Deep Multimodal Learning: Merging Sensory Data for Massive MIMO Channel Prediction

Yuwen Yang, Feifei Gao, Chengwen Xing, Jianping An, Ahmed Alkhateeb

Research output: Contribution to journalArticlepeer-review

Abstract

Existing work in intelligent communications has recently made preliminary attempts to utilize multi-source sensing information (MSI) to improve the system performance. However, the research on MSI aided intelligent communications has not yet explored how to integrate and fuse the multimodal sensory data, which motivates us to develop a systematic framework for wireless communications based on deep multimodal learning (DML). In this paper, we first present complete descriptions and heuristic understandings on the framework of DML based wireless communications, where core design choices are analyzed in the view of communications. Then, we develop several DML based architectures for channel prediction in massive multipleinput multiple-output (MIMO) systems that leverage various modality combinations and fusion levels. The case study of massive MIMO channel prediction offers an important example that can be followed in developing other DML based communication technologies. Simulation results demonstrate that the proposed DML framework can effectively exploit the constructive and complementary information of multimodal sensory data to assist the current wireless communications.

Original languageEnglish (US)
JournalIEEE Journal on Selected Areas in Communications
DOIs
StateAccepted/In press - 2020

Keywords

  • Channel estimation
  • channel prediction
  • Communication systems
  • Computational modeling
  • Data mining
  • Data models
  • deep learning
  • Deep multimodal learning (DML)
  • Feature extraction
  • massive MIMO
  • Wireless communication
  • wireless communications

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Deep Multimodal Learning: Merging Sensory Data for Massive MIMO Channel Prediction'. Together they form a unique fingerprint.

Cite this