On Complex Event Processing for Real-Time Situational Awareness

Abstract

Abstract. In this paper we give an overview of the existing research results and open research challenges in applying complex event processing for real-time situational awareness. We consider two different viewpoints: better detection of emerging complex situations and prediction of future situations. In order to illustrate these viewpoints we consider two application areas: activity recognition from the video content and social media observation, respectively.

A situation refinement model for complex event processing

“…A primary motive for enriching CEP systems is to provide better insights about emerging complex situations by developing the relationship between event data flows and current business changes reside in background knowledge [7,45]. In other words, the aim is to achieve a higher level of situational awareness by inferring more expressive complex events based on the correlation between event data and background knowledge [27].…”

“…Any data stream mining approach used for CEP systems must have a high degree of flexibility to adapt to the changes in situations of interest in near real-time [14][15][16][17].…”

“…Using CEP technology to detect complex situations early within the application context requires the utilization of various types of external knowledge sources. Therefore, external knowledge in the application domain is needed to enrich event data and to identify CEP rules towards detecting critical situations in near real-time [27,45].…”

Heterarchy: An Interorganizational Approach to Securing the United States Against a Pandemic Threat

“…This is especially significant at the heterarchy's peripheries because higher-level decisions can be simultaneously made, such as whether pandemic alerts should be raised or quarantines should be extended geographically. As agencies depend more on stakeholders for information, such "situational assessment" operations become more sophisticated, e.g., complex event processing, geographic information systems, and predictive analytics (FEMA 2012;Stojanovic 2011;ESRI 2013;Yu et al 2009). Such systems reinforce heterarchical thinking across boundaries and may facilitate greater accuracy, timeliness, and consistency in a given scenario.…”

A Rule-Based Virtual Director Enhancing Group Communication

“…To support uncertainty in order to deal with noisy sensor information a Markov Logic Network algorithm will be integrated. However, using Markov Logic Networks in event processing raises new challenges and there are several issues that need to be resolved [10]. These include the incorporation and use of numerical temporal constraints in the inference process, the simultaneous learning of numerical parameters, and the logical structure of the knowledge base expressing complex events.…”