Evonik Digital Research

A joined research project with University Duisburg-Essen

Psychology of Technology
A particular focus of our work is put on the investigation of how people are affected by IoT systems tracking their data and how Evonik in particular can be prepared for the application of a multi-stage emergency recognition system at the workplace.
Locating Workers by Floor Vibration Sensing
In an emergency case, rescue helpers must know where workers are. We measure the floor vibration using an array of piezoelectric sensors. Signal processing, feature extraction, pattern recognition, and machine learning techniques are applied on the sensor data to locate workers in need of help.
Sensing Abnormal Situations with Audio
In case of an emergency, audio surveillance data is used to detect abnormal sounds. The system will detect explosions, people shouting for help, or simply knocking on the floor. This allows to locate people in need of help although they are not moving.
Detecting Rescue Targets with Video
We use the image information to detect people lying on the floor or waving with their hands. For privacy reasons, we will use a preprocessing approach to anonymize the character information from the cameras. Then we use these anonymous image data for people gesture and situation perception detection. Recognition of humans and their body position in video streams are achieved in this stage.
Psychological Study I
The aim of study I was to investigate in greater detail how people perceive tracking by IoT systems and what factors contribute to their intention to use smart technology.
Psychological Study II
The purpose of study II was to re-examine the privacy calculus in order to investigate its applicability within the framework of smart technology usage at the workplace.
Ongoing Research
During the following project phase the engineering team will improve the sensing and machine learning approaches while the psychology team will further investigate how workers perceive the potential benefits and dangers of such a system. Both teams together will use these results to investigate how privacy-sensitive IoT systems can be designed and rolled-out in such a way that they fulfill their task while enjoying acceptance on the user side.