A Survey of Machine Learning in Pedestrian Localization Systems: Applications, Open Issues and Challenges

Abstract

With the popularization of machine learning (ML) techniques and the increased chipset's performance, the application of ML to pedestrian localization systems has received significant attention in the last years. Several survey papers have attempted to provide a state-of-the-art overview, but they usually limit their scope to a particular type of positioning system or technology. In addition, they are written from the point of view of ML techniques and their practice, not from the point of view of the localization system and the specific problems that ML techniques can help to solve. This article is intended to offer a comprehensive state-of-the-art survey of the ML techniques that have been adopted over the last ten years to improve the performance of pedestrian localization systems, addressing the applicability of ML techniques in this domain, along with the main localization strategies. It concludes by indicating the underlying open issues and challenges associated with the existing systems, and possible future directions in which ML techniques could improve the performance of pedestrian localization systems. Among other open issues, most previous authors have focused their attention on position estimation accuracy, which wastes the potential of ML techniques to improve other performance parameters (e.g., response time, computational complexity, robustness, scalability or energy efficiency). This study shows that there is a strong trend towards the application of supervised learning. Consequently, there are many potential research opportunities in the use of other learning types, such as unsupervised and reinforcement learning, to improve the performance of pedestrian localization systems.

A Tutorial on Terahertz-Band Localization for 6G Communication Systems

“…However, this category can only perform data preprocessing, and location information cannot be obtained. [38]- [40], [42], [209], [210]. In summary, despite the channel at THz frequencies being more deterministic than at lower frequencies, which suits geometry-based methods well, we argue that learning-based methods still have advantages in two aspects.…”

“…In terms of localization, a number of surveys exist and share the localization basics and performance metrics in common. However, their goals are totally different and their main focuses can be categorized based on the environment (indoor [32], [35], [39], [41], outdoor [2], [33], [44] or both), techniques (SLAM [2], MDS [36], machine learning (ML) [38]- [40], etc. ), and signal types (radio signal [5], [6], visible light [9], RFID [41], etc.).…”

“…The taxonomy of localization techniques will be detailed in Section II-A. From the application point of view, the localization systems for autonomous driving [2], [33], [44], emergency response [32], network tracking [5], device-free localization [34], and pedestrian localization [40] are surveyed. More recent works outlook the potential enablers in the B5G and 6G systems [42], show the localization potential with map-based techniques [43], describe basic localization algorithms for the 6G systems [8], and explore the fundamental limits of ISAC.…”

Feature-Based Generalized Gaussian Distribution Method for NLoS Detection in Ultra-Wideband (UWB) Indoor Positioning System

“…In brief, among the mentioned NLoS identification methods in the literature,the threshold difference between the first-path power and received power have been widely used in different ML algorithms [16], [32], [33]. In our analysis we will use the above 7 signal components to calculate our 4 key features which are the estimated distance by using equation (5), first path power level by equation ( 17), received power level by equation (18)and the power difference between the first and the received power level by equation (19).…”

Heterogeneous Transfer Learning for Wi-Fi Indoor Positioning Based Hybrid Feature Selection

“…Currently, more than 80% of the world’s population owns a smartphone [ 5 ], it is estimated that most people spend around 80% of their daily lives indoors [ 6 ], and 74% of smart device owners are active users of smartphone location-based applications [ 7 , 8 ]. The predominant use of location-based information is required for a variety of applications, including but not limited to: military use (originally designed for this purpose based on Global Positioning System (GPS)), shopping malls to guide customers to obtain services, hospitals to monitor patients for better health services, marketing to assist in the display of advertisements, emergency services, navigation, social networking services, multimedia geotagging, location and tourism, and so on [ 1 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ]. Although GPS receivers are known for their promising and dependable accuracy in an outdoor environment, their applications are limited to indoor positioning due to the complex nature of the indoor environment, which includes: no direct line of sight, poor GPS signal penetration through complex internal buildings, and severe internal channel conditions such as shadows and multipath fade [ 14 , 15 ].…”