Artificial Intelligence in Wireless Positioning System: Taxonomy and Recent Framework

Abstract

The diversity of technologies and approaches in Wireless Positioning Systems (WPS) necessitates a structured taxonomy to better understand their capabilities and limitations. Recent advancements in Artificial Intelligence (AI) have significantly enhanced the accuracy and efficiency of WPS by leveraging sophisticated frameworks. The traditional reliance on signal-based metrics, such as received signal strength (RSS), faces significant challenges in adapting to environmental dynamics and mitigating inaccuracies, highlighting the critical role of Artificial Intelligence (AI) in developing more intelligent and adaptive frameworks within Wireless Positioning Systems (WPS). This paper aims to identify and analyze the potential of AI-enhanced WPS frameworks in improving accuracy and robustness, with a specific focus on Wi-Fi and RSS-based methods such as signal fingerprinting technique. The methods taken to characterize the taxonomy include Systematic Literature Review (SLR) and Bibliometric Analysis to identify, categorize, and analyze WPS frameworks that leverage AI to process RSS data and improve position estimation. This study provides a structured taxonomy and highlights the transformative impact of AI in refining WPS based on Wi-Fi and RSS. The findings underscore the potential of AI-driven approaches to address current challenges in wireless positioning, paving the way for more robust and scalable systems. The proposed taxonomy and insights provide a foundation for future research and practical applications, offering pathways to more precise, efficient, and adaptable WPS frameworks.