A method of measuring the AM/PM conversion of a device under test having a local oscillator is described. A device under test with an embedded local oscillator is provided. A signal source is connected to an input of the device under test. A receiver is connected to an output of the device under test. An input signal is provided by the signal source. The input signal has an initial power level. The input signal is input to the device under test. The power level of the input signal is changed. An output signal of the device under test is measured at different power levels of the input signal.

Class types of input signals having unknown class types are automatically classified using a neural network. The neural network learns features associated with a plurality of different observed signals having respective different known class types. The neural network then recognizes features of the input signals having unknown class types that at least partially match at least some of the features associated with the plurality of different observed signals having respective different known class types. The neural network determines probabilities that each of the input signals has each of the known class types based on strengths of the matches between the recognized features of the input signals and the features associated with plurality of different observed signals. The neural network classifies each of the input signals as having one of the respective different known class types based on a highest determined probability.

Class types of input signals having unknown class types are automatically classified using a neural network. The neural network learns features associated with a plurality of different observed signals having respective different known class types. The neural network then recognizes features of the input signals having unknown class types that at least partially match at least some of the features associated with the plurality of different observed signals having respective different known class types. The neural network determines probabilities that each of the input signals has each of the known class types based on strengths of the matches between the recognized features of the input signals and the features associated with plurality of different observed signals. The neural network classifies each of the input signals as having one of the respective different known class types based on a highest determined probability.

A quantum modulation classifier. The quantum modulation classifier includes a trained quantum variational classifier including a plurality of qubits. The quantum variational classifier includes an embedding stage operable to apply a quantum embedding technique to embed a modulated radio signal, a variational stage operable to receive the modulated radio signal from the embedding stage and pass the modulated radio signal through a plurality of variational layers, and a measurement stage operable to receive the modulated radio signal from the variational stage and extract measurement results to classify the modulated radio signal.

A quantum modulation classifier. The quantum modulation classifier includes a trained quantum variational classifier including a plurality of qubits. The quantum variational classifier includes an embedding stage operable to apply a quantum embedding technique to embed a modulated radio signal, a variational stage operable to receive the modulated radio signal from the embedding stage and pass the modulated radio signal through a plurality of variational layers, and a measurement stage operable to receive the modulated radio signal from the variational stage and extract measurement results to classify the modulated radio signal.

Measuring MDEVM of a DUT includes splitting an RF signal output by a DUT into first and second RF signals; acquiring and digitizing the first and second RF signals in first and second channels without demodulating the first and second RF signals; performing equalization of the first and second RF signals; measuring first and second modulation distortion (MD) error vectors of the equalized first and second RF signals; performing cross-correlation of the first and second MD error vectors across the first and second channels; averaging the cross-correlated MD error vectors over symbols and packets of the RF signal; and dividing the averaged cross-correlated MD error vectors by signal power of an ideal signal to obtain cross-correlated MDEVMs over a time period or bandwidth of a waveform of the RF signal, where performing the cross-correlation suppresses contribution of uncorrelated noise.

Measuring MDEVM of a DUT includes splitting an RF signal output by a DUT into first and second RF signals; acquiring and digitizing the first and second RF signals in first and second channels without demodulating the first and second RF signals; performing equalization of the first and second RF signals; measuring first and second modulation distortion (MD) error vectors of the equalized first and second RF signals; performing cross-correlation of the first and second MD error vectors across the first and second channels; averaging the cross-correlated MD error vectors over symbols and packets of the RF signal; and dividing the averaged cross-correlated MD error vectors by signal power of an ideal signal to obtain cross-correlated MDEVMs over a time period or bandwidth of a waveform of the RF signal, where performing the cross-correlation suppresses contribution of uncorrelated noise.

A ripple detection device and a ripple suppression device. The ripple detection device includes: a ripple sampling unit, at least two DC sampling units, and a digital signal processing unit; the ripple sampling unit outputs a first voltage signal at an output port of a non-isolated DC/DC bidirectional energy conversion unit to the digital signal processing unit; the DC sampling unit outputs a first DC signal in a second voltage signal at a connected port of the non-isolated DC/DC bidirectional energy conversion unit to the digital signal processing unit and blocks an AC signal in the second voltage signal to be output to the digital signal processing unit; the digital signal processing unit determines a ripple noise signal at the output port of the non-isolated DC/DC bidirectional energy conversion unit according to the first voltage signal and the first DC signal.

Measuring MDEVM of a DUT includes splitting an RF signal output by a DUT into first and second RF signals; acquiring and digitizing the first and second RF signals in first and second channels without demodulating the first and second RF signals; performing equalization of the first and second RF signals; measuring first and second modulation distortion (MD) error vectors of the equalized first and second RF signals; performing cross-correlation of the first and second MD error vectors across the first and second channels; averaging the cross-correlated MD error vectors over symbols and packets of the RF signal; and dividing the averaged cross-correlated MD error vectors by signal power of an ideal signal to obtain cross-correlated MDEVMs over a time period or bandwidth of a waveform of the RF signal, where performing the cross-correlation suppresses contribution of uncorrelated noise.

Measuring MDEVM of a DUT includes splitting an RF signal output by a DUT into first and second RF signals; acquiring and digitizing the first and second RF signals in first and second channels without demodulating the first and second RF signals; performing equalization of the first and second RF signals; measuring first and second modulation distortion (MD) error vectors of the equalized first and second RF signals; performing cross-correlation of the first and second MD error vectors across the first and second channels; averaging the cross-correlated MD error vectors over symbols and packets of the RF signal; and dividing the averaged cross-correlated MD error vectors by signal power of an ideal signal to obtain cross-correlated MDEVMs over a time period or bandwidth of a waveform of the RF signal, where performing the cross-correlation suppresses contribution of uncorrelated noise.