50 years of data mining and OR: upcoming trends and challenges

Data mining involves extracting interesting patterns from data and can be found at the heart of operational research (OR), as its aim is to create and enhance decision support systems. Even in the early days, some data mining approaches relied on traditional OR methods such as linear programming and forecasting, and modern data mining methods are based on a wide variety of OR methods including linear and quadratic optimization, genetic algorithms and concepts based on artificial ant colonies. The use of data mining has rapidly become widespread, with applications in domains ranging from credit risk, marketing, and fraud detection to counter-terrorism. In all of these, data mining is increasingly playing a key role in decision making. Nonetheless, many challenges still need to be tackled, ranging from data quality issues to the problem of how to include domain experts' knowledge, or how to monitor model performance. In this paper, we outline a series of upcoming trends and challenges for data mining and its role within OR.     

Analysing steady-state simulation output using vector autoregressive processes with exogenous variables

A simulation study often requires computation of a point estimate and confidence region for the steady-state mean of a stochastic output process. The literature offers a variety of statistical techniques, including replication/deletion, the batch-means method, and spectrum analysis. We present a new multivariate output-analysis technique that is based on the general autoregressive time-series model with exogenous variables to set up a joint confidence region for the steady-state mean. We demonstrate our technique by an extensive computational experiment, and show that it performs at least as well as other output-analysis techniques, without having some of their drawbacks.     

Probability distributions for the run-and-tumble bacterial dynamics: An analogy to the Lorentz model

In this paper, we exploit an analogy of the run-and-tumble process for bacterial motility with the Lorentz model of electron conduction in order to obtain analytical results for the intermediate scattering function. This allows to obtain an analytical result for the van Hove function in real space for two-dimensional systems. We furthermore consider the 2D circling motion of bacteria close to solid boundaries with tumbling, and show that the analogy to electron conduction in a magnetic field allows to predict the effective diffusion coefficient of the bacteria. The latter is shown to be reduced by the circling motion of the bacteria.     

Anwendung der Reaktionskristallisation in der Hydrometallurgie und der anorganisch-chemischen Technik

With respect to several technical reaction crystallizations (jarosite, goethite, alunite, ammonium hexavanadate, calcium carbonate, zine carbonate) some fundamental problems of the reaction crystallization from solutions are discussed: 1) Adjustment of the rates of reaction and growth; 2) Selection of the chemical compounds according to their solubility; 3) Selection of suitable reactants; 4) Selection of the range of pH. The morphology of precipitates has been examined. With the use of low reaction rates and concentrated initial solutions homodisperse crystallite agglomerates were found to be characteristic of the precipitates.     

Anodic and Cathodic Platinum Dissolution Processes Involve Different Oxide Species

The degradation of Pt-containing oxygen reduction catalysts for fuel cell applications is strongly linked to the electrochemical surface oxidation and reduction of Pt. Here, we study the surface restructuring and Pt dissolution mechanisms during oxidation/reduction for the case of Pt(100) in 0.1 M HClO₄ by combining operando high-energy surface X-ray diffraction, online mass spectrometry, and density functional theory. Our atomic-scale structural studies reveal that anodic dissolution, detected during oxidation, and cathodic dissolution, observed during the subsequent reduction, are linked to two different oxide phases. Anodic dissolution occurs predominantly during nucleation and growth of the first, stripe-like oxide. Cathodic dissolution is linked to a second, amorphous Pt oxide phase that resembles bulk PtO₂ and starts to grow when the coverage of the stripe-like oxide saturates. In addition, we find the amount of surface restructuring after an oxidation/reduction cycle to be potential-independent after the stripe-like oxide has reached its saturation coverage.