Active Sensing for Communications by Learning

doi:10.1109/JSAC.2022.3155496

Return

Active Sensing for Communications by Learning

2022-06-01

DOI：10.1109/JSAC.2022.3155496

Original

Original request for help

Save

Abstract

En 中文

This paper proposes a deep learning approach to a class of active sensing problems in wireless communications in which an agent sequentially interacts with an environment over a predetermined number of time frames to gather information in order to perform a sensing or actuation task for maximizing some utility function. In such an active learning setting, the agent needs to design an adaptive sensing strategy sequentially based on the observations made so far. To tackle such a challenging problem in which the dimension of historical observations increases over time, we propose to use a long short-term memory (LSTM) network to exploit the temporal correlations in the sequence of observations and to map each observation to a fixed-size state information vector. We then use a deep neural network (DNN) to map the LSTM state at each time frame to the design of the next measurement step. Finally, we employ another DNN to map the final LSTM state to the desired solution. We investigate the performance of the proposed framework for adaptive channel sensing problems in wireless communications. In particular, we consider the adaptive beamforming problem for mmWave beam alignment and the adaptive reconfigurable intelligent surface sensing problem for reflection alignment. Numerical results demonstrate that the proposed deep active sensing strategy outperforms the existing adaptive or nonadaptive sensing schemes.

Keywords:

Sensors

Channel estimation

Wireless communication

Array signal processing

Task analysis

Deep learning

Adaptive systems

Active learning

adaptive sensing

beam alignment

reconfigurable intelligent surface (RIS)

recurrent neural network (RNN)

Journal

IEEE Journal on Selected Areas in Communications

IF:

17.2

Papers:

6.4K

Citations:

3.1W

Organization

university of toronto

Scholars:

14.8W

Papers: 12.0W

Citations: 165

Cited Papers

Thirty-day rat toxicity study reveals reversible liver toxicity of mifepristone (RU486) and metapristone

Toxicology Mechanisms and Methods

IF0

2016-02-23

PREAI

Yingying Xiao; Yewei Zhu; Suhong Yu; Cuicui Yan; Rodney J. Y. Ho; Jian Liu; Tao Li; Jie Wang; Liyuan Wan; Xingtian Yang; Huo Xu; Jichuang Wang; Xiaohuang Tu; Lee Jia

Save

Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS

IF17.2

2021-08-01