Abstract
In a Wi-Fi indoor positioning system (IPS), the performance of the IPS depends on the channel state information (CSI), which is often limited due to the multipath fading effect, especially in indoor environments involving multiple non-line-of-sight propagation paths. In this paper, we propose a novel IPS utilizing trajectory CSI observed from predetermined trajectories instead of the CSI collected at each stationary location; thus, the proposed method enables all the CSI along each route to be continuously encountered in the observation. Further, by using a generative adversarial network (GAN), which helps enlarge the training dataset, the cost of trajectory CSI collection can be significantly reduced. To fully exploit the trajectory CSI’s spatial and temporal information, the proposed IPS employs a deep learning network of a one-dimensional convolutional neural network–long short-term memory (1DCNN-LSTM). The proposed IPS was hardware-implemented, where digital signal processors and a universal software radio peripheral were used as a modem and radio frequency transceiver, respectively, for both access point and mobile device of Wi-Fi. We verified that the proposed IPS based on the trajectory CSI far outperforms the state-of-the-art IPS based on the CSI collected from stationary locations through extensive experimental tests and computer simulations.
Highlights
In a Wi-Fi indoor positioning system (IPS), the performance of the IPS depends on the channel state information (CSI), which is often limited due to the multipath fading effect, especially in indoor environments involving multiple non-line-of-sight propagation paths
The proposed deep learning models of 1DCNN-long and short-term memory (LSTM) and generative adversarial network (GAN) were implemented with TensorFlow 2.0 on an NVidia RTX 2080Ti graphics processing unit (GPU) using the Ubuntu 20.04 operating system
It has been observed that, for both laboratory and corridor signal environments, the value for the inter-reference point (RP) spacing turns out to be not a major factor affecting the performance of the proposed IPS, which should be taken as granted because our method is based on the trajectory CSI continuously measured in between adjacent RPs instead of the single-point CSI measured at each RP
Summary
CSI contains fine-grained information of the wireless channel, especially for OFDMbased systems, because it can be separately obtained for each subcarrier, where RSSI provides coarse-grained information for the entire frequency band [11]. Let T and R denote the transmit (Tx) and receive (Rx) signal vectors generated from the RF transceiver. We utilize a universal software radio peripheral (USRP), which is a reconfigurable RF transceiver including a field-programmable gate array, to generate Wi-Fi signals in the 2.4 GHz band. Where N denotes the additive white Gaussian noise vector with H being the channel, which can be acquired from the CSI. The ith subcarrier channel Hi is a complex-valued quantity that can be written as: Hi = | Hi |e j∠ Hi ,. Where |Hi | and ∠ Hi are the amplitude and phase of the channel for the ith subcarrier, respectively. The amplitude of the channel, Hi , is considered, ignoring the phase information owing to random jitters and noise caused by the imperfect hardware in the RF transceiver [16]
Sign-in/Register to view highlights & summary 
Published Version (
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 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.
