FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

QL-CBR hybrid approach for adapting context-aware services

Downloads

Downloads per month over past year

Belaidouni, Somia, Miraoui, Moeiz and Tadj, Chakib. 2022. « QL-CBR hybrid approach for adapting context-aware services ». Computer Systems Science and Engineering, vol. 43, nº 3. pp. 1085-1098.

[thumbnail of Tadj-C-2022-24515.pdf]
Preview
PDF
Tadj-C-2022-24515.pdf - Published Version
Use licence: Creative Commons CC BY.

Download (2MB) | Preview

Abstract

A context-aware service in a smart environment aims to supply services according to user situational information, which changes dynamically. Most exist- ing context-aware systems provide context-aware services based on supervised algorithms. Reinforcement algorithms are another type of machine-learning algo- rithm that have been shown to be useful in dynamic environments through trial- and-error interactions. They also have the ability to build excellent self-adaptive systems. In this study, we aim to incorporate reinforcement algorithms (Q-learn- ing) into a context-aware system to provide relevant services based on a user’s dynamic context. To accelerate the convergence of reinforcement learning (RL) algorithms and provide the correct services in real situations, we propose a com- bination of the Q-learning and case-based reasoning (CBR) algorithms. We then analyze how the incorporation of CBR enables Q-learning to become more effi- cient and adapt to changing environments by continuously producing suitable ser- vices. Simulation results demonstrate the effectiveness of the proposed approach compared to the traditional CBR approach.

Item Type: Peer reviewed article published in a journal
Professor:
Professor
Tadj, Chakib
Affiliation: Génie électrique
Date Deposited: 16 Jun 2022 20:33
Last Modified: 23 Jun 2022 15:47
URI: https://espace2.etsmtl.ca/id/eprint/24515

Actions (login required)

View Item View Item