Patrick Koch

Learn More
Cultured human hepatocytes are a valuable in vitro system for evaluating new molecular entities as inducers of cytochrome P450 (P450) enzymes. The present study summarizes data obtained from 62 preparations of cultured human hepatocytes that were treated with vehicles (saline or dimethylsulfoxide, 0.1%), beta-naphthoflavone (33 microM), phenobarbital (100(More)
Slow Feature Analysis (SFA) has been established as a robust and versatile technique from the neurosciences to learn slowly varying functions from quickly changing signals. Recently, the method has been also applied to classification tasks. Here we apply SFA for the first time to a time series classification problem originating from gesture recognition. The(More)
Objective. Experimental studies demonstrate that β-adrenergic agonists markedly stimulate alveolar fluid clearance if concentrations of 10–6 M are achieved in alveolar fluid. However, no studies have determined whether aerosolized β-adrenergic agonists are delivered to the distal air spaces of the lung in therapeutic concentrations in patients with(More)
Based on the information of the interdisciplinary task force on allergy diagnostics in the metal branch, in 2001, the German Contact Dermatitis Research Group (DKG) compiled two metalworking fluid (MWF) test series with currently and previously used components, respectively. After 2 years of patch testing, we present results obtained with these series,(More)
Kernel-based methods like Support Vector Machines (SVM) have been established as powerful techniques in machine learning. The idea of SVM is to perform a mapping φ from the input space to a higher-dimensional feature space using a kernel function k, so that a linear learning algorithm can be employed. However, the burden of choosing the appropriate kernel(More)
In this paper, the performance assessment of the hybrid Archive-based Micro Genetic Algorithm (AMGA) on a set of bound-constrained synthetic test problems is reported. The hybrid AMGA proposed in this paper is a combination of a classical gradient based single-objective optimization algorithm and an evolutionary multi-objective optimization algorithm. The(More)
In this paper, we propose a new evolutionary algorithm for multi-objective optimization. The proposed algorithm benefits from the existing literature and borrows several concepts from existing multi-objective optimization algorithms. The proposed algorithm employs a new kind of selection procedure which benefits from the search history of the algorithm and(More)
Learning complex game functions is still a difficult task. We apply temporal difference learning (TDL), a well-known variant of the reinforcement learning approach, in combination with n-tuple networks to the game Connect-4. Our agent is trained just by self-play. It is able, for the first time, to consistently beat the optimal-playing Minimax agent (in(More)
Learning board games by self-play has a long tradition in computational intelligence for games. Based on Tesauro's seminal success with TD-Gammon in 1994, many successful agents use temporal difference learning today. But in order to be successful with temporal difference learning on game tasks, often a careful selection of features and a large number of(More)
A novel multimodal behavioral biometric technique is implemented to authenticate/identify users by the way they interact with the input devices namely mouse and keyboard. It is also shown how behavioral biometrics is more efficient and secure than physiological biometric systems and moreover the most secured system is that which uses combination of both.(More)