Combined higher order statistics and artificial intelligence signal analysis

1. A test and measurement instrument for analyzing signals, comprising:

an input configured to receive a signal;

a analog to-digital converter configured to convert the signal into a digital signal; and

one or more processors configured to:

determine a recovered clock signal based on the digital signal,

set window positions for a fast Fourier transform of the digital signal,

isolate the digital signal into a series of windowed waveform data based on the window positions,

transform each of the windowed waveform data into a frequency-domain windowed waveform data using a fast Fourier transform, and

determine high-order spectrum data of each of the frequency-domain windowed waveform data;

a bit pattern recognition neural network configured to receive the frequency-domain windowed waveform data and output a bit pattern; and

a multiplexing switch configured to receive the frequency-domain windowed waveform data and route it to particular path based on the bit pattern, wherein the one or more processors include determining the high-order spectrum data of each of the frequency-domain windowed waveform data for each path; and

a neural network configured to provide a respective neural network for each path for classifying each windowed waveform data based on the high-order spectrum data of the respective path.

2. The test and measurement instrument of claim 1 , further comprising a threshold gate configured to receive the high-order spectrum data and pass the high-order spectrum data that do not violate the threshold and set the high-order spectrum data that violate the threshold to a nominal value.

3. The test and measurement instrument of claim 2 , wherein the nominal value is zero.

4. The test and measurement instrument of claim 1 , wherein the high-order spectrum data includes at least one of a magnitude value, a phase value, or complex value.

5. The test and measurement instrument of claim 1 , wherein the one or more processors are further configured to average the high-order spectrum data of each of the frequency-domain windowed waveform data and each respective neural network is configured to classify each windowed waveform data based on the average of the high-order spectrum data.

6. The test and measurement instrument of claim 1 , wherein the one or more processors are further configured to determine a transfer function of a channel of the test and measurement instrument based on the output bit pattern of the bit pattern recognition neural network.

7. The test and measurement instrument of claim 1 , wherein the neural network is configured to output at least one of a bit error rate, distortion, pattern decoding, a jitter measurement, signal-to-noise ratio, and inter-symbol interference based on classifying the windowed waveform data.

8. The test and measurement instrument of claim 1 , wherein the one or more processors are configured to isolate the digital signal into a series of windowed waveform data based on the window positions using a Tukey window function.

9. A method for analyzing an input signal in a test and measurement system, comprising:

receiving an input signal;

determining a recovered clock signal based on the input signal;

setting window positions for fast Fourier transforms of the digital signal;

isolating the input signal into a series of windowed waveform data based on the window positions;

transforming each of the windowed waveform data into a frequency-domain windowed waveform data using a fast Fourier transform;

determining high-order spectrum data of each of the frequency-domain windowed waveform data;

detecting a bit pattern based on the frequency-domain windowed waveform data by a bit pattern recognition neural network;

routing the frequency-domain windowed waveform data to a particular neutral network based on the bit pattern; and

classifying the high-order spectrum data of each of the frequency-domain windowed waveform data.

10. The method of claim 9 , further comprising passing high-order spectrum data that do not violate a threshold to the neural network and setting the high-order spectrum data that violate the threshold to a nominal value.

11. The method of claim 9 , wherein the high-order spectrum data includes at least one of a magnitude value, a phase value, or a complex value.

12. The method of claim 9 , further comprising averaging the high-order spectrum data of each of the frequency-domain windowed waveform data for a particular bit pattern prior to classifying the high-order spectrum data of each of the frequency-domain windowed waveform data based on the bit pattern.

13. The method of claim 9 , wherein classifying each windowed waveform data includes outputting at least one of a bit error rate, distortion, pattern decoding, a jitter measurement, signal-to-noise ratio, and inter-symbol interference based on classifying each windowed waveform.

14. The method of claim 9 , wherein isolating the digital signal into a series of windowed waveform data based on the window positions includes using a Tukey window function.

15. One or more non-transitory computer-readable storage media comprising instructions, which, when executed by one or more processors of a test and measurement instrument, cause the test and measurement instrument to:

determine a recovered clock signal based on an input signal;

set window positions for fast Fourier transforms of the digital signal;

isolate the input signal into a series of windowed waveform data based on the window positions;

transform each of the windowed waveform data into a frequency-domain windowed waveform data using a fast Fourier transform;

determine high-order spectrum data of each of the frequency-domain windowed waveform data;

detect a bit pattern based on the frequency-domain windowed waveform data by a bit pattern recognition neural network;

route the frequency-domain windowed waveform data to a particular neutral network based on the bit pattern; and

classify the high-order spectrum data of each of the frequency-domain windowed waveform data.

16. The one or more non-transitory computer-readably storage media of claim 15 , further comprising instructions that cause the test and measurement to pass high-order spectrum data that do not violate a threshold to the neural network and set the high-order spectrum data that violate the threshold to a nominal value.

17. The one or more non-transitory computer-readably storage media of claim 15 , further comprising instructions that cause the test and measurement to average the high-order spectrum data of each of the frequency-domain windowed waveform data for a particular bit pattern prior to classifying the high-order spectrum data of each of the frequency-domain windowed waveform data based on the bit pattern.