Active learning for spectroscopic data regression

In this work, we introduce an active learning approach for the estimation of chemical concentrations from spectroscopic data. Its main objective is to opportunely collect training samples in such a way as to minimize the error of the regression process while minimizing the number of training samples used, and thus to reduce the costs related to training sample collection. In particular, we propose two different active learning strategies developed for regression approaches based on partial least squares regression, ridge regression, kernel ridge regression, and support vector regression. The first strategy uses a pool of regressors in order to select the samples with the greatest disagreements among the different regressors of the pool, while the second one is based on adding samples that are distant from the current training samples in the feature space. For support vector regression, a specific strategy based on the selection of the samples distant from the support vectors is proposed. Experimental results on three different real data sets are reported and discussed. Copyright © 2012 John Wiley & Sons, Ltd.     

New N-acylamino acids and derivatives from renewable fatty acids: gelation of hydrocarbons and thermal properties

This work reports the synthesis of new fatty N-acylamino acids and N-acylamino esters from the C16:0, C18:0, C18:1, and C18:1(OH) fatty acid families and demonstrates the activity of these compounds as organogel agents. Compounds were heated and dissolved in various solvents (n-hexane, toluene, and gasoline). Only saturated C16:0 and C18:0 derived from alanine were able to form gels in toluene, and saturated C16:0 derived from phenylalanine showed gelation in n-hexane. This is the first evidence that fatty N-acylamino esters and N-acylamino acid derivatives of l-serine and fatty acids C16:0, C18:0, and C18:1 are able to form gels with hexane. This observation confirms the importance of the hydroxyl group in the segment derivative of l-serine in forming good gels.     

Parallel protocol for the selective methylation and alkylation of primary amines

One of the still unresolved problems in parallel synthesis is the availability of a general and rapid method for the transformation of a primary amine into the corresponding secondary amine without the issue of polyalkylation. Following the Fukuyama method, which is based on the alkylation of o-nitrobenzenesulfonamides, followed by removal of the sulfonyl group, we have developed a simple protocol which can be easily applied to parallel synthesis making use of supported reagents and scavengers. To verify the robustness of the method, a small representative array of secondary amines have been prepared. Moreover, taking advantage of the possibility to use different supported reagents in the same pot, we also prepared, starting from primary amines, a series of differently substituted tertiary amines.     

FirmNet: the scope of firms and the allocation of task in a knowledge-based economy

The increasing knowledge intensity of jobs, typical of a knowledge economy, highlights the role of firms as integrators of know how and skills. As economic activity becomes mainly intellectual and requires the integration of specific and idiosyncratic skills, firms need to allocate skills to tasks and traditional hierarchical control may result increasingly ineffective. In this work, we explore under what circumstances networks of agents, which bear specific skills, may self-organize in order to complete tasks. We use a computer simulation approach and investigate how local interaction of agents, endowed with skills and individual decision-making rules, may produce aggregate network structure able to perform tasks. To design algorithms that mimic individual decision-making, we borrow from computer science literature and, in particular, from studies addressing protocols that produce cooperation in P2P networks. We found that self-organization depends on imitation of successful peers, competition among agents holding specific skills, and the structural features of, formal or informal, organizational networks embedding both professionals, holding skills, and project managers, holding access to jobs.

Well-posedness for a mean field model of Ginzburg–Landau vortices with opposite degrees

In this paper we analyze the hydrodynamic equations for Ginzburg–Landau vortices as derived by E (Phys. Rev. B. 50(3):1126–1135, 1994). In particular, we are interested in the mean field model describing the evolution of two patches of vortices with equal and opposite degrees. Many results are already available for the case of a single density of vortices with uniform degree. This model does not take into account the vortex annihilation, hence it can also be seen as a particular instance of the signed measures system obtained in Ambrosio et al. (Ann. Inst. H. Poincaré Anal. Non Linéaire 28(2):217–246, 2011) and related to the Chapman et al. (Eur. J. Appl. Math. 7(2):97–111, 1996) formulation. We establish global existence of L ^p solutions, exploiting some optimal transport techniques introduced in this context in Ambrosio and Serfaty (Commun. Pure Appl. Math. LXI(11):1495–1539, 2008). We prove uniqueness for L ^∞ solutions, as expected by analogy with the incompressible Euler equations in fluidodynamics. We also consider the corresponding Dirichlet problem in a bounded domain. Moreover, we show some simple examples of 1-dimensional dynamic.     

Tracy–Widom statistic for the largest eigenvalue of autoscaled real matrices

Eigenanalysis is common practice in biostatistics, and the largest eigenvalue of a data set contains valuable information about the data. However, to make inferences about the size of the largest eigenvalue, its distribution must be known. Johnstone's theorem states that the largest eigenvalues l₁ of real random covariance matrices are distributed according to the Tracy–Widom distribution of order 1 when properly normalized to , where η_np and ξ_np are functions of the data matrix dimensions n and p. Very often, data are expressed in terms of correlations (autoscaling) for which case Johnstone's theorem does not work because the normalizing parameters η_np and ξ_np are not theoretically known. In this paper we propose a semi‐empirical method based on test‐equating theory to numerically approximate the normalization parameters in the case of autoscaled matrices. This opens the way of making inferences regarding the largest eigenvalue of an autoscaled data set. The method is illustrated by means of application to two real‐life data sets. Copyright © 2011 John Wiley & Sons, Ltd.