CIRNN: An Ultra-Wideband Non-Line-of-Sight Signal Classifier Based on Deep-Learning

Abstract

Non-line-of-sight (NLOS) error is the main factor that reduces indoor positioning accuracy. Identifying NLOS signals and eliminating NLOS errors are the keys to improving indoor positioning accuracy. To better identify NLOS signals, a multi-stream model channel-impulse-response-neural-network (CIRNN) was proposed. The inputs of CIRNN include the channel impulse response (CIR) and a small number of channel parameters. To make a more obvious comparison between NLOS signals and line-ofsight (LOS) signals, a new energy normalization method is proposed. Fusing multi-dimensional features, the CIRNN network has a good convergence performance and shows stronger sensitivity to NLOS signals. Experimental results show that the CIRNN achieves the best accuracy on the open-source data set, the F1 score is 89.3%. At the same time, the working efficiency of CIRNN meets industry needs, CIRNN can refresh the target position at about 92.6 Hz per second.

Deep Learning Technique for Power Domain Non-Orthogonal Multiple Access Using Optimised LSTM in Cooperative Networks

“…The physical layer security of wireless network jointly implements the passive beam forming and active beam forming algorithm by calling the IRS-based NOMA technology in the wireless networks and also enhancing the spectrum efficiency by comparing it with traditional OMA techniques like TimeDivisionMultiple Access (TDMA) [4]. To improve the principles of NOMA in reliability and efficiency, the basic things needed are Bit Error Ratio (BER) and allocation of resources is carried out [5][6][7]. The downlink scheme of NOMA-based technology uses a random selection of users to transmit signals in a unicastmulticast system, which many multicast users can access.…”