Keynotes: Academic and Industry Perspectives

Designing Information, Communication, and Experiences in Ubiquitous Hybrid Worlds

It seems like a paradox but it will soon become reality: The rate at which computers disappear will be matched by the rate at which information technology will increasingly permeate our environment and our lives". This statement by Streitz & Nixon illustrates that new challenges for designing the interaction of humans with computers embedded in everyday objects will arise. While disappearance is a major aspect, "smart" artefacts are also characterized by sensors collecting data about the environment, the devices and humans acting in this context in order to provide ambient intelligence-based support. The resulting issues are discussed based on the distinction between "system-oriented, importunate smartness", implying more or less automatic behaviour of smart environments, and "people-oriented, empowering smartness", where the empowering function is in the foreground. The latter approach can be summarized as "smart spaces make people smarter" which is achieved by keeping "the human in the loop" and empowering people to be in control, making informed decisions and taking actions. Whatever type of smartness will be employed, representations of people, content and contexts play a central role. Last but not least, privacy issues in sensor-based smart environments are being discussed ranging from being a legal and moral right to becoming a commodity and privilege. The approaches and concepts will be illustrated with examples taken from different research projects ranging from smart rooms over cooperative buildings to hybrid cities.

Spatial and Temporal Modeling for AmI Systems: Industrial Applications

The talk presents two ongoing research projects at Siemens Corporate Research and Technology in the domain of Ambient Assisted Living (AAL) and Public Surveillance. One key feature in both domains is the ability to detect and identify specific behavioral patterns of persons. While AAL applications mainly focus on providing assistance functionalty to the user, Public Surveillance applications aim at detecting (and possibly preventing) potentially dangerous situations. To this end adequate models (e.g. of human behavior or processes) have to be constructed, taking into account spatial context and temporal dependencies. These models can be evaluated using standard approaches such as DL-reasoning, whereas alternative methods (e.g. graph-based spatial reasoning, or abductive reasoning) may turn out to be more flexible and performant.
Speaker:

Michael Pirker, Corporate Technology, SIEMENS AG, Munich, Germany