Radio technologies for environment-aware wireless communications

In this paper, we critically review the potential of today's terrestrial wireless communication systems including wireless cellular technologies (GSM, UMTS, LTE, NR), wireless local area networks (WLANs), and wireless sensor networks (WSNs), for estimating channel state information (CSI), the ratio between training and information symbols and the rate of channel variation, and the potential use of CSI in environment aware wireless communications. The research reveals, that early communication systems provide means for narrowband channel estimation and the CSI is only available as channel attenuation based on signal level measurements. By increasing the spectral bandwidth of communications, the CSI is estimated in some form of channel impulse response (CIR) in almost all currently used radio technologies, but this information is generally not available outside the communication systems. Also, the CSI is estimated only for the channel with active communications. The new radio technology (NR) offers the possibility of estimating the CIR for non-active channels as well, and thus the possibility of initiating environmentally aware wireless communications.

Improving CSI-based Massive MIMO Indoor Positioning using Convolutional Neural Network

Multiple-input multiple-output (MIMO) is an enabling technology to meet the growing demand for faster and more reliable communications in wireless networks with a large number of terminals, but it can also be applied for position estimation of a terminal exploiting multipath propagation from multiple antennas. In this paper, we investigate new convolutional neural network (CNN) structures for exploiting MIMO-based channel state information (CSI) to improve indoor positioning. We evaluate and compare the performance of three variants of the proposed CNN structure to five NN structures proposed in the scientific literature using the same sets of training-evaluation data. The results demonstrate that the proposed residual convolutional NN structure improves the accuracy of position estimation and keeps the total number of weights lower than the published NN structures. The proposed CNN structure yields from 2cm to 10cm better position accuracy than known NN structures used as a reference.