Stephan Hutterer

Brain tumor classification using AFM in combination with data mining techniques.

Although classification of astrocytic tumors is standardized by the WHO grading system, which is mainly based on microscopy-derived, histomorphological features, there is great interobserver variability. The main causes are thought to be the complexity of morphological details varying from tumor to tumor and from patient to patient, variations in the technical histopathological procedures like staining protocols, and finally the individual experience of the diagnosing pathologist. Thus, to raise astrocytoma grading to a more objective standard, this paper proposes a methodology based on atomic force microscopy (AFM) derived images made from histopathological samples in combination with data mining techniques. By comparing AFM images with corresponding light microscopy images of the same area, the progressive formation of cavities due to cell necrosis was identified as a typical morphological marker for a computer-assisted analysis. Using genetic programming as a tool for feature analysis, a best model was created that achieved 94.74% classification accuracy in distinguishing grade II tumors from grade IV ones. While utilizing modern image analysis techniques, AFM may become an important tool in astrocytic tumor diagnosis. By this way patients suffering from grade II tumors are identified unambiguously, having a less risk for malignant transformation. They would benefit from early adjuvant therapies.

Overview: a simulation based metaheuristic optimization approach to optimal power dispatch related to a smart electric grid

The implementation of intelligent power grids, in form of smart grids, introduces new challenges to the optimal dispatch of power. Thus, optimization problems need to be solved that become more and more complex in terms of multiple objectives and an increasing number of control parameters. In this paper, a simulation based optimization approach is introduced that uses metaheuristic algorithms for minimizing several objective functions according to operational constraints of the electric power system. The main idea is the application of simulation for computing the fitness-values subject to the solution generated by a metaheuristic optimization algorithm. Concerning the satisfaction of constraints, the central concept is the use of a penalty function as a measure of violation of constraints, which is added to the cost function and thus minimized simultaneously. The corresponding optimization problemis specified with respect to the emerging requirements of future smart electric grids.

Probabilistic Electric Vehicle Charging Optimized With Genetic Algorithms and a Two-Stage Sampling Scheme

Probabilistic power flow studies represent essential challenges in nowadays power system operation and research. Here, especially the incorporation of intermittent supply plants with optimal control of dispatchable demand like electric vehicle charging power shows nondeterministic aspects. Using simulation-based optimization, such probabilistic and dynamic behavior can be fully integrated within the metaheuristic optimization process, yielding into a generic approach suitable for optimization in uncertain environments. A practical problem scenario is demonstrated that computes optimal charging schedules of a given electrified fleet in order to meet both power flow constraints of the distribution grid while satisfying vehicle-owners’ energy demand and considering stochastic supply of wind power plants. Since solution- evaluation through simulation is computational expensive, a new fitness-based sampling scheme will be proposed, that avoids unnecessary evaluations of less-performant solution candidates.

Software-Enabled Investigation in Metaheuristic Power Grid Optimization

Actual developments in power grid research, analysis, and operation are dominated clearly by the strong convergence of electrical engineering with information technology. Hence, new control abilities in power grids come up that revolutionize traditional optimization issues, requiring novel solution methods. At the same time, heuristic algorithms have emerged to be highly capable of handling those new optimization problems. In this work, a simulation-based optimization approach is proposed that enables investigation with metaheuristic algorithms for domain experts, where especially the power engineering point of view gets highlighted. HeuristicLab is demonstrated as a framework for optimization, which facilitates usage and development of optimization algorithms in a way that is attractive not only to computer scientists. From a software point of view, architectural aspects are treated that enable the decoupling of optimization algorithms and problems, which is a basic fundament of the framework. Further, interprocess communication is discussed that enables the interaction of optimization algorithms and simulation problems, and a practical showcase demonstrates the frameworks application to real-world power grid optimization issues.

Genetic programming enabled evolution of control policies for dynamic stochastic optimal power flow

The optimal power flow (OPF) is one of the central optimization problems in power grid engineering, building an essential tool for numerous control as well as planning issues. Methods for solving the OPF that mainly treat steady-state situations have been studied extensively, ignoring uncertainties of system variables as well as their volatile behavior. While both the economical as well as well as technical importance of accurate control is high, especially for power flow control in dynamic and uncertain power systems, methods are needed that provide (near-) optimal actions quickly, eliminating issues on convergence speed or robustness of the optimization. This paper shows an approximate policy-based control approach where optimal actions are derived from policies that are learned offline, but that later provide quick and accurate control actions in volatile situations. These policies are evolved using genetic programming, where multiple and interdependent policies are learned synchronously with simulation-based optimization. Finally, an approach is available for learning fast and robust power flow control policies suitable to highly dynamic power systems such as smart electric grids.

Evolutionary computation enabled controlled charging for e-mobility aggregators

Optimal integration of electric vehicles (EVs) into modern power grids plays a promising role in future operation of smart power systems. The role of aggregators as e-mobility service providers is getting investigated steadily in recent times and forms a fruitful ground for control of EV charging. Within this paper, a policy-based control approach is shown that applies an evolutionary simulation optimization procedure for learning valid charging policies offline, that lead to accurate charging decisions online during operation. This approach provides a trade-off between local and distributed control, since the centrally applied learning procedure ensures satisfaction of the operators requirements during the learning phase, where final control is applied decentrally after distributing the learned policies to the agents. Since the needed information that the aggregator has to provide to the agents is crucial, further analysis on the achieved control policies concerning their data requirements are conducted.

Data mining techniques for AFM- based tumor classification

The present paper deals with the application of atomic force microscopy (AFM) as a tool for morphological characterization of histological brain tumor samples. Data mining techniques will be applied for automatic identification of brain tumor tissues based on AFM images by means of classifying grade II and IV tumors. The rapid advancement of AFM in recent years turned it into a valuable and useful tool to determine the topography of surface nanoscale structures with high precision. Therefore, it is used in a variety of applications in life science, materials science, electrochemistry, polymer science, biophysics, nanotechnology, and biotechnology. Minkowski functionals are used (in particular the Euler- Poincaré characteristic) as a feature descriptor to characterize global geometric structures in images related to the topology of the AFM image. In order to improve classification accuracy on the one hand, but to infer interpretable information from AFM images for domain experts on the other hand, feature analysis and reduction will be applied. From a data mining point of view, Genetic Programming will be introduced as a sophisticated method for both feature analysis and reduction as well as for producing highly accurate and interpretable models. Support Vector Machines will be used for comparison reasons when talking about reachable model accuracy.

Evolutionary algorithm based control policies for flexible optimal power flow over time

General optimal power flow (OPF) is an important problem in the operation of electric power grids. Solution methods to the OPF have been studied extensively that mainly solve steady-state situations, ignoring uncertainties of state variables as well as their near-future. Thus, in a dynamic and uncertain power system, where the demand as well as the supply-side show volatile behavior, optimization methods are needed that provide solutions very quickly, eliminating issues on convergence speed or robustness of the optimization. This paper introduces a policy-based approach where optimal control policies are learned offline for a given power grid based on evolutionary computation, that later provide quick and accurate control actions in volatile situations. With such an approach, its no more necessary to solve the OPF in each new situation by applying a certain optimization procedure, but the policies provide (near-) optimal actions very quickly, satisfying all constraints in a reliable and robust way. Thus, a method is available for flexible and optimized power grid operation over time. This will be essential for meeting the claims for the future of smart grids.

Heuristic power scheduling of electric vehicle battery charging based on discrete event simulation

Since the electrification of individual traffic may cause a critical load to power grids, methods have to be investigated that are capable of handling its highly stochastic behaviour. From a power grids point of view, forecasting applications are needed for computing optimal power generation schedules that satisfy end-users energy needs while considering installed capacities in the grid. In this paper, an optimization framework is being proposed, that uses metaheuristic algorithms for finding these schedules based on individual traffic simulation using discrete-event methodology. Evolution Strategy implemented in HeuristicLab is used as optimization algorithm, where the used parameterization and the achieved results will be shown.

Data mining supported analysis of medical atomic force microscopy images

Taking a look at actual developments in the field of bioinformatics, computer support in different fields of medicine and biology is an increasing field of interest. Especially for recognition and classification of various kinds of diseases, researchers already identified the usage of data mining techniques as supporting tool for computer supported analysis and diagnosis. In order to build such tools, highly accurate and machine-readable data is needed. Therefore, atomic force microscopy (AFM) is shown within this paper as measurement technology, that provides true 3-D data of any tissue and thus is able to build the fundament for further computational processing steps. Within two practical examples dealing with brain tumor tissue on the one hand and myocardial muscle tissue on the other hand, data mining supported analysis of AFM images will be demonstrated. The combination of data mining techniques with AFM measurements at nanoscale therefore forms a promising fundament for future computer enabled support systems in medicine and biology.