A probabilistic logic programming event calculus

Skarlatidis, Anastasios; Artikis, Alexander; Filippou, Jason; Παλιούρας, Γεώργιος

doi:10.1017/s1471068413000690

Cited by 43 publications

(35 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though, most of the times, this is not sufficient for expressing temporal correlations among the observed patterns. In order to represent uncertain data and time dependencies, probabilistic temporal logic (PTL) programming paradigms have been proposed [29] [30] [31] [32]. Such approaches extend the syntax and the semantics of probabilistic logic programs by terms of allowing for reasoning about point probabilities over time intervals through the use of probabilistic temporal rules.…”

Section: Event Predictionmentioning

confidence: 99%

Event correlation and forecasting over high-dimensional streaming sensor data

Papataxiarhis

Hadjiefthymiades

2018

2018 14th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

View full text Add to dashboard Cite

Event management in sensor networks is a multidisciplinary field involving several steps across the processing chain. In this paper, we discuss the major steps that should be performed in real-or near real-time event handling including event detection, correlation, prediction and filtering. First, we discuss existing univariate and multivariate change detection schemes for the online event detection over sensor data. Next, we propose an online event correlation scheme that intends to unveil the internal dynamics that govern the operation of a system and are responsible for the generation of various types of events. We show that representation of event dependencies can be accommodated within a probabilistic temporal knowledge representation framework that allows the formulation of rules. We also address the important issue of identifying outdated dependencies among events by setting up a time-dependent framework for filtering the extracted rules over time. The proposed theory is applied on the maritime domain and is validated through extensive experimentation with real sensor streams originating from large-scale sensor networks deployed in ships.

show abstract

Section: Event Predictionmentioning

confidence: 99%

Event correlation and forecasting over high-dimensional streaming sensor data

Papataxiarhis

Hadjiefthymiades

2018

2018 14th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

View full text Add to dashboard Cite

show abstract

“…There has also been a large amount of research in KRR temporal reasoning techniques with approaches derived from the event calculus (EC) being particularly well suited to SU reasoning [14]. Modern approaches combining EC with probabilistic logic programming [15] seem particularly promising to address both T L and U H attributes.…”

Section: Mapping Csu Problem Attributes To CC Approachesmentioning

confidence: 99%

Cognitive computing for coalition situational understanding

Preece

Cerutti

Braines

et al. 2017

2017 IEEE SmartWorld, Ubiquitous Intelligence &Amp; Computing, Advanced &Amp; Trusted Computed, Scalable Computing &Amp; Commun

View full text Add to dashboard Cite

Abstract-The term cognitive computing (CC) refers to computer systems that harness multiple techniques from artificial intelligence (AI) and signal processing (SP). Situational understanding (SU) involves creating and reasoning about models of an environment and events. Coalition operations are defined by multiple partners seeking to achieve a common purpose. This paper characterises the SU problem in a coalition operations context -coalition situational understanding (CSU) -in terms of a set of problem attributes. The paper argues that CSU problems require CC system solutions involving a hybrid of AI and SP approaches. The paper outlines some of the architectural choices for CC CSU systems.

show abstract

“…For CHR with and without priorities, there is a more realistic sophisticated metacomplexity result derived from the Logical Algorithms (LA) formalism [33]. For CHR with and without priorities, there is a more realistic sophisticated metacomplexity result derived from the Logical Algorithms (LA) formalism [33].…”

Section: Termination and Time Complexity Analysismentioning

confidence: 99%

“…Inductive logic programming algorithms are one obvious candidate for this purpose, because they allow to operate in more expressive, relational logical frameworks such as RDF 2 or OWL 3 , which form the backbone of the Semantic Web [33,34]. However, their expressiveness has to be paid for with a high computational complexity.…”

Section: Applications In Linked Data and Semantic Webmentioning

confidence: 99%

“…In [32], each input event is defined as a set of alternatives, each with its occurrence probability, with all alternatives summing to a probability value of 1, or less than 1 if non-occurrence is possible. Skarlatidis et al [33] represent and reason over probabilistic data streams using the ProbLog logic programming framework [16]. This degree is propagated to a Markov Logic Network [11] expressing the complex event patterns using weighted utility formulas.…”

Section: Event Recognition Under Uncertaintymentioning

confidence: 99%

See 1 more Smart Citation

Rule Technologies: Foundations, Tools, and Applications

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The Semantic Web uses ontologies to associate meaning to Web content so machines can process it. One inherent problem to this approach is that, as its popularity increases, there is an ever growing number of ontologies available to be used, leading to difficulties in choosing appropriate ones. With that in mind, we created a system that allows users to evaluate ontologies/rules. It is composed by the Metadata description For Ontologies/Rules (MetaFOR), an ontology in OWL, and a tool to convert any OWL ontology to MetaFOR. With the MetaFOR version of an ontology, it is possible to use SWRL rules to identify anomalies in it. These can be problems already documented in the literature or user defined ones. SWRL is familiar to users, so it is easier to define new project specific anomalies. We present a case study where the system detects 9 problems, from the literature, and two user defined ones.

show abstract

A probabilistic logic programming event calculus

Cited by 43 publications

References 34 publications

Event correlation and forecasting over high-dimensional streaming sensor data

Event correlation and forecasting over high-dimensional streaming sensor data

Cognitive computing for coalition situational understanding

Rule Technologies: Foundations, Tools, and Applications

Contact Info

Product

Resources

About