Track-track association (TTA) in complex environment for multi-sensor fusion is a challenging topic due to the uncertainty of measurements, biased data, mismatch caused by different resolution etc. In this work, we proposed an end-to-end deep learning model, named the spatial-temporal attention network (STAN) for TTA tasks in complex scenarios. Three modules in the backbone of STAN for intra-track and inter-track feature representation are based on self-attention mechanism, e.g., the motion mode encoder (MME) module to encode the motion pattern of single moving targets, the spatial structure extraction (SSE) module for capturing the inter-track spatial interaction relation of an individual sensor, and the spatialtemporal fusion (STF) module for intra-track modeling on temporal dimensions, respectively. A relation reasoning head (RRH) is built for track-track relation reasoning based on the encoded track features. Experimental results on different tasks show that our proposed method achieved superior performance for track-track association compared with previous methods.

In this paper, we study joint adaptive M-QAM modulation and power adaptation for a downlink two-user non-orthogonal multiple access (NOMA) network. Without sacrificing bit error rate (BER), joint adaptive transmission can fully utilize the time-varying nature of wireless channels, by allowing both power and rate to adapt to channel fading. Two adaptive power allocation strategies, namely,Scheme 1andScheme 2, each of which guarantees the minimum target rate for one user while supporting the highest possible rate for the other, are first proposed. Then, based on the two power schemes, the performance of joint adaptive transmission in terms of average spectral efficiency (SE) is studied for continuous-rate and discrete-rate modulation, while guaranteeing the minimum required rate and BER requirements. With the focus on practical discrete-rate M-QAM modulation, it is proved that for the strong user inScheme 1and the weak user inScheme 2, their average SEs converge to the minimum target rates. In order to further increase the total transmission rate, we then propose a dynamic rate and power adaptation (DRPA) algorithm, aiming to increase the rate of one user without sacrificing the rate of the other. It is shown that at high SNRs, the DRPA algorithm allows the strong user inScheme 1and the weak user inScheme 2to continue to increase their transmission rates until reaching the highest modulation order that the system can support. Hence, the total transmission rate can be greatly increased at high SNRs due to the adoption of DRPA, by allowing both users in each scheme to reach the highest transmission rate in the system.

This paper investigates the performance of an uplink Non-orthogonal Multiple Access (NOMA) with discrete M-QAM modulation and fixed power coefficients. Specifically, an uplink NOMA with a base station and two users are considered and two different performance metrics, namely bit error rate and spectral efficiency, are investigated. We provide closed-form expressions for the average spectral efficiency of NOMA with M-QAM which shows that the performance of the weak user is limited to a certain value which depends on the power coefficients solely. Moreover, results of closed-form expressions and simulation are compared to verify the expressions and to analyze the performance of the proposed NOMA system. The simulation results show that increasing the power coefficient of weak user can improve the weak user's performance in high SNRs, but it does not work well in low SNRs.