Nowadays, research and development of various indoor positioning systems (IPS) have been increasing owing to flourishing social and commercial interest in location-based services (LBSs). Among LBS technologies, we used the Bluetooth low energy beacon in our system, which consumes less energy and is embedded in many current smartphones and tablets. In particular, the fingerprinting method has become a prime choice in the design of IPS owing to its good location estimation and the fact that a line-of-sight from access points is not required. We propose an improved two-step fingerprinting localization using multiple fingerprint features to enhance the localization accuracy. The proposed system uses a propagation model to convert RSS of beacons to distance and estimate the weighted centroid (WC) of nearby beacons. The estimated WCs along with signal strength and rank of the nearby beacons are stored in the server database for localization instead of RSS from all the deployed beacons. First, the proposed system makes use of diverse fingerprinting features to increase localization accuracy that also reduces both the physical size of the database and the amount of data communication with the server in the execution phase; second, affinity propagation clustering minimizes the searching space of RPs and reduces the computational cost; third, exponential averaging is introduced to smooth the noisy RSS. The experimental results obtained by real field deployment show that the proposed method significantly improves the performance of the positioning system in both the positioning accuracy and radio-map database size. INDEX TERMS Affinity propagation clustering, BLE, Exponential averaging, RSS, Weighted centroid.

No abstract

As smartphone built-in sensors, wireless technologies, and processor computing power become more advanced and global positioning system (GPS)-based positioning technologies are improving, location-based services (LBS) have become a part of our daily lives. At the same time, demand has grown for LBS applications in indoor environments, such as indoor path finding and navigation, marketing, entertainment, and location-based information retrieval. In this paper, we demonstrate the design and implementation of a smartphone-based indoor LBS system for location services consisting of smartphone applications and a server. The proposed indoor LBS system uses hybrid indoor positioning methods based on Bluetooth beacons, Geomagnetic field, Inertial Measurement Unit (IMU) sensors, and smartphone cameras and can be used for three types of indoor LBS applications. The performance of each positioning method demonstrates that our system retains the desired accuracy under experimental conditions. As these results illustrate that our system can maintain positioning accuracy to within 2 m 80% of the time, we believe our system can be a real solution for various indoor positioning service needs.

Indoor positioning systems have received increasing attention because of their wide range of indoor applications. However, the positioning system generally suffers from a large error in localization and has low solidity. The main approaches widely used for indoor localization are based on the inertial measurement unit (IMU), Bluetooth, Wi-Fi, and ultra-wideband. The major problem with Bluetooth-based fingerprinting is the inconsistency of the radio signal strength, and the IMU-based localization has a drift error that increases with time. To compensate for these drawbacks, in the present study, a novel positioning system with IMU sensors and Bluetooth low energy (BLE) beacon for a smartphone are introduced. The proposed trusted K nearest Bayesian estimation (TKBE) integrates BLE beacon and pedestrian dead reckoning positionings. The BLE-based positioning, using both the K-nearest neighbor (KNN) and Bayesian estimation, increases the accuracy by 25% compared with the existing KNN-based positioning, and the proposed fuzzy logic-based Kalman filter increases the accuracy by an additional 15%. The overall performance of TKBE has an error of <1 m in our experimental environments. INDEX TERMS Bayesian estimation, Bluetooth low energy (BLE), fingerprints, fuzzy-logic system, indoor positioning, K-nearest neighbor (KNN), pedestrian dead reckoning (PDR).

The unstable nature of radio frequency signals and the need for external infrastructure inside buildings have limited the use of positioning techniques, such as Wi-Fi and Bluetooth fingerprinting. Compared to these techniques, the geomagnetic field exhibits stable signal strength in the time domain. However, existing magnetic positioning methods cannot perform well in a wide space because the magnetic signal is not always discernible. In this paper, we introduce deep recurrent neural networks (DRNNs) to build a model that is capable of capturing long-range dependencies in variable-length input sequences. The use of DRNNs is brought from the idea that the spatial/temporal sequence of magnetic field values around a given area will create a unique pattern over time, despite multiple locations having the same magnetic field value. Therefore, we can divide the indoor space into landmarks with magnetic field values and find the position of the user in a particular area inside the building. We present long short-term memory DRNNs for spatial/temporal sequence learning of magnetic patterns and evaluate their positioning performance on our testbed datasets. The experimental results show that our proposed models outperform other traditional positioning approaches with machine learning methods, such as support vector machine and k-nearest neighbors.INDEX TERMS Deep recurrent neural network (DRNN), fingerprinting, geomagnetic field, long short-term memory (LSTM).