Steffen Nienke

Bladder volume estimation from electrical impedance tomography

Non-invasive estimation of bladder volume is required to progress from scheduled voiding to a demand-driven emptying scheme for patients with impaired bladder volume sensation. Electrical impedance tomography (EIT) is a promising candidate for the non-invasive monitoring of bladder volume. This article focuses on four estimation algorithms used to map recorded EIT data to a volume estimate. Two different approaches are presented: the tomographic algorithms (one based on global impedance, the other on equivalent circular diameter) rely on the reconstruction of a tomographic image and then extract a volume estimate, whereas the parametric algorithms (one based on neural networks, the other on the singular value difference method) directly map the raw data to a volume estimate. The four algorithms presented here are evaluated for volume estimation error, noise tolerance and suppression of varying urine conductivity based on finite element simulation data.

Introducing an Information Logistics Approach to Support the Development of Future Energy Grid Management.

Due to the drastically increasing amount of data, decision making in companies heavily relies on having the right data available. Also because of an increasing complexity of structures and processes, quick and precise flows of information become more important. This paper introduces a new approach for modelling information flows, creating a basis for an efficient information management. It can be used to structure the information requirements and identify gaps within the information processing. To display its benefits, the proposed Information Logistics Notation (ILN) is applied to the information logistics of todays and future energy market and grid stability management, both processes of increasing complexity.

Information flows and optimization for a holistic industrial energy management

Due to the changing energy market with regards to fight against the climate change, manufacturing companies are forced to enhance their efforts in energy management. Since the topic was mostly neglected for quite a while, there are no concepts that cover an holistic approach for industrial energy management. This paper presents a way to merge the existing partial systems for manufacturing companies by looking at the crucial information flows and solving the subsequent holistic optimization problem using the concept of walrasian auction with integrated Q-learning algorithm. The result can support business by identifying the needed (information-) resources and implementing a holistic optimization of energy usage.

Energy forecasting and modelling in rural areas

Energy forecasting and modeling in rural areas is accomplished through NRG4CAST platform through which a set of real-time prediction and trend detection services are developed based on advanced machine learning, trend detection, prediction, optimisation and reasoning capabilities in order to provide to stakeholders unique service for energy consumption, network failure and energy prices prediction. In order to build up reliable services different type of information are assessed and combined from internal and external sources: historical and current information from the local energy distribution network (energy consumption and network devices status), information about the local environment (natural and social), energy prices (national and international).