Abstract
Fingerprinting localization approach is widely used in indoor positioning applications owing to its high reliability. However, the learning procedure of radio signals in fingerprinting is time-consuming and labor-intensive. In this paper, an affinity propagation clustering (APC)-based fingerprinting localization system with Gaussian process regression (GPR) is presented for a practical positioning system with the reduced offline workload and low online computation cost. The proposed system collects sparse received signal strength (RSS) data from the deployed Bluetooth low energy beacons and trains them with the Gaussian process model. As the signal estimation component, GPR predicts not only the mean RSS but also the variance, which indicates the uncertainty of the estimation. The predicted RSS and variance can be employed for probabilistic-based fingerprinting localization. As the clustering component, the APC minimizes the searching space of reference points on the testbed. Consequently, it also helps to reduce the localization estimation error and the computational cost of the positioning system. The proposed method is evaluated through real field deployments. Experimental results show that the proposed method can reduce the offline workload and increase localization accuracy with less computational cost. This method outperforms the existing methods owing to RSS prediction using GPR and RSS clustering using APC.
Highlights
Indoor location-based service (LBS) has been attracting significant interest in recent times owing to an increase in the number of smart devices and technologies being used
Despite the requirement of manually collecting the received signal strength (RSS) to begin the algorithm (RSS clustering with affinity propagation clustering (APC)), this method can be helpful while updating the fingerprint radio map in a timely manner
The Gaussian process regression (GPR) and APC are used in many kinds of literature, we find that there is no related literature that combines them to address the real issues of conventional fingerprinting localization like offline workload and computational complexity
Summary
Indoor location-based service (LBS) has been attracting significant interest in recent times owing to an increase in the number of smart devices and technologies being used. The study in reference [14] combines the traditional fingerprinting with weighted centroid localization (WCL) to yield acceptable location estimation by employing a fewer number of RPs across the testbed. Despite the requirement of manually collecting the RSS to begin the algorithm (RSS clustering with APC), this method can be helpful while updating the fingerprint radio map in a timely manner. Another approach to reduce human effort in acquiring the radio map is to use crowdsourcing, machine learning, and a fusion of similarity-based sequence and dead reckoning [16,17,18].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
