A framework for event co-occurrence detection in event streams

TL;DR

This paper introduces a novel automaton-based framework for detecting co-occurrence patterns in multimedia event streams, facilitating causal analysis and supporting applications like recommendation systems.

Contribution

It presents a new automaton-based method for efficient co-occurrence detection in single and multiple event streams, including a visual co-occurrence matrix for analysis.

Findings

Efficient one-pass pattern counting in event streams

Visual co-occurrence matrix for event characterization

Reusable causality rules for multimedia analysis

Abstract

This paper shows that characterizing co-occurrence between events is an important but non-trivial and neglected aspect of discovering potential causal relationships in multimedia event streams. First an introduction to the notion of event co-occurrence and its relation to co-occurrence pattern detection is given. Then a finite state automaton extended with a time model and event parameterization is introduced to convert high level co-occurrence pattern definition to its corresponding pattern matching automaton. Finally a processing algorithm is applied to count the occurrence frequency of a collection of patterns with only one pass through input event streams. The method proposed in this paper can be used for detecting co-occurrences between both events of one event stream (Auto co-occurrence), and events from multiple event streams (Cross co-occurrence). Some fundamental results concerning the characterization of event co-occurrence are presented in form of a visual co- occurrence matrix. Reusable causality rules can be extracted easily from co-occurrence matrix and fed into various analysis tools, such as recommendation systems and complex event processing systems for further analysis.