Advances in Indoor Positioning Systems and Their Application to the Internet of Things (IoT)

Dear Colleagues,

Satellite navigation systems, such as GPS, Galileo, GLONASS or BeiDou, are, in most cases, unable to operate properly inside buildings or underground and often totally lose the ability to locate the object or person of interest. This means that work on the development of sensors that allow the location of people and objects inside buildings, or underground, has become a field of research of enormous interest, since exact positioning indoors is usually as important as that outdoors and, in some cases, such as for health or safety issues, even more so.

Different techniques have been developed during the last few years for solving this problem, based on different technologies whose theoretical bases fundamentally differ because of the types of sensors that are intended to be implemented over them, which can be divided into two main categories: sensors developed specifically for indoor positioning, such as inertial indoor positioning systems, and devices designed for other uses that can be used or adapted for solving the indoor positioning problem.

However, the problem is far from being solved, because newly developed, specific positioning sensors and all the current devices that can be used as positioning sensors are continually being developed, and they offer new possibilities that allow new advances in addressing the indoor positioning problem. Some of the ways in which the advances can be obtained are, for example, the development of the specific sensors themselves; the adaptation of all the used devices to the solution of the indoor positioning problem, incorporating the necessary features; and the analytics and machine learning techniques that can be developed to improve the exactitude in positioning.

With the fast and extensive development that data science and big data technologies have experienced in the last few years—in the application of their knowledge to solve the problem of the treatment of big data, allowing dealing with enormous amounts of data, the problem of indoor position has garnered even more interest, because the data science discipline includes a Knowledge Area Group (KAG) on data engineering that deals with all the knowledge related to the development of the infrastructure that allows collecting and processing data from the sensors, and this includes the development of sensor networks and edge infrastructure for gathering sensor data, the connections between the sensors and the data centers, the ELT (extract–load–transfer) data pipeline using data lakes storage, and other areas.

The development of data science has been associated with the development of another area called the Internet of Things, which is focused on all the knowledge related to data coming from connected objects, and this is directly related to the case of indoor positioning (as well as outdoor positioning) because the positioning problem is really the exact positioning of the sensors. When working with data science and IoT problems, the research problems will be, in many cases, machine learning problems, so that discipline is also involved in the indoor positioning problem.

From the above, this Special Issue invites contributions on the following topics (but is not limited to them):

Indoor positioning sensor hardware;
Indoor positioning sensor software;
The adaptation of devices made for other purposes to indoor positioning hardware;
The adaptation of devices made for other purposes to indoor positioning hardware;
Indoor positioning data engineering;
Indoor positioning data analytics;
The data fusion of indoor positioning distributed sensors;
Context definition and management;
Machine learning techniques;
The integration of IA techniques;
Twin systems based on indoor positioning systems;
Real-time data collection from indoor positioning systems;
Software engineering for indoor positioning data systems;
Human–computer interaction;
Visual pattern recognition;
Environment modelling and reconstruction from images;
Surveillance systems;
Big data analytics platforms and tools for data fusion and analytics;
Cloud computing technologies and their use for indoor positioning systems;
The optimization of sensor network and edge computing infrastructure, and the connectivity between edge facilities and cloud datacenters;
5G radio access and end-to-end network slicing optimization.

Prof. Dr. Juan J. Cuadrado-Gallego
Prof. Dr. Yuri Demchenko
Guest Editors