Indoor Intelligent Fingerprint-Based Localization: Principles, Approaches and Challenges

TLDR

The rapid growth of IoT has driven widespread use of location‑based services, but GPS is ineffective indoors, prompting the development of various indoor localization methods, notably fingerprinting, which has attracted attention for its promising performance. This study surveys recent fingerprint‑based indoor localization technologies that employ machine learning and intelligent algorithms, and proposes an architecture that enables future systems to self‑adapt and self‑learn. We summarize and compare the working principles of state‑of‑the‑art systems on accuracy, latency, energy consumption, complexity, and robustness, and discuss challenges, potential solutions, and improvement measures. The proposed architecture demonstrates how advanced techniques can render indoor localization smarter.

Abstract

With the rapid development of Internet of Things (IoT) technology, location-based services have been widely applied in the construction of smart cities. Satellite-based location services have been utilized in outdoor environments, but they are not suitable for indoor technology due to the absence of global positioning system (GPS) signal. Therefore, many indoor localization technologies and systems have emerged by utilizing many other signals. In particular, fingerprinting localization has recently garnered attention because its promising performance. In this work, we aim to study recent indoor localization technologies and systems based on various fingerprints, which use machine learning and intelligent algorithms. We also present the architecture of intelligent localization. The development of indoor localization technology should have the ability of self-adaptation and self-learning in the future. And the architecture shows how to make localization become more "smart" by advanced techniques. The state-of-the-art localization systems' working principles are summarized and compared in terms of their localization accuracy, latency, energy consumption, complexity, and robustness. We also discuss the challenges of existing indoor localization technologies, potential solutions to these challenges, and possible improvement measures.