ML-Based Hybrid Approach for Improved Indoor Source Localization.

Saved in:

Bibliographic Details
Title:	ML-Based Hybrid Approach for Improved Indoor Source Localization.
Authors:	Rao, Soma Simritha¹, Sumana, Madhireddy¹, Sarma, Achanta Dattatreya¹ ad_sarma@yahoo.com, Sridher, Tunguturi¹, Lakshmanna, Kuruva¹
Source:	Progress in Electromagnetics Research C. 2025, Vol. 158, p253-260. 8p.
Subjects:	Wireless localization, Indoor positioning systems, System integration, Wireless geolocation systems, K-nearest neighbor classification
Abstract:	The field of navigation has been relentlessly evolving to fulfil its long-standing objective of building a highly accurate universal navigation system. However, in highly urban and indoor locations, line-of-sight signals cannot be guaranteed, and conventional terrestrial-based and satellite-based techniques cannot perform optimally. This paper strives to establish navigation via signals of opportunity (NAVSOP) by proposing a Wireless Fidelity (Wi-Fi)-based indoor localization method using Received Signal Strength Indicator (RSSI) technique. This proposed method employs fingerprinting along with the K-Nearest Neighbour (KNN) and again KNN with Inverse Distance Weighting (IDW) approach to offer superior position estimation accuracy. In this paper, we develop a new neighbourhood dataset by expanding target neighbourhood locations by random point generator algorithm, thereby propounding the utility of NAVSOP for indoor environments to enable future navigation applications in real-world civilian and military domains. The results obtained via the novel IDW approach give a reduced uncertainty in position error estimation of 0.68 m as compared to the traditional approaches of fingerprinting with KNN (1.13 m) and trilateration (2.3 m). [ABSTRACT FROM AUTHOR]
	Copyright of Progress in Electromagnetics Research C is the property of Electromagnetics Academy and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The field of navigation has been relentlessly evolving to fulfil its long-standing objective of building a highly accurate universal navigation system. However, in highly urban and indoor locations, line-of-sight signals cannot be guaranteed, and conventional terrestrial-based and satellite-based techniques cannot perform optimally. This paper strives to establish navigation via signals of opportunity (NAVSOP) by proposing a Wireless Fidelity (Wi-Fi)-based indoor localization method using Received Signal Strength Indicator (RSSI) technique. This proposed method employs fingerprinting along with the K-Nearest Neighbour (KNN) and again KNN with Inverse Distance Weighting (IDW) approach to offer superior position estimation accuracy. In this paper, we develop a new neighbourhood dataset by expanding target neighbourhood locations by random point generator algorithm, thereby propounding the utility of NAVSOP for indoor environments to enable future navigation applications in real-world civilian and military domains. The results obtained via the novel IDW approach give a reduced uncertainty in position error estimation of 0.68 m as compared to the traditional approaches of fingerprinting with KNN (1.13 m) and trilateration (2.3 m). [ABSTRACT FROM AUTHOR]
ISSN:	19378718
DOI:	10.2528/PIERC25043004