Citation

Rizwan, Muhammad and Ng, Yin Hoe and Wong, Hin Yong and Tan, Chee Keong and Kurniawan, Tonni Agustiono (2025) Precise indoor localization using a lightweight 2D-CNN with adaptive temperature guided iterative self-knowledge distillation. Scientific Reports, 15 (1). ISSN 2045-2322

Text s41598-025-25589-x.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Fingerprint-based indoor localization leveraging Wi-Fi and Bluetooth received signal strength stands as a prominent infrastructure-less positioning technique. While positioning accuracy is essential, achieving it under practical deployment constraints remains a key challenge. Convolutional Neural Networks (CNNs), recognized for their robust pattern recognition capabilities, hold the potential to significantly enhance indoor positioning accuracy. However, the inherent architectural complexity of deep CNNs restricts their deployment on resource-constrained devices. Knowledge distillation (KD) offers a viable strategy by transferring of knowledge from a complex model to a simpler, more efficient one. This study proposes a novel lightweight 2D CNN architecture integrating squeeze-and-excitation (SE) modules with an adaptive temperature guided iterative self-knowledge distillation (SKD). The SE mechanism dynamically recalibrates CNN filter responses, prioritizing those capturing salient features, while the iterative SKD progressively refines the model’s performance during the training process. Unlike conventional KD approaches necessitating distinct teacher and student models, our proposed technique employs a single lightweight model, significantly reduces computational overhead. Empirical evaluation on the HDLC public datasets demonstrates that our architecture, without the incorporation of SKD, yields a notable 8.32% improvement in positioning accuracy over conventional CNNs, achieving a 3D average positioning error (APE) of 2.60 m. Furthermore, the integration of the iterative SKD strategy further enhances the positioning accuracy to 1.66%, resulting in a 3D APE of 2.24 m. These findings underscore the efficacy of the proposed framework as a resource-efficient and practical solution for accurate indoor localization, facilitating its real-time implementation on resource-constrained platforms.

Item Type:	Article
Uncontrolled Keywords:	3D convolutional neural network, Computational complexity, Indoor localization, Knowledge distillation, Receiver signal strength indicator
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Nurin Syazwani Azmi
Date Deposited:	10 Dec 2025 06:54
Last Modified:	13 Dec 2025 08:09
URII:	http://shdl.mmu.edu.my/id/eprint/15030

Downloads

Edit (login required)