Abstract Complex Event Processing (CEP) is an established software technology to extract relevant information from massive data streams. Currently, domain experts have to determine manually CEP rules that define a situation of interest. However, often CEP rules cannot be formulated by experts, because the relevant interdependencies and relations between the data are not explicitly known, but inherently hidden in the data streams. To cope with this problem, we present a new learning approach for ...
Multi-Agent Systems (MAS) lack advanced concepts for data stream processing, which inhibits their effective use in mobile ecosystems, where built-in smartphone sensors can provide valuable data about the current physical environment of the mobile user. With beliefs, plans, and goals, cognitive agent frameworks provide useful abstractions for the development of complex systems but do not contain effective mechanisms to sufficiently bridge the abstraction gap that exists between low-level streamin...
Nowadays, mobile recommender systems running on user's smart devices have become popular. However, most implemented mechanisms require continuous user interaction to provide personalized recommendations, and thus weaken the usability. This paper provides an innovative approach for taking advantage of user's movement data as implicit user feedback for deriving recommendations. By means of a real-world museum scenario a beacon infrastructure for tracking sojourn times is presented. Then we show ho...
Bike-sharing systems are becoming very popular in big cities. They provide a cheap and green mean of transportation used for commuting and leisure. Being a shared limited resource, it is common to reach imbalanced situations where some stations have either no bikes or only empty slots, thus decreasing the performance of the system. To solve such situations, trucks are typically used to move bikes among stations in order to reach a more homogeneous distribution. Recently, research works are focus...
This paper provides an innovative approach for taking advantage of user’s movement data as implicit user feedback for deriving recommendations in large facilities. By means of a real-world museum scenario a beacon infrastructure for tracking sojourn times is presented. Then we show how sojourn times can be integrated in a collaborative filtering algorithm approach in order to outcome accurate recommendations.
With the increase of existing sensor devices grows the data volume that is available to software systems to understand the physical world. The use of this sensor data in Multi-Agent Systems (MAS) could allow agents to improve their comprehension of the environment and provide additional information for their decision making. Unfortunately, conventional BDI agents cannot make sense of low-level sensor data directly due to their limited event comprehension capabilities: The agents react to single,...
Operating a Bicycle Sharing System over some time without the operator’s intervention causes serious imbalances, which prevents the rental of bikes at some stations and the return at others. To cope with such problems, user-based bicycle rebalancing approaches offer incentives to influence the users’ behavior in an appropriate way. In this paper, an event-driven agent architecture is proposed, which uses Complex Event Processing to predict the future demand at the bike stations using live data a...
In this paper, we consider the route coordination problem in emergency evacuation of large smart buildings. The building evacuation time is crucial in saving lives in emergency situations caused by imminent natural or man-made threats and disasters. Conventional approaches to evacuation route coordination are static and predefined. They rely on evacuation plans present only at a limited number of building locations and possibly a trained evacuation personnel to resolve unexpected contingencies. ...