Machine Learning for High-Precision Indoor Localization

View at publisher Summarise with VIRAT
Authors: Xiaotian Zhao, Mashida Dangsalae, Apidet Booranawong, Nattha Jindapetch
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This chapter introduces the application of machine learning for high-precision indoor localization in advanced systems designed for multi-building and multi-floor environments. It provides a foundational overview of ML techniques relevant to RSSI-based localization using Wi-Fi fingerprinting. The developed system utilizes ML models such as kNN, CNN, and LSTM to effectively manage high-dimensional and nonlinear data. Additionally, system enhancements—including dataset dimensionality reduction and the combination of CNN, LSTM, and stacking methods—further improve localization accuracy in complex indoor settings. This work lays the groundwork for building efficient, scalable, and robust indoor positioning systems for future applications.

Fields of Study & Subjects

Indoor and Outdoor Localization Technologies Optical Wireless Communication Technologies Human Mobility and Location-Based Analysis

Publication details

Journal / source
CRC Press eBooks
Pages
160–204
Publication date
23 March 2026
Language
EN
Document type
Book chapter