Siemens Aktiengesellschaft

Sartorius Stedim Biotech Gmbh

Viega Technology Gmbh & Co. Kg

Katrin Müller

Thomas Loewe

Thomas Friese

Jens-Christian Holst

Willfried Wienholt

Winfried Reif

Florian Ansgar Jaeger

Mario Strauss

Klaus Heidinger

Nicolas Moegelin

Pedro Miranda

Jörn Hartung

Dirk Opalla

Various embodiments of the teachings herein include a computer aided method for generating training data for a neural network designed to determine a pollutant concentration at a measurement station from a pollutant emission. The method may include: providing a measurement series of the concentration containing a value above a threshold; providing a measurement series for a variable related to the pollutant concentration; providing a transmission model modelling a relationship between the pollutant emission, the measured variable, and the pollutant immission at the measurement station; computing a first value of the pollutant immission using the transmission model using a value of the measured variable; computing a second value of the pollutant immission using the transmission model by numerically altering the measured value of the measured variable; and generating a synthetic measurement series as training data by an alteration based at least in part on a relative change in computed values.

Computer-assisted method for generating training data for a neural network for predicting a concentration of pollutants at a measuring station

Various embodiments include a method for verifying sensors for a sensor network including a reference sensor comprising: identifying a first sensor; locating the identified sensor; comparing a measured value recorded by the identified sensor to a measured value recorded at the same time and within a defined spatial environment using the reference sensor; determining a deviation of the measured value of the identified sensor from the measured value of the reference sensor; and assigning the sensor to precisely one of at least two categories depending on an amount of the deviation.

Method for verifying sensors in a sensor network, and sensor network

A system for providing infrastructure impacts on an urban area is provided. Area specific content data of a selected urban area is loaded from a database, and infrastructure impacts on the selected urban area are calculated by a calculation unit depending on the loaded area specific content data and technology parameters of predefined infrastructure levers set by a user.

System for providing infrastructure impacts on an urban area

Growing community of inventors

Berlin, Germany

Katrin Müller