The main purpose of this research is to improve localization accuracy of an active Radio Frequency Identification, RFID tag, in 3D indoor space. The paper presents a new RFID based 3D Indoor Positioning System which shows performance improvement. The proposed positioning system combines two methods: the Scene Analysis technique and Artificial Neural Network. The results of both simulation using Log-Distance Path Loss Model and physical experiments validate that the proposed positioning system improves the localization accuracy of an RFID tag compared with well-known Scene Analysis technique solutions

The purpose of this research is to find an optimal number and configuration of readers in RFID based 3D Indoor Positioning System. The system applies a Hybrid Scene Analysis - Neural Network algorithm to estimate target's position with a desired accuracy. The system's accuracy and cost depend on a number of utilized readers and their arrangement. Readers' deployment is crucial for the localization accuracy too. The system optimization enhances the system cost-efficiency. The arrangement analysis was based on simulations and validated by physical experiment. The results of this research define a trade-off between a number of readers and their deployment and the system performance in terms of localization accuracy.

The purpose of this research is to improve performance of the Hybrid Scene Analysis - Neural Network indoor localization algorithm applied in Real-time Locating System, RTLS. A properly customized structure of Neural Network and training algorithms for specific operating environment will enhance the system’s performance in terms of localization accuracy and precision. Due to nonlinearity and model complexity, a heuristic analysis is suitable to evaluate NN performance for different environmental conditions. Efficiency of the proposed customization of a Neural Network is verified by simulations and validated by physical experiments. This research also concerns the influence of size of Neural Network training set. The results prove that, better localization accuracy is with a NN system which is properly customized with respect to a training method, number of neurons and type of transfer function in the hidden layer and also type of transfer function in the output layer.

Real-time Locating Systems (RTLSs) have the ability to precisely locate the position of things and people in real time. They are needed for security and emergency applications, but also for healthcare and home care appliances. The research aims for developing an analytical method to customize RTLSs, in order to improve localization performance in terms of precision. The proposed method is based on Angle of Arrival (AoA), a ranging technique and fingerprinting method along with an analytically defined uncertainty of AoA, and a localization uncertainty map. The presented solution includes three main concerns: geometry of indoor space, RTLS arrangement, and a statistical approach to localization precision of a pair of location sensors using an AoA signal. An evaluation of the implementation of the customized RTLS validates the analytical model of the fingerprinting map. The results of simulations and physical experiments verify the proposed method. The research confirms that the analytically established fingerprint map is the valid representation of RTLS’ performance in terms of precision. Furthermore, the research demonstrates an impact of workspace geometry and workspace layout onto the RTLS’ performance. Moreover, the studies show how the size and shape of a workspace and the placement of the calibration point affect the fingerprint map. Withal, the performance investigation defines the most effective arrangement of location sensors and its influence on localization precision. © 2016 by the authors; licensee MDPI, Basel, Switzerland.

The increased potential and effectiveness of Real-time Locating Systems (RTLSs) substantially influence their application spectrum. They are widely used, inter alia, in the industrial sector, healthcare, home care, and in logistic and security applications. The research aims to develop an analytical method to customize UWB-based RTLS, in order to improve their localization performance in terms of accuracy and precision. The analytical uncertainty model of Angle of Arrival (AoA) localization in a 3D indoor space, which is the foundation of the customization concept, is established in a working environment. Additionally, a suitable angular-based 3D localization algorithm is introduced. The paper investigates the following issues: the influence of the proposed correction vector on the localization accuracy; the impact of the system’s configuration and LS’s relative deployment on the localization precision distribution map. The advantages of the method are verified by comparing them with a reference commercial RTLS localization engine. The results of simulations and physical experiments prove the value of the proposed customization method. The research confirms that the analytical uncertainty model is the valid representation of RTLS’ localization uncertainty in terms of accuracy and precision and can be useful for its performance improvement. The research shows, that the Angle of Arrival localization in a 3D indoor space applying the simple angular-based localization algorithm and correction vector improves of localization accuracy and precision in a way that the system challenges the reference hardware advanced localization engine. Moreover, the research guides the deployment of location sensors to enhance the localization precision.