Project: Deep Learning for Mobile Communication

Internet-of-Things (IoT) communication is featured by massive connection, sporadic transmission, and small-sized data packets. In 6G wireless systems, IoT can be enabled by grant-free non-orthogonal random access (NORA). We propose a deep neural network-aided message passing-based block sparse Bayesian learning (DNN-MP-BSBL) algorithm to enable joint user activity detection (UAD) and channel estimation (CE) in grant-free NORA system. Our investigations show that the DNN-MP-BSBL algorithm achieves excellent UAD and CE accuracy with a small number of iterations, hence capable of supporting low-latency IoT communication with massive Machine Type Communication (MTC) devices with limited resources.

DNN Bayesian Learning for 6G Massive IoT

 

Reference:

  • Z. Zhang, Y. Li, C. Huang, Q. Guo, C. Yuen and Y. L. Guan, "DNN-Aided Block Sparse Bayesian Learning for User Activity Detection and Channel Estimation in Grant-Free Non-Orthogonal Random Access," IEEE Transactions on Vehicular Technology, vol. 68, no. 12, pp. 12000-12012, Dec. 2019.

 

For more information, you may contact our Professor Guan Yong Liang.