Artificial Intelligence-Based Classification of Multipath Types for Vehicular Localization in Dense Environments

Citation

Bakhuraisa, Yaser A. and Abd. Aziz, Azlan and Tan, Kim Geok and Mahmud, Azwan and Ahmad Kayani, Aminuddin and Noor, Noor Maizura (2024) Artificial Intelligence-Based Classification of Multipath Types for Vehicular Localization in Dense Environments. International Journal of Integrated Engineering, 16 (2). pp. 93-101. ISSN 2229-838X

[img] Text
10.+15833+93-101.pdf - Published Version
Restricted to Repository staff only

Download (760kB)

Abstract

Multipath-geometry is a promising approach for vehicular localization in line of sight (LOS) and non-line of sight (NLOS) scenarios. In this approach, identifying the type of the propagated multipath components (MPCs) is an important preliminary stage. However, identifying the type of the MPC in dense multipath environments is challenging. The previous works proposed iterative methods for this task. These iterative methods have their limitations such as required more in-depth analysis and high complexity of computation. However, by leveraging artificial intelligence advantages, a lower complexity identification method is proposed in this work. We utilized supervised learning algorithms to distinguish the direct link, first-order, and higher-order MPs of millimeter-Wave Vehicle-to-Infrastructure (V2I) communication. In particular, four algorithms namely KNN, and SVM, MLP, and LSTM have been applied. The characteristics of the multipath component including received signal strength and elevation and azimuth angle of arrival are considered as features to train the proposed models. The results showed that the accuracy rates of the classification are ranged between 96.70% and 84.0%. The best accuracy rate was 96.70% obtained by LSTM, followed by 94.47 % obtained by MLP. Whereas, 93.67% and 84.0% accuracy rats were achieved by KNN and SVM respectively

Item Type: Article
Uncontrolled Keywords: V2I, mm-wave, machine learning, classification, multipath component
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 03 Jul 2024 03:28
Last Modified: 03 Jul 2024 03:28
URII: http://shdl.mmu.edu.my/id/eprint/12596

Downloads

Downloads per month over past year

View ItemEdit (login required)