Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Association Rule Learning from Time Series Data and Knowledge Graphs

Erkan Karabulut, Victoria Degeler, Paul Groth

TL;DR

Initial evaluation shows that the proposed approach is able to learn a high number of association rules with semantic information which are more generalizable and set a foundation for further work on using semantic association rule learning especially in the context of industrial applications.

Abstract

Digital Twins (DT) are a promising concept in cyber-physical systems research due to their advanced features including monitoring and automated reasoning. Semantic technologies such as Knowledge Graphs (KG) are recently being utilized in DTs especially for information modelling. Building on this move, this paper proposes a pipeline for semantic association rule learning in DTs using KGs and time series data. In addition to this initial pipeline, we also propose new semantic association rule criterion. The approach is evaluated on an industrial water network scenario. Initial evaluation shows that the proposed approach is able to learn a high number of association rules with semantic information which are more generalizable. The paper aims to set a foundation for further work on using semantic association rule learning especially in the context of industrial applications.

Semantic Association Rule Learning from Time Series Data and Knowledge Graphs

TL;DR

Initial evaluation shows that the proposed approach is able to learn a high number of association rules with semantic information which are more generalizable and set a foundation for further work on using semantic association rule learning especially in the context of industrial applications.

Abstract

Digital Twins (DT) are a promising concept in cyber-physical systems research due to their advanced features including monitoring and automated reasoning. Semantic technologies such as Knowledge Graphs (KG) are recently being utilized in DTs especially for information modelling. Building on this move, this paper proposes a pipeline for semantic association rule learning in DTs using KGs and time series data. In addition to this initial pipeline, we also propose new semantic association rule criterion. The approach is evaluated on an industrial water network scenario. Initial evaluation shows that the proposed approach is able to learn a high number of association rules with semantic information which are more generalizable. The paper aims to set a foundation for further work on using semantic association rule learning especially in the context of industrial applications.
Paper Structure (7 sections, 2 figures, 1 table, 1 algorithm)

This paper contains 7 sections, 2 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Semantic Rule Learning and Inference Pipeline
  3. A Naive Semantic Rule Learning Approach - Naive SemRL
  4. Preliminary Evaluation and Industrial Use Case
  5. A Semantic Rule Quality Criterion
  6. Industrial Use Case
  7. Conclusions and Future Work

Figures (2)

  • Figure 1: Semantic association rule learning and inference pipeline.
  • Figure 2: KG construction example for a drinking water network scenario.

Theorems & Definitions (1)

  • Definition 4.1: Semantic Expressivity