RSSI-Based Indoor Localization Using Leaky Coaxial Cable with a PNN Approach

This paper proposes a probabilistic neural network-based (PNN-based) localization method using multiple leaky coaxial cables (LCX) for indoor multipath-rich environment. LCX which can be used as antennas has been applied to wireless communication widely in recent years. Different from conventional localization methods based on time of arrival (ToA) or time difference of arrival (TDoA), we present a probabilistic neural network (PNN) approach by utilizing received signal strength indicator (RSSI) in LCX system. The proposal is aimed at the two-dimensional localization in a trajectory. We evaluate the localization performance of the PNN-based method using RSSI data from LCX. In addition, we also compare the performance of the PNN-based method over the same environment but using conventional monopole antennas. The results show the PNN-based localization method using LCX is promising and is better than that using monopole antennas.