Graph Neural Network Assisted Efficient Signal Detection for OTFS Systems

Zhang, Xufan; Zhang, Shengyu; Xiao, Lixia; Li, Shuo; Jiang, Tao

doi:10.1109/lcomm.2023.3286800

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the conventional DL methods might struggle to effectively utilize the structural complexity of the input data, especially in the context of the OTFS system with its specific factor graph structure. To mitigate this, a graphical neural network (GNN)-based detector for OTFS is proposed in [104]. Transmit symbols are represented as nodes in a graph, and the GNN iteratively processes these nodes through aggregation, update, and output modules.…”

Section: ) Nn Based Detectionmentioning

confidence: 99%

Profuse Channel Estimation and Signal Detection Techniques for Orthogonal Time Frequency Space in 6G Epoch: A Survey

Sabapathy,

Prabhu,

Maruthu

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Orthogonal time frequency space (OTFS) modulation is a booming multicarrier modulation technique and a promising candidate for achieving quality of services in high mobility scenarios of 5G new radio (NR) and beyond wireless communication systems. OTFS addresses the high Doppler channel environment aiding the 2D delay-Doppler (DD) domain rather than the conventional time frequency domain. OTFS exploits several 2D transformations to transform a temporally variant multipath channel into a nearly invariant DD. The information symbols are embedded and the channel is represented sparsely in the DD domain. OTFS combats the challenges like inter-symbol interference, inter-carrier interference, etc., and outperforms the orthogonal frequency division multiplexing scheme. This paper presents a detailed survey of various channel estimation (CE) and signal detection (SD) techniques with vital mathematical expressions adopted to achieve enhanced performance. The significant benefits, techniques aided, and challenges in CE and SD for OTFS to a wide range of applications in high mobility scenarios are also discussed. Moreover, the crucial lessons erudite from the review along with the future research directions and key challenges in integration of OTFS with recent technologies for achieving 6G benchmarks are conversed in this paper.

show abstract

Section: ) Nn Based Detectionmentioning

confidence: 99%