Citation

Rizwan, Muhammad and Ng, Yin Hoe and Wong, Hin Yong and Tan, Chee Keong (2025) Enhancing Indoor Localization With Temporally-Aware Separable Group Shuffled CNNs and Skip Connections. IEEE Access, 13. pp. 30274-30286. ISSN 2169-3536

Text Enhancing Indoor Localization With Temporally-Aware Separable Group Shuffled CNNs and Skip Connections.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Fingerprint-based indoor localization is the predominant localization approach for GPSrestricted environments due to its minimal hardware requirements. However, its performance is affected by signal fluctuations caused by shadowing, fading, and multipath effect, which necessitates models capable of capturing temporal variations. Numerous machine learning and deep learning algorithms have been introduced to surmount this limitation, within which the convolutional neural network (CNN) stands out as the most prominent. The 1D and 2D CNN models developed for indoor localization have the ability to extract spatial features but not temporal, leading to degradation in online localization accuracy. In contrast to 2D CNNs, 3D CNNs possess the ability to extract spatio-temporal information, but their computational complexity precludes real-time implementation. In this paper, a novel 3D-separable CNN for indoor localization is designed using skip connections and group shuffling. By employing depth-wise and point-wise convolutions, separable convolutions significantly reduce computational complexity, achieving a 10-fold improvement over conventional convolution, which facilitating real-time applications at the cost of reduced accuracy. Incorporating skip connections and group shuffling can help offset this accuracy decline. The 2D CNN, 2D separable CNN, and 3D CNN are used as benchmarks and evaluated on the UJILIB public dataset. Numerical results reveal that the proposed model is able to attain a positioning accuracy of 66.28% with an average positioning error of 1.04 meters in distance. Compared to the 2D separable CNN, the proposed 3D separable CNN outperforms it by achieving a 24.03% lower average positioning error.

Item Type:	Article
Uncontrolled Keywords:	3D separable convolutional neural network, computational complexity, fingerprint
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	06 Mar 2025 02:32
Last Modified:	06 Mar 2025 02:32
URII:	http://shdl.mmu.edu.my/id/eprint/13600

Downloads

Edit (login required)