Back to results
US 12,726,220 B2Granted
System and method for neural network aided interference estimation
AssigneeNovAtel Inc.
InventorsRobert Hang, Graham Fader
Life of this patent
Estimating the term…
Abstract
A system and method for utilizing a neural network or other artificial intelligence to identify windows of potential interference in a radio frequency signal is provided. The identified windows are then utilized in a rules-based interference detection system to identify a center, upper, and lower frequencies of the interference. The identified interference may then be remediated using conventional techniques.
Claims16
A computer implemented method comprising:
- receiving a radio frequency (RF) signal at one or more antennas;
- converting the received RF signal from a time domain to a frequency domain;
- using a machine learning system on the converted RF signal to identify one or more windows of interference, when interference is present in the received RF signal;
- providing each identified window of interference to a rules-based interference detection system;
- and
- identifying, using the rules-based interference detection system, a center frequency, an upper frequency, and a lower frequency for RF interference contained within the window of interference.
3 more elements
A system comprising:
- a processor;
- a machine learning module configured to analyze a received radio frequency signal to identify a window of interference;
- a rules-based interference detection module configured to identify a center frequency and bandwidth for RF interference contained within the window of interference;
- and
- wherein an upper frequency and a lower frequency are set at a point where the interference contained in the window of interference is a predefined lower power level from the identified center frequency.
2 more elements
Dependencies are inferred from the claim text.