RFID indoor localization based on support vector regression and k-means

Abstract

Systems need to know the physical locations of objects and people to optimize user experience and solve logistical and security issues. Also, there is a growing demand for applications that need to locate individual assets for industrial automation. This work proposes an indoor positioning system (IPS) able to estimate the item-level location of stationary objects using off-the-shelf equipment. By using RFID technology, a machine learning model based on support vector regression (SVR) is proposed. A multi-frequency technique is developed in order to overcome off-the-shelf equipment constraints. A k-means approach is also applied to improve accuracy. We have implemented our system and evaluated it using real experiments. The localization error is between 17 and 31 cm in 2.25m2 area coverage.