Logic-based representation, reasoning and machine learning for event recognition

Abstract

Today's organisations require techniques for automated transformation of the large data volumes they collect during their operations into operational knowledge. This requirement may be addressed by employing event recognition systems that detect activities/events of special significance within an organisation, given streams of 'low-level' information that is very difficult to be utilised by humans. Numerous event recognition systems have been proposed in the literature. Recognition systems with a logic-based representation of event structures, in particular, have been attracting considerable attention because, among others, they exhibit a formal, declarative semantics, they haven proven to be efficient and scalable, and they are supported by machine learning tools automating the construction and refinement of event structures. In this paper we review representative approaches of logic-based event recognition, and discuss open research issues of this field.

Real-Time Complex Event Recognition and Reasoning–a Logic Programming Approach

“…In particular, we plan to investigate how a rule representation of complex events (in large pattern bases) may help in verification of event patterns (e.g., discovering patterns that can never be detected according to inconsistency problems). We also plan to utilize machine-learning techniques to automatically generate both event patterns and the domain knowledge required for knowledge-based CEP (see Artikis et al (2010), and XHAIL system (Ray 2009)). Further, event revision is another area where logic reasoning will help in managing consequences when certain events are retracted.…”

“…However, our approach also differs from related work of Motakis and Zaniolo (1995); Artikis et al (2010); Lausen, Ludäsher, and May (1998) ;Paschke, Kozlenkov, and Boley (2010); and Bry and Eckert (2007). The main difference lies in the execution model (based on EDBCR).…”

“…Much work (Motakis & Xaniolo 1995;Artikis et al 2010;Lausen Ludäscher, and May 1998;Paschke, Kozlenkov, and Boley (2010) ;Bry & 48 D. Anicic et al Eckert (2007) in the area of rule-based CEP has been carried out, proposing various kinds of logic rule-based approaches to process complex events. As pointed out in Bry & Eckert (2007), rules can be effectively used for describing so-called ''virtual'' event patterns.…”

“…It has been shown (Artikis et al 2010;Kowalski and Sergot 1986;Miller and Shanahan 1999;Lausen, Ludäscher, and May, 1998;Alferes, Banti, and Brogi 2006;Bry and Eckert 2007;Haley 1987;Paschke, Kozenkov, and Boley 2010) that logic-based approaches for event processing have various advantages. First, they are expressive enough and convenient to represent diverse complex event patterns and come with a clear formal declarative semantics; as such, they are free of operational side-effects.…”

Event processing under uncertainty

“…Consider, for example, the Chronicle Recognition System [13] that has been successfully applied to cardiac monitoring [10], in addition to intrusion detection and mobility management in computer networks [14], and distributed diagnosis of web services [26]. A comprehensive introduction to AI-based event recognition systems may be found in [3,5]. In this section we focus on systems that handle various types of uncertainty.…”