Article: UWB time of flight-based indoor IoT localisation solution with deep learning optimised by meta-heuristics Journal: International Journal of Sensor Networks (IJSNET) 2024 Vol.44 No.2 pp.99 - 123 Abstract: Nowadays, indoor localisation is among the most important challenges in IoT networks. Furthermore, deep learning techniques are emerging as a leading method. Additionally, meta-heuristic algorithms attract several research domains due to its efficiency in resolving optimisation problems. In this work, a deep learning model optimised by meta-heuristic algorithms and based on time of flight (ToF) measurements captured by ultra-wide band technology, as an indoor IoT localisation solution, is proposed. The findings showed that optimisation with the grey wolf optimiser can accelerate convergence towards optimal parameters during the learning phase. Compared with three among recent and widely applied localisation solutions, the suggested solution provided more accurate positions of the IoT mobile object as it yielded better results in terms of localisation accuracy (98.92%), mean absolute error (0.057 m) and mean squared error (0.0095 m). In addition to standard comparisons, inferential statistical procedures were employed to emphasise the superior performance of the proposed approach. Inderscience Publishers - linking academia, business and industry through research

Title: UWB time of flight-based indoor IoT localisation solution with deep learning optimised by meta-heuristics

Authors: Sihem Tlili; Sami Mnasri; Thierry Val

Addresses: UT2J, CNRS-IRIT (RMESS), University of Toulouse II, Toulouse, France; Faculty of Science of Gafsa, University of Gafsa, Gafsa, Tunisia ' Applied College, University of Tabuk, Tabuk 47512, KSA; CNRS-IRIT (RMESS), University of Toulouse II, Toulouse, France ' UT2J, CNRS-IRIT (RMESS), University of Toulouse II, Toulouse, France

Abstract: Nowadays, indoor localisation is among the most important challenges in IoT networks. Furthermore, deep learning techniques are emerging as a leading method. Additionally, meta-heuristic algorithms attract several research domains due to its efficiency in resolving optimisation problems. In this work, a deep learning model optimised by meta-heuristic algorithms and based on time of flight (ToF) measurements captured by ultra-wide band technology, as an indoor IoT localisation solution, is proposed. The findings showed that optimisation with the grey wolf optimiser can accelerate convergence towards optimal parameters during the learning phase. Compared with three among recent and widely applied localisation solutions, the suggested solution provided more accurate positions of the IoT mobile object as it yielded better results in terms of localisation accuracy (98.92%), mean absolute error (0.057 m) and mean squared error (0.0095 m). In addition to standard comparisons, inferential statistical procedures were employed to emphasise the superior performance of the proposed approach.

Keywords: internet of things; IoT; indoor localisation; meta-heuristic optimisation; ultra-wide band; UWB; time of flight; ToF; grey wolf optimiser; arithmetic optimisation algorithm.

DOI: 10.1504/IJSNET.2024.136695

International Journal of Sensor Networks, 2024 Vol.44 No.2, pp.99 - 123

Received: 23 Jun 2023
Accepted: 31 Oct 2023
Published online: 16 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: UWB time of flight-based indoor IoT localisation solution with deep learning optimised by meta-heuristics

Keep up-to-date