Localization Approach Based on Ray-Tracing Simulations and Fingerprinting Techniques for Indoor–Outdoor Scenarios

Abstract

The increase of the technology related to radio localization and the exponential rise in the data traffic demanded requires a large number of base stations to be installed. This increase in the base stations density also causes a sharp rise in energy consumption of cellular networks. Consequently, energy saving and cost reduction is a significant factor for network operators in the development of future localization networks. In this paper, a localization method based on ray-tracing and fingerprinting techniques is presented. Simulation tools based on high frequencies are used to characterize the channel propagation and to obtain the ray-tracing data. Moreover, the fingerprinting technique requires a costly initial learning phase for cell fingerprint generation (radio-map). To estimate the localization of mobile stations, this paper compares power levels and delay between rays as cost function with different distance metrics. The experimental results show that greater accuracy can be obtained in the location process using the delay between rays as a cost function and the Mahalanobis distance as a metric instead of traditional methods based on power levels and the Euclidean distance. The proposed method appears well suited for localization systems applied to indoor and outdoor scenarios and avoids large and costly measurement campaigns.

Improving the performance of a radio-frequency localization system in adverse outdoor applications

“…The results from simulation scenario shows that both random forest and gradient boosting (implemented as XGBoost) obtains suitable performance evaluated as mean distance error from true value. These results, 1.38 m for random forest and 2.52 m for gradient boosting, are consistent with results that used only simulation data as found in [25,[39][40][41].…”

Tuning Selection Impact on Kriging-Aided In-Building Path Loss Modeling

“…Therefore, in order to identify a feasible amount of tuning samples from a measurement campaign with practical separation sampling distance, Fig. 6 describes the cost function in terms of Euclidean distance [16] to select the minimum value of the curves-i.e., the minimum cost in terms of MAE, tuning samples and separation distance-calculated as follows…”

Fingerprint Feature Extraction for Indoor Localization

“…Alternatively, we may need to use different RF technologies to develop novel localization methods for specific location-based applications that require centimeter or even sub-centimeter accuracy. In the future, we plan to investigate fingerprint-based methods [ 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 ] using different RF technologies, as described below.…”

“…Many fingerprint-based localization methods rely on RF fingerprints to achieve the submeter, centimeter, or even sub-centimeter level of localization accuracy. Those methods use different RF technologies, including the Wi-Fi frequency-hopping approach [ 45 ], UWB spatial signal prediction [ 46 ], IEEE 802.11ad mmWaves [ 47 ], 5G massive MIMO [ 48 , 49 ], cellular time-reversal technique [ 50 ], Wi-Fi channel responses from multiple OFDM subcarriers [ 51 ], Wi-Fi time-reversal radio transmission [ 52 ], Wi-Fi ray tracing [ 53 ], BLE ray tracing [ 41 ], and 6G reconfigurable intelligent surface (RISs) [ 54 , 55 ]. Three types of diversities are adopted by the methods to ink fingerprints, which are spatial diversity [ 47 , 48 , 49 ], spectral diversity [ 45 , 46 , 50 , 51 , 52 ], and configurational diversity [ 54 , 55 ].…”