Unlock instant, AI-driven research and patent intelligence for your innovation.

Learning radio signals using radio signal transformers

A technology of radio signal and signal conversion, applied in neural learning methods, electrical components, transmission monitoring, etc., can solve problems that cannot be easily optimized, changed signal or channel parameters, etc.

Active Publication Date: 2020-06-09
VIRGINIA TECH INTPROP INC
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, such legacy systems have been configured to handle all types of radio signals and radio signal parameters relying on the artificial configuration of transformations when deployed, and cannot be easily optimized for varying signal or channel parameters

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Learning radio signals using radio signal transformers
  • Learning radio signals using radio signal transformers
  • Learning radio signals using radio signal transformers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] figure 1 is a contextual diagram of an example of a radio receiver using a machine learning system 130 with a radio signal transducer 134 to determine the number of wireless transmitters in a building.

[0030]The radio machine learning system 130 includes a radio signal parameter estimator 132 , a signal transformer 134 and a learning model 136 . Learning models 136 may include models for regression or classification using neural networks. The radio machine learning system 130 may be deployed within the radio signal receiver 107 . Deploying the over-the-air machine learning system 130 onto the radio signal receiver 107 may include, for example, providing the over-the-air machine learning system 130 to the radio signal receiver 107 as a software download across one or more networks.

[0031] By way of example, user 105 may use radio signal receiver 107 including radio machine learning system 130 with radio signal transducer 134 to detect radio signals output by one o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Methods, systems, and apparatus, including computer programs encoded on a storage medium, for processing radio signals. In once aspect, a system is disclosed that includes a processor and a storage device storing computer code that includes operations. The operations may include obtaining first output data generated by a first neural network based on the first neural network processing a receivedradio signal, receiving, by a signal transformer, a second set of input data that includes (i) the received radio signal and (ii) the first output data, generating, by the signal transformer, data representing a transformed radio signal by applying one or more transforms to the received radio signal, providing the data representing the transformed radio signal to a second neural network, obtainingsecond output data generated by the second neural network, and determining based on the second output data a set of information describing the received radio signal.

Description

[0001] Related Application Cross Reference [0002] The application claims to have been filed on May 3, 2017 and is titled "System and Method for Improving Performance of Learning Based Radio Communications and Sensing Systems with Radio Transformer Networks), which is incorporated herein by reference in its entirety. Background technique [0003] Machine learning models are becoming more common in radio applications. Such systems couple machine learning techniques with hardware radio components to quickly convert samples of individual radio signals into useful information, such as bits of information, human-understandable markers, or other types of information. [0004] However, such legacy systems have been configured to handle all types of radio signals and radio signal parameters relying on the artificial configuration of transformations when deployed, and cannot be easily optimized for changing signal or channel parameters. Contents of the invention [0005] Accordin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04B1/00
CPCH04B1/0003G06N3/08G06N3/045H04B17/309
Inventor T·J·奥谢
Owner VIRGINIA TECH INTPROP INC