Deep learning-based code indexed modulation for autonomous underwater vehicles systems

The Multiuser Direct Sequence Spread Spectrum (DSSS) has been proposed for the autonomous underwater vehicles (AUV) communication systems in a long transmission distance to transmit multiple users over the same channel bandwidth. Unfortunately, the DSSS data rate is limited by four users as a maximum due to the extensive multipath arrivals. This paper proposes a new scheme for the AUV communication systems called, deep learning coded index modulation-spread spectrum (DL-CIM-SS), to overcome the increasing data rate restriction of limited users number. The proposed DL-CIM-SS transmits the majority of information bits via the index of spreading code instead of transmitting all information bits physical. That doesn't only harvest more energy efficiency as the majority of information bits are not transmitted physically anymore, but also provide almost perfect detection at the receiver end. To further save the AUV energy, a pre-processing stage is added before feeding the received signal into the DL-based detector; the DL-based detector becomes environment-independent and no more training will be required during the online deployment. The proposed DL-CIM-SS performance is evaluated in this paper over simulation and measured underwater acoustic channels. The simulation results show the ability of the proposed scheme to increase the underwater acoustic data rate with significant energy efficiency improvement and low system bit and symbol error rate.

• Record URL:
  • https://doi.org/10.1016/j.vehcom.2020.100314
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S2214209620300851
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/22142096
• Supplemental Notes:
  • © 2020 Elsevier Inc. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Qasem, Zeyad A H
  • Leftah, Hussein A
  • 0000-0002-1738-9951
  • Sun, Haixin
  • Qi, Jie
  • Wang, Junfeng
  • Esmaiel, Hamada
  • 0000-0001-7317-8908
• Publication Date: 2021-4

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Serial:
  • Vehicular Communications
  • Volume: 28
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 2214-2096
  • Serial URL: http://www.sciencedirect.com/science/journal/22142096/1/2

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Communication systems; Machine learning; Underwater vehicles
• Subject Areas: Data and Information Technology; Marine Transportation; Vehicles and Equipment;

Filing Info

• Accession Number: 01760839
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 21 2020 1:48PM