Stochastic search for semiparametric linear regression models

This paper introduces and analyzes a stochastic search method for parameter estimation in linear regression models in the spirit of Beran and Millar [Ann. Statist. 15(3) (1987) 1131–1154]. The idea is to generate a random finite subset of a parameter space which will automatically contain points which are very close to an unknown true parameter. The motivation for this procedure comes from recent work of Dümbgen et al. [Ann. Statist. 39(2) (2011) 702–730] on regression models with log-concave error distributions.

Combinations of dexmedetomidine and alfaxalone with butorphanol in cats: application of an innovative stepwise optimisation method to identify optimal clinical doses for intramuscular anaesthesia

OBJECTIVES The aim of this study was to optimise dexmedetomidine and alfaxalone dosing, for intramuscular administration with butorphanol, to perform minor surgeries in cats. METHODS Initially, cats were assigned to one of five groups, each composed of six animals and receiving, in addition to 0.3 mg/kg butorphanol intramuscularly, one of the following: (A) 0.005 mg/kg dexmedetomidine, 2 mg/kg alfaxalone; (B) 0.008 mg/kg dexmedetomidine, 1.5 mg/kg alfaxalone; (C) 0.012 mg/kg dexmedetomidine, 1 mg/kg alfaxalone; (D) 0.005 mg/kg dexmedetomidine, 1 mg/kg alfaxalone; and (E) 0.012 mg/kg dexmedetomidine, 2 mg/kg alfaxalone. Thereafter, a modified 'direct search' method, conducted in a stepwise manner, was used to optimise drug dosing. The quality of anaesthesia was evaluated on the basis of composite scores (one for anaesthesia and one for recovery), visual analogue scales and the propofol requirement to suppress spontaneous movements. The medians or means of these variables were used to rank the treatments; 'unsatisfactory' and 'promising' combinations were identified to calculate, through the equation first described by Berenbaum in 1990, new dexmedetomidine and alfaxalone doses to be tested in the next step. At each step, five combinations (one new plus the best previous four) were tested. RESULTS None of the tested combinations resulted in adverse effects. Four steps and 120 animals were necessary to identify the optimal drug combination (0.014 mg/kg dexmedetomidine, 2.5 mg/kg alfaxalone and 0.3 mg/kg butorphanol). CONCLUSIONS AND RELEVANCE The investigated drug mixture, at the doses found with the optimisation method, is suitable for cats undergoing minor clinical procedures.

SOP: Parallel surrogate global optimization with Pareto center selection for computationally expensive single objective problems

This paper presents a parallel surrogate-based global optimization method for computationally expensive objective functions that is more effective for larger numbers of processors. To reach this goal, we integrated concepts from multi-objective optimization and tabu search into, single objective, surrogate optimization. Our proposed derivative-free algorithm, called SOP, uses non-dominated sorting of points for which the expensive function has been previously evaluated. The two objectives are the expensive function value of the point and the minimum distance of the point to previously evaluated points. Based on the results of non-dominated sorting, P points from the sorted fronts are selected as centers from which many candidate points are generated by random perturbations. Based on surrogate approximation, the best candidate point is subsequently selected for expensive evaluation for each of the P centers, with simultaneous computation on P processors. Centers that previously did not generate good solutions are tabu with a given tenure. We show almost sure convergence of this algorithm under some conditions. The performance of SOP is compared with two RBF based methods. The test results show that SOP is an efficient method that can reduce time required to find a good near optimal solution. In a number of cases the efficiency of SOP is so good that SOP with 8 processors found an accurate answer in less wall-clock time than the other algorithms did with 32 processors.

Towards Faster Method Search Through Static Ecosystem Analysis

Software developers are often unsure of the exact name of the method they need to use to invoke the desired behavior in a given context. This results in a process of searching for the correct method name in documentation, which can be lengthy and distracting to the developer. We can decrease the method search time by enhancing the documentation of a class with the most frequently used methods. Usage frequency data for methods is gathered by analyzing other projects from the same ecosystem - written in the same language and sharing dependencies. We implemented a proof of concept of the approach for Pharo Smalltalk and Java. In Pharo Smalltalk, methods are commonly searched for using a code browser tool called "Nautilus", and in Java using a web browser displaying HTML based documentation - Javadoc. We developed plugins for both browsers and gathered method usage data from open source projects, in order to increase developer productivity by reducing method search time. A small initial evaluation has been conducted showing promising results in improving developer productivity.

Immediate Search in the IDE as an Example of Socio-Technical Congruence in Search-Driven Development

Search-driven development is mainly concerned with code reuse but also with code navigation and debugging. In this essay we look at search-driven navigation in the IDE. We consider Smalltalk-80 as an example of a programming system with search-driven navigation capabilities and explore its human factors. We present how immediate search results lead to a user experience of code browsing rather than one of waiting for and clicking through search results. We explore the socio-technical congruence of immediate search, ie unification of tasks and breakpoints with method calls, which leads to simpler and more extensible development tools. Eventually we conclude with remarks on the socio-technical congruence of search-driven development.

Addendum: search for ν μ → ν e oscillations with the OPERA experiment in the CNGS beam

A first result of the search for ν ( )μ( ) → ν ( )e( ) oscillations in the OPERA experiment, located at the Gran Sasso Underground Laboratory, is presented. The experiment looked for the appearance of ν ( )e( ) in the CNGS neutrino beam using the data collected in 2008 and 2009. Data are compatible with the non-oscillation hypothesis in the three-flavour mixing model. A further analysis of the same data constrains the non-standard oscillation parameters θ (new) and suggested by the LSND and MiniBooNE experiments. For large values (>0.1 eV(2)), the OPERA 90% C.L. upper limit on sin(2)(2θ (new)) based on a Bayesian statistical method reaches the value 7.2 × 10(−3).

Scheduling the production of rolling ingots: Industrial context, model, and solution method

We study a real-world scheduling problem arising in the context of a rolling ingots production. First we review the production process and discuss peculiarities that have to be observed when scheduling a given set of production orders on the production facilities. We then show how to model this scheduling problem using prescribed time lags between operations, different kinds of resources, and sequence-dependent changeovers. A branch-and-bound solution procedure is presented in the second part. The basic principle is to relax the resource constraints by assuming infinite resource availability. Resulting resource conflicts are then stepwise resolved by introducing precedence relationships among operations competing for the same resources. The algorithm has been implemented as a beam search heuristic enumerating alternative sets of precedence relationships.

Search for charged Higgs bosons through the violation of lepton universality in t art events using collision data at sqrts=7 TeV with the AT experiment

In several extensions of the Standard Model, the top quark can decay into a bottom quark and a light charged Higgs boson H+, t -> bH(+), in addition to the Standard Model decay t -> bW. Since W bosons decay to the three lepton generations equally, while H+ may predominantly decay into tau nu, charged Higgs bosons can be searched for using the violation of lepton universality in top quark decays. The analysis in this paper is based on 4.6 fb(-1) of proton-proton collision data at root s = 7 TeV collected by the ATLAS experiment at the Large Hadron Collider. Signatures containing leptons (e or mu) and/or a hadronically decaying tau (tau(had)) are used. Event yield ratios between e+ tau(had) and e + mu, as well as between mu + tau(had) and mu + e, final states are measured in the data and compared to predictions from simulations. This ratio-based method reduces the impact of systematic uncertainties in the analysis. No significant deviation from the Standard Model predictions is observed. With the assumption that the branching fraction B(H+ -> tau nu) is 100%, upper limits in the range 3.2%-4.4% can be placed on the branching fraction B(t -> bH(+)) for charged Higgs boson masses m(H+) in the range 90-140GeV. After combination with results from a search for charged Higgs bosons in t (t) over bar decays using the tau(had) + jets final state, upper limits on B(t -> bH(+)) can be set in the range 0.8%-3.4%, for m(H+) in the range 90-160GeV.

Search for νμ→νe oscillations with the OPERA experiment in the CNGS beam

A first result of the search for nu(mu)->nu(e) oscillations in the OPERA experiment, located at the Gran Sasso Underground Laboratory, is presented. The experiment looked for the appearance of nu(e) in the CNGS neutrino beam using the data collected in 2008 and 2009. Data are compatible with the non-oscillation hypothesis in the three-flavour mixing model. A further analysis of the same data constrains the non-standard oscillation parameters theta(new) and Delta m(new)(2) suggested by the LSND and MiniBooNE experiments. For large Delta m(new)(2) values (>0.1 eV(2)), the OPERA 90% C.L. upper limit on sin(2)(2 theta(new)) based on a Bayesian statistical method reaches the value 7.2 x 10(-3).

Detecting outlying studies in meta-regression models using a forward search algorithm.

When considering data from many trials, it is likely that some of them present a markedly different intervention effect or exert an undue influence on the summary results. We develop a forward search algorithm for identifying outlying and influential studies in meta-analysis models. The forward search algorithm starts by fitting the hypothesized model to a small subset of likely outlier-free studies and proceeds by adding studies into the set one-by-one that are determined to be closest to the fitted model of the existing set. As each study is added to the set, plots of estimated parameters and measures of fit are monitored to identify outliers by sharp changes in the forward plots. We apply the proposed outlier detection method to two real data sets; a meta-analysis of 26 studies that examines the effect of writing-to-learn interventions on academic achievement adjusting for three possible effect modifiers, and a meta-analysis of 70 studies that compares a fluoride toothpaste treatment to placebo for preventing dental caries in children. A simple simulated example is used to illustrate the steps of the proposed methodology, and a small-scale simulation study is conducted to evaluate the performance of the proposed method. Copyright © 2016 John Wiley & Sons, Ltd.

MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images

This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. For this purpose, we propose a Multi-Atlas Segmentation Constrained Graph (MASCG) method. The MASCG method uses multi-atlas based mesh fusion results to initialize a bone sheetness based multi-label graph cut for an accurate hip CT segmentation which has the inherent advantage of automatic separation of the pelvic region from the bilateral proximal femoral regions. We then introduce a graph cut constrained graph search algorithm to further improve the segmentation accuracy around the bilateral hip joint regions. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 15-fold cross validation. When the present approach was compared to manual segmentation, an average surface distance error of 0.30 mm, 0.29 mm, and 0.30 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. A further look at the bilateral hip joint regions demonstrated an average surface distance error of 0.16 mm, 0.21 mm and 0.20 mm for the acetabulum, the left femoral head, and the right femoral head, respectively.

Exploring Multi-Component Superconducting Compounds by a High-Pressure Method and Ceramic Combinatorial Chemistry

In this short review, we provide some new insights into the material synthesis and characterization of modern multi-component superconducting oxides. Two different approaches such as the high-pressure, high-temperature method and ceramic combinatorial chemistry will be reported with application to several typical examples. First, we highlight the key role of the extreme conditions in the growth of Fe-based superconductors, where a careful control of the composition-structure relation is vital for understanding the microscopic physics. The availability of high-quality LnFeAsO (Ln = lanthanide) single crystals with substitution of O by F, Sm by Th, Fe by Co, and As by P allowed us to measure intrinsic and anisotropic superconducting properties such as Hc2, Jc. Furthermore, we demonstrate that combinatorial ceramic chemistry is an efficient way to search for new superconducting compounds. A single-sample synthesis concept based on multi-element ceramic mixtures can produce a variety of local products. Such a system needs local probe analyses and separation techniques to identify compounds of interest. We present the results obtained from random mixtures of Ca, Sr, Ba, La, Zr, Pb, Tl, Y, Bi, and Cu oxides reacted at different conditions. By adding Zr but removing Tl, Y, and Bi, the bulk state superconductivity got enhanced up to about 122 K.