Smart buildings are becoming a new standard in construction, which allows for many possibilities to introduce ergonomics and energy savings. These contain simple improvements, such as controlling lights and optimizing heating or air conditioning systems in the building, but also more complex ones, such as indoor movement tracking of building users. One of the necessary components is an indoor localization system, especially without any device worn by the person being located. These types of solutions are important in locating people inside smart buildings, managing hospitals of the future and other similar institutions. The article presents a prototype of an innovative energy-efficient device for radio tomography, in which the hardware and software layers of the solution are presented. The presented example consists of 32 radio sensors based on a Bluetooth 5 protocol controlled by a central unit. The preciseness of the system was verified both visually and quantitatively by the image reconstruction as a result of solving the inverse tomographic problem using three neural networks.

This article presents research results on a smart building prediction, navigation and asset management system. The main goal of this work was to combine all comfort subsystems, such as lighting, heating or air conditioning control, into one coherent management system supported by navigation using radio tomographic imaging techniques and computational intelligence in order to improve the building’s ability to track users and then maximize the energy efficiency of the building by analyzing their behavior. In addition, the data obtained in this way were used to increase the quality of navigation services, improve the safety and ergonomics of using the room access control system and create a centralized control panel enriched with records of the working time of individual people. The quality of the building’s user habit learning is ensured by a network of sensors collecting environmental data and thus the setting values of the comfort modules. The advantage of such a complex solution is an increase in the accuracy of navigation services provided, an improvement in the energy balance, an improvement in the level of safety and faster facility diagnostics. The solution uses proprietary small device assemblies with implementation of popular wireless transmission standards such as Bluetooth, Wi-Fi, ZigBee or Z-Wave. These PANs (personal area networks) are used to update and transmit environmental and navigation data (Bluetooth), to maintain the connection of other PANs to the master server (Wi-Fi) and to communicate with specific end devices (ZigBee and Z-Wave).

This thesis describes the implementation of the author's ultra-wideband (UWB) marker system in terms of its use in large-scale warehousing, asset management and as an in-building navigation system. The work encompasses both the hardware solution and the software and algorithmic part

Industrial ultra-wideband (UWB) tags can share a limited ranging-update budget through gateway-side admission control. We evaluate an artificial intelligence (AI)-assisted priority rule that combines predictive uncertainty, nonlinear age of information (AoI), and a cold-start indicator, using dimensionally explicit coefficients. The dataset contains 166,142 cleaned range events from seven tags and eight anchors. Forecasting is evaluated on sessions held out in chronological order within each device. Replay draws 16 paired synthetic fleets of 100 virtual tags from 598 overlapping 80 s windows of three test sessions of one physical tag. Two state-update assumptions are compared. Under causal state updates using only recorded observations, the proposed priority rule does not outperform periodic scheduling at any evaluated budget from 5% to 40%; at a 20% evaluation budget, its mean absolute raw-range reconstruction error is 10.23% higher. At the same budget, retrospective replay with linearly interpolated state updates yields lower error (0.361 m versus 0.366 m) and an estimated matched-quality reduction of 2.49% in admitted evaluation cycles (95% paired-replay interval: 1.58–3.46%). This reduction is conditional on the interpolated retrospective replay assumptions, which use subsequent observations to reconstruct controller state non-causally. Admitted-cycle count serves only as a proxy for relative tag energy under an equal per-cycle cost assumption; electrical energy consumption was not directly measured. The replay evidence is limited to three physical sessions from a single device, so these findings do not establish generalizability to independent devices, environments, or simultaneous physical fleets.

The main idea of the presented work was to optimize the operation of commercial premises using personnel location data acquired with the help of radio tomography. This data was then processed by specialized artificial intelligence algorithms and used better to manage the building's energy resources and fixed assets. A prominent feature of the system is the use of the latest generation of Bluetooth LE and IEEE 802.11n technology, which, combined with machine learning mechanisms, led to creating of a flexible and versatile platform to support building operations.