Deep learning (DL) based autoencoder (AE) has been proposed recently as a promising, and potentially disruptive approach to design the physical layer of beyond-5G communication systems. Compared to a traditional communication system with a multiple-block structure, the DL based AE approach provides a new paradigm to physical layer design with a pure data-driven and end-to-end learning based solution. In this paper, we address the dynamic interference in a multiuser Gaussian interference channel. We show that standard constellation are not optimal for this context, in particular, for a high interference condition. We propose a novel adaptive DL based AE to overcome this problem. With our approach, dynamic interference can be learned and predicted, which updates the learning processing for the decoder. Compared to other machine learning approaches, our method does not rely on a fixed training function, but is adaptive and applicable to practical systems. In comparison with the conventional system using n-psk or n-QAM modulation schemes with zero force (ZF) and minimum mean square error (MMSE) equalizer, the proposed adaptive deep learning (ADL) based AE demonstrates a significant achievable BER in the presence of interference, especially in strong and very strong interference scenarios. The proposed approach has laid the foundation of enabling adaptable constellation for 5G and beyond communication systems, where dynamic and heterogeneous network conditions are envisaged. INDEX TERMS Deep learning, Autoencoder, 5G physical layer, and Interference channel.
With the increasing demand for process
safety and production efficiency,
many research efforts have been made for nonstationary process monitoring
in recent years. However, existing methods usually neglect dynamic
characteristics of industrial processes, which may lead to misleading
results. Only few literature studies address the problem of nonstationary
dynamic process monitoring, and most of them are mainly based on the
assumption that nonstationary variables are integrated with the same
order I = 1. In order to deal with the general case,
where nonstationary variables are integrated with different or higher
orders, dynamic stationary subspace analysis (DSSA) is proposed in
this paper. In DSSA, the time shift technique is introduced to model
dynamic relationships, and an optimization problem is described to
estimate the stationary projection matrix similar to stationary subspace
analysis (SSA). Different from traditional SSA, the alternating direction
method of multipliers is utilized to solve the optimization problem,
and detailed iteration expressions are derived. After the stationary
projection matrix is obtained, the Mahalanobis distance is adopted
for monitoring stationary components of augmented data. The monitoring
performance of DSSA is demonstrated by case studies on a simulated
nonstationary dynamic process, a nonstationary continuous stirred
tank reactor, and a practical ultra-supercritical power plant.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.