Open AccessReal-time RSS-based positioning system using neural network algorithm
Author(s) -
Safae El Abkari,
Jamal El Mhamdi,
El Hassan El Abkari
Publication year - 2021
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v22.i3.pp1601-1610
Subject(s) - rss , artificial neural network , computer science , grid , signal strength , real time computing , process (computing) , algorithm , signal (programming language) , artificial intelligence , wireless sensor network , mathematics , computer network , geometry , programming language , operating system
Locating services have come under the spotlight in recent years in various applications. However, locating methods that use received signal strength have low accuracy due to signal fluctuations. For this purpose, we present a Wi-Fi based locating system using artificial neural network to enhance the positioning process performances. We optimized the Levenberg Marquardt algorithm to propose the better configuration of the multi-layer time-delay perception neural network. We achieved an average error of 10.3 centimeters with a grid of 0.4 meter in four tests. Yet, due to the instability of the received signal strength RSS-based locating systems present a limitation in the resolution finesse that depends on the grid size.