Reliability measures for local nodes assessment in classification trees

Most of the modem developments with classification trees are aimed at improving their predictive capacity. This article considers a curiously neglected aspect of classification trees, namely the reliability of predictions that come from a given classification tree. In the sense that a node of a tree represents a point in the predictor space in the limit, the aim of this article is the development of localized assessment of the reliability of prediction rules. A classification tree may be used either to provide a probability forecast, where for each node the membership probabilities for each class constitutes the prediction, or a true classification where each new observation is predictively assigned to a unique class. Correspondingly, two types of reliability measure will be derived-namely, prediction reliability and classification reliability. We use bootstrapping methods as the main tool to construct these measures. We also provide a suite of graphical displays by which they may be easily appreciated. In addition to providing some estimate of the reliability of specific forecasts of each type, these measures can also be used to guide future data collection to improve the effectiveness of the tree model. The motivating example we give has a binary response, namely the presence or absence of a species of Eucalypt, Eucalyptus cloeziana, at a given sampling location in response to a suite of environmental covariates, (although the methods are not restricted to binary response data).

Refined method of potential enhancement in the equilibria characterization of activated carbon. Comparison with GCMC and DFT

In this paper, we present a technique for equilibria characterization of activated carbon having slit-shaped pores. This method was first developed by Do (Do, D. D. A new method for the characterisation of micro-mesoporous materials. Presented at the International Symposium on New Trends in Colloid and Interface Science, September 24-26, 1998 Chiba, Japan) and applied by his group and other groups for characterization of pore size distribution (PSD) as well as adsorption equilibria determination of a wide range of hydrocarbons. It is refined in this paper and compared with the grand canonical Monte Carlo (GCMG) simulation and density functional theory (DFT). The refined theory results in a good agreement between the pore filling pressure versus pore width and those obtained by GCMG and DFT. Furthermore, our local isotherms are qualitatively in good agreement with those obtained by the GCMC simulations. The main advantage of this method is that it is about 4 orders of magnitude faster than the GCMC simulations, making it suitable for optimization studies and design purposes. Finally, we apply our method and the GCMG in the derivation of the PSD of a commercial activated carbon. It was found that the PSD derived from our method is comparable to that derived from the GCMG simulations.

A proposed new classification system for whiplash associated disorders - implications for assessment and management

The development of chronic symptoms following whiplash injury is common and contributes substantially to costs associated with this condition. The currently used Quebec Task Force classification system of whiplash associated disorders is primarily based on the severity of signs and symptoms following injury and its usefulness has been questioned. Recent evidence is emerging that demonstrates differences in physical and psychological impairments between individuals who recover from the injury and those who develop persistent pain and disability. Motor dysfunction, local cervical mechanical hyperalgesia and psychological distress are present soon after injury in all whiplash injured persons irrespective of recovery. In contrast those individuals who develop persistent moderate/severe pain and disability show a more complex picture, characterized by additional impairments of widespread sensory hypersensitivity indicative of underlying disturbances in central pain processing as well as acute posttraumatic stress reaction, with these changes present from soon after injury. Based on this heterogeneity a new classification system is proposed that takes into account measurable disturbances in motor, sensory and psychological dysfunction. The implications for the management of this condition are discussed. (C) 2004 Elsevier Ltd. All rights reserved.

The mental health country profile: Background, design and use of a systematic method of appraisal

This article describes the construction and use of a systematic structured method of mental health country situation appraisal, in order to help meet the need for conceptual tools to assist planners and policy makers develop and audit policy and implementation strategies. The tool encompasses the key domains of context, needs, resources, provisions and outcomes, and provides a framework for synthesizing key qualitative and quantitative information, flagging up gaps in knowledge, and for reviewing existing policies. It serves as an enabling tool to alert and inform policy makers, professionals and other key stakeholders about important issues which need to be considered in mental health policy development. It provides detailed country specific information in a systematic format, to facilitate global sharing of experiences of mental health reform and strategies between policy makers and other stakeholders. Lastly, it is designed to be a capacity building tool for local stakeholders to enhance situation appraisal, and multisectorial policy development and implementation.

Distortional buckling of I-beams by finite element method

Distortional buckling, unlike the usual lateral-torsional buckling in which the cross-section remains rigid in its own plane, involves distortion of web in the cross-section. This type of buckling typically occurs in beams with slender web and stocky flanges. Most of the published studies assume the web to deform with a cubic shape function. As this assumption may limit the accuracy of the results, a fifth order polynomial is chosen here for the web displacements. The general line-type finite element model used here has two nodes and a maximum of twelve degrees of freedom per node. The model not only can predict the correct coupled mode but also is capable of handling the local buckling of the web.

Local liquid holdups and hysteresis in a 2-D packed bed using X-ray radiography

An X-ray visualization technique has been used for the quantitative determination of local liquid holdups distribution and liquid holdup hysteresis in a nonwetting two-dimensional (2-D) packed bed. A medical diagnostic X-ray unit has been used to image the local holdups in a 2-D cold model having a random packing of expanded polystyrene beads. An aqueous barium chloride solution was used as a fluid to achieve good contrast on X-ray images. To quantify the local liquid holdup, a simple calibration technique has been developed that can be used for most of the radiological methods such as gamma ray and neutron radiography. The global value of total liquid holdup, obtained by X-ray method, has been compared with two conventional methods: drainage and tracer response. The X-ray technique, after validation, has been used to visualize and quantify, the liquid hysteresis phenomena in a packed bed. The liquid flows in preferred paths or channels that carry droplets/rivulets of increasing size and number as the liquid flow rate is increased. When the flow is reduced, these paths are retained and the higher liquid holdup that persists in these regions leads to the holdup hysteresis effect. Holdup in some regions of the packed bed may be an order of magnitude higher than average at a particular flow rate. (c) 2005 American Institute of Chemical Engineers

Better prediction of protein contact number using a support vector regression analysis of amino acid sequence

Background: Protein tertiary structure can be partly characterized via each amino acid's contact number measuring how residues are spatially arranged. The contact number of a residue in a folded protein is a measure of its exposure to the local environment, and is defined as the number of C-beta atoms in other residues within a sphere around the C-beta atom of the residue of interest. Contact number is partly conserved between protein folds and thus is useful for protein fold and structure prediction. In turn, each residue's contact number can be partially predicted from primary amino acid sequence, assisting tertiary fold analysis from sequence data. In this study, we provide a more accurate contact number prediction method from protein primary sequence. Results: We predict contact number from protein sequence using a novel support vector regression algorithm. Using protein local sequences with multiple sequence alignments (PSI-BLAST profiles), we demonstrate a correlation coefficient between predicted and observed contact numbers of 0.70, which outperforms previously achieved accuracies. Including additional information about sequence weight and amino acid composition further improves prediction accuracies significantly with the correlation coefficient reaching 0.73. If residues are classified as being either contacted or non-contacted, the prediction accuracies are all greater than 77%, regardless of the choice of classification thresholds. Conclusion: The successful application of support vector regression to the prediction of protein contact number reported here, together with previous applications of this approach to the prediction of protein accessible surface area and B-factor profile, suggests that a support vector regression approach may be very useful for determining the structure-function relation between primary sequence and higher order consecutive protein structural and functional properties.

GCMC-surface area of carbonaceous materials with N-2 and Ar adsorption as an alternative to the classical BET method

In this paper we apply a new method for the determination of surface area of carbonaceous materials, using the local surface excess isotherms obtained from the Grand Canonical Monte Carlo simulation and a concept of area distribution in terms of energy well-depth of solid–fluid interaction. The range of this well-depth considered in our GCMC simulation is from 10 to 100 K, which is wide enough to cover all carbon surfaces that we dealt with (for comparison, the well-depth for perfect graphite surface is about 58 K). Having the set of local surface excess isotherms and the differential area distribution, the overall adsorption isotherm can be obtained in an integral form. Thus, given the experimental data of nitrogen or argon adsorption on a carbon material, the differential area distribution can be obtained from the inversion process, using the regularization method. The total surface area is then obtained as the area of this distribution. We test this approach with a number of data in the literature, and compare our GCMC-surface area with that obtained from the classical BET method. In general, we find that the difference between these two surface areas is about 10%, indicating the need to reliably determine the surface area with a very consistent method. We, therefore, suggest the approach of this paper as an alternative to the BET method because of the long-recognized unrealistic assumptions used in the BET theory. Beside the surface area obtained by this method, it also provides information about the differential area distribution versus the well-depth. This information could be used as a microscopic finger-print of the carbon surface. It is expected that samples prepared from different precursors and different activation conditions will have distinct finger-prints. We illustrate this with Cabot BP120, 280 and 460 samples, and the differential area distributions obtained from the adsorption of argon at 77 K and nitrogen also at 77 K have exactly the same patterns, suggesting the characteristics of this carbon.

Beyond the sphere of the English facial approximation literature: Ramifications of German papers on western method concepts

In the English literature, facial approximation methods have been commonly classified into three types: Russian, American, or Combination. These categorizations are based on the protocols used, for example, whether methods use average soft-tissue depths (American methods) or require face muscle construction (Russian methods). However, literature searches outside the usual realm of English publications reveal key papers that demonstrate that the Russian category above has been founded on distorted views. In reality, Russian methods are based on limited face muscle construction, with heavy reliance on modified average soft-tissue depths. A closer inspection of the American method also reveals inconsistencies with the recognized classification scheme. This investigation thus demonstrates that all major methods of facial approximation depend on both face anatomy and average soft-tissue depths, rendering common method classification schemes redundant. The best way forward appears to be for practitioners to describe the methods they use (including the weight each one gives to average soft-tissue depths and deep face tissue construction) without placing them in any categorical classificatory group or giving them an ambiguous name. The state of this situation may need to be reviewed in the future in light of new research results and paradigms.

Efficient accommodation of local minima in watershed model calibration

The Gauss-Marquardt-Levenberg (GML) method of computer-based parameter estimation, in common with other gradient-based approaches, suffers from the drawback that it may become trapped in local objective function minima, and thus report optimized parameter values that are not, in fact, optimized at all. This can seriously degrade its utility in the calibration of watershed models where local optima abound. Nevertheless, the method also has advantages, chief among these being its model-run efficiency, and its ability to report useful information on parameter sensitivities and covariances as a by-product of its use. It is also easily adapted to maintain this efficiency in the face of potential numerical problems (that adversely affect all parameter estimation methodologies) caused by parameter insensitivity and/or parameter correlation. The present paper presents two algorithmic enhancements to the GML method that retain its strengths, but which overcome its weaknesses in the face of local optima. Using the first of these methods an intelligent search for better parameter sets is conducted in parameter subspaces of decreasing dimensionality when progress of the parameter estimation process is slowed either by numerical instability incurred through problem ill-posedness, or when a local objective function minimum is encountered. The second methodology minimizes the chance of successive GML parameter estimation runs finding the same objective function minimum by starting successive runs at points that are maximally removed from previous parameter trajectories. As well as enhancing the ability of a GML-based method to find the global objective function minimum, the latter technique can also be used to find the locations of many non-global optima (should they exist) in parameter space. This can provide a useful means of inquiring into the well-posedness of a parameter estimation problem, and for detecting the presence of bimodal parameter and predictive probability distributions. The new methodologies are demonstrated by calibrating a Hydrological Simulation Program-FORTRAN (HSPF) model against a time series of daily flows. Comparison with the SCE-UA method in this calibration context demonstrates a high level of comparative model run efficiency for the new method. (c) 2006 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.

Ecoregion classification using a bayesian approach and centre-focused clusters

Ecological regions are increasingly used as a spatial unit for planning and environmental management. It is important to define these regions in a scientifically defensible way to justify any decisions made on the basis that they are representative of broad environmental assets. The paper describes a methodology and tool to identify cohesive bioregions. The methodology applies an elicitation process to obtain geographical descriptions for bioregions, each of these is transformed into a Normal density estimate on environmental variables within that region. This prior information is balanced with data classification of environmental datasets using a Bayesian statistical modelling approach to objectively map ecological regions. The method is called model-based clustering as it fits a Normal mixture model to the clusters associated with regions, and it addresses issues of uncertainty in environmental datasets due to overlapping clusters.

Evaluation of a method for fusing LIDAR data and multispectral images for building detection

In this paper, we describe the evaluation of a method for building detection by the Dempster-Shafer fusion of LIDAR data and multispectral images. For that purpose, ground truth was digitised for two test sites with quite different characteristics. Using these data sets, the heuristic model for the probability mass assignments of the method is validated, and rules for the tuning of the parameters of this model are discussed. Further we evaluate the contributions of the individual cues used in the classification process to the quality of the classification results. Our results show the degree to which the overall correctness of the results can be improved by fusing LIDAR data with multispectral images.

An empirical study of Hoelfding Racing for model selction in K-nearest neighbor classification

Racing algorithms have recently been proposed as a general-purpose method for performing model selection in machine teaming algorithms. In this paper, we present an empirical study of the Hoeffding racing algorithm for selecting the k parameter in a simple k-nearest neighbor classifier. Fifteen widely-used classification datasets from UCI are used and experiments conducted across different confidence levels for racing. The results reveal a significant amount of sensitivity of the k-nn classifier to its model parameter value. The Hoeffding racing algorithm also varies widely in its performance, in terms of the computational savings gained over an exhaustive evaluation. While in some cases the savings gained are quite small, the racing algorithm proved to be highly robust to the possibility of erroneously eliminating the optimal models. All results were strongly dependent on the datasets used.