https://github.com/hectorta1989/mimo-phy-security-analysis-with-eavesdropper

Analysis of physical layer security of MIMO system using Machine Learning algorithms vs theoretical best
https://github.com/hectorta1989/mimo-phy-security-analysis-with-eavesdropper

computernetworks machinelearning-python phy

Last synced: 3 months ago
JSON representation

Analysis of physical layer security of MIMO system using Machine Learning algorithms vs theoretical best

• Host: GitHub
• URL: https://github.com/hectorta1989/mimo-phy-security-analysis-with-eavesdropper
• Owner: HectorTa1989
• License: mit
• Created: 2021-10-16T23:46:20.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-10-28T03:13:19.000Z (over 3 years ago)
• Last Synced: 2025-01-07T06:47:55.113Z (5 months ago)
• Topics: computernetworks, machinelearning-python, phy
• Language: Jupyter Notebook
• Homepage:
• Size: 6.14 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MIMO-PHY security with Eavesdropper

Analysis of physical layer security of MIMO system using ML algorithms vs theoretical best

Various MIMO channels have been implemented (Line of Sight, Rayleigh fading, etc). 

The main analysis done was to compare the physical layer security provided by 

antenna selection (any subset of the transmit antennas) using ML algorithms

to the theoretical maximum security rate. 

The main conclusion is that as the ML algorithms can approach the theoretical curves

as the training data increase. This is a problem where synthetic data can be used

as the channels are random in nature, so by using random channels good results

can be achieved.