Machine Learning aided Efficient and Robust Algorithms for Spectrum Knowledge Acquisition in Wideband Autonomous Cognitive Radios

Abstract

Abstract The overall objective of this project is to conduct fundamental research that will lead to the development of a machine‐learning aided efficient and robust spectral activity detector algorithm for autonomous wideband cognitive radios. The technical approach is to perform fundamental research, modeling, and simulation to develop robust spectrum knowledge acquisition algorithms for non‐ Gaussian processes. The anticipated outcome is to develop a comprehensive spectral activity detection framework that is computationally and technically efficient and robust. Research on real‐time sensing of a wide spectrum band could benefit future space communication systems and offer significant and comprehensive benefits to our national war‐fighting and peacekeeping capabilities. In particular, we envision the possibility of having a single radio device/system that may meet all communications needs of a user, whether it is broadband internet, TV/multimedia, satellite radio, voice communications or GPS/location services. Furthermore, the proposed regularized robust estimator algorithm can be useful in detection problems encountered in various sensor systems including bio‐medical image and astronomical signal processing.

Document Details

Document Type
DoD Grant Award
Publication Date
Jul 18, 2016
Source ID
FA94531510314

Entities

People

  • Sudharman Jayaweera

Organizations

  • Air Force Research Laboratory
  • United States Air Force
  • University of New Mexico

Tags

Fields of Study

  • Computer science

Readers

  • Astronomy and Astrophysics.
  • Neural Network Machine Learning.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms
  • Space