Improve Model Quality Research Articles

GA-BASED TIME SERIES MODELS WITH THRESHOLD IN TWO DOMAINS

A new threshold time series model is proposed whose submodels are extended from AR to SARIMA and whose domains having thresholds are extended to two. By these two extensions, the newly proposed models offer more flexibility to piecewisely approximate nonstationary time series by a finite number of local stationary models. A genetic algorithm is applied to simultaneously search for appropriate model structures, estimate the optimal model coefficients, as well as partition space by finding appropriate thresholds. The resulting model is applied to a synthetic multi-frequency sine wave and two financial time series with improved modeling quality. The proposed model is also applied to seismogram analysis in order to recognize earthquake wave pattern related to locate arrival time of different waves.

Subspace like identification incorporating prior information

The subspace identification methods have proved to be a powerful tool, which can further benefit from the prior information incorporation algorithm proposed in this note. In the industrial environment, there is often some knowledge about the identified system (known static gains, dominant time constants, low frequency character, etc.), which can be used to improve model quality and its compliance with first principles. The proposed algorithm has two stages. The first one is similar to the subspace methods as it uses their interpretation as an optimization problem of finding parameters of an optimal multi-step linear predictor for the experimental data. This problem is reformulated in the Bayesian framework allowing prior information incorporation in the form of the mean value and the covariance of the impulse response, which is shown to be useful for the incorporation of several prior information types. The second stage with state space model realization from the posterior impulse response estimate is different from the standard subspace methods as it is based on the structured weighted lower rank approximation, which is necessary to preserve the prior information incorporated in the first stage.

UML behavioral consistency checking using instantiable Petri nets

Model-driven engineering (MDE) development methods are gaining increasing attention from industry. In MDE, the model is the primary artifact and serves several goals, including code generation, requirements traceability, and model-based testing. MDE thus enables cost-effective building of models versus direct coding of an application. Thus model-based formal verification of behavioral consistency is desirable as it helps improve model quality. Our approach is based on translation of a UML model to instantiable Petri nets (IPN). This formalism is based on the semantics of Petri nets, but introduces the concepts of type and instance. This allows one to accurately capture these concepts in UML models. IPN support hierarchical descriptions natively, and use the notion of transition synchronization for composition of behaviors. This is a general and powerful mechanism borrowed from process algebra. We show that IPN allow one to adequately address the challenges of translation from UML for analysis purposes. The approach has been implemented and experimental results are presented.

Systematic analysis of the effect of multiple templates on the accuracy of comparative models of protein structure

BackgroundAlthough multiple templates are frequently used in comparative modeling, the effect of inclusion of additional template(s) on model accuracy (when compared to that of corresponding single-template based models) is not clear. To address this, we systematically analyze two-template models, the simplest case of multiple-template modeling. For an existing target-template pair (single-template modeling), a two-template based model of the target sequence is constructed by including an additional template without changing the original alignment to measure the effect of the second template on model accuracy.ResultsEven though in a large number of cases a two-template model showed higher accuracy than the corresponding one-template model, over the entire dataset only a marginal improvement was observed on average, as there were many cases where no change or the reverse change was observed. The increase in accuracy due to the structural complementarity of the templates increases at higher alignment accuracies. The combination of templates showing the highest potential for improvement is that where both templates share similar and low (less than 30%) sequence identity with the target, as well as low sequence identity with each other. The structural similarity between the templates also helps in identifying template combinations having a higher chance of resulting in an improved model.ConclusionInclusion of additional template(s) does not necessarily improve model quality, but there are distinct combinations of the two templates, which can be selected a priori, that tend to show improvement in model quality over the single template model. The benefit derived from the structural complementarity is dependent on the accuracy of the modeling alignment. The study helps to explain the observation that a careful selection of templates together with an accurate target:template alignment are necessary to the benefit from using multiple templates in comparative modeling and provides guidelines to maximize the benefit from using multiple templates. This enables formulation of simple template selection rules to rank targets of a protein family in the context of structural genomics.

Using multiple templates to improve quality of homology models in automated homology modeling

When researchers build high-quality models of protein structure from sequence homology, it is today common to use several alternative target-template alignments. Several methods can, at least in theory, utilize information from multiple templates, and many examples of improved model quality have been reported. However, to our knowledge, thus far no study has shown that automatic inclusion of multiple alignments is guaranteed to improve models without artifacts. Here, we have carried out a systematic investigation of the potential of multiple templates to improving homology model quality. We have used test sets consisting of targets from both recent CASP experiments and a larger reference set. In addition to Modeller and Nest, a new method (Pfrag) for multiple template-based modeling is used, based on the segment-matching algorithm from Levitt's SegMod program. Our results show that all programs can produce multi-template models better than any of the single-template models, but a large part of the improvement is simply due to extension of the models. Most of the remaining improved cases were produced by Modeller. The most important factor is the existence of high-quality single-sequence input alignments. Because of the existence of models that are worse than any of the top single-template models, the average model quality does not improve significantly. However, by ranking models with a model quality assessment program such as ProQ, the average quality is improved by approximately 5% in the CASP7 test set.

Exploring the extremes of sequence/structure space with ensemble fold recognition in the program Phyre

Structural and functional annotation of the large and growing database of genomic sequences is a major problem in modern biology. Protein structure prediction by detecting remote homology to known structures is a well-established and successful annotation technique. However, the broad spectrum of evolutionary change that accompanies the divergence of close homologues to become remote homologues cannot easily be captured with a single algorithm. Recent advances to tackle this problem have involved the use of multiple predictive algorithms available on the Internet. Here we demonstrate how such ensembles of predictors can be designed in-house under controlled conditions and permit significant improvements in recognition by using a concept taken from protein loop energetics and applying it to the general problem of 3D clustering. We have developed a stringent test that simulates the situation where a protein sequence of interest is submitted to multiple different algorithms and not one of these algorithms can make a confident (95%) correct assignment. A method of meta-server prediction (Phyre) that exploits the benefits of a controlled environment for the component methods was implemented. At 95% precision or higher, Phyre identified 64.0% of all correct homologous query-template relationships, and 84.0% of the individual test query proteins could be accurately annotated. In comparison to the improvement that the single best fold recognition algorithm (according to training) has over PSI-Blast, this represents a 29.6% increase in the number of correct homologous query-template relationships, and a 46.2% increase in the number of accurately annotated queries. It has been well recognised in fold prediction, other bioinformatics applications, and in many other areas, that ensemble predictions generally are superior in accuracy to any of the component individual methods. However there is a paucity of information as to why the ensemble methods are superior and indeed this has never been systematically addressed in fold recognition. Here we show that the source of ensemble power stems from noise reduction in filtering out false positive matches. The results indicate greater coverage of sequence space and improved model quality, which can consequently lead to a reduction in the experimental workload of structural genomics initiatives.

Implementing Molecular Connectivity Theory, a Basic Tool in Modeling Drugs

The concepts of chain graph, general graph, and complete graph have been used to implement the graph framework of molecular connectivity (MC) theory. Some concepts of this theory have been addressed using “external” theoretical concepts belonging mostly to quantum or structural chemistry, with no direct counterpart in graph theory. Thus, while the concept of chain graph can be used to tackle the cis‐trans isomerism problem, the concept of pseudograph, or general graph can be used to tackle the description of the sigma‐, pi‐, and nonbonding n‐electrons. The concept of complete graph can instead be used to tackle the electron core problem of the atoms of a molecule. Graph concepts can also be used to tackle the problem of the hydrogen contribution in hydrogen depleted graphs, which are encoded by the aid of a perturbation parameter, which differentiates between compounds with similar hydrogen‐suppressed chemical graphs, like the graphs of CH3F and BH2F. These concepts have allowed redesign of a central parameter of MC theory, the valence delta, giving MC indices with improved model quality as exemplified here with different properties for each treated topic. © 2007 Wiley‐Liss, Inc. and the American Pharmacists Association J Pharm Sci 96:1856–1871, 2007

Darwin Calibrator—Improving Project Productivity and Model Quality for Large Water Systems

This article discusses how optimization modeling provides engineers with a flexible and intelligent tool to achieve their water supply goals in the most cost‐effective manner. The article discusses a case study of using Haestad Methods' Darwin optimization technology to calibrate a water distribution model for the city of Guayaquil, Ecuador. The city hired Envirosoft and its local affiliated company Aquatec S.A. to develop an effective action plan for various tasks that included: an expansion program to manage installation of the required water and sewer connections; the design of new water and sewer networks; 30‐year master plans for the water, wastewater, and drainage systems; and, an action plan for the reduction of unaccounted‐for water. Envirosoft adopted WaterGEMS and Darwin software for hydraulic network simulation and optimization modeling. The goal of the project was to build an accurate hydraulic model of the water distribution network.

A methodology for building neural networks models from empirical engineering data

Neural networks (NN) are general tools for modeling functional relationships in engineering. They are used to model the behavior of products and the properties of processes. Nevertheless, their use is often ad hoc. This paper provides a sound basis for using NN as tools for modeling functional relationships implicit in empirical engineering data. First, a clear definition of a modeling task is given, followed by reviewing the theoretical modeling capabilities of NN and NN model estimation. Subsequently, a procedure for using NN in engineering practice is described and illustrated with an example of modeling marine propeller behavior. Particular attention is devoted to better estimation of model quality, insight into the influence of measurement errors on model quality, and the use of advanced methods such as stacked generalization and ensemble modeling to further improve model quality. Using a new method of ensemble of SG( k-NN), one could improve the quality of models even if they are close to being optimal.

Modeling restricted bivariate censored lowflow data

Environmental studies often result in censored data. In this article, the lowflow quantiles Q*7,2 and Q*7,10 below a limit are treated as censored data. These streamflow quantiles are important for water resources planning and management. Our partial all-subsets censored regression procedure identifies a few important explanatory variables, such as drainage area, basin slope, soil-infiltration index, rainfall index, and some combinations of them. The proposed maximum likelihood estimation method incorporates the restriction Q*7,2≥Q*7,10 and the bivariate probability distribution of the quantiles to improve model quality. Analyses of the lowflow quantiles obtained from streams in West-Central Florida show that our procedure is more appropriate than the commonly used univariate main-effects models in predicting quantiles. Copyright © 1999 John Wiley & Sons, Ltd.

A disaggregate Box-Cox Logit mode choice model of intercity passenger travel in Germany and its implications for high-speed rail demand forecasts

We show that enriching logit mode choice model specification by mode attributes, socio economic variables and trip purpose characteristics significantly improves model quality, and that Box-Cox transformations applied to model attributes imply an asymmetry of the reaction curve, as well as more reasonable properties (diminishing marginal values of time savings, elasticities and values of time that differ among the modes) than those of the linear logit model. Moreover, the model yielded very different high speed rail market shares for Germany than results obtained with the usual linear utility functions.