Neural network interpolation of band-unlimited signals

Abstract

Techniques and instruments for training a neural network (NN) for interpolation of data are described. In one aspect, sampled signal data is provided to the NN. Each sampled signal data includes a threshold event information and at least one sample taken during a threshold event of an analog signal. Each threshold event information indicates a duration from a time when the sampled signal data is taken to when the analog signal equals a threshold event value. The NN determines predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data. NN parameters are adjusted based on errors between each predicted threshold event information and a ground truth threshold event information for each sampled signal data.

Description

LG Ref: LI-PAT005-PCT01NEURAL NETWORK INTERPOLATION OF BAND-UNLIMITED SIGNALSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority to co-pending U.S. Provisional Patent Application No. 63 / 723,447, filed on November 21, 2024, entitled “NEURAL NETWORK INTERPOLATION OF BAND-UNLIMITED SIGNALS,” the contents of which is incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] This disclosure relates to time and frequency analyzer systems and methods, and in particular to systems and methods for predicting threshold event timing of band-unlimited signals using neural network interpolation.BACKGROUND

[0003] Time analyzers can perform interval measurements, i.e. measurements of the time period between two input signal events and can totalize a specific group of events. A time interval analyzer generally includes a continuous time counter and a continuous event counter. Typically, the device includes a measurement circuit on each of a plurality of measurement channels. Each channel receives an input signal. By directing a signal across the channels to a given measurement circuit so that the circuit receives two input signals, the circuit is able to measure the time interval between two events in the signals.SUMMARY OF THE DISCLOSURE

[0004] In some aspects, the techniques described herein relate to a method for training a neural network for interpolation of signals, including: providing, to the neural network, a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when the sampled signal data is taken to when the analog signal is equal to a threshold event value; determining, by the neural network, a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data; and adjusting parameters of the neural network based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

[0005] In some aspects, the techniques described herein relate to a method, the method further including: providing a test sampled signal data to the neural network after training;LG Ref: LI-PAT005-PCT01 and generating, by the neural network, predicted test threshold event information associated with the test sampled signal data.

[0006] In some aspects, the techniques described herein relate to a method, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument.

[0007] In some aspects, the techniques described herein relate to a method, including: receiving a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples of the sampled signal data is taken to when the analog signal is equal to a threshold event value; and training threshold event prediction circuitry, by: providing each sampled signal data in the plurality of sampled signal data to the threshold event prediction circuitry, determining a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data, and adjusting parameters of the threshold event prediction circuitry based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

[0008] In some aspects, the techniques described herein relate to a method, wherein the plurality of sampled signal data includes at least one of: a rising edge of the analog signal, a falling edge of the analog signal, or a pulse of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to at least one of: rising edge parameters, falling edge parameters, or pulse parameters.

[0009] In some aspects, the techniques described herein relate to a method, the method further including: providing a test sampled signal data to the threshold event prediction circuitry after training; and generating predicted test threshold event information associated with the test sampled signal data.

[0010] In some aspects, the techniques described herein relate to a method, wherein the plurality of sampled signal data corresponds to a rising edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to rising edge parameters for predicting threshold event information in relation to the rising edge, the method including: configuring the threshold event prediction circuitry based on the rising edge parameters, and generating the predicted test threshold event information for the rising edge.

[0011] In some aspects, the techniques described herein relate to a method, wherein theLG Ref: LI-PAT005-PCT01 plurality of sampled signal data corresponds to the falling edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to falling edge parameters for predicting threshold event information in relation to the falling edge, the method including: configuring the threshold event prediction circuitry based on the falling edge parameters, and generating the predicted test threshold event information for the falling edge.

[0012] In some aspects, the techniques described herein relate to a method, the method including: prior to generating the predicted test threshold event information: determining that the test sampled signal data includes one of a rising edge, a falling edge, or a pulse, configuring the threshold event prediction circuitry with parameters associated with the one of the rising edge, the falling edge, or the pulse, and generating the predicted test threshold event information for the determined one of the rising edge, the falling edge, or the pulse.

[0013] In some aspects, the techniques described herein relate to a method, wherein determining that the test sample signal data includes one of the rising edge, the falling edge, or the pulse includes determining that the test sample signal data includes the one of the rising edge, the falling edge, or the pulse based on a neural network classifier.

[0014] In some aspects, the techniques described herein relate to a method, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument.

[0015] In some aspects, the techniques described herein relate to a method, wherein the analog signal contains no frequency components above half of a frequency at which it is sampled.

[0016] In some aspects, the techniques described herein relate to a method, wherein the analog signal contains frequency components above half of a frequency at which it is sampled.

[0017] In some aspects, the techniques described herein relate to a method, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0018] In some aspects, the techniques described herein relate to a method, wherein the threshold event information indicates a duration from a time when a sample of the sampled signal data nearest to the predicted threshold event is taken to a time of the predicted threshold event.

[0019] In some aspects, the techniques described herein relate to a method, wherein the threshold event prediction circuitry comprises a trained neural network.LG Ref: LI-PAT005-PCT01

[0020] In some aspects, the techniques described herein relate to a method, the method further including: receiving an indication of a user selection of the threshold event information; and selectively accessing, by the threshold event prediction circuitry, a set of the parameters for predicting the selected threshold event information.

[0021] In some aspects, the techniques described herein relate to a method, the method further including: receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event value.

[0022] In some aspects, the techniques described herein relate to a measurement instrument that includes an input port configured to receive an analog signal; an analog-to-digital converter (ADC) coupled with the input port, the ADC configured to sample the analog signal at a sampling rate and generate test sampled signal data corresponding to a threshold event of the analog signal; threshold event prediction circuitry coupled with the ADC, the threshold event prediction circuitry configured to: receive the test sample signal data and generate predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

[0023] In some aspects, the techniques described herein relate to a measurement instrument, wherein the threshold event prediction circuitry is trained on a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples is taken to when the analog signal is equal to a threshold event value.

[0024] In some aspects, the techniques described herein relate to a measurement instrument, wherein the threshold event prediction circuitry is configured to receive threshold event prediction parameters corresponding to a trained neural network, and to generate the predicted test threshold event information based on the threshold event prediction parameters.

[0025] In some aspects, the techniques described herein relate to a measurement instrument, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0026] In some aspects, the techniques described herein relate to measurement instrument, wherein the threshold event information indicates a duration from a time when a sample of the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

[0027] In some aspects, the techniques described herein relate to measurement instrument,LG Ref: LI-PAT005-PCT01 wherein the threshold event prediction circuitry is configured to: receive an indication of a user selection of the threshold event information; and selectively access a set of the threshold event prediction parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

[0028] In some aspects, the techniques described herein relate to measurement instrument, wherein the threshold event prediction circuitry is configured to: receive an indication of a user selection of the threshold event value; and configure the threshold event prediction circuitry based on the received indication of the user selection of the threshold event value.

[0029] In some aspects, the techniques described herein relate to a method, including: receiving an analog signal; sampling, by an analog-to-digital converter (ADC), the analog signal at a sampling rate; generating, by the ADC, test sampled signal data corresponding to a threshold event of the analog signal; and generating, by threshold event prediction circuitry, predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

[0030] In some aspects, the techniques described herein relate to a method, further including: training the threshold event prediction circuitry on a plurality of sampled signal data, each sampled signal data on the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples in the test sampled signal data is taken to when the analog signal is equal to a threshold event value.

[0031] In some aspects, the techniques described herein relate to a method, further including: receiving, by the threshold event prediction circuitry, threshold event prediction parameters from a trained neural network; and generating the predicted test threshold event information based on the threshold event prediction parameters.

[0032] In some aspects, the techniques described herein relate to a method, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0033] In some aspects, the techniques described herein relate to a method, wherein the threshold event information indicates a duration from a time when a sample in the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

[0034] In some aspects, the techniques described herein relate to a method, further including:LG Ref: LI-PAT005-PCT01 receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event information; and selectively accessing a set of parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

[0035] In some aspects, the techniques described herein relate to a method, further including: receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event value; and configuring the threshold event prediction circuitry based on the received indication of the user selection of the threshold event value.BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Many aspects of the present disclosure can be better understood with reference to the following drawings. The components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Moreover, in the drawings, like reference numerals designate corresponding parts throughout the several views.

[0037] Figure 1 shows a block diagram of an example measurement instrument.

[0038] Figure 2 shows a block diagram illustrating training of the threshold event prediction circuitry of the example measurement system.

[0039] Figure 3 shows a block diagram of an example artificial neural network, which can be implemented by the threshold event prediction circuitry

[0040] Figure 4 shows a block diagram of an example threshold event prediction system.

[0041] Figure 5 shows a flow diagram of an example process which can be implemented by the measurement instrument and / or the threshold event prediction system.

[0042] Figure 6 shows a flow diagram of an example process which can be implemented by the measurement instrument and / or the threshold event prediction system.

[0043] Additional advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or can be learned by practice of the disclosure. The advantages of the disclosure will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure, as claimed.

[0044] Like reference numbers and designations in the various drawings indicate like elements.LG Ref: LI-PAT005-PCT01DETAILED DESCRIPTION

[0045] Many modifications herein will come to mind to one skilled in the art to which the disclosure pertains having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the disclosures are not to be limited to the specific aspects disclosed and that modifications are intended to be included within the scope of the appended claims. The skilled artisan will recognize many variants and adaptations of the aspects described herein. These variants and adaptations are intended to be included in the teachings of this disclosure and to be encompassed by the claims herein.

[0046] Although specific terms are employed herein, they are used in ageneric and descriptive sense only and not for purposes of limitation.

[0047] As will be apparent to those of skill in the art upon reading this disclosure, each of the individual aspects described and illustrated herein has discrete components and features which can be readily separated from or combined with the features of any of the other several aspects without departing from the scope or spirit of the present disclosure.

[0048] Any recited method can be carried out in the order of events recited or in any other order that is logically possible. That is, unless otherwise expressly stated, it is in no way intended that any method or aspect set forth herein be construed as requiring that its steps be performed in a specific order. Accordingly, where a method claim does not specifically state in the claims or descriptions that the steps are to be limited to a specific order, it is no way intended that an order be inferred, in any respect. This holds for any possible non-express basis for interpretation, including matters of logic with respect to arrangement of steps or operational flow, plain meaning derived from grammatical organization or punctuation, or the number or type of aspects described in the specification.

[0049] All publications mentioned herein are incorporated herein by reference to disclose and describe the methods and / or materials in connection with which the publications are cited. The publications discussed herein are provided solely for their disclosure prior to the filing date of the present application. Nothing herein is to be construed as an admission that the present invention is not entitled to antedate such publication by virtue of prior invention. Further, the dates of publication provided herein can be different from the actual publication dates, which can require independent confirmation.

[0050] While aspects of the present disclosure can be described and claimed in a particular statutory class, such as the system statutory class, this is for convenience only and one of skill in the art will understand that each aspect of the present disclosure can be described and claimed in any statutory class.

[0051] It is also to be understood that the terminology used herein is for the purpose of describing particular aspects only and is not intended to be limiting. Unless defined otherwise,LG Ref: LI-PAT005-PCT01 all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the disclosed compositions and methods belong. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the specification and relevant art and should not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0052] Prior to describing the various aspects of the present disclosure, the following definitions are provided and should be used unless otherwise indicated. Additional terms may be defined elsewhere in the present disclosure.

[0053] As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items. Expressions such as “at least one of,” when preceding a list of elements, modify the entire list of elements and do not modify the individual elements of the list.

[0054] As used in the specification and the appended claims, the singular forms “a,” “an” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a proton beam degrader,” “a degrader foil,” or “a conduit,” includes, but is not limited to, two or more such proton beam degraders, degrader foils, or conduits, and the like.

[0055] The various concepts introduced above and discussed in greater detail below can be implemented in any of numerous ways, as the described concepts are not limited to any particular manner of implementation. Examples of specific implementations and applications are provided primarily for illustrative purposes.

[0056] As used herein, the terms “optional” or “optionally” means that the subsequently described event or circumstance can or cannot occur, and that the description includes instances where said event or circumstance occurs and instances where it does not.

[0057] Signal timing detection or prediction can be performed by instruments such as time interval analyzers and frequency analyzers. In general, such instruments measure time intervals between events of a signal. By measuring these time intervals, useful metrics and statistics related to signals can be calculated, such as rise time, fall time, and pulse width of a signal. Moreover, time interval information can be useful in applications such as photon counting, frequency counting, and feedback control and decoding applications.

[0058] Accurately predicting or detecting certain timing events with high resolution (e.g., sub-nanosecond resolution) is a challenge using conventional tools. This is particularly true, for example, when the signal is band unlimited or when the signal has a bandwidth that is close to the Nyquist bandwidth. Detecting certain timing events (e.g., the occurrence of aLG Ref: LI-PAT005-PCT01 rising edge, a falling edge, or a pulse in a signal) can be particularly challenging in analog signals that transition very rapidly. In such signals, sampling of the signal can produce sampled data that does not accurately reflect the waveform. For example, the sampled data might not include any samples at a particular region or point of interest (e.g., at the rising edge or falling edge of the signal). Time interval analyzers and frequency analyzers can utilize linear interpolation techniques to interpolate a line or curve between sampled points at a region of interest. In this way, a particular timing of an event of interest (e.g., crossing of a threshold voltage level) can be determined based on the interpolated line. However, linear interpolation techniques can produce significant artefacts that negatively impact the timing analysis, particularly when applied to detect or predict timing events with high resolution.

[0059] Moreover, linear interpolation techniques to detect timing events can have insufficient accuracy particularly when the signal is not sampled according to the Nyquist criterion. The Nyquist criterion is a rule that states that a signal must be sampled at a frequency that is at least twice the highest frequency in the signal to avoid losing information. If the sampling frequency is less than double the maximum frequency, a phenomenon called aliasing occurs. Stated differently, applying interpolation techniques to accurately determine when a signal crosses a threshold requires that the signal is properly sampled (i.e., that there are no frequency components in the signal higher than ! > the sampling frequency or Nyquist frequency). There are inevitably some frequencies above the Nyquist frequency because of non-idealities, and thus conventional interpolation techniques for predicting timing events always yield some degree of error.

[0060] As discussed herein, devices, systems, and methods for threshold timing prediction of signals are described that address the limitations above. As an example, a novel measurement instrument is described. The measurement instrument includes threshold event prediction circuitry that can include or implement a neural network to accurately predict timing information associated with the occurrence of threshold events in an analog signal (e.g., the occurrence of a rising edge, a falling edge, or a pulse of the analog signal). In some implementations, the neural network predicts a timing at which the analog signal is predicted to cross a threshold event value, and the threshold value can be, for example, a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value. Further, the threshold event prediction circuitry can generate predicted test threshold event information, which can include timing or duration information based on a sample time of one of the samples of the analog signal and a time at which the analog signal is predicted to cross the threshold event value.

[0061] The neural network can be trained based on training data that includes a variety ofLG Ref: LI-PAT005-PCT01 analog or sampled signal information associated with any of a variety of threshold events, as well as timing or duration information associated with such signals. During operation, the trained neural network utilize parameters obtained, generated, or modified based on the training to accurately and efficiently predict crossings of a threshold event value and / or generate predicted threshold event information

[0062] In some implementations, waveforms are sampled many times and superimposed on one another to get a high-quality collection of datapoints at or near a region of interest in a signal. Interpolation techniques can be utilized to find sampled points that are close to an actual point at which the signal crosses the threshold event value. Once the region at which the threshold event value crossing occurs has been identified or detected, a number of the surrounding sampled points (e.g., four points above and / or below the detected threshold event value crossing) can be fed into the trained neural network to determine the actual point of the threshold event value crossing, as well as timing or duration information associated with the threshold event value crossing.

[0063] The use of a trained neural network in the threshold event prediction circuitry facilitates accurate prediction of timing information associated with threshold events, even when the input signal is not sampled according to the Nyquist criterion. That is, using the trained neural network, the timing information can be accurately predicted for band-unlimited signals containing frequency components greater than half the sampling frequency. The systems and methods provided herein can generate accurate predictions using interpolation for signals having high bandwidth (e.g., band-unlimited signals) with a low sampling rate (e.g., below the Nyquist frequency). As such, the systems and methods provided herein can utilize sampling circuitry (e.g., an analog -to-digital converter (ADC)) that has a lower sampling rate (and lower cost) than otherwise would be needed, for example in conventional approaches, for accurate timing predictions. Further, in some aspects, by including the neural network within the measurement instrument, and in some cases on a same chip as the ADC, the interpolation and timing predictions can be performed in real-time by the measurement instrument. This is advantageous over approaches where post-processing is applied for interpolation in order to achieve accurate timing predictions.

[0064] Figure 1 is a block diagram illustrating a measurement instrument 110, in accordance with one or more implementations of the present disclosure. As shown in Figure 1, the measurement instrument 110 includes an input port 112, an analog -to-digital converter (ADC) 114, and threshold event prediction circuitry 116.

[0065] The input port 112 is configured to receive an analog signal. The input port 112 can include be a BNC quick connector, other coaxial connector, or other appropriate connector forLG Ref: LI-PAT005-PCT01 analog connections.

[0066] The ADC 114 is communicatively coupled to the input port 112. The ADC 114 receives the analog signal input to the input port 112 and converts the analog signal to a digital signal. More particularly, the ADC 114 samples the analog signal at a sampling rate, and outputs the sampled digital signal. The sampled digital signal includes test sampled signal data corresponding to a threshold event of the analog signal.

[0067] In some implementations, the analog signal contains no frequency components above half of a frequency at which it is sampled. For example, the analog signal can be fdtered by a fdter, such as an anti-aliasing fdter, to remove high-frequency components prior to sampling by the ADC 114. In some implementations, the fdter can be included in the measurement instrument 110. As the analog signal can contain no frequency components above half of the sampling frequency, the Nyquist criterion is satisfied, and accurate interpolation of the signal can be performed by the threshold event prediction circuitry 116.

[0068] In some implementations, the analog signal contains frequency components above half of a frequency at which it is sampled. For example, the analog signal can be a band- unlimited signal, or any signal that is not sufficiently band limited to satisfy the Nyquist criterion based on a sampling rate of the ADC 114. In such examples, even where the analog signal is not sampled according to the Nyquist criterion (i.e. the signal contains frequency components greater than 'A the sampling frequency of the ADC 114), the threshold event prediction circuitry 116 can perform accurate interpolation of the signal and accurately predict timing information utilizing a neural network as will be described in further detail herein.

[0069] The threshold event prediction circuitry 116 is communicatively coupled to the ADC 114. The threshold event prediction circuitry 116 receives the test sample signal data from the ADC 114 and generates predicted test threshold event information based on the test sample signal data. The predicted test threshold event information can include a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value. The threshold event prediction circuitry 116 can include, or otherwise be executed by, a computer processor configured to perform the various functions and operations described herein. For example, the threshold event prediction circuitry 116 can be executed by a computer processor selectively activated or reconfigured by a stored computer program, or can be a specially constructed computing platform for carrying out the features and operations described herein.

[0070] In some implementations, the threshold event prediction circuitry 116 includes memory which stores instructions for performing one or more of the features or operations described herein, and the threshold event prediction circuitry 116 can be operable to executeLG Ref: LI-PAT005-PCT01 instructions stored, for example, in the memory to perform the functions of the threshold event prediction circuitry 116 described herein. The memory can be or include any computer- readable storage medium, including, for example, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive, optical storage device, magnetic storage device, electrically erasable programmable read-only memory (EEPROM), organic storage media, or the like.

[0071] As an example, a threshold event can be any event associated with the analog signal of interest. For example, in various implementations, the threshold event can be the occurrence of a rising edge, a falling edge, or a pulse of the analog signal. Detection of such threshold events facilitates further measurement or analysis of the analog signal, such as determination of rise time of the analog signal, fall time of the analog signal, pulse width of the analog signal, photon counting (e.g., as can be indicated by pulses in the analog signal), and frequency counting (e.g., as can be indicated by occurrence of events, such as zero crossings or the like, occurring within a specific period of time).

[0072] In some implementations, the threshold event prediction circuitry 116 predicts a timing at which the analog signal is predicted to cross a threshold event value. The threshold event value can be any value associated with any threshold event. In some implementations, the threshold value can be one or more of a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value. However, implementations are not limited thereto, and in various implementations, any value of any parameter associated with an analog signal can be utilized as the threshold value.

[0073] In an aspect, the threshold event can be the occurrence of a rising edge of the analog signal, and the threshold event value can be a threshold voltage value indicative of the occurrence of a rising edge. For example, the threshold event value can be a voltage value that is at a mid-point between a low level and a high level of the analog signal. As such, the crossing of the threshold event value indicates the occurrence of a rising edge of the analog signal, as the analog signal transitions from the low level to the high level.

[0074] The threshold event prediction circuitry 116 generates the predicted test threshold event information, which can include a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value. That is, the test threshold event information can include timing or duration information, which can be based on a sample time of one of the samples and a time at which the analog signal is predicted to cross the threshold event value. In some implementations, the test threshold event information includes a duration from a time when a sample of the test sampled signal data nearest to the crossing of the predicted threshold event value is taken toLG Ref: LI-PAT005-PCT01 a time of the predicted crossing of the threshold event value.

[0075] In some implementations, the measurement instrument 110 can provide an output indicative of a result of the threshold event prediction circuitry. For example, the test threshold event information can be output by the threshold event prediction circuitry 116. In some implementations, the output can be received by a computing device. For example, a computing device can receive the test threshold event information and can display the test threshold event information on a display that is communicatively coupled to the computing device. The computing device can be communicatively coupled to the measurement instrument 110 via any wired or wireless channel. In some implementations, the measurement instrument 110 includes a communications port for facilitating communications with the computing device.

[0076] In some implementations, the measurement instrument 110 can include a threshold event prediction parameters database 118 (shown in Figure 1 as simply “parameters database” 118). The threshold event prediction parameters database 118 can store parameters that are accessible to the threshold event prediction circuitry 116 and which can be loaded into or otherwise utilized by the threshold event prediction circuitry 116 to generate the predicted test threshold event information. The threshold event prediction parameters database 118 can be stored in any computer-readable storage medium, including, for example, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive, optical storage device, magnetic storage device, electrically erasable programmable read-only memory (EEPROM), organic storage media, or the like.

[0077] In some implementations, the threshold event prediction circuitry 116 can be trained to predict crossings of the threshold event value and / or generate the predicted test threshold event information by employing one or more artificial intelligence or machine learning techniques, which in some aspects can be implemented at least in part by the threshold event prediction circuitry 116. Some or all of the operations performed by the threshold event prediction circuitry 116 can be performed automatically, for example, in response to receiving the test sampled signal data from the ADC 114. The threshold event prediction circuitry 116 can predict crossings of the threshold event value and / or generate the predicted test threshold event information by using past data (e.g., the threshold event prediction circuitry 116 can be trained based on past data) which indicates crossings of the threshold event value and / or test threshold event information associated with analog signals, and the threshold event prediction circuitry 116 can compare the received test sampled signal data with the past data to predict or determine the crossings of the threshold event value and / or the predicted test threshold event information based on similarities or deviations from the past data or from a trained model contained within, managed by, or otherwise accessible to the threshold event predictionLG Ref: LI-PAT005-PCT01 circuitry 116.

[0078] “Artificial intelligence” is used herein to broadly describe any computationally intelligent systems and methods that can learn knowledge (e.g., based on training data), and use such learned knowledge to adapt its approaches for solving one or more problems, for example, by making inferences based on a received input, such as the test sampled signal data received from the ADC 114.

[0079] The threshold event prediction circuitry 116 can include or otherwise employ, for example, neural network, deep learning, convolutional neural network, Bayesian program learning, support vector machines, and pattern recognition techniques to solve problems such as predicting crossings of a threshold event value and / or generating predicted test threshold event information based on received test sampled signal data. Further, the predict crossings of the threshold event value and / or generate the predicted test threshold event information can implement any one or combination of the following computational algorithms and / or techniques: classification, regression, supervised learning, unsupervised learning, feature learning, clustering, decision trees, or the like.

[0080] As will be described in further detail herein, in some examples, the threshold event prediction circuitry 116 can be a trained neural network. Utilizing a trained neural network in the threshold event prediction circuitry facilitates accurate prediction of timing information associated with threshold events, even when the input signal is band-unlimited and / or is not sampled according to the Nyquist criterion. This permits the ADC 114 in the measurement instrument 110 to have a lower sampling rate (and lower cost) than otherwise would be needed for accurate timing predictions. Further, in some examples, by including the neural network within the measurement instrument 110, and in some examples on a same chip as the ADC 114, the interpolation and timing predictions can be performed in real-time by the measurement instrument 110. This is advantageous over approaches where post-processing is applied for interpolation in order to achieve accurate timing predictions.

[0081] Figure 2 is a block diagram illustrating training of the threshold event prediction circuitry 116, in accordance with one or more implementations. The threshold event prediction circuitry 116 can be trained based on training data 210. The training data 210 can include any signal information. For example, the training data 210 can include a variety of analog or sampled signal information associated with any of a variety of threshold events (e.g., the occurrence of a rising edge, a falling edge, or a pulse of the analog signal). Further, the training data 210 can include timing or duration information associated with signals (e.g., threshold event information which can include a duration from a time when a sample nearest to a crossing of a threshold event value is taken to a time of the crossing of the threshold eventLG Ref: LI-PAT005-PCT01 value).

[0082] Other training input 220 can further be provided to the threshold event prediction circuitry 116 for training. The other training input 220 can include manually-entered input, such as one or more variable or adjustable parameters, coefficient values, labels, classifiers, or the like, to adjust or otherwise manage a threshold event prediction model or threshold event prediction parameters developed in the threshold event prediction circuitry 116 through the training process.

[0083] Using the training data 210, the threshold event prediction circuitry 116 can implement an iterative training process. Training can be based on a wide variety of learning rules or training algorithms. For example, the learning rules can include one or more of the following: back-propagation, real-time recurrent learning, pattem-by-pattem learning, supervised learning, interpolation, weighted sum, reinforced learning, temporal difference learning, unsupervised learning, and / or recording learning.

[0084] The back-propagation learning algorithm is a common method of training artificial neural networks (and can be employed, for example, with the artificial neural network 300 shown in Figure 3). Back-propagation generally includes two phases: propagation and weight update. In the propagation phase, a training pattern's input is forward propagated through the neural network in order to generate the propagation's output activations. Then, the propagation's output activations are backward propagated through the neural network using the training pattern target in order to generate deltas (i.e., the difference between the input and output values) of all output and hidden neurons. In the weight update phase, for each weight-synapse the following steps are generally performed: 1. Multiply its output delta and input activation to get the gradient of the weight; 2. Subtract a ratio (percentage) of the gradient from the weight. The propagation and weight update phases are repeated as desired until performance of the network is satisfactory.

[0085] The threshold event prediction circuitry 116 can learn to modify its behavior in response to the training data 210, and obtain, generate, and / or modify the threshold event prediction parameters 230 of the threshold event prediction circuitry 116. The threshold event prediction parameters 230 can represent any information upon which the threshold event prediction circuitry 116 can determine an appropriate response to new data or situations. For example, the threshold event prediction parameters 230 can represent relationships between received test sample signal data and crossings of a threshold event value and / or threshold event information. In some implementations, the threshold event prediction parameters 230 can be stored in the threshold event prediction parameters database 118.

[0086] Based on the training, the threshold event prediction circuitry 116 can learn to modifyLG Ref: LI-PAT005-PCT01 its behavior, and can apply the parameters of the trained threshold event prediction circuitry 116 (e.g., which can be contained in the threshold event prediction parameters database 118) to alter the manner in which it makes determinations or predictions with respect to new input, such as, for example, test sampled signal data received from the ADC 114.

[0087] Figure 3 is a block diagram illustrating an example artificial neural network 300, which can be implemented by the threshold event prediction circuitry 116, in accordance with one or more implementations. Artificial neural networks (ANNs) are artificial intelligence models that are used to estimate or approximate functions that can depend on a large number of inputs, and which are generally unknown. Such neural networks generally include a system of interconnected “neurons” which exchange information between each other. The connections have numeric weights that can be tuned based on experience, and thus neural networks are adaptive to inputs and are capable of learning.

[0088] The artificial neural network 300 shown in Figure 3 includes a plurality of “neurons” arranged in a plurality of separate layers which are connected to one another. For example, the neural network 300 can include an input layer 310 including input neurons ii through is, a hidden layer 320 including hidden layer neurons hi through lu, and an output layer 330 including output neurons fi and fs. While the neural network 300 of Figure 3 is shown having three layers, it should be readily appreciated that additional layers can be included in the neural network 300 as desired to achieve optimal training and performance of the threshold event prediction circuitry 116. Similarly, the number of neurons in each layer are provided as merely an example, and it should be readily understood that each layer can include any number of neurons.

[0089] The neural network 300 can be trained by providing training data 210 to the input layer 310. As described previously herein, the training data 210 can include analog or sampled signal information associated with any of a variety of threshold events (e.g., the occurrence of a rising edge, a falling edge, or a pulse of the analog signal), and can further include timing or duration information associated with signals (e.g., threshold event information which can include a duration from a time when a sample nearest to a crossing of a threshold event value is taken to a time of the crossing of the threshold event value). Through training, the neural network 300 can generate and / or modify the hidden layer 320, which represents weighted connections mapping the training data 210 provided at the input layer 310 to known output information at the output layer 330 (e.g., classification of a known signal as including a particular threshold event and / or threshold event information associated with a particular threshold event). Relationships between neurons of the input layer 310, hidden layer 320 and output layer 330, formed through the training process and which can include weight connection relationships, are generally referred to herein as “threshold event predictionLG Ref: LI-PAT005-PCT01 parameters,” and can be stored, for example, in the threshold event prediction parameters database 118. More particularly, the threshold event prediction parameters can include the weights and biases of the neural network 300. The weights are the strength of the connections between neurons, and the biases are the number of hidden and output neurons. In some implementations, the threshold event prediction parameters can include hyperparameters of the neural network 300, which can include, for example, the number of hidden layers, the number of nodes in each layer, the type of activation function, the learning rate, the type of optimizer, the type of loss function, the batch size, the dropout rate, or any other parameters of the neural network 300.

[0090] Once the neural network 300 has been sufficiently trained, the neural network 300 can be provided with non-training signal data at the input layer 310 (e.g., the test sampled signal data received from the ADC 114.). During operation, the neural network 300 can utilize parameters associated with the trained neural network 300 (which can be stored in the threshold event prediction parameters database 118) to perform operations (such as making predictions or generating data) based on the received test sampled signal data at the output layer 330. For example, the neural network 300 can predict crossings of a threshold event value and / or generate predicted test threshold event information.

[0091] In some implementations, the threshold event prediction circuitry 116 (which can be or include the neural network 300) can be selectively configurable. For example, the threshold event prediction circuitry 116 can be operable to selectively implement a variety of different configurations of the neural network 300. For example, a number of layers, a number of neurons, and / or values of any of the threshold event prediction parameters of the neural network 300 can be adjusted, for example, based on user input or any input indicating selection of a neural network configuration. In some implementations, user input can be provided via a computing device communicatively coupled to the measurement instrument 110 or can be directly provided to the measurement instrument 110 via one or more user input elements.

[0092] In some implementations, the threshold event prediction circuitry 116 (which can be or include the neural network 300) can be trained based on a plurality of different signal types, threshold event types, threshold event values, or threshold event information, and distinct sets of threshold event prediction parameters 230 can be produced for distinct training configurations of the threshold event prediction circuitry 116. For example, one set of threshold event prediction parameters 230 can correspond to rising edge parameters for prediction of crossings of a threshold event value and / or generation of predicted test threshold event information associated with a rising edge of a signal. Another set of threshold event prediction parameters 230 can correspond to falling edge parameters for prediction ofLG Ref: LI-PAT005-PCT01 crossings of a threshold event value and / or generation of predicted test threshold event information associated with a falling edge of a signal. Yet another set of threshold event prediction parameters 230 can correspond to pulse parameters for prediction of crossings of a threshold event value and / or generation of predicted test threshold event information associated with a pulse of a signal. Each of the threshold event prediction parameters 230 of a particular set (e.g., rising edge parameters, falling edge parameters, or pulse parameters) can be associated with one another and stored as a set in the threshold event prediction parameters database 118. As such, upon selection of a particular neural network configuration (e.g., rising edge, falling edge, or pulse), the threshold event prediction circuitry 116 can access an associated set of threshold event prediction parameters, which can be loaded into or otherwise utilized by the threshold event prediction circuitry 116 during operation thereof.

[0093] In some implementations, the threshold event prediction circuitry 116 and / or any parameters utilized by the threshold event prediction circuitry 116 can be configurable based on user input which can be provided, for example, via a computing device communicatively coupled to the measurement instrument 110. For example, in some implementations, the threshold event prediction circuitry 116 can receive an indication of a user selection of threshold event prediction parameters to be implemented, and the threshold event prediction circuitry 116 can load the selected threshold event prediction parameters from the threshold event prediction parameters database 118. The threshold event prediction parameters can be, for example, weights and biases of a neural network included in or implemented by the threshold event prediction circuitry 116.

[0094] In some implementations, the threshold event prediction circuitry 116 can receive an indication of a user selection of a particular type of threshold event information (e.g., duration or timing information in relation to a predicted crossing of a threshold event value that is associated with a particular type of threshold event, such as the occurrence of a rising edge, a falling edge, or a pulse of an analog signal). In response, the threshold event prediction circuitry 116 can access and load a set of parameters, e.g., from the threshold event prediction parameters database 118, for predicting the selected type of threshold event information.

[0095] In some implementations, the threshold event prediction circuitry 116 can receive an indication of a user selection of a threshold event value (e.g., a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value), and the threshold event prediction circuitry 116 can be configured based on the selected threshold event value. For example, the threshold event prediction circuitry 116 can be configured to predict the test threshold event information based on the selected threshold event value.

[0096] In some implementations, the threshold event prediction circuitry 116 can determineLG Ref: LI-PAT005-PCT01 that test sample data includes one of a rising edge, a falling edge, or a pulse based on a neural network classifier. For example, the neural network 300 can include or implement a classifier that is operable to classify received test sample data as having or otherwise being indicative of a rising edge, a falling edge, or a pulse.

[0097] In some implementations, the sampled signal data (e.g., the training data 210) and the test sampled signal data are provided to a same analog -to-digital front end of the measurement instrument 110. For example, the sampled signal data and the test sampled signal data can be provided to the measurement instrument 110 via a same port, such as the input port 112. In some implementations, the sampled signal data and the test sampled data can be provided to the ADC 114, and in other implementations, the sampled signal data and the text sampled data can be provided directly to the threshold event prediction circuitry 116.

[0098] Figure 4 is a block diagram illustrating a threshold event prediction system 400 (which can be referred to herein as “system” 400), in accordance with one or more implementations of the present disclosure. As shown in Figure 4, the system 400 includes the measurement instrument 110, a communications network 402, global threshold event prediction circuitry 404, and a global threshold event prediction parameters database 406.

[0099] The measurement instrument 110 can be the same or substantially the same as the measurement instrument 110 described previously herein, for example, with respect to Figure 1. For example, the measurement instrument 110 can include the input port 112, the ADC 114, the threshold event prediction circuitry 116, and the threshold event prediction parameters database 118, as previously described herein. In some implementations, the measurement instrument 110 is communicatively coupled or couplable to a computing device 408, for example, over any wired or wireless communication channel. The computing device 408 can be utilized to control one or more functions of the measurement instrument 110, such as by controlling a configuration of the threshold event prediction circuitry 116 (which can be or include, for example, a neural network). Further, the computing device 408 can be utilized to display and / or control waveform measurements (e.g., rise time, fall time, pulse width, duty cycle), event counts (e.g., frequency counting or photon counting), time stamps associated with events, event and interval statistics, timing information, histograms, or any other information associated with signals received by the measurement instrument 110. Such information can be displayed, for example, by any display included in or otherwise communicatively coupled to the computing device 408.

[0100] The global threshold event prediction circuitry 404 and the global threshold event prediction parameters database 406 can be communicatively coupled to the measurement instrument 110 over the communications network 402. The communications network 402 canLG Ref: LI-PAT005-PCT01 be any network operable to facilitate communication between the measurement instrument 110 and the global threshold event prediction circuitry 404 and the global threshold event prediction parameters database 406. The communications network 402 can utilize one or more protocols to communicate via one or more physical networks, including local area networks, wireless networks, dedicated lines, intranets, the Internet, and the like.

[0101] The global threshold event prediction circuitry 404 and the global threshold event prediction parameters database 406 can be the same or substantially the same as the threshold event prediction circuitry 116 and the threshold event parameters database 118, respectively, as previously described herein. However, in the system 400, the measurement instrument 110 is operable to receive information associated with the global threshold event prediction circuitry 404 and / or information stored in the global threshold event prediction parameters database 406, and to implement or configure the threshold event prediction circuitry 116 based on the received information. For example, in some implementations, the measurement instrument 110 can communicate with the global threshold event prediction circuitry 404 over the communications network 402 to receive information associated with a neural network of the global threshold event prediction circuitry 404. Such information can include, for example, the number of hidden layers, the number of nodes in each layer, the type of activation function, the learning rate, the type of optimizer, the type of loss function, the batch size, the dropout rate, or any other information associated with the neural network of the global threshold event prediction circuitry 404. Upon receiving the information associated with the neural network of the global threshold event prediction circuitry 404, a computer processor or processing circuitry of the measurement instrument 110 can be configured to implement the threshold event prediction circuitry 116 based on the received information. Accordingly, the threshold event prediction circuitry 116 of the measurement instrument 110 can be configured based on (e.g., to be the same as) one or more configurations received from the global threshold event prediction circuitry 404.

[0102] Similarly, in some implementations, the measurement instrument 110 can receive threshold event prediction parameters from the global threshold event prediction parameters database 406. The received threshold event prediction parameters can be stored in the threshold event prediction parameters database 118 included in the measurement instrument 110 and / or loaded directly into the threshold event prediction circuitry 116 for use during operation of the measurement instrument 110. In some implementations, the threshold event prediction parameters database 118 can be omitted from the measurement instrument 110, and threshold event prediction parameters received by the measurement instrument 110 from the global threshold event prediction parameters database 406 can be loaded directly into the threshold event prediction circuitry 116.LG Ref: LI-PAT005-PCT01

[0103] The global threshold event prediction circuitry 404 can be trained in a same or substantially similar way as previously described herein with respect to training of the threshold event prediction circuitry 116. For example, the global threshold event prediction circuitry 404 can be trained based on a plurality of different signal types, threshold event types, threshold event values, or threshold event information, and distinct sets of threshold event prediction parameters can be produced for distinct training configurations of the global threshold event prediction circuitry 404. For example, one set of threshold event prediction parameters can correspond to rising edge parameters for prediction of crossings of a threshold event value and / or generation of predicted test threshold event information associated with a rising edge of a signal. Another set of threshold event prediction parameters can correspond to falling edge parameters for prediction of crossings of a threshold event value and / or generation of predicted test threshold event information associated with a falling edge of a signal. Yet another set of threshold event prediction parameters can correspond to pulse parameters for prediction of crossings of a threshold event value and / or generation of predicted test threshold event information associated with a pulse of a signal. Each of the threshold event prediction parameters of a particular set (e.g., rising edge parameters, falling edge parameters, or pulse parameters) can be associated with one another and stored as a set in the global threshold event prediction parameters database 406.

[0104] Accordingly, the threshold event prediction circuitry 116 in the measurement instrument 110 is configurable based on information received from the global threshold event prediction circuitry 404 and / or the global threshold event prediction parameters database 406.

[0105] In some implementations, the measurement instrument 110 is operable to receive information from the global threshold event prediction circuitry 404 and / or the global threshold event prediction parameters database 406 based on user input, for example, via the computing device 408. For example, the threshold event prediction circuitry 116 can receive an indication of a user selection of threshold event prediction parameters to be implemented by the measurement instrument 110, and the threshold event prediction circuitry 116 can thus load the selected threshold event prediction parameters from the global threshold event prediction parameters database 406 or from the global threshold event prediction circuitry 404 (which can be a trained neural network as previously discussed herein). The threshold event prediction parameters can be, for example, weights and biases of the global threshold event prediction circuitry 404 in a particular configuration (e.g., for detection and prediction based on rising edge, falling edge, or pulse of an analog signal). Once so configured, the threshold event prediction circuitry 116 can generate predicted test threshold event information based on the test sample signal data received from the ADC 114 during operation of the measurement instrument 110.LG Ref: LI-PAT005-PCT01

[0106] In some implementations, the threshold event prediction circuitry 116 can receive an indication of a user selection of a particular type of threshold event information (e.g., duration or timing information in relation to a predicted crossing of a threshold event value that is associated with a particular type of threshold event, such as the occurrence of a rising edge, a falling edge, or a pulse of an analog signal). In response, the threshold event prediction circuitry 116 can access and load a set of parameters from the global threshold event prediction parameters database 406 for predicting the selected type of threshold event information. Accordingly, the threshold event prediction circuitry 116 can generate predicted test threshold event information of the selected type based on the test sample signal data received from the ADC 114 during operation of the measurement instrument 110.

[0107] In some implementations, the threshold event prediction circuitry 116 can receive an indication of a user selection of a threshold event value (e.g., a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value), and the threshold event prediction circuitry 116 can be configured based on the selected threshold event value. For example, the threshold event prediction circuitry 116 can be configured to predict the test threshold event information based on the selected threshold event value.

[0108] Figure 5 shows a flow diagram of an example process 500 which can be implemented, for example, by the measurement instrument 110 and / or the threshold event prediction system 400. At 502, the process 500 includes receiving a plurality of sampled signal data with respective plurality of threshold event information. The plurality of sampled signal data can be received, for example, by the threshold event prediction circuitry 116. As an example, the plurality of sampled signal data can be training data 210 that is used for training the threshold event prediction circuitry 116 of the measurement instrument 110 and / or the global threshold event prediction circuitry 404 of the system 400. Each sampled signal data can include at least one sample taken during a threshold event of an analog signal. The threshold event can be, for example, the occurrence of a rising edge, a falling edge, or a pulse of the analog signal. The threshold event information indicates a duration from a time when one of the samples of the sampled signal data is taken to when the analog signal is equal to a threshold event value.

[0109] At 504 through 508, the process 500 includes training threshold event prediction circuitry. The threshold event prediction circuitry can be, for example, the threshold event prediction circuitry 116 described with respect to Figure 1 and / or the global threshold event prediction circuitry 404 described with respect to Figure 4. At 504, training the threshold event prediction circuitry includes providing each of the plurality of sampled signal data to the threshold event prediction circuitry. For example, each of the plurality of sampled signal data can be provided to the threshold event prediction circuitry 116 from the ADC 114 of the measurement instrument 110. In some implementations, each of the plurality of sampledLG Ref: LI-PAT005-PCT01 signal data can be provided as training data 210 from any source of training data.

[0110] At 506, the process 500 includes determining predicted threshold event information corresponding to the threshold event of the analog signal. The threshold event can be any threshold event, and in some implementations, can be the occurrence of a rising edge, a falling edge, or a pulse of the analog signal. The predicted threshold event information corresponding to the threshold event can be, for example, predicted timing or duration information in relation to a sample time of one of the samples in the sampled signal data when the analog signal is predicted to cross the threshold event value.[oni] At 508, the process 500 includes adjusting parameters of the threshold event prediction circuitry based on errors between the predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data. The ground truth threshold event information can be, for example, known and accurate threshold event information associated with each of the plurality of sampled signal data. For example, the plurality of sampled signal data can be training data 210 having known associated threshold event information associated therewith. Accordingly, the threshold event prediction circuitry 116 and / or the global threshold event prediction circuitry 404 can adjust the parameters based on an error or difference between the predicted threshold event information and the ground truth event information. The parameters can be, for example, threshold event prediction parameters and can include weights and biases of a neural network implemented by the threshold event prediction circuitry 116 and / or the global threshold event prediction circuitry 404. In some implementations, the threshold event prediction parameters can include one or more hyperparameters of the neural network.

[0112] Once the threshold event prediction circuitry 116 and / or the global threshold event prediction circuitry 404 has been sufficiently trained, for example by the process 500, the threshold event prediction circuitry 116 and / or the global threshold event prediction circuitry 404 can be utilized to accurately and efficiently predict test threshold event information associated with test sampled signal data that is received from the ADC 114 of the measurement instrument 110.

[0113] Figure 6 shows a flow diagram of an example process 600 which can be implemented, for example, by the measurement instrument 110 and / or the threshold event prediction system 400. At 602, the process 600 includes receiving an analog signal. The analog signal can be, for example, an analog signal received by the measurement instrument 110 fortesting or analysis. In some implementations, the analog signal is received by the measurement instrument 110 via the input port 112.

[0114] At 604, the process 600 includes sampling, by an analog-to-digital converter (ADC),LG Ref: LI-PAT005-PCT01 the analog signal at a sampling rate. The ADC can be, for example, the ADC 114 of the measurement instrument 110, which receives the analog signal via the input port 112. The ADC 114 samples the analog signal at a sampling rate. In some implementations, the sampling is performed at a sampling rate such that the analog signal contains no frequency components above half of a frequency at which it is sampled. In other implementations, the analog signal can contain frequency components above half of a frequency at which it is sampled.

[0115] At 606, the process 600 includes generating, by the ADC, test sampled signal data corresponding to a threshold event of the analog signal. The ADC 114 can generate the test sampled signal data, for example, by the sampling of the analog signal as described at 604. However, the generated test sampled signal data includes test sampled signal data that corresponds to a threshold event of the analog signal. For example, the test sampled signal data can correspond to the occurrence of a rising edge, a falling edge, or a pulse of the analog signal.

[0116] At 608, the process 600 includes generating, by threshold event prediction circuitry, predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value. The threshold event value can be any value associated with any threshold event. In some implementations, the threshold value can be one or more of a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value. In some aspects, the threshold event can be the occurrence of a rising edge of the analog signal, and the threshold event value can be a threshold voltage value indicative of the occurrence of a rising edge. For example, the threshold event value can be a voltage value that is at a mid-point between a low level and a high level of the analog signal. As such, the crossing of the threshold event value indicates the occurrence of a rising edge of the analog signal, as the analog signal transitions from the low level to the high level. In some implementations, the test threshold event information includes a duration from a time when a sample of the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

[0117] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the examples disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. SkilledLG Ref: LI-PAT005-PCT01 artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

[0118] Aspects implemented in computer software can in other aspects be implemented in software, firmware, middleware, microcode, hardware description languages, or any combination thereof. A code segment or machine-executable instructions can represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment can be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. can be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc.

[0119] The actual software code or specialized control hardware used to implement these systems and methods is not limiting of the invention. Thus, the operation and behavior of the systems and methods were described without reference to the specific software code being understood that software and control hardware can be designed to implement the systems and methods based on the description herein.

[0120] When implemented in software, the functions can be stored as one or more instructions or code on a non-transitory computer-readable or processor-readable storage medium. The steps of a method or algorithm disclosed herein can be embodied in a processorexecutable software module which can reside on a computer-readable or processor-readable storage medium. A non-transitory computer-readable or processor-readable media includes both computer storage media and tangible storage media that facilitate transfer of a computer program from one place to another. A non-transitory processor-readable storage media can be any available media that can be accessed by a computer. By way of example, and not limitation, such non-transitory processor-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other tangible storage medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer or processor. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media. Additionally, the operations of a method or algorithm can reside as one or any combination or set of codes and / or instructions on a non-transitory processor-readable medium and / or computer-readable medium, which can be incorporated into a computer program product.LG Ref: LI-PAT005-PCT01

[0121] The examples disclosed herein are illustrative and not limiting in nature. Details disclosed with respect to the methods described herein included in one example or aspect can be applied to other examples and aspect. Any aspect of the present disclosure that has been described herein can be disclaimed, i.e., excluded from the claimed subject matter whether by proviso or otherwise.ASPECTS OF THE DISCLOSURE

[0122] The present disclosure will be better understood upon reading the following numbered aspects, which should not be confused with the claims. Each of the numbered aspects described below can, in some instances, be combined with aspects described elsewhere in the disclosure. The following listing of example aspects is supported by the disclosure provided herein.

[0123] Aspect 1: A method for training a neural network for interpolation of signals, including: providing, to the neural network, a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when the sampled signal data is taken to when the analog signal is equal to a threshold event value; determining, by the neural network, a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data; and adjusting parameters of the neural network based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

[0124] Aspect 2: The method of any one of Aspects 1-14, further including: providing a test sampled signal data to the neural network after training; and generating, by the neural network, predicted test threshold event information associated with the test sampled signal data.

[0125] Aspect 3: The method of any one of Aspects 1-14, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument.

[0126] Aspect 4: The method of any one of Aspects 1-14, wherein the plurality of sampled signal data includes at least one of: a rising edge of the analog signal, a falling edge of the analog signal, or a pulse of the analog signal, wherein the parameters of the neural network (116; 300) correspond to at least one of: rising edge parameters, falling edge parameters, or pulse parameters.

[0127] Aspect 5: The method of any one of Aspects 1-14, comprising: providing atest sampled signal data to the neural network (116; 300) after training; and generating predictedLG Ref: LI-PAT005-PCT01 test threshold event information associated with the test sampled signal data.

[0128] Aspect 6: The method of any one of Aspects 1-14, wherein the plurality of sampled signal data corresponds to a rising edge of the analog signal, and wherein the parameters of the neural network (116; 300) correspond to rising edge parameters for predicting threshold event information in relation to the rising edge, the method comprising: configuring the neural network (116; 300) based on the rising edge parameters, and generating the predicted test threshold event information for the rising edge.

[0129] Aspect ?: The method of any one of Aspects 1-14, wherein the plurality of sampled signal data corresponds to the falling edge of the analog signal, and wherein the parameters of the neural network (116; 300) correspond to falling edge parameters for predicting threshold event information in relation to the falling edge, the method comprising: configuring the neural network (116; 300) based on the falling edge parameters, and generating the predicted test threshold event information for the falling edge.

[0130] Aspect 8: The method any one of Aspects 1-14, comprising: prior to generating the predicted test threshold event information: determining that the test sampled signal data includes one of a rising edge, a falling edge, or a pulse, configuring the neural network (116; 300) with parameters associated with the one of the rising edge, the falling edge, or the pulse, and generating the predicted test threshold event information for the determined one of the rising edge, the falling edge, or the pulse.

[0131] Aspect 9: The method of any one of Aspects 1-14, wherein: determining that the test sample signal data includes one of the rising edge, the falling edge, or the pulse includes determining that the test sample signal data includes the one of the rising edge, the falling edge, or the pulse based on a neural network (300) classifier.

[0132] Aspect 10: The method of any one of Aspects 1-14, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument (110).

[0133] Aspect 11: The method of any one of Aspects 1-14, wherein the analog signal contains no frequency components above half of a frequency at which it is sampled.

[0134] Aspect 12: The method of any one of Aspects 1-14, wherein the analog signal contains frequency components above half of a frequency at which it is sampled.

[0135] Aspect 13: The method of any one of Aspects 1-14, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0136] Aspect 14: The method of any one of Aspects 1-14, wherein the threshold eventLG Ref: LI-PAT005-PCT01 information indicates a duration from a time when a sample of the sampled signal data nearest to the predicted threshold event is taken to a time of the predicted threshold event.

[0137] Aspect 15: A method, including: receiving a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples of the sampled signal data is taken to when the analog signal is equal to a threshold event value; and training threshold event prediction circuitry, by: providing each sampled signal data in the plurality of sampled signal data to the threshold event prediction circuitry, determining a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data, and adjusting parameters of the threshold event prediction circuitry based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

[0138] Aspect 16. The method of any one of the Aspects 15-29, wherein the plurality of sampled signal data includes at least one of: a rising edge of the analog signal, a falling edge of the analog signal, or a pulse of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to at least one of: rising edge parameters, falling edge parameters, or pulse parameters.

[0139] Aspect 17. The method of any one ofthe Aspects 15-29, further including: providing a test sampled signal data to the threshold event prediction circuitry after training; and generating predicted test threshold event information associated with the test sampled signal data.

[0140] Aspect 18. The method of any one of the Aspects 15-29, wherein the plurality of sampled signal data corresponds to a rising edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to rising edge parameters for predicting threshold event information in relation to the rising edge, the method including: configuring the threshold event prediction circuitry based on the rising edge parameters, and generating the predicted test threshold event information for the rising edge.

[0141] Aspect 19. The method of any one of the Aspects 15-29, wherein the plurality of sampled signal data corresponds to the falling edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry correspond to falling edge parameters for predicting threshold event information in relation to the falling edge, the method including: configuring the threshold event prediction circuitry based on the falling edgeLG Ref: LI-PAT005-PCT01 parameters, and generating the predicted test threshold event information for the falling edge.

[0142] Aspect 20. The method of any one ofthe Aspects 15-29, including: priorto generating the predicted test threshold event information: determining that the test sampled signal data includes one of a rising edge, a falling edge, or a pulse, configuring the threshold event prediction circuitry with parameters associated with the one of the rising edge, the falling edge, or the pulse, and generating the predicted test threshold event information for the determined one of the rising edge, the falling edge, or the pulse.

[0143] Aspect 21. The method of any one of the Aspects 15-29, wherein determining that the test sample signal data includes one of the rising edge, the falling edge, or the pulse includes determining that the test sample signal data includes the one of the rising edge, the falling edge, or the pulse based on a neural network classifier.

[0144] Aspect 22. The method of any one of the Aspects 15-29, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument.

[0145] Aspect 23. The method of any one of the Aspects 15-29, wherein the analog signal contains no frequency components above half of a frequency at which it is sampled.

[0146] Aspect 24. The method of any one of the Aspects 15-29, wherein the analog signal contains frequency components above half of a frequency at which it is sampled.

[0147] Aspect 25. The method of any one of the Aspects 15-29, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0148] Aspect 26. The method of any one of the Aspects 15-29, wherein the threshold event information indicates a duration from a time when a sample of the sampled signal data nearest to the predicted threshold event is taken to a time of the predicted threshold event.

[0149] Aspect 27. The method of any one of the Aspects 15-29, wherein the threshold event prediction circuitry comprises a trained neural network.

[0150] Aspect 28. The method of any one of the Aspects 15-29, further including: receiving an indication of a user selection of the threshold event information; and selectively accessing, by the threshold event prediction circuitry, a set of the parameters for predicting the selected threshold event information.

[0151] Aspect 29. The method of any one of the Aspects 15-29, further including: receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event value.

[0152] Aspect 30. A measurement instrument, including: an input port configured to receiveLG Ref: LI-PAT005-PCT01 an analog signal; an analog-to-digital converter (ADC) coupled with the input port, the ADC configured to sample the analog signal at a sampling rate and generate test sampled signal data corresponding to a threshold event of the analog signal; threshold event prediction circuitry coupled with the ADC, the threshold event prediction circuitry configured to: receive the test sample signal data and generate predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

[0153] Aspect 31. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event prediction circuitry is trained on a plurality of sampled signal data with respective plurality of threshold event information, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples is taken to when the analog signal is equal to a threshold event value.

[0154] Aspect 32. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event prediction circuitry is configured to receive threshold event prediction parameters corresponding to a trained neural network, and to generate the predicted test threshold event information based on the threshold event prediction parameters.

[0155] Aspect 33. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0156] Aspect 34. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event information indicates a duration from a time when a sample of the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

[0157] Aspect 35. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event prediction circuitry is configured to: receive an indication of a user selection of the threshold event information; and selectively access a set of the threshold event prediction parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

[0158] Aspect 36. The measurement instrument of any one of the Aspects 30-36, wherein the threshold event prediction circuitry is configured to: receive an indication of a user selection of the threshold event value; and configure the threshold event prediction circuitry based on the received indication of the user selection of the threshold event value.

[0159] Aspect 37. A method, including: receiving an analog signal; sampling, by an analog-LG Ref: LI-PAT005-PCT01 to-digital converter (ADC), the analog signal at a sampling rate; generating, by the ADC, test sampled signal data corresponding to a threshold event of the analog signal; and generating, by threshold event prediction circuitry, predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

[0160] Aspect 38. The method of any one of the Aspects 37-43, further including: training the threshold event prediction circuitry on a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples in the test sampled signal data is taken to when the analog signal is equal to a threshold event value.

[0161] Aspect 39. The method of any one of the Aspects 37-43, further including: receiving, by the threshold event prediction circuitry, threshold event prediction parameters from a trained neural network; and generating the predicted test threshold event information based on the threshold event prediction parameters.

[0162] Aspect 40. The method of any one of the Aspects 37-43, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

[0163] Aspect 41. The method of any one of the Aspects 37-43, wherein the threshold event information indicates a duration from a time when a sample in the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

[0164] Aspect 42. The method of any one of the Aspects 37-43, further including: receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event information; and selectively accessing a set of parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

[0165] Aspect 43. The method of any one of the Aspects 37-43, further including: receiving, by the threshold event prediction circuitry, an indication of a user selection of the threshold event value; and configuring the threshold event prediction circuitry based on the received indication of the user selection of the threshold event value.

[0166] From the foregoing, it will be seen that aspects herein are well adapted to attain all the ends and objects hereinabove set forth together with other advantages which are obviousLG Ref: LI-PAT005-PCT01 and which are inherent to the structure.

[0167] While specific elements and steps are discussed in connection to one another, it is understood that any element and / or steps provided herein is contemplated as being combinable with any other elements and / or steps regardless of explicit provision of the same while still being within the scope provided herein.

[0168] It will be understood that certain features and subcombinations are of utility and can be employed without reference to other features and subcombinations. This is contemplated by and is within the scope of the claims.

[0169] Since many possible aspects can be made without departing from the scope thereof, it is to be understood that all matter herein set forth or shown in the accompanying drawings and detailed description is to be interpreted as illustrative and not in a limiting sense.

[0170] It is also to be understood that the terminology used herein is for the purpose of describing particular aspects only and is not intended to be limiting. The skilled artisan will recognize many variants and adaptations of the aspects described herein. These variants and adaptations are intended to be included in the teachings of this disclosure and to be encompassed by the claims herein.

Claims

LG Ref: LI-PAT005-PCT01CLAIMSWhat is claimed is:

1. A method for training a neural network for interpolation of signals, comprising: providing, to the neural network (116; 300), a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when the sampled signal data is taken to when the analog signal is equal to a threshold event value; determining, by the neural network, a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data; and adjusting parameters of the neural network based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

2. The method of claim 1, comprising: providing a test sampled signal data to the neural network (116; 300) after training; and generating, by the neural network, predicted test threshold event information associated with the test sampled signal data.

3. The method of claim 2, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog-to-digital front end of a measurement instrument (110).

4. The method of claim 1, wherein the plurality of sampled signal data includes at least one of: a rising edge of the analog signal, a falling edge of the analog signal, or a pulse of the analog signal, wherein the parameters of the neural network (116; 300) correspond to at least one of: rising edge parameters, falling edge parameters, or pulse parameters.

5. The method of claim 4, comprising: providing a test sampled signal data to the neural network (116; 300) after training; and generating predicted test threshold event information associated with the test sampled signal data.LG Ref: LI-PAT005-PCT016. The method of claim 5, wherein the plurality of sampled signal data corresponds to a rising edge of the analog signal, and wherein the parameters of the neural network (116; 300) correspond to rising edge parameters for predicting threshold event information in relation to the rising edge, the method comprising: configuring the neural network (116; 300) based on the rising edge parameters, and generating the predicted test threshold event information for the rising edge.

7. The method of claim 5, wherein the plurality of sampled signal data corresponds to the falling edge of the analog signal, and wherein the parameters of the neural network (116; 300) correspond to falling edge parameters for predicting threshold event information in relation to the falling edge, the method comprising: configuring the neural network (116; 300) based on the falling edge parameters, and generating the predicted test threshold event information for the falling edge.

8. The method of claim 5, comprising: prior to generating the predicted test threshold event information: determining that the test sampled signal data includes one of a rising edge, a falling edge, or a pulse, configuring the neural network (116; 300) with parameters associated with the one of the rising edge, the falling edge, or the pulse, and generating the predicted test threshold event information for the determined one of the rising edge, the falling edge, or the pulse.

9. The method of claim 8, wherein: determining that the test sample signal data includes one of the rising edge, the falling edge, or the pulse includes determining that the test sample signal data includes the one of the rising edge, the falling edge, or the pulse based on a neural network (300) classifier.

10. The method of claim 5, wherein the plurality of sampled signal data and the test sampled signal data are provided to a same analog -to-digital front end of a measurement instrument (110).

11. The method of claim 1, wherein the analog signal contains no frequency components above half of a frequency at which it is sampled.

12. The method of claim 1, wherein the analog signal contains frequency components aboveLG Ref: LI-PAT005-PCT01 half of a frequency at which it is sampled.

13. The method of claim 1, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

14. The method of claim 1, wherein the threshold event information indicates a duration from a time when a sample of the sampled signal data nearest to the predicted threshold event is taken to a time of the predicted threshold event.

15. A method, comprising : receiving a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when the sampled signal data is taken to when the analog signal is equal to a threshold event value; and training threshold event prediction circuitry (116), by: providing each sampled signal data in the plurality of sampled signal data to the threshold event prediction circuitry (116), determining a plurality of predicted threshold event information by determining predicted threshold event information corresponding to the threshold event of the analog signal for each sampled signal data in the plurality of sampled signal data, and adjusting parameters of the threshold event prediction circuitry (116) based on errors between each predicted threshold event information in the plurality of predicted threshold event information and a ground truth threshold event information for each of the plurality of sampled signal data.

16. The method of claim 15, wherein the plurality of sampled signal data includes at least one of: a rising edge of the analog signal, a falling edge of the analog signal, or a pulse of the analog signal, wherein the parameters of the threshold event prediction circuitry (116) correspond to at least one of: rising edge parameters, falling edge parameters, or pulse parameters.

17. The method of claim 16, comprising: providing a test sampled signal data to the threshold event prediction circuitry (116) afterLG Ref: LI-PAT005-PCT01 training; and generating predicted test threshold event information associated with the test sampled signal data.

18. The method of claim 17, wherein the plurality of sampled signal data corresponds to a rising edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry (116) correspond to rising edge parameters for predicting threshold event information in relation to the rising edge, the method comprising: configuring the threshold event prediction circuitry (116) based on the rising edge parameters, and generating the predicted test threshold event information for the rising edge.

19. The method of claim 17, wherein the plurality of sampled signal data corresponds to the falling edge of the analog signal, and wherein the parameters of the threshold event prediction circuitry (116) correspond to falling edge parameters for predicting threshold event information in relation to the falling edge, the method comprising: configuring the threshold event prediction circuitry (116) based on the falling edge parameters, and generating the predicted test threshold event information for the falling edge.

20. The method of claim 17, comprising: prior to generating the predicted test threshold event information: determining that the test sampled signal data includes one of a rising edge, a falling edge, or a pulse, configuring the threshold event prediction circuitry (116) with parameters associated with the one of the rising edge, the falling edge, or the pulse, and generating the predicted test threshold event information for the determined one of the rising edge, the falling edge, or the pulse.

21. The method of claim 20, wherein: determining that the test sample signal data includes one of the rising edge, the falling edge, or the pulse includes determining that the test sample signal data includes the one of the rising edge, the falling edge, or the pulse based on a neural network (300) classifier.

22. The method of claim 17, wherein the plurality of sampled signal data and the testLG Ref: LI-PAT005-PCT01 sampled signal data are provided to a same analog-to-digital front end of a measurement instrument (110).

23. The method of claim 15, wherein the analog signal contains no frequency components above half of a frequency at which it is sampled.

24. The method of claim 15, wherein the analog signal contains frequency components above half of a frequency at which it is sampled.

25. The method of claim 15, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

26. The method of claim 15, wherein the threshold event information indicates a duration from a time when a sample of the sampled signal data nearest to the predicted threshold event is taken to a time of the predicted threshold event.

27. The method of claim 15, wherein the threshold event prediction circuitry (116) comprises a trained neural network (300).

28. The method of claim 15, further comprising: receiving an indication of a user selection of the threshold event information; and selectively accessing, by the threshold event prediction circuitry (116), a set of the parameters for predicting the selected threshold event information.

29. The method of claim 15, further comprising: receiving, by the threshold event prediction circuitry (116), an indication of a user selection of the threshold event value.

30. A measurement instrument (110), comprising : an input port (112) configured to receive an analog signal; an analog-to-digital converter (ADC) (114) coupled with the input port (112), the ADC (114) configured to sample the analog signal at a sampling rate and generate test sampled signal data corresponding to a threshold event of the analog signal; and threshold event prediction circuitry (116) coupled with the ADC (114), the threshold event prediction circuitry (116) configured to:LG Ref: LI-PAT005-PCT01 receive the test sample signal data and generate predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

31. The measurement instrument (110) of claim 30, wherein the threshold event prediction circuitry (116) is trained on a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples is taken to when the analog signal is equal to a threshold event value.

32. The measurement instrument (110) of claim 30, wherein the threshold event prediction circuitry (116) is configured to receive threshold event prediction parameters (230) corresponding to a trained neural network (300), and to generate the predicted test threshold event information based on the threshold event prediction parameters (230).

33. The measurement instrument (110) of claim 30, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

34. The measurement instrument (110) of claim 30, wherein the threshold event information indicates a duration from a time when a sample of the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

35. The measurement instrument (110) of claim 32, wherein the threshold event prediction circuitry (116) is configured to: receive an indication of a user selection of the threshold event information; and selectively access a set of the threshold event prediction parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

36. The measurement instrument (110) of claim 30, wherein the threshold event prediction circuitry (116) is configured to: receive an indication of a user selection of the threshold event value; andLG Ref: LI-PAT005-PCT01 configure the threshold event prediction circuitry (116) based on the received indication of the user selection of the threshold event value.

37. A method, comprising: receiving an analog signal; sampling, by an analog -to-digital converter (ADC) (114), the analog signal at a sampling rate; generating, by the ADC (114), test sampled signal data corresponding to a threshold event of the analog signal; and generating, by threshold event prediction circuitry (116), predicted test threshold event information that includes a duration in relation to a sample time of one of the samples in the test sampled signal data when the analog signal is predicted to cross a threshold event value.

38. The method of claim 37, further comprising: training the threshold event prediction circuitry (116) on a plurality of sampled signal data, each sampled signal data in the plurality of sampled signal data including a threshold event information and at least one sample taken during a threshold event of an analog signal, where each threshold event information indicates a duration from a time when one of the samples in the test sampled signal data is taken to when the analog signal is equal to a threshold event value.

39. The method of claim 37, further comprising: receiving, by the threshold event prediction circuitry (116), threshold event prediction parameters (230) from a trained neural network (300); and generating the predicted test threshold event information based on the threshold event prediction parameters (230).

40. The method of claim 37, wherein the threshold event value is at least one of: a threshold voltage value, a threshold current value, a threshold timing value, or a threshold frequency value.

41. The method of claim 37, wherein the threshold event information indicates a duration from a time when a sample in the test sampled signal data nearest to the crossing of the predicted threshold event value is taken to a time of the predicted crossing of the threshold event value.

42. The method of claim 37, further comprising: receiving, by the threshold event prediction circuitry (116), an indication of a userLG Ref: LI-PAT005-PCT01 selection of the threshold event information; and selectively accessing a set of parameters for predicting the selected threshold event information based on the received indication of the user selection of the threshold event information.

43. The method of claim 37, further comprising: receiving, by the threshold event prediction circuitry (116), an indication of a user selection of the threshold event value; and configuring the threshold event prediction circuitry (116) based on the received indication of the user selection of the threshold event value.

Images