sawmills’ competence development areas and to suggest models and methods for their capacity building. The sampling frame included 22 sawmills that represented 72,5% of all the registered sawmills in Kenya. The results confirmed that the sawmills’ technological level was backwards, productivity low, raw material recovery unacceptable and workers’ professional education low. The future challenges will be how to establish the sawmills’ capacity building and workers’ competence development. Sawmilling industry development requires various actions through new development models and approaches. Activities should be started for technological development and workers’ competence development. This requires re-starting of vocational training in sawmilling and the establishment of more effective co-operation between the sawmills and their stakeholder groups. In competence development the Enterprise Competence Management Model of Nurminen (2007) can be used, whereas the best training model and approach would be a practically oriented learning at work model in which the short courses, technical assistance and extension services would be the key functions.