Abstract
Wireless local area network (WLAN) fingerprint positioning is an indoor localization technique with high accuracy and low hardware requirements. However, collecting received signal strength (RSS) samples for the fingerprint database is time-consuming and labor-intensive, hindering the use of this technique. The popular crowdsourcing sampling technique has been introduced to reduce the workload of sample collection, but has two challenges: one is the heterogeneity of devices, which can significantly affect the positioning accuracy; the other is the requirement of users’ intervention in traditional crowdsourcing, which reduces the practicality of the system. In response to these challenges, we have proposed a new WLAN indoor positioning strategy, which incorporates a new preprocessing method for RSS samples, the implicit crowdsourcing sampling technique, and a semi-supervised learning algorithm. First, implicit crowdsourcing does not require users’ intervention. The acquisition program silently collects unlabeled samples, the RSS samples, without information about the position. Secondly, to cope with the heterogeneity of devices, the preprocessing method maps all the RSS values of samples to a uniform range and discretizes them. Finally, by using a large number of unlabeled samples with some labeled samples, Co-Forest, the introduced semi-supervised learning algorithm, creates and repeatedly refines a random forest ensemble classifier that performs well for location estimation. The results of experiments conducted in a real indoor environment show that the proposed strategy reduces the demand for large quantities of labeled samples and achieves good positioning accuracy.
Highlights
Driven by the progress in technology, demand guidance, and the innovative service model, the geographic information service industry is developing rapidly and is profoundly changing people’s lives
Some other signals and techniques have been exploited for indoor positioning, such as Radio Frequency Identification (RFID), wireless local area network (WLAN), Bluetooth, Ultra Wideband (UWB), sound, computer vision, and Light Emitting Diode (LED) [1]
The existing indoor positioning algorithms fall into several categories: methods based on distance models and geometric information, such as time of arrival (TOA) and angle of arrival (AOA); methods based on a similarity measure, such as Nearest Neighbor (NN); methods based on a probability model, such as the Bayesian Network and Gaussian Mixture Model (GMM); and methods to predict and track user locations using the Bayesian filtering theory, such as improved Kalman filtering and enhanced particle filtering
Summary
Driven by the progress in technology, demand guidance, and the innovative service model, the geographic information service industry is developing rapidly and is profoundly changing people’s lives. The main contributions of this paper are summarized as follows: (1) A new WLAN fingerprint positioning framework is proposed, which includes a RSS sample acquisition program, a receiving module, a preprocessing module, a fingerprint database, and a semi-supervised learning classifier. The varying RSS samples collected by diverse devices are normalized and discretized through preprocessing This reduces the influence of the signal value difference on the positioning accuracy while providing a suitable samples set for the subsequent training process. The rest of the paper is organized as follows: Section 2 reviews the related work on reducing the effort of collecting RSS samples in fingerprint positioning techniques, including some existing crowdsourcing systems, the methods fusing multiple kinds of sensor data, and existing strategies that use a semi-supervised learning technique.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
