Improved customer choice predictions using ensemble methods

In this paper various ensemble learning methods from machine learning and statistics are considered and applied to the customer choice modeling problem. The application of ensemble learning usually improves the prediction quality of flexible models like decision trees and thus leads to improved predictions. We give experimental results for two real-life marketing datasets using decision trees, ensemble versions of decision trees and the logistic regression model, which is a standard approach for this problem. The ensemble models are found to improve upon individual decision trees and outperform logistic regression.     

Semihydrogenation of Acetylene on Indium Oxide: Proposed Single‐Ensemble Catalysis

Indium oxide catalyzes acetylene hydrogenation with high selectivity to ethylene (>85 %); even with a large excess of the alkene. In situ characterization reveals the formation of oxygen vacancies under reaction conditions, while an in depth theoretical analysis links the surface reduction with the creation of well‐defined vacancies and surrounding In₃O₅ ensembles, which are considered responsible for this outstanding catalytic function. This behavior, which differs from that of other common reducible oxides, originates from the presence of four crystallographically inequivalent oxygen sites in the indium oxide surface. These resulting ensembles are 1) stable against deactivation, 2) homogeneously and densely distributed, and 3) spatially isolated and confined against transport; thereby broadening the scope of oxides in hydrogenation catalysis.     

碳纤维组合超微园盘电极的伏安特性与理论验证

用12根直径7μm碳纤维均匀胶结在外径1mm、内径0．4mm的有机玻璃毛细管外围，形成组合超微园盘电极。并与Ag/AgCl参比电极和铂丝辅助电极构成复合三电极系统。在K3Pe(CN)6／K4Pe(CN)6和Cd^2 ／KCl溶液体系中，测定了这种复合式的组合超微电极的循环伏安特性和阶梯扫描伏安特性。理论计算与实验曲线一致。该电极系统具有良好的组合超微电极的性能。由于单电极间距离远大于本身直径，扩散场互不干扰，因此，组合超微电极的响应具有加和性。应用这种复合超微电极，测定了工业污水中的镉含量，与普通极谱法测定结果一致。     

Dual Electrode Ensembles with Core and Shell Nanoelectrodes for Dopamine Sensing Applications

This paper presents the fabrication of dual electrode ensembles for electrochemical sensing of dopamine. A new dual electrode ensemble consists of vertically aligned core nanowire electrodes and a shell electrode with a hemi‐cylindrical nanocavity structure and submicron inter‐electrode spacing between the two working electrodes. By using a 3‐dimensional cavity structure of two working electrodes, collection efficiency in redox cycling of dopamine is enhanced. Initial measurement results show the ability to detect 200 μM concentration of dopamine with 69% collection efficiency on a dual electrode ensemble.     

Quasicrystals,model sets,and automatic sequences

We survey mathematical properties of quasicrystals, first from the point of view of harmonic analysis, then from the point of view of morphic and automatic sequences.     

A dynamical partition function for the Lorentz gas

In this paper we introduce a dynamically defined partition function for the Lorentz gas and investigate its connection with the classical ensembles and the phase-space probability measure derived from periodic orbit expansions. Numerical evidence is presented to support the equivalence of these measures and to link them to the thermodynamic quantities for the Lorentz gas. This also suggests a new dynamical basis for the assumption of equala priori probabilities in the microcanonical ensemble.     

A characterization of convex calibrable sets in with respect to anisotropic norms

A set is called “calibrable” if its characteristic function is an eigenvector of the subgradient of the total variation. The main purpose of this paper is to characterize the “-calibrability” of bounded convex sets in with respect to a norm (called anisotropy in the sequel) by the anisotropic mean -curvature of its boundary. It extends to the anisotropic and crystalline cases the known analogous results in the Euclidean case. As a by-product of our analysis we prove that any convex body C satisfying a -ball condition contains a convex -calibrable set K such that, for any V[|K|,|C|], the subset of C of volume V which minimizes the -perimeter is unique and convex. We also describe the anisotropic total variation flow with initial data the characteristic function of a bounded convex set.     

Ensemble Effects on Methanol Oxidation to Formaldehyde on Ferric Molybdate Catalysts

The properties of Mo-doped iron oxide are compared with those of the single oxides of Fe and Mo, and with stoichiometric ferric molybdate for the selective oxidation of methanol. It is found that Mo oxide segregates to the surface of the iron oxide at low loadings, while at higher loadings, but below the stoichiometric ratio, presents layers of ferric molybdate at the surface. The relationship between bulk loading and surface Mo is explored, and it is concluded that the reactivity is dominated by ensemble effects. Simple modelling indicates that four or more Fe cation ensembles are required to combust methanol to CO₂, ensembles of two Mo cations are required for selective oxidation to formaldehyde, whereas it seems that isolated single sites of either Fe or Mo produce CO.