| Sahin Albayrak | The Role of AI in Shaping Smart Services and Smart Systems | |
|---|---|---|
| TU Berlin |
Services and Systems must include a set of features to remain competent and future conform:
intelligent behaviour, personalisation, adaptivity, scalability,
manageability, ease of use and user friendliness, security, and self-healing capabilities.
As a consequence, new architectural models are needed,
which provide the users with access to a cognitive behaviour aspect of the system,
and which may draw inspiration from the brain sciences.
On the other hand, we have to use knowledge representation and semantic modeling, e.g.,
ontologies for representing our environment or basic properties of services and systems.
This would naturally involve Agent Technology, AI, and Software Technology.
So, approaches from many different disciplines have to work in integration.
Integrated frameworks handling such different aspects are called "Serviceware Frameworks". They contain a scalable Service Architecture, which facilitates merging different selected features into a service, as well as a scalable so-called Service Engine with a Serviceware Infrastructure. For creating Smart Services and Smart Systems, we use engineering approaches that include innovative service description languages and tools. In this presentation, a framework with the properties and features just described will be presented. A sample application developed with this framework will also be presented: the "Smart Energy Assistant". |
|
| Wolfgang Bibel | Early History and Perspectives of Automated Deduction | |
| TU Darmstadt | With this talk we want to pay tribute to the late Professor Gerd Veenker who deserves the historic credit of initiating the formation of the German AI community. We present a summary of his scientific contributions in the context of the early approaches to theorem proving and, against this background, we point out future perspectives of Automated Deduction for AI. | |
| Martin Buss | Cognitive Technical Systems – What Is the Role of Artificial Intelligence? | |
| TU München | The CoTeSys cluster of excellence investigates cognition for technical systems such as vehicles, robots, and factories. Cognitive technical systems (CTS) are information processing systems equipped with artificial sensors and actuators, integrated and embedded into physical systems, and acting in a physical world. They differ from other technical systems as they perform cognitive control and have cognitive capabilities. Cognitive control orchestrates reflexive and habitual behavior in accord with longterm intentions. Cognitive capabilities such as perception, reasoning, learning, and planning turn technical systems into systems that "know what they are doing". The cognitive capabilities will result in systems of higher reliability, flexibility, adaptivity, and better performance. They will be easier to interact and cooperate with. | |
| Thomas Christaller | Artificial Intelligence is Engineering Intelligence – Why should we care about Natural Intelligence? | |
| Fraunhofer IAIS, Sankt Augustin | Artificial Intelligence is about designing and constructing artefacts, normally not
about explaining human intelligence. So, why should we care about natural
intelligence when talking about AI? There are several important more or less recent
findings in brain science as well as ethology which require a deeper rethinking on
the AI side. Based on them, the hypothesis in this talk is: The rising complexity of
the behaviour system and of personalized social relationships was one of the major
reasons for developing intelligence -- contrary to the huge resource consumption
that intelligence costs an individual. The most important result of this development
was the capability of forecasting the behaviour of conspecifics for survival in a
complex social environment. This capability was also useful for other purposes,
including forecasting behaviour of individuals of other species and nature itself.
A second focus in the talk will be language and the hypothesized reasons or causes for its evolution and its primary usages. This will lead to the concept of imitation and its neural basis. Some plausible speculations will be given, why all these findings fit into a relatively consistent picture of natural intelligence. The conclusion will be some examples on how these findings can inspire AI research and the construction of AI systems. | |
| Yuval Elovici | Applying Machine Learning Techniques to Detect Malicious Code in Network Traffic | |
| Ben Gurion U. of the Negev, Beer-Sheva, Israel | In a recent online safety survey conducted by America Online and the National Cyber Security Alliance (NCSA) 81% of the respondents were found to be lacking recently-updated anti-virus software, a properly-configured firewall, and/or spyware protection. Nevertheless, 74% of the respondents use the Internet for "sensitive" transactions from home computers, such as banking, stock trading, or reviewing personal medical information. One way to prevent users from being infected by such threats is to clean the traffic at the NSP level. In this talk I will present a system for an Early Detection, Alert and Response (eDare) aimed at cleaning NSP traffic. The proposed system employs powerful network traffic scanners for cleaning traffic from known threats. Remaining suspicious traffic is monitored and Machine Learning (ML) algorithms are invoked for identifying unknown threats. Neural Networks and Bayesian Networks are used for static code analysis in order to determine whether a file contain malicious code. Temporal reasoning techniques are being used to analyze the spread of malicious code in the network. The ML algorithms are being evaluated and preliminary results are very promising. The eDare system was deployed and tested in a security lab with segregated pure and infected environments. We have collected a massive repository of over 30,000 executable threats of various kinds and have used them to train and test the effectiveness of eDare. We were able to reach an automatic detection rate of over 96% with less than 4% false positive. | |
| Dieter Fox | Location-Based Activity Recognition | |
| U. of Washington, Seattle, USA | Knowledge of a person's location provides important context information for many applications, ranging from services such as E911 to personal guidance systems that help cognitively-impaired individuals move safely through their community. Location information is also extremely helpful for estimating a person's high-level activities. In this talk we show how Bayesian filtering and conditional random fields can be applied to estimate the location and activity of a person using sensors such as GPS or WiFi. The techniques track a person on graph structures that represent a street map or a skeleton of the free space in a building. We also show how to learn a user's significant places and daily movements through the community. Our models use multiple levels of abstraction so as to bridge the gap between raw GPS measurements and high level information such as a user's mode of transportation, her current goal, and her significant places (e.g. home or work place). Finally, we will discuss recent work on using a multi-sensor board so as to better estimate a person's activities. | |