From October 21st to 23rd, the 12th International Conference on Wireless Communications and Signal Processing (WCSP 2020) was successfully held in Nanjing.

The academic paper Deep Learning-Based Joint Activity Detection and Channel Estimation for Massive Access: When More Antennas Meet Few Pilots by Xiaodan Shao, as the first author (supervisor: Research Professor Xiaoming Chen) was awarded the Best Paper Award at the conference.

This paper considers the problem of joint activity detection and channel estimation for massive grant-free random access with sporadic traffic devices. In particular, a deep learning network is developed for the recovery of device state matrix, which can effectively adapt to general complex channel settings with a finite number of training data. The proposed algorithm is computationally efficient and requires a short length of pilot sequences for achieving a satisfactory performance, which is appealing for achieving intelligent device detection in massive machine-type communication.

It is reported that a total of 210 academic papers were accepted for this conference, and 8 best papers were selected among them.