Joint Active User Detection and Channel Estimation Via Bayesian Learning Approaches in MTC Communications

Coordinated Pilot Transmissions for Detecting the Signal Sparsity Level in Massive IoT Networks

“…Hanxiao et al [40] proposed a deep learning approach consisting of a preamble detection neural network for a first tentative/rough MUD followed by a data detection neural network exploiting the information data signals to refine MUD. Finally, AI-based MUD may also leverage Bayesian learning [41]- [44]. Indeed, Zhang et al [41] developed two CS-MUD Bayesian inference algorithms exploiting sparse prior information of the estimated channel vector.…”

“…Finally, AI-based MUD may also leverage Bayesian learning [41]- [44]. Indeed, Zhang et al [41] developed two CS-MUD Bayesian inference algorithms exploiting sparse prior information of the estimated channel vector. Similar approaches, but also exploiting the correlation of user activity over successive access slots, are proposed in [42].…”

“…However, having and exploiting this information would certainly improve the MUD performance. Specifically, the iterative mechanisms proposed in [20]- [35], [41]- [44] face the challenge of setting an appropriate stopping criterion, although the proposals in [26], [27] are more resilient in this regard, since the signal sparsity level is implicitly and iteratively estimated together with MUD. Moreover note that the deep learning-based mechanisms proposed in [37], [38], [40] have a fixed depth in terms of the number of layers and do not adapt well to highly-varying sparsity levels.…”

User Activity Detection for Irregular Repetition Slotted Aloha Based MMTC

“…The sparse Bayesian learning (SBL) framework has been employed to perform UAD in MMTC [22]. Faster SBL algorithms for UAD in MMTC have also been developed [23]. Other low complexity algorithms for UAD include approximate message passing [24] and orthogonal matching pursuit [25].…”