Prediction and Decision-Making in Intelligent Environments Supported by Knowledge Graphs, A Systematic Review.

Elvira Amador-Domínguez,Emilio Serrano,Juan F De Paz,Daniel Manrique

doi:10.3390/s19081774

Elvira Amador-Domínguez, Emilio Serrano + Show 2 more

Open Access

https://doi.org/10.3390/s19081774

Copy DOI

Abstract

Ambient Intelligence is currently a lively application domain of Artificial Intelligence and has become the central subject of multiple initiatives worldwide. Several approaches inside this domain make use of knowledge bases or knowledge graphs, both previously existing and ad hoc. This form of representation allows heterogeneous data gathered from diverse sources to be contextualized and combined to create relevant information for intelligent systems, usually following higher level constraints defined by an ontology. In this work, we conduct a systematic review of the existing usages of knowledge bases in intelligent environments, as well as an in-depth study of the predictive and decision-making models employed. Finally, we present a use case for smart homes and illustrate the use and advantages of Knowledge Graph Embeddings in this context.

Highlights

According to Augusto et al.: “An Intelligent Environment is one in which the actions of numerous networked controllers is orchestrated by self-programming pre-emptive processes in such a way as to create an interactive holistic functionality that enhances occupants experiences” [1]
We propose the use of Knowledge Graph Embeddings (KGE) in the particular case of smart homes
To illustrate some of the tasks that a KGE built over a knowledge graphs (KGs) can solve, we present the following scenario based on the idea presented by Fast et al [49]: Consider a house, composed of four separate rooms, each one provided with cameras

Summary

Introduction

According to Augusto et al.: “An Intelligent Environment is one in which the actions of numerous networked controllers is orchestrated by self-programming pre-emptive processes in such a way as to create an interactive holistic functionality that enhances occupants experiences” [1]. In this particular context the term “environment” is popularly associated with homes, it encompasses broader scenarios, such as buildings, streets or other areas. Intelligent environments are technologically based on the combination of several socio-technical innovations such as the Internet of Things (IoT), mobile Internet access, smartphones, data analytics, open data initiatives, and sharing economy models [2]. Developing responsive and smarter environments is one of the main present objectives, as shown by the number of research projects developed to pursue this goal, such as Km4City [3] or RoomPathy [4].

Methods

Results

Conclusion