US 12,695,527 B2 · Method and apparatus for modulated signal identification

Abstract

A computer-implemented method and an apparatus for automatic modulation recognition that enables the detection and identification of modulation schemes in received raw signals with a signal receiving unit without prior information about the raw signal detail, comprising a computing unit configured to transform received raw signals from time domain to frequency domain including the noise in the signal with segmenting the signal and computing its modulation in multiple image with the spectrogram extraction process in order to capture temporal dependencies and sequential information by treating the raw signals as images; augmentation of the data for increasing the dataset size for increasing the accuracy with the limited data; training the data for enabling the network to learn spatiotemporal relationships based on a signal-to-noise ratio level; applying the data to one algorithm of two, which are convolutional neural network and convolutional neural network long short-term memory network hybrid algorithm.

Claims13

Dependent claims

A computer-implemented method for automatic modulation recognition that enables the detection and identification of modulation schemes in received raw signals with a signal receiving unit without prior information about the raw signal detail, comprising at least one computing unit configured to achieve following steps:

transforming received raw signals from time domain to frequency domain including the noise in the signal with segmenting the signal and computing its modulation in multiple images with the spectrogram extraction process in order to capture temporal dependencies and sequential information by treating the raw signals received from signal receiving unit as images;
augmentation of the data for increasing the dataset size for increasing the accuracy with the limited data;
training the data for enabling the network to learn spatiotemporal relationships based on a predefined or a precalculated signal-to-noise ratio (SNR) level;
and
applying the data to one algorithm of two, which are at least one-dimension convolutional neural network (CNN) and at least one-dimension convolutional neural network (CNN) long short-term memory network (LSTM) hybrid algorithm.

2 more elements

An apparatus for automatic modulation recognition that enables the detection and identification of modulation schemes in received signals with a signal receiving unit without pre-defined prior information about the signal details comprising:

at least one at least one signal receiving unit that receives the raw signals, and at least one computing unit that coupled to at least one memory medium;
a transform unit that transforms the raw signals from time domain to frequency domain with Cohen's Time Frequency Transform (CTFT) with combining Cohen's Class;
and
at least one augmentation unit that enlarges of the data for increasing the dataset size for increasing the accuracy with the limited data;
wherein the computing unit also includes:
an accuracy module configured to train the data for enabling the network to learn spatiotemporal relationships with treating the signals as images that applies two-dimensional convolutional neural network (2D-CNN) model;
a general module configured to capture temporal dependencies and sequential information on the spectrogram that applies two-dimensional convolutional neural network (2D-CNN) and long short-term memory network (LSTM) hybrid algorithm;
and
a decision unit configured to selecting one of the accuracy module and general module for increase the accuracy according to the signal-to-noise ratio (SNR) level which is predefined input of the apparatus.

6 more elements

Dependencies are inferred from the claim text.

Method and apparatus for modulated signal identification

Life of this patent

Method and apparatus for modulated signal identification

Life of this patent

Abstract

Claims13