An integrative Weighted Path Loss and Extreme Learning Machine approach to Rfid based Indoor Positioning

Abstract

In recent years, applying RFID technology to develop an Indoor Positioning System (IPS) has become a hot research topic. The most prominent advantage of active RFID IPS comes from its unique identification of different objects in indoor environment. However, certain drawbacks of existing RFID IPSs, such as high cost of RFID readers and active tags, as well as heavy dependence on the density of reference tags to provide the location based service, largely limit the applications of active RFID IPS. In order to overcome these drawbacks, we develop a cost-efficient RFID IPS by using cheaper active RFID tags, sensors and reader. In addition, one localization algorithm: integrated Weighted Path Loss (WPL) -Extreme Learning Machine (ELM) which combines the fast estimation of WPL and the high localization accuracy of ELM is proposed. According to the algorithm, an indoor environment is divided into small zones firstly and an ELM model is developed for each zone during the offline phase. During the online phase, the WPL approach is used to determine the zone of the target primarily, then the ELM model of that zone is deployed to provide the final estimated location of the target. Based on our experimental result, this integrated algorithm provides a higher localization efficiency and accuracy than existing approaches.

Platform and Algorithm Development for a RFID-Based Indoor Positioning System

“…In addition to the experimental results in [15,16] a more elaborate and comprehensive performance evaluation of the proposed three localization algorithms: WPL, ELM, WPL-ELM was demonstrated in this paper. Our experimental results show that the WPL approach enhances the precision of localization accuracy by 38% over LANDMARC and 17% over enhanced LANDMARC.…”

“…Since the model-based approaches can provide a location estimation of a target in a short time and fingerprintingbased approaches can provide a higher localization accuracy in general, following this idea, we proposed another localization algorithm: WPL-ELM in [16], which integrates the fast estimation of WPL and the high localization accuracy of ELM together. During the offline phase, the indoor environment is divided into small zones first and an ELM model is developed for each zone.…”

Extreme learning machine for indoor location fingerprinting

“…This approach is similar with the work proposed by Zou et al (2013), with the exception that they use the signal strength of the reference tags collected during offline phase instead of online phase to train the ELM. However, with this difference, we do not think that the work is a proper translation of LANDMARC because the signal strength in online phase may significantly deviate from offline phase.…”

“…Although those models may perform well in static environment, they do not anticipate the possibilities of having the signal strength fingerprints in the online phase differ from those collected during offline phase. Zou et al (2013) proposed a combination of Weighted Path Loss (WPL) and ELM regression, where WPL helps to coarsely determine the zone in which the tracking tag is located to reduce the training time. Assuming that reference tags and tracking tags are identical, the signal strength data from reference tags during offline phase and the corresponding coordinates are used to train the ELM.…”

Machine learning for indoor positioning based on received signal strength

“…However, they seem to be sporadic and lacking in comprehensive study on issues pertaining to the topology or configuration of ELM. Letchner, Fox, and LaMarca Weighted Path Loss (WPL) and ELM regression [88], where WPL helps to coarsely determine the zone in which the tracking tag is located to reduce the training time. The RSS data from reference tags during training phase and the corresponding coordinates are then used to train the ELM.…”