Mobile Device Localization in 5G Wireless Networks (original) (raw)

Environment-Aware Location Estimation in Cellular Networks

We propose a novel mobile positioning algorithm for cellular networks based on the estimation of the radio propagation environment. Since radio propagation characteristics vary in different environments, knowing the environment of the mobile user is essential for accurate Received Signal Strength- (RSS-) based location estimation. The key feature of our method is its capability to estimate the environment of themobile user using machine learning techniques and to utilize this information for enhancing RSSbased distance calculations. The proposed algorithm, namely, EARBALE, has been evaluated using field measurements collected from a GSM network in diverse geographic locations. Our approach turns out to be significantly beneficial, enhancing estimation accuracy, and thereby enabling high-performance mobile positioning in a practical and cost-effective manner. Additionally, it is computationally light-weight and can be integrated onto any RSS-based algorithm as an enhancement add-on.

Automatic Positioning of Mobile Users via GSM Signal Measurements

Automatic Positioning of Mobile Users via GSM Signal Measurements, 2021

Today the need for mobile communication systems and the high increase in the number of users have also made the development of new generation mobile applications indispensable. Obtaining location information has been one of the most interesting and significant areas of improvement. The purpose of the services used to determine the location is generally to obtain the information of the users such as approximate location, speed, and time. The GPS is the most preferred and globally accurate positioning system among global positioning systems. However, in addition high installation cost of the system; galactic and meteorological factors, high buildings, other physical obstacles, and especially indoor areas are some of the main constraints that can lead to serious signal degradation and losses which may cause the system to be out of service. In this context, there is an urgent need for positioning systems that will be alternative and complementary to global positioning systems. The cellular network is widely used by almost everyone and its coverage area is increasing day by day. The network has been trained and tested in the simulation environment using machine learning algorithms, namely, extreme learning machine (ELM), generalized regression neural network (GRNN), and nearest neighborhood (NN). When compared to other cellular localization methods in the literature, the proposed system performs positioning with much higher accuracies with distance error rates below a meter (m) at minimum, and between 76-216 m on average. The test results show that it can successfully localize the mobile users with a significant accuracy for indoor, where GPS signals are very weak or cannot be received at all; and it can also stand in the breach for outdoor, where GPS may be disabled for different reasons.

Localization of LTE Measurement Records with Missing Information

INFOCOM, 2016

As cellular networks like 4G LTE networks get more and more sophisticated, mobiles also measure and send enormous amount of mobile measurement data (in TBs/week/metropolitan) during every call and session. The mobile measurement records are saved in data center for further analysis and mining, however, these measurement records are not geo-tagged because the measurement procedures are implemented in mobile LTE stack. Geo-tagging (or localizing) the stored measurement record is a fundamental building block towards network analytics and troubleshooting since the measurement records contain rich information on call quality, latency, throughput, signal quality, error codes etc. In this work, our goal is to localize these mobile measurement records. Precisely, we answer the following question: what was the location of the mobile when it sent a given measurement record? We design and implement novel machine learning based algorithms to infer whether a mobile was outdoor and if so, it infers the latitude-longitude associated with the measurement record. The key technical challenge comes from the fact that measurement records do not contain sufficient information required for triangulation or RF fingerprinting based techniques to work by themselves. Experiments performed with real data sets from an operational 4G network in a major metropolitan show that, the median accuracy of our proposed solution is around 20 m for outdoor mobiles and outdoor classification accuracy is more than 98%.

BeamMaP: Beamforming-based Machine Learning for Positioning in Massive MIMO Systems

2019

Existing positioning techniques can mostly overcome problems caused by path loss, background noise and Doppler effects, but multiple paths in complex indoor or outdoor environments present additional challenges. In this paper, we propose BeamMaP that can instantaneously locate users after training input data and steer the beams efficiently in a distributed massive Multiple-Input Multiple-Output (MIMO) system. To simulate a realistic environment, we evaluate the positioning accuracy with channel fingerprints collected from uplink Received Signal Strength (RSS) data, including Line-of-Sight (LoS) and Non-Lineof-Sight (NLoS), in the training data sets. Based on the adaptive beamforming, we employ the Rice distribution to sample the current mobile users locations in the testing data sets. Our simulation results achieve Reduced Root-Mean-Squared Estimation Error (RMSE) performance with increasing volume of training data. We prove our proposed model is more efficiency and steady in the po...

Position location based on measurement reports in LTE cellular networks

2018 IEEE 19th Wireless and Microwave Technology Conference (WAMICON), 2018

This paper proposes a new method to estimate the accuracy of locating LTE cellular subscribers. The proposed method is hybrid network-based method; it depends on the Reference Signal Received Power (RSRP) measurements and the predicted cell serving area. It uses LTE measurements and cell information, together with a simple predictive model, for the user equipment (UE) geo-location in two dimensions plan. The proposed work is evaluated by comparing estimations with Global Positioning System measurements in various scenarios determined by the number of sectors and sites that UE simultaneously reports. The root mean square error is calculated for the method validation. The main result shows how the location accuracy depends on the number of reported sectors and sites.

Machine Learning-based Advance d Localization Method in Wireless Communication

2018

In existing localization research area, most of the localization methods suffer from propagation loss because of multi-path effects and sensitivity of the components of wireless technology, e.g. Received Signal Strength Indicator (RSSI). It is leading to miss estimation of localization methods and degradation of estimation accuracy. In this paper, a new advance localization method is proposed in different point of view. Knearest neighbor (KNN) algorithm is adopted to get the best estimation accuracy and RSSI is used as main feature for estimating unknown position of mobile user. We extend to estimate a circle region instead of one coordinate position with the aid of circle theory as a new idea. The objective of this research is to improve the accuracy of localization methods and to mitigate the sensitivity of the existing methods. In this study, an advance localization method is proposed by considering existing finger printing method from a different point of view. In addition, Radi...