Fast automatic two-stage nonlinear model identification based on the extreme learning machine

It is convenient and effective to solve nonlinear problems with a model that has a linear-in-the-parameters (LITP) structure. However, the nonlinear parameters (e.g. the width of Gaussian function) of each model term needs to be pre-determined either from expert experience or through exhaustive search. An alternative approach is to optimize them by a gradient-based technique (e.g. Newton’s method). Unfortunately, all of these methods still need a lot of computations. Recently, the extreme learning machine (ELM) has shown its advantages in terms of fast learning from data, but the sparsity of the constructed model cannot be guaranteed. This paper proposes a novel algorithm for automatic construction of a nonlinear system model based on the extreme learning machine. This is achieved by effectively integrating the ELM and leave-one-out (LOO) cross validation with our two-stage stepwise construction procedure [1]. The main objective is to improve the compactness and generalization capability of the model constructed by the ELM method. Numerical analysis shows that the proposed algorithm only involves about half of the computation of orthogonal least squares (OLS) based method. Simulation examples are included to confirm the efficacy and superiority of the proposed technique.

Prophylactic ranitidine treatment in critically ill children - a population pharmacokinetic study

Aims: To characterize the population pharmacokinetics of ranitidine in critically ill children and to determine the influence of various clinical and demographic factors on its disposition. Methods: Data were collected prospectively from 78 paediatric patients (n = 248 plasma samples) who received oral or intravenous ranitidine for prophylaxis against stress ulcers, gastrointestinal bleeding or the treatment of gastro-oesophageal reflux. Plasma samples were analysed using high-performance liquid chromatography, and the data were subjected to population pharmacokinetic analysis using nonlinear mixed-effects modelling. Results: A one-compartment model best described the plasma concentration profile, with an exponential structure for interindividual errors and a proportional structure for intra-individual error. After backward stepwise elimination, the final model showed a significant decrease in objective function value (-12.618; P <0.001) compared with the weight-corrected base model. Final parameter estimates for the population were 32.1lh for total clearance and 285l for volume of distribution, both allometrically modelled for a 70kg adult. Final estimates for absorption rate constant and bioavailability were 1.31h and 27.5%, respectively. No significant relationship was found between age and weight-corrected ranitidine pharmacokinetic parameters in the final model, with the covariate for cardiac failure or surgery being shown to reduce clearance significantly by a factor of 0.46. Conclusions: Currently, ranitidine dose recommendations are based on children's weights. However, our findings suggest that a dosing scheme that takes into consideration both weight and cardiac failure/surgery would be more appropriate in order to avoid administration of higher or more frequent doses than necessary.

An Examination of Transformation Techniques to Investigate and Interpret Multivariate Geochemical Data Analysis: Tellus Case Study

This research aims to use the multivariate geochemical dataset, generated by the Tellus project, to investigate the appropriate use of transformation methods to maintain the integrity of geochemical data and inherent constrained behaviour in multivariate relationships. The widely used normal score transform is compared with the use of a stepwise conditional transform technique. The Tellus Project, managed by GSNI and funded by the Department of Enterprise Trade and Development and the EU’s Building Sustainable Prosperity Fund, involves the most comprehensive geological mapping project ever undertaken in Northern Ireland. Previous study has demonstrated spatial variability in the Tellus data but geostatistical analysis and interpretation of the datasets requires use of an appropriate methodology that reproduces the inherently complex multivariate relations. Previous investigation of the Tellus geochemical data has included use of Gaussian-based techniques. However, earth science variables are rarely Gaussian, hence transformation of data is integral to the approach. The multivariate geochemical dataset generated by the Tellus project provides an opportunity to investigate the appropriate use of transformation methods, as required for Gaussian-based geostatistical analysis. In particular, the stepwise conditional transform is investigated and developed for the geochemical datasets obtained as part of the Tellus project. The transform is applied to four variables in a bivariate nested fashion due to the limited availability of data. Simulation of these transformed variables is then carried out, along with a corresponding back transformation to original units. Results show that the stepwise transform is successful in reproducing both univariate statistics and the complex bivariate relations exhibited by the data. Greater fidelity to multivariate relationships will improve uncertainty models, which are required for consequent geological, environmental and economic inferences.

Chemisorption and reactivity of furan on Pd{111}

XPS, HREELS, ARUPS and Delta phi data show that furan chemisorbs non-dissociatively on Pd{111} at 175 K, the molecular plane being significantly tilted with respect to the surface normal. Bonding involves both the oxygen lone pair and significant a interaction with the substrate. The degree of decomposition that accompanies molecular desorption is a strong function of coverage: similar to 40% of the adsorbate desorbs molecularly from the saturated monolayer. Decomposition occurs via decarbonylation to yield COa and H-a followed by desorption rate limited loss of H-2 and CO. It seems probable that an adsorbed C3H3 species formed during this process undergoes subsequent stepwise dehydrogenation ultimately yielding H-2 and C-a.

Predicting Functional Recovery after Acute Ankle Sprain

INTRODUCTION:Ankle sprains are among the most common acute musculoskeletal conditions presenting to primary care. Their clinical course is variable but there are limited recommendations on prognostic factors. Our primary aim was to identify clinical predictors of short and medium term functional recovery after ankle sprain.
METHODS:A secondary analysis of data from adult participants (N = 85) with an acute ankle sprain, enrolled in a randomized controlled trial was undertaken. The predictive value of variables (age, BMI, gender, injury mechanism, previous injury, weight-bearing status, medial joint line pain, pain during weight-bearing dorsiflexion and lateral hop test) recorded at baseline and at 4 weeks post injury were investigated for their prognostic ability. Recovery was determined from measures of subjective ankle function at short (4 weeks) and medium term (4 months) follow ups. Multivariate stepwise linear regression analyses were undertaken to evaluate the association between the aforementioned variables and functional recovery.
RESULTS:Greater age, greater injury grade and weight-bearing status at baseline were associated with lower function at 4 weeks post injury (p<0.01; adjusted R square=0.34). Greater age, weight-bearing status at baseline and non-inversion injury mechanisms were associated with lower function at 4 months (p<0.01; adjusted R square=0.20). Pain on medial palpation and pain on dorsiflexion at 4 weeks were the most valuable prognostic indicators of function at 4 months (p< 0.01; adjusted R square=0.49).
CONCLUSION:The results of the present study provide further evidence that ankle sprains have a variable clinical course. Age, injury grade, mechanism and weight-bearing status at baseline provide some prognostic information for short and medium term recovery. Clinical assessment variables at 4 weeks were the strongest predictors of recovery, explaining 50% of the variance in ankle function at 4 months. Further prospective research is required to highlight the factors that best inform the expected convalescent period, and risk of recurrence.

Haplotypes spanning SPEC2, PDZ-GEF2 and ACSL6 genes are associated with schizophrenia

Chromosome 5q22-33 is a region where studies have repeatedly found evidence for linkage to schizophrenia. In this report, we took a stepwise approach to systematically map this region in the Irish Study of High Density Schizophrenia Families (ISHDSF, 267 families, 1337 subjects) sample. We typed 289 SNPs in the critical interval of 8 million basepairs and found a 758 kb interval coding for the SPEC2/PDZ-GEF2/ACSL6 genes to be associated with the disease. Using sex and genotype-conditioned transmission disequilibrium test analyses, we found that 19 of the 24 typed markers were associated with the disease and the associations were sex-specific. We replicated these findings with an Irish case-control sample (657 cases and 414 controls), an Irish parent-proband trio sample (187 families, 564 subjects), a German nuclear family sample (211 families, 751 subjects) and a Pittsburgh nuclear family sample (247 families, 729 subjects). In all four samples, we replicated the sex-specific associations at the levels of both individual markers and haplotypes using sex- and genotype-conditioned analyses. Three risk haplotypes were identified in the five samples, and each haplotype was found in at least two samples. Consistent with the discovery of multiple estrogen-response elements in this region, our data showed that the impact of these haplotypes on risk for schizophrenia differed in males and females. From these data, we concluded that haplotypes underlying the SPEC2/PDZ-GEF2/ACSL6 region are associated with schizophrenia. However, due to the extended high LD in this region, we were unable to distinguish whether the association signals came from one or more of these genes.

A multi-output two-stage locally regularized model construction method using the extreme learning machine

This paper investigates the construction of linear-in-the-parameters (LITP) models for multi-output regression problems. Most existing stepwise forward algorithms choose the regressor terms one by one, each time maximizing the model error reduction ratio. The drawback is that such procedures cannot guarantee a sparse model, especially under highly noisy learning conditions. The main objective of this paper is to improve the sparsity and generalization capability of a model for multi-output regression problems, while reducing the computational complexity. This is achieved by proposing a novel multi-output two-stage locally regularized model construction (MTLRMC) method using the extreme learning machine (ELM). In this new algorithm, the nonlinear parameters in each term, such as the width of the Gaussian function and the power of a polynomial term, are firstly determined by the ELM. An initial multi-output LITP model is then generated according to the termination criteria in the first stage. The significance of each selected regressor is checked and the insignificant ones are replaced at the second stage. The proposed method can produce an optimized compact model by using the regularized parameters. Further, to reduce the computational complexity, a proper regression context is used to allow fast implementation of the proposed method. Simulation results confirm the effectiveness of the proposed technique. © 2013 Elsevier B.V.

Evaluation of methodologies to determine vegetable oil species present in oil mixtures: Proposition of an approach to meet the EU legislation demands for correct vegetable oils labelling

Refined vegetable oils are widely used in the food industry as ingredients or components in many processed food products in the form of oil blends. To date, the generic term 'vegetable oil' has been used in the labelling of food containing oil blends. With the introduction of new EU Regulation for Food Information (1169/2011) due to take effect in 2014, the oil species used must be clearly identified on the package and there is a need for development of fit for purpose methodology for industry and regulators alike to verify the oil species present in a product. The available methodologies that may be employed to authenticate the botanical origin of a vegetable oil admixture were reviewed and evaluated. The majority of the sources however, described techniques applied to crude vegetable oils such as olive oil due to the lack of refined vegetable oil focused studies. Nevertheless, DNA based typing methods and stable isotopes procedures were found not suitable for this particular purpose due to several issues. Only a small number of specific chromatographic and spectroscopic fingerprinting methods in either targeted or untargeted mode were found to be applicable in potentially providing a solution to this complex authenticity problem. Applied as a single method in isolation, these techniques would be able to give limited information on the oils identity as signals obtained for various oil types may well be overlapping. Therefore, more complex and combined approaches are likely to be needed to identify the oil species present in oil blends employing a stepwise approach in combination with advanced chemometrics. Options to provide such a methodology are outlined in the current study.

An Efficient LS-SVM-Based Method for Fuzzy System Construction

This paper proposes an efficient learning mechanism to build fuzzy rule-based systems through the construction of sparse least-squares support vector machines (LS-SVMs). In addition to the significantly reduced computational complexity in model training, the resultant LS-SVM-based fuzzy system is sparser while offers satisfactory generalization capability over unseen data. It is well known that the LS-SVMs have their computational advantage over conventional SVMs in the model training process; however, the model sparseness is lost, which is the main drawback of LS-SVMs. This is an open problem for the LS-SVMs. To tackle the nonsparseness issue, a new regression alternative to the Lagrangian solution for the LS-SVM is first presented. A novel efficient learning mechanism is then proposed in this paper to extract a sparse set of support vectors for generating fuzzy IF-THEN rules. This novel mechanism works in a stepwise subset selection manner, including a forward expansion phase and a backward exclusion phase in each selection step. The implementation of the algorithm is computationally very efficient due to the introduction of a few key techniques to avoid the matrix inverse operations to accelerate the training process. The computational efficiency is also confirmed by detailed computational complexity analysis. As a result, the proposed approach is not only able to achieve the sparseness of the resultant LS-SVM-based fuzzy systems but significantly reduces the amount of computational effort in model training as well. Three experimental examples are presented to demonstrate the effectiveness and efficiency of the proposed learning mechanism and the sparseness of the obtained LS-SVM-based fuzzy systems, in comparison with other SVM-based learning techniques.

Inappropriate prescribing of combination inhalers in Northern Ireland: retrospective cross-sectional cohort study of prescribing practice in primary care

BACKGROUND: Asthma management guidelines advocate a stepwise approach to asthma therapy, including the addition of a long-acting bronchodilator to inhaled steroid therapy at step 3. This is almost exclusively prescribed as inhaled combination therapy.

AIMS: To examine whether asthma prescribing practice for inhaled combination therapy (inhaled corticosteroid/long-acting β2-agonist (ICS/LABA)) in primary care in Northern Ireland is in line with national asthma management guidelines.

METHODS: Using data from the Northern Ireland Enhanced Prescribing Database, we examined initiation of ICS/LABA in subjects aged 5-35 years in 2010.

RESULTS: A total of 2,640 subjects (67%) had no inhaled corticosteroid monotherapy (ICS) in the study year or six months of the preceding year (lead-in period) and, extending this to a 12-month lead-in period, 52% had no prior ICS. 41% of first prescriptions for ICS/LABA were dispensed in January to March. Prior to ICS/LABA prescription, in the previous six months only 17% had a short-acting β2-agonist (SABA) dispensed, 5% received oral steroids, and 17% received an antibiotic.

CONCLUSIONS: ICS/LABA therapy was initiated in the majority of young subjects with asthma without prior inhaled steroid therapy. Most prescriptions were initiated in the January to March period. However, the prescribing of ICS/LABA did not appear to be driven by asthma symptoms (17% received SABA in the previous 6 months) or severe asthma exacerbation (only 5% received oral steroids). Significant reductions in ICS/LABA, with associated cost savings, would occur if the asthma prescribing guidelines were followed in primary care.

Kernel based approaches to local nonlinear non-parametric variable selection

In this paper, we consider the variable selection problem for a nonlinear non-parametric system. Two approaches are proposed, one top-down approach and one bottom-up approach. The top-down algorithm selects a variable by detecting if the corresponding partial derivative is zero or not at the point of interest. The algorithm is shown to have not only the parameter but also the set convergence. This is critical because the variable selection problem is binary, a variable is either selected or not selected. The bottom-up approach is based on the forward/backward stepwise selection which is designed to work if the data length is limited. Both approaches determine the most important variables locally and allow the unknown non-parametric nonlinear system to have different local dimensions at different points of interest. Further, two potential applications along with numerical simulations are provided to illustrate the usefulness of the proposed algorithms.

Drug therapies in severe asthma - the era of stratified medicine

Difficult-to-treat asthma affects up to 20% of patients with asthma and is associated with significant healthcare cost. It is an umbrella term that defines a heterogeneous clinical problem including incorrect diagnosis, comorbid conditions and treatment non-adherence; when these are effectively addressed, good symptom control is frequently achieved. However, in 3–5% of adults with difficult-to-treat asthma, the problem is severe disease that is unresponsive to currently available treatments. Current treatment guidelines advise the ‘stepwise’ increase of corticosteroids, but it is now recognised that many aspects of asthma are not corticosteroid responsive, and that this ‘one size fits all’ approach does not deliver clinical benefit in many patients and can also lead to side effects. The future of management of severe asthma will involve optimisation with currently available treatments, particularly corticosteroids, including addressing non-adherence and defining an ‘optimised’ corticosteroid dose, allied with the use of ‘add-on’ target-specific novel treatments. This review examines the current status of novel treatments and research efforts to identify novel targets in the era of stratified medicines in severe asthma.

Proprioceptive acuity predicts muscle co-contraction of the tibalis anterior and gastrocnemius medialis in older adults’ dynamic postural control

Older adults use a different muscle strategy to cope with postural instability, in which they ‘co-contract’ the muscles around the ankle joint. It has been suggested that this is a compensatory response to age-related proprioceptive decline however this view has never been assessed directly. The current study investigated the association between proprioceptive acuity and muscle co-contraction in older adults. We compared muscle activity, by recording surface EMG from the bilateral tibalis anterior and gastrocnemius medialis muscles, in young (aged 18-34) and older adults (aged 65-82) during postural assessment on a fixed and sway-referenced surface at age-equivalent levels of sway. We performed correlations between muscle activity and proprioceptive acuity, which was assessed using an active contralateral matching task. Despite successfully inducing similar levels of sway in the two age groups, older adults still showed higher muscle co-contraction. A stepwise regression analysis showed that proprioceptive acuity measured using variable error was the best predictor of muscle co-contraction in older adults. However, despite suggestions from previous research, proprioceptive error and muscle co-contraction were negatively correlated in older adults, suggesting that better proprioceptive acuity predicts more co-contraction. Overall, these results suggest that although muscle co-contraction may be an age-specific strategy used by older adults, it is not to compensate for age-related proprioceptive deficits.

A Molecular Mechanism for Sequential Activation of a G Protein-Coupled Receptor

Ligands targeting G protein-coupled receptors (GPCRs) are currently classified as either orthosteric, allosteric, or dualsteric/bitopic. Here, we introduce a new pharmacological concept for GPCR functional modulation: sequential receptor activation. A hallmark feature of this is a stepwise ligand binding mode with transient activation of a first receptor site followed by sustained activation of a second topographically distinct site. We identify 4-CMTB (2-(4-chlorophenyl)-3-methyl-N-(thiazol-2-yl)butanamide), previously classified as a pure allosteric agonist of the free fatty acid receptor 2, as the first sequential activator and corroborate its two-step activation in living cells by tracking integrated responses with innovative label-free biosensors that visualize multiple signaling inputs in real time. We validate this unique pharmacology with traditional cellular readouts, including mutational and pharmacological perturbations along with computational methods, and propose a kinetic model applicable to the analysis of sequential receptor activation. We envision this form of dynamic agonism as a common principle of nature to spatiotemporally encode cellular information.

Are food-related perceptions associated with meal portion size decisions? A cross-sectional study

The purpose of this study was to test a comprehensive model of meal portion size determinants consisting of sociodemographic, psychological and food-related variables, whilst controlling for hunger and thirst.
Using cross-sectional nationally representative data collected in 2075 participants from the Island of Ireland (IoI) and Denmark (DK), eight separate hierarchical multiple regression analyses were conducted to examine the association between food-related variables and meal portion size (i.e. pizza, vegetable soup, chicken salad and a pork meal) within each country. Stepwise regressions were run with physiological control measures (hunger and thirst) entered in the first step, sociodemographic variables (sex, age, body mass index (BMI)) in the second step; psychological variables (cognitive restraint, uncontrolled eating, emotional eating, general health interest (GHI)) in the third step and food-related variables (expected fillingness, liking, expected healthfulness, food familiarity) in the fourth step.
Sociodemographic variables accounted for 2-19% of the variance in meal portion sizes; psychological variables explained an additional 3-8%; and food-related variables explained an additional 2-12%. When all four variable groups were included in the regression models, liking and sometimes expected healthfulness was positively associated with meal portion size. The strongest association was for liking, which was statistically significant in both countries for all meal types. Whilst expected healthfulness was not associated with pizza portion size in either country, it was positively associated with meals that have a healthier image (vegetable soup; chicken salad and in IoI, the pork meal).
In conclusion, after considering sociodemographic and psychological variables, and the food-related variables of liking and expected healthfulness, there may be little merit in manipulating the satiating power, at least of these type of meals, to maintain or promote weight loss.
Keywords: Meal portion size; psychological variables; expected fillingness; expected healthfulness; food liking; food familiarity.