Calibration of multidimensional spectrometers

Abstract

Disclosed herein are spectrometer-assisted systems, as well as associated methods, computing devices, and computer-readable media. For example, in some embodiments, a spectrometer-assisted device may receive, for each of a plurality of calibration samples of an analyte of different known concentrations, an array of spectrometer output intensities of the calibration samples, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, and may use the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities to train a machine learning computational model to output a concentration of the analyte in the target sample based on the input array of spectrometer output intensities of the target sample, and may use the trained machine learning computational model as a calibration model of the analyte for subsequent spectrometer operations.

Description

[Background technology]

[0001] Many scientific instruments require calibration, i.e., a correlation between the output of the scientific instrument and a known state or property. A spectrometer, for example, may output an intensity that is a function of a property of a sample, and calibration of such a spectrometer may define the relationship between the output intensity and the property of the sample. Summary of the Invention [Means for solving the problem]

[0002] Disclosed herein are spectrometer-assisted systems, as well as associated methods, computing devices, and computer-readable media. For example, in some embodiments, the spectrometer-assisted apparatus may generate, for each of a plurality of calibration samples of different known concentrations of an analyte, an array of spectrometer output intensities of the calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, and the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities may be used to train a machine learning computational model to output a concentration of the analyte in the target sample based on an input array of spectrometer output intensities of the target sample, and the trained machine learning computational model may be used as a calibration model of the analyte for subsequent spectrometer operations.

[0003] The spectrometer-assisted embodiments disclosed herein may achieve improved performance compared to conventional approaches. In conventional spectroscopic measurements, a user is required to identify a single deflection quantity (representing a diffraction order and wavelength in optical spectroscopic measurements, or a mass-to-charge ratio in mass spectrometry measurements) and use that single deflection quantity to determine the concentration of an analyte in a sample. For example, a user of optical spectroscopic measurements may use a spectrometer to analyze an unknown sample, obtain an output intensity signal with peaks at different diffraction orders and wavelengths, and then be required to select a single diffraction order and wavelength in which the output intensity has a peak, for use in determining the concentration of an analyte associated with the diffraction order and wavelength. However, an analyte (e.g., a single element) is typically associated with multiple peaks in the output intensity signal, and any information provided by these additional peaks is conventionally discarded. Rule-based algorithms regarding which individual peaks should be utilized to determine an analyte concentration often fail due to their inability to account for all analytical conditions and samples. There have been some attempts to utilize the average or sum of the output intensities at different deflection quantities (e.g., diffraction orders / wavelengths or mass-to-charge ratios) to determine the concentration of the analyte of interest, but these attempts have failed to achieve significant improvement over the "single" deflection quantity approach.

[0004] The embodiments disclosed herein enable spectrometer-assisted devices to utilize much more information about the spectrometer's output intensity signal than has previously been utilized in determining analyte concentrations, thus providing improved accuracy in spectrometer technology (e.g., improvements in the computer technology that supports such spectrometers, among other improvements). Furthermore, by reducing the need for expert users to be able to selectively identify the specific amount of bias that is dependent for a particular concentration determination, the embodiments disclosed herein enable non-expert users to comfortably determine analyte concentrations in samples, increasing accuracy, dynamic range, and throughput, and decreasing costs.

[0005] Various of the embodiments disclosed herein may improve upon conventional approaches to achieve the technical advantage of more accurate determination of analyte concentration in a sample by constructing a calibration model that uses more output intensity signals in the concentration determination. Such technical advantages are not achievable with routine conventional approaches, and all users of a system including such embodiments will benefit from these advantages (e.g., by assisting the user in performing a technical task, such as determining the analyte concentration in a sample, by a guided human-machine interaction process). For example, various of the embodiments disclosed herein may enable the performance of calibration-less semi-quantitative analysis that differs from conventional approaches. Thus, the technical features of the embodiments disclosed herein, as well as the combination of features of the embodiments disclosed herein, are clearly unconventional in the field of spectrometry. The computational and user interface features disclosed herein not only involve the collection and comparison of information, but also apply new analytical and technical techniques to modify the operation of the spectrometry assistance system. Thus, the present disclosure introduces functionality that could not be performed by conventional computing devices or humans.

[0006] Thus, embodiments of the present disclosure may be useful for any of a number of technical purposes, such as controlling analyte concentration determinations in a particular technical system or process (e.g., a spectroscopic measurement system or process) and determining characteristics of a sample by processing data obtained from a spectroscopic sensor.

[0007] In some embodiments, the spectrometer support device may include first logic for generating, for each of a plurality of calibration samples of an analyte of different known concentrations, an array of spectrometer output intensities of the calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for training a machine learning computational model using the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities and outputting a concentration of the analyte in the target sample based on an input array of spectrometer output intensities of the target sample; and third logic for using the trained machine learning computational model as a calibration model for the analyte for subsequent spectrometer operations.

[0008] In some embodiments, the spectrometer support device may include first logic for generating an array of spectrometer output intensities for a sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, second logic for providing the received array of spectrometer output intensities to a trained machine learning computational model, where the trained machine learning computational model is for outputting a concentration of an analyte in the sample, and third logic for outputting the concentration of the analyte in the sample.

[0009] In some embodiments, the spectrometer support device may include first logic for generating an array of spectrometer output intensities for the sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, second logic for generating a concentration of an analyte in the sample based on the received array of spectrometer output intensities, and third logic for outputting the concentration of the analyte in the sample and a feature association indicator associated with one or more of the spectrometer output intensities.

[0010] In some embodiments, the spectrometer output device may include first logic for generating an array of spectrometer output intensities for a sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, second logic for generating a concentration of an analyte in the sample based on the received array of spectrometer output intensities without the need for a user to select one or more of the data representing the amounts of deflection prior to generating the concentration of the analyte in the sample, and third logic for outputting the concentration of the analyte in the sample.

[0011] In some embodiments, the spectrometer support device may include first logic for generating, for each of a plurality of calibration samples of an analyte of different known concentrations, an array of spectrometer output intensities of the calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for using the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities to retrain a pre-trained machine learning computation model or to generate a pre-processing method for use with a pre-trained machine learning computation model to output a concentration of the analyte in the target sample based on an input array of spectrometer output intensities of the target sample; and third logic for using the re-trained machine learning computation model or to execute the pre-processing method with the pre-trained machine learning computation model as a calibration model of the analyte for subsequent spectrometer operation.

[0012] These and other embodiments disclosed herein may solve one or more of the technical problems of conventional spectroscopic measurements, such as the technical problem of insufficient calibration that cannot adequately identify analyte concentrations during actual operation and requires a specialized operator to perform, by building, using, and transferring calibration models that use more output intensity signals than conventional approaches in determining concentration.

[0013] The embodiments will be readily understood by the following detailed description taken in conjunction with the accompanying drawings, in which: To facilitate this description, like reference numerals refer to like structural elements, and in which: The embodiments are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which: [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a block diagram of a spectroscopic measurement system configured to perform or facilitate the assistance operations disclosed herein, in accordance with various embodiments. [Diagram 2] 1 is a diagram of a detector array on which an image of an echelle spectrum is formed in a spectrometry system in accordance with various embodiments. [Diagram 3] FIG. 2 is a block diagram of an exemplary spectrometer assistance module for performing assistance operations, according to various embodiments. [Figure 4] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Diagram 5] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 6] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 7] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 8] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 9] 1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 10]1A-1C are diagrams of example arrangements of spectrometer output intensities that may be used by the spectrometer assistance modules disclosed herein, in accordance with various embodiments. [Figure 11] FIG. 1 is a diagram of a machine learning computational model that may be included in a spectrometer assistance module, according to various embodiments. [Figure 12] FIG. 1 is a diagram of a set of training data that may be used to train a machine learning computational model included in a spectrometer assistance module, according to various embodiments. [Figure 13] 1 is a flow diagram of an exemplary method for performing a spectrometer-assisted operation, according to various embodiments. [Figure 14] 1 is a flow diagram of an exemplary method for performing a spectrometer-assisted operation, according to various embodiments. [Figure 15] 1 is a flow diagram of an exemplary method for performing a spectrometer-assisted operation, according to various embodiments. [Figure 16] 1 is a flow diagram of an exemplary method for performing a spectrometer-assisted operation, according to various embodiments. [Figure 17] 1 is a flow diagram of an exemplary method for performing a spectrometer-assisted operation, according to various embodiments. [Figure 18] FIG. 1 is a diagram of an example of a graphical user interface that may be used to implement some or all of the assistance methods disclosed herein, according to various embodiments. [Figure 19] FIG. 1 is a block diagram of an example computing device that may perform some or all of the spectrometer-assisted methods disclosed herein, according to various embodiments. [Figure 20] FIG. 1 is a block diagram of an example spectrometer-assisted system that may perform some or all of the spectrometer-assisted methods disclosed herein, according to various embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] In the following detailed description, reference is made to the accompanying drawings which form a part of this specification, in which like numerals designate like parts throughout and which show, by way of illustration, embodiments which may be implemented. It is to be understood that other embodiments may be utilized and structural or logical changes may be made without departing from the scope of the present disclosure. Therefore, the following detailed description is not to be taken in a limiting sense.

[0016] Various operations may be described as multiple separate actions or operations, in the order that is most helpful in understanding the subject matter disclosed herein. However, the order of description should not be construed as implying that these operations are necessarily order dependent. In particular, these operations may not be performed in the order presented. The operations described may be performed in a different order than in the described embodiment. Various additional operations may be performed and / or described operations may be omitted in additional embodiments.

[0017] FIG. 1 is a block diagram of a spectroscopic measurement system 10 configured to perform or facilitate the supporting operations disclosed herein, according to various embodiments. In particular, FIG. 1 illustrates an optical spectroscopic measurement system 10, but the embodiments disclosed herein may also be used with other types of spectroscopic measurement systems, such as mass spectrometry measurement systems. The optical spectroscopic measurement system 10 of FIG. 1 may include a light source 11, an optical device 12, a detector array 13, a processor 14, a memory 15, and an input / output (I / O) unit 16. The light source 11 may be a plasma source, such as an inductively coupled plasma (ICP) source. The optical device 12 may include an echelle grating and a prism (and / or further gratings) to generate an echelle spectrum of the light generated by the light source 11. An image of the two-dimensional echelle spectrum may be formed on the detector array 13. Such an image is further described below with reference to FIG. 2. The detector array 13 may be, for example, a charge-coupled device (CCD) array. Detector array 13 includes an array of detector elements or pixels that generate output signals representative of detected spectral values, and in some embodiments detector array 13 may have at least about 1024 x 1024 pixels (1 megapixels). Rectangular detector array 13 may be, but is not necessarily, square.

[0018] The detector array 13 may be configured to generate spectral values ​​corresponding to the detected amounts of light in the echelle spectrum and transfer the spectral values ​​to the processor 14. The processor 14 may include one or more commercially available processing devices, such as one or more commercially available microprocessors (e.g., any one or more of the processing devices 4002 discussed below with reference to FIG. 19). The memory 15 may include any one or more suitable storage devices, such as one or more suitable semiconductor memory devices (e.g., any one or more of the storage devices 4004 discussed below with reference to FIG. 19), and may be used to store non-transitory computer readable instructions that, when executed by the processor 14, cause the spectroscopy measurement system 10 to perform one or more embodiments of the methods disclosed herein. The I / O unit 16 may include any suitable circuitry (e.g., interface device 4006, display device 4010, or any one or more of other I / O devices 4012 discussed below with reference to FIG. 19) and may be configured to input data or commands to the spectroscopy measurement system 10, output data from the spectroscopy measurement system 10, and / or enable communication between the spectroscopy measurement system 10 and other instruments or computing devices. Some or all of the components of the spectroscopy measurement system 10 may together implement a spectrometer support module 1000 disclosed herein (e.g., as discussed below with reference to FIG. 3), or the spectrometer support module 1000 may be implemented by another set of hardware and / or software components and may communicate with the spectroscopy measurement system 10 via the I / O unit 16.

[0019] FIG. 2 illustrates the detector array 13 on which an echelle spectrum 20 is imaged in the spectroscopic measurement system 10, according to various embodiments. The echelle spectrum 20 is illustrated in FIG. 2 as including diffraction orders 7 that each extend approximately horizontally. That is, the diffraction orders 7 extend approximately in a first direction of the detector array 13, which may be referred to as the x-direction in the example of FIG. 2. The diffraction orders 7 therefore extend approximately perpendicular to a second direction of the detector array 13 that is perpendicular to the first direction, which may be referred to as the y-direction. The diffraction orders 7 of the echelle spectrum 20 are typically slightly curved, so that the degree to which the diffraction orders 7 are parallel or perpendicular to the first and second directions may vary across the echelle spectrum.

[0020] 2, the first direction (x-direction) is parallel to the long side of the rectangular detector array 13, while the second direction (y-direction) is parallel to the short side. It will be understood that the orientation of the detector array is selected to best fit the two-dimensional spectrum, and that the terms first direction and second direction are interchangeable.

[0021] Diffraction orders 7 are regions of high light intensity and, therefore, high spectral value. The diffraction orders 7 are separated by valleys or troughs 8 of low light intensity and therefore low spectral value. An echelle spectrum 20 typically has one or more spectral value peaks that are characteristic of a particular substance. For example, when using an ICP as light source 11 to generate the echelle spectrum 20, a peak is typically present that represents the presence of carbon dioxide. In FIG. 2, a first peak 1 and a second peak 2 are represented diagrammatically. In an actual echelle spectrum 20, typically three or more peaks will be present. Each peak is located in a diffraction order 7 and constitutes, at least locally, a maximum value for that diffraction order 7. It can be seen that each peak extends in both a first direction (x direction in FIG. 2) and a second direction (y direction in FIG. 2). It should be noted that in a typical embodiment, the peaks may have a length and width of only a few pixels, for example, 3-5 pixels.

[0022] Different substances will produce peaks at various locations in the optical spectrum. As discussed above, a single peak in the optical spectrum is traditionally used to identify an analyte (e.g., a single element) in a sample being tested by the spectroscopic measurement system 10. However, an analyte is typically associated with multiple peaks in the output intensity signal, and any information provided by these additional peaks is traditionally discarded. As discussed further below, the embodiments disclosed herein enable a spectrometer support device (which may be implemented by the spectroscopic measurement system 10 or by another system in communication with the spectroscopic measurement system 10) to utilize much more information about the spectrometer output intensity signal than previously utilized in determining analyte concentrations, thus providing improved accuracy to spectrometer technology (e.g., improvements in computer technology supporting such spectrometers, among other improvements).

[0023] 3 is a block diagram of a spectrometer assistance module 1000 for performing assistance operations, according to various embodiments. The spectrometer assistance module 1000 may be implemented by a circuit (e.g., including electrical and / or optical components) such as a programmed computing device. The logic of the spectrometer assistance module 1000 may be included in a single computing device or may be distributed across multiple computing devices in communication with each other as needed. An example of a computing device that may implement the spectrometer assistance module 1000, alone or in combination, is discussed with reference to the computing device 4000 of FIG. 19, and an example of a system of interconnected computing devices in which the spectrometer assistance module 1000 may be implemented across one or more of the computing devices is discussed herein with reference to the spectrometer assistance system 5000 of FIG. 20. The spectrometer support module 1000 may be implemented, for example, by the spectroscopic measurement system 10 of FIG. 1 (e.g., together with some or all of the processor 14, memory 15, and I / O unit 16), by another spectroscopic measurement system 10, or by a computing system in communication with a spectroscopic measurement system such as the spectroscopic measurement system 10 of FIG. 1.

[0024] The spectrometer support module 1000 may include spectrometer intensity logic 1002, training logic 1004, analyte concentration logic 1006, and output logic 1008. As used herein, the term "logic" may include an apparatus that performs a set of operations associated with the logic. For example, any of the logic elements included in the spectrometer support module 1000 may be implemented by one or more computing devices programmed with instructions that cause one or more processing devices of the computing devices to perform a set of associated operations. In certain embodiments, the logic elements may include one or more non-transitory computer-readable media having instructions that, when executed by one or more processing devices of the one or more computing devices, cause the one or more computing devices to perform the set of associated operations. As used herein, the term "module" may refer to a collection of one or more logic elements that together perform a function associated with the module. Different ones of the logic elements in a module may take the same form or different forms. For example, some logic in a module may be implemented by a programmed general-purpose processing device, while other logic in a module may be implemented by an application-specific integrated circuit (ASIC). In another embodiment, different ones of the logic elements in a module may be associated with different sets of instructions executed by one or more processing devices. A module may not include all of the logic elements shown in the associated figure, e.g., a module may include a subset of the logic elements shown in the associated figure when the module performs a subset of the operations discussed herein with reference to the module.

[0025] The spectrometer intensity logic 1002 may generate an array of spectrometer output intensities based on data output by the spectrometer as the spectrometer is analyzing a sample. During analysis, the spectrometer may separate spectral components associated with analytes present in the sample (e.g., the elemental composition of the sample) by deflecting these spectral components differently onto a detector, and the intensities measured at the detector for different amounts of deflection may provide a signature of one or more analytes present in the sample. For example, as described above with reference to Figures 1 and 2, an optical spectrometer may include a diffraction grating or other optical element that deflects radiation of different wavelengths differently to one or more locations on the detector such that the intensity of the incident radiation at a location on the detector represents an intensity associated with a particular wavelength of radiation. In another example, a mass spectrometer may include electric and / or magnetic fields that deflect ions of different mass to charge ratios differently to locations on the detector such that the intensity of the incident ions at a location on the detector represents an intensity associated with a particular mass to charge ratio. Thus, for any sample analyzed by the spectrometer, the spectrometer intensity logic 1002 may generate an array of spectrometer output intensities associated with the sample, and different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection (e.g., diffraction order / wavelength or mass-to-charge ratio). As used herein, "amount of deflection" includes amounts of dispersion, as appropriate in a given spectroscopic measurement system. The embodiments disclosed herein may be used with any characteristic of the output of a spectrometer that, like amount of deflection, represents multiple characteristic observables that act as proxies for the identity of the analyte in the sample.

[0026] 4-10 show exemplary arrays of spectrometer output intensities that may be used by spectrometer support module 1000, according to various embodiments. In particular, any of the arrays of spectrometer output intensities shown in FIGS. 4-10 may be generated by spectrometer intensity logic 1002 based on intensity data provided to spectrometer intensity logic 1002 by a spectrometer. The arrays of spectrometer output intensities generated by spectrometer intensity logic 1002 may be background corrected intensities, where the background correction is performed according to any suitable technique (e.g., any suitable background correction technique known in the art). Although FIGS. 4-10 and the other accompanying figures may describe the spectrometer output intensity as a function of diffraction order / wavelength (as appropriate for optical spectroscopy measurements), this is merely for ease of explanation, and the spectrometer output intensity may also be a function of other parameters that represent the amount of deflection (e.g., mass-to-charge ratio, as appropriate for mass spectrometry measurements, etc.).

[0027] FIG. 4 illustrates an array of spectrometer output intensities 102 in the form of a plot of intensity as a function of wavelength. The array of spectrometer output intensities 102 illustrated in FIG. 4 may include several peaks at specific wavelengths (e.g., wavelengths labeled WL1, WL2, ..., WL8). The wavelengths at which peaks occur in the array of spectrometer output intensities 102 may be a function of the analytes (e.g., elements) present in the sample under analysis by the spectrometer, and the magnitude of the associated intensity at these peaks may indicate the concentration of the analyte in the sample. For single element samples, the wavelength locations of these peaks (referred to herein as "peak wavelengths") may be characteristic of that element (e.g., in optical emission spectroscopy, peak wavelengths associated with aluminum may include 185.580 nanometers, 220.462 nanometers, etc.). FIG. 5 shows the same array of spectrometer output intensities 102 shown in FIG. 4, but in a "heat map" format in which peaks in the array of spectrometer output intensities 102 of FIG. 4 are represented as having "lighter" grayscale values ​​at locations associated with wavelengths WL1, WL2, ..., WL8, as shown.

[0028] The spectrometer intensity logic 1002 may generate an array of spectrometer output intensities 102 for each of a number of different samples. In particular, during calibration, the spectrometer intensity logic 1002 may generate an array of spectrometer output intensities 102 for each of a number of calibration samples, where the different calibration samples have different known concentrations of an analyte of interest (e.g., an element of interest). For example, during calibration, the spectrometer may be provided with different single-element solution calibration samples having different known concentrations of molybdenum or another element of interest, and the spectrometer intensity logic 1002 may generate a different array of spectrometer output intensities 102 for each of these calibration samples. FIG. 6 shows a set of five such arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-5) associated with five different concentrations (labeled C1, C2, ..., C5) of the analyte of interest in the corresponding calibration samples. In the particular example of FIG. 6, the concentration of the analyte of interest may increase from C1 to C5, and it should be noted that as the concentration of the analyte of interest increases, the magnitude of the intensity in the corresponding array of spectrometer output intensities 102 increases.

[0029] As shown in Figures 4 and 5, the array of spectrometer output intensities 102 may be represented in any of a number of ways. For example, Figure 7 shows a set of five arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-5) associated with five different concentrations (labeled C1, C2, ..., C5) of an analyte of interest in a corresponding calibration sample, including five wavelengths (labeled W1, W2, ..., W5) at which intensity peaks occur. Figure 8 shows the same set of five arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-5) associated with five different concentrations (labeled C1, C2, ..., C5) of an analyte of interest in a corresponding calibration sample, but now only the magnitude of the peaks is of interest, represented as a set of the intensity magnitudes of the peaks at each of the five wavelengths (labeled W1, W2, ..., W5). For example, the array of spectrometer output intensities 102-5 in Figure 8 exhibits a magnitude of approximately 50 units for the peak associated with wavelength WL1, a magnitude of approximately 80 units for the peak associated with wavelength WL2, etc. Figure 8 thus illustrates one way in which the array of spectrometer output intensities 102 may be specified (i.e., by the magnitude of the peak for each of the associated peak wavelengths).

[0030] Figures 9-10 show another way in which an array of spectrometer output intensities 102 may be represented. Figure 9 is a reproduction of Figure 7 (for clarity of illustration) that includes a set of five arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-5) associated with five different concentrations (labeled C1, C2, ..., C5) of an analyte of interest in a corresponding calibration sample, including five wavelengths (labeled W1, W2, ..., W5) at which intensity peaks occur. 10 shows the same set of five arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-5) associated with five different concentrations (labeled C1, C2, ..., C5) of the analyte of interest in the corresponding calibration samples, but now only the relative peak magnitudes are of interest, expressed as an aggregate of the relative intensity magnitudes of the peaks at each of the five wavelengths (labeled W1, W2, ..., W5). For example, the array of spectrometer output intensities 102-5 in FIG. 10 shows that approximately 25% of the total aggregate intensity magnitude of the peaks associated with wavelengths WL1, WL2, ..., WL5 is provided by the intensity magnitude of the peak associated with wavelength WL1, approximately 72% of the total aggregate intensity magnitude of the peaks associated with wavelengths WL1, WL2, ..., WL5 is provided by the intensity magnitude of the peak associated with wavelength WL2, etc. Thus, FIG. 10 illustrates another way in which an array of spectrometer output intensities 102 can be specified (ie, by the relative peak magnitudes for each of the associated peak wavelengths).

[0031] The training logic 1004 may use the sequence of spectrometer output intensities 102 of the calibration samples together with the known concentrations of the analyte of interest in the calibration samples to train a machine learning computational model to output a concentration of the analyte of interest in the target sample based on the input sequence of spectrometer output intensities 102 of the target sample. In particular, the training logic 1004 may adjust parameters of an untrained or pre-trained machine learning computational model according to known training techniques such that when a sequence of spectrometer output intensities 102 associated with a calibration sample of known concentration is input to the machine learning computational model, the output of the machine learning computational model is equal to or close to the value of the known concentration. Such a trained machine learning computational model may thus be used as a calibration model of the analyte of interest for a subsequent spectrometer operation that relates spectrometer intensity output to analyte concentration.

[0032] FIG. 11 is a diagram of a machine learning computational model 110 that may be trained by the training logic 1004 using the calibration data. The number of nodes in the input layer of the machine learning computational model 110 may be equal to the dimension of the tensor provided to the machine learning computational model 110, and an example number of tensors that may be provided to the machine learning computational model 110 is described below with reference to FIG. 12. The number of hidden layers in the machine learning computational model 110, the number of nodes in each hidden layer, and the connectivity between layers may take any suitable value. For example, in some embodiments, the machine learning computational model 110 may include 8 hidden layers, 12-128 nodes in each hidden layer, and full (also referred to as "dense") connectivity between layers. In some particular embodiments, the number of nodes in a particular layer increases for the first layer (e.g., increases between 12 and 128 in the first six layers) and decreases for the last layer (e.g., decreases from 128 to 1 for the output layer). The activation functions used between layers, the error functions used to train the machine learning computational model 110, and the training technique itself may be selected as suitable. For example, in some embodiments, the activation function used between layers may be rectified linear (ReLu), the error function used to train the machine learning computational model may be mean standard error (MSE), and the training technique used to train the machine learning computational model 110 may be gradient-based. In some embodiments, the number of output nodes in the machine learning computational model 110 may be 1 (corresponding to the concentration of the analyte of interest in the target sample, as discussed above). As known in the art, the training data (i.e., the array of spectrometer output intensities 102 of the calibration samples along with the known concentration of the analyte of interest in the calibration samples) may be normalized, encoded / decoded, or otherwise processed as part of training and using the machine learning computational model 110.

[0033] As discussed above, the array of spectrometer output intensities 102 input to the machine learning computational model 110 may take any of a number of forms. For example, FIG. 12 illustrates a set of training data 112 that may be generated by the spectrometer intensity logic 1002 and used by the training logic 1004 to train the machine learning computational model 110, according to various embodiments. The training data 112 may include a set of arrays of spectrometer output intensities 102 (labeled 102-1, 102-2, ..., 102-N) and their associated concentrations labeled (C1, C2, ..., CN). Each array of spectrometer output intensities 102 may include a first subarray 102A that includes a magnitude of the spectrometer output intensity at each of a number of peak wavelengths (labeled WL1, WL2, ..., WLM) associated with an analyte of interest. In some embodiments, each array of spectrometer output intensities 102 may also include a second subarray 102B that includes pairwise ratios of the magnitudes of spectrometer output intensities at different peak wavelengths (e.g., the magnitude of the intensity associated with peak wavelength WL1 divided by the magnitude of the intensity associated with peak wavelength WL2, labeled WL1 / WL2, etc.). For analytes whose relative magnitudes associated with peak wavelengths are consistent across different concentrations of the analyte of interest (as described above with reference to FIG. 10), including ratios of different peak magnitudes in the tensor input to the machine learning computational model 110 may aid in training the machine learning computational model 110 in more quickly recognizing the relevance of this information in determining the concentration of the analyte of interest in a sample. In some embodiments, the array of spectrometer output intensities 102 input to the machine learning computational model 110 may include only the first subarray 102A and may not include the second subarray 102B, or may include other representations of the array of spectrometer output intensities 102 (e.g., other functions or combinations of the intensity at different peak wavelengths and / or the magnitude of the intensity data at non-peak wavelengths).Furthermore, the array of spectrometer output intensities 102 input to the machine learning computational model 110 may not represent the intensity magnitudes at all peak wavelengths associated with the analyte of interest, but may represent the intensity magnitudes at a subset of the peak wavelengths.

[0034] The training logic 1004 may train a different machine learning computational model 110 for each different analyte of interest. For example, the training logic 1004 may use calibration data for each of a plurality of single element samples to generate a plurality of associated machine learning computational models 110, each associated with a different specific element. In other embodiments, a single machine learning computational model 110 may be trained to generate concentrations of a plurality of analytes of interest based on an array of spectrometer output intensities 102, and in such embodiments, the number of output nodes of the machine learning computational model 110 may be equal to the number of analytes whose concentrations may be determined by the machine learning computational model 110. Although various of the embodiments disclosed herein may be described with reference to a single analyte of interest associated with a single machine learning computational model 110, this is merely for ease of illustration, and any of the techniques disclosed herein may generate concentrations of a plurality of analytes of interest using a single machine learning computational model 110.

[0035] In some embodiments, the training logic 1004 may use training data including one or more saturated spectrometer output intensities to train the machine learning computational model 110. Traditionally, peak wavelengths where the spectrometer output intensity saturates (i.e., reaches the upper limit of the intensity that can be resolved by the detector) are discarded during subsequent analysis. However, the techniques disclosed herein allow intensity data associated with multiple peak wavelengths to be used together to determine analyte concentration, and thus having the training logic 1004 use some training data including saturated intensities may help the machine learning computational model 110 to contextualize such data and, when input, rely more heavily on non-saturated intensities to make appropriate concentration determinations. Because the analyte concentration determination techniques disclosed herein can properly determine concentration even when saturation occurs (and when there are no low sensitivity peaks from the intensity signal representing a low concentration sample), the spectrometer assistance module 1000 disclosed herein can significantly increase the dynamic range of the spectrometer over conventional approaches. In some embodiments, the training data may be preprocessed by the training logic 1004 to remove some or all of the saturated or otherwise aberrant spectrometer output intensities before being used to train the machine learning computational model. For example, the training logic 1004 may preprocess the training data by performing an initial linearity check, during which the magnitudes of peaks associated with different samples are compared to determine whether the ratio of the peak magnitudes is approximately equal to the ratio of the concentrations of the associated analytes in the samples, as would be expected based on the laws of physics. If one or more peaks fail this linearity check (e.g., due to saturation, insufficient intensity, or interference), the peaks may be discarded from the set of data used to train the machine learning computational model.

[0036] In some embodiments, the training logic 1004 may retrain the machine learning computational model 110. For example, when a calibration of a spectrometer is re-run for a particular analyte, the training logic 1004 may use the new calibration data to retrain the pre-trained machine learning computational model 110 (e.g., to correct for drift or other changes since the previous calibration and / or to improve the quality of the calibration by using more data). In another example, a machine learning computational model 110 trained to output the concentration of one or more particular analytes at a particular spectrometer may be retrained by the training logic 1004 to output the concentration of the analytes at a different spectrometer. When retraining the machine learning computational model 110 for a different spectrometer, the training logic 1004 may use a transfer learning technique in which only the last fully connected layer of the pre-trained machine learning computational model 110 (or another subset of the parameters of the pre-trained machine learning computational model 110) is retrained while other parameters remain fixed. Utilizing such techniques may reduce the training burden associated with building machine learning computational models 110 for other spectrometers while still achieving customization of the machine learning computational model 110 for the particular spectrometer at hand. Transfer learning approaches may also take into account the operating conditions (e.g., acquisition settings) of different instruments, which may be used in combination with the training data described above (which may cover all elements of interest across a concentration range that covers the dynamic range of the instrument) to build a complete model of the behavior of the first instrument, which may then be easily deployed on a second instrument by performing a set of linear transformations of the complete model from the first instrument.

[0037] In some embodiments, the training logic 1004 may perform transfer learning techniques that do not require retraining of the machine learning computational model 110. The training logic 1004 may be configured to do such techniques, for example, when the internal or operating conditions of the device change (which may result in changes in the measured intensity for the same concentration of a given analyte) or when deploying the machine learning computational model 110 to a second device with different operating conditions. In both such cases, the training logic 1004 may renormalize the intensities before the machine learning computational model 110 is used to output concentration data. To renormalize the intensities, the training logic 1004 may utilize a new sequence of intensities that represent at least one known concentration of the selected analyte measured by the device. These concentrations need not be predefined and can be selected, for example, by a user or service technician of the device. In some embodiments, the concentrations may be selected to fall within a linear regime of a calibration curve for the selected analyte, while in other embodiments, the concentrations need not fall within such a linear regime (e.g., as the linear regime changes as the machine learning computational model 110 is retrained with more data). The training logic 1004 may use an existing trained machine learning computational model 110 to generate the set of regularization parameters by generating a function of the form: I[I1,I2,I3,...,In]=f(concentration), It returns an array of intensities (I1, I2, I3, ..., In), one for each observed spectral emission of a particular element, associated with a given concentration value in the same normalized intensity-concentration space used to train the machine learning computational model 110. This function may take any of a number of forms, for example, the function may be represented as a lookup table containing tuple values ​​of (intensity, concentration) evaluated over a concentration span (which may cover the entire dynamic range of the instrument), or as a machine learning based function trained to map concentration values ​​back to an array of intensities, among other forms. Using this function, the training logic 1004 may convert the measured array of intensities into the normalized intensity-concentration space of the machine learning computational model 110. The analyte concentration logic 1004 may then use the converted intensity array with the existing machine learning computational model 110 to predict the concentration of a given analyte in a sample.

[0038] The analyte concentration logic 1006 may use the trained machine learning computational model 110 as a calibration model during subsequent spectrometer operation. In particular, when the spectrometer is used to analyze a sample in which the concentration of the analyte is unknown, the spectrometer intensity logic 1002 may generate an array of spectrometer output intensities 102 associated with the sample and provide the array of spectrometer output intensities 102 to the trained machine learning computational model 110, which outputs the concentration of the analyte in the sample. Thus, in contrast to conventional approaches, the spectrometer assistance module 1000 may generate the analyte concentration without the user having to select a diffraction order / wavelength, mass-to-charge ratio, or other specific data representing the amount of deflection prior to generating the concentration of the analyte, reducing the burden on the user and making trouble-free operation of the spectrometer achievable by non-expert users.

[0039] In some embodiments, the analyte concentration logic 1006 may also generate one or more feature relevance indicators associated with the analyte concentration output by the machine learning computational model. The feature relevance indicators may indicate which of the elements in the array 102 of spectrometer output intensities were more important to the determination of the analyte concentration than other spectrometer output intensities. In some embodiments, the feature relevance indicators may include which of the peak wavelengths (and their associated intensity magnitudes) were most predictive of the analyte concentration (e.g., when the array of spectrometer output intensities 102 includes the first subarray 102A of FIG. 12 ) and / or which of the peak wavelengths (and their associated intensity magnitudes) were most predictive of the analyte concentration (e.g., when the array of spectrometer output intensities 102 includes the second subarray 102B of FIG. 12 or other combination of intensity data). For example, the analyte concentration logic 1006 may generate a list of the most relevant diffraction orders, peak wavelengths, or combinations of peak wavelengths for particulate analyte concentration determination. The analyte concentration logic 1006 may implement any feature relevance scoring method known in the art, such as linear regression feature relevance, logistic regression feature relevance, or decision tree feature relevance.

[0040] In some embodiments, the analyte concentration logic 1006 may perform further processing on the output of the trained machine learning computational model to identify the concentration of the analyte in the sample. For example, in some embodiments, the analyte concentration logic 1006 may utilize the feature relevance indicators to identify which peak wavelengths were most important to the output of the machine learning computational model and may use the intensity magnitudes of these peak wavelengths to determine the analyte concentration. In some particular embodiments, the analyte concentration logic 1006 may round the analyte concentration indicated by the intensity magnitudes of these "most important" peak wavelengths and may use a mode of the rounded intensity magnitudes to determine the analyte concentration. In some other particular embodiments, the analyte concentration logic 1006 may calculate a weighted average of the analyte concentration indicated by the intensity magnitudes of the "most important" peak wavelengths, with weights assigned to each peak wavelength according to the feature relevance indicators (e.g., representing the relative influence of the output intensities associated with different ones of the peak wavelengths). In other particular embodiments, the analyte concentration logic 1006 may round up the analyte concentrations as indicated by the intensity magnitudes of all peak wavelengths, sort the analyte concentrations by decreasing frequency, and calculate a weighted average of the set of analyte concentrations that occur with the greatest frequency.

[0041] The output logic 1008 may output the concentration of the analyte in the sample determined by the analyte concentration logic 1006 (using the trained machine learning computational model 110). In some embodiments, the output logic 1008 may also output one or more feature relevance indicators generated by the analyte concentration logic 1006 (e.g., to allow a user to verify which peak wavelengths were selected as most important for the analyte concentration determination). In some embodiments, the output logic 1008 may output the analyte concentration and / or the feature relevance indicator to a display device (e.g., via a graphical user interface (GUI) such as GUI 3000 of FIG. 18). In some embodiments, the output logic 1008 may output the analyte concentration and / or the feature relevance indicator to a storage device (e.g., storage device 4004 of computing device 4000 of FIG. 19). In some embodiments, the output logic 1008 may output the analyte concentration and / or feature relevance indicator to an interface device (e.g., interface device 4006 of computing device 4000 of FIG. 19) for transmission to a local or remote computing device.

[0042] 13-17 are flow diagrams of methods of performing spectrometer-assisted operations, according to various embodiments. Although the operations of the methods of FIGS. 13-17 may be illustrated with reference to certain embodiments disclosed herein (e.g., the spectrometer-assisted module 1000 discussed herein with reference to FIG. 3, the GUI 3000 discussed herein with reference to FIG. 18, the computing device 4000 discussed herein with reference to FIG. 19, and / or the spectrometer-assisted system 5000 discussed herein with reference to FIG. 20), the methods of FIGS. 13-17 may be used in any suitable configuration to perform any suitable assisted operations. Although the operations are shown in a particular order once each in FIGS. 13-17, the operations may be reordered and / or performed repeatedly as desired and appropriate (e.g., various operations performed may be performed in parallel, as appropriate).

[0043] 13, an array of spectrometer output intensities of calibration samples may be generated for each of a plurality of calibration samples of an analyte at different known concentrations at 2002. Different ones of the spectrometer output intensities in the array may be associated with data representing different amounts of deflection. For example, spectrometer intensity logic 1002 of spectrometer support module 1000 may perform the operations of 2002.

[0044] In 2004, the machine learning computational model may be trained using a plurality of known concentrations of the analyte in the calibration samples and a plurality of associated sequences of spectrometer output intensities to output a concentration of the analyte in the target sample based on an input sequence of spectrometer output intensities of the target sample. For example, training logic 1004 of spectrometer assistance module 1000 may perform the operations of 2004.

[0045] In 2006, the trained machine learning computational model may be used as a calibration model of the analyte for subsequent spectrometer operations. For example, the analyte concentration logic 1006 of the spectrometer support module 1000 may perform the operations of 2006.

[0046] 14 , an array of spectrometer output intensities for a sample may be generated at 2102. Different ones of the spectrometer output intensities in the array may be associated with data representing different amounts of deflection. For example, spectrometer intensity logic 1002 of spectrometer support module 1000 may perform the operations of 2102.

[0047] At 2104, the received sequence of spectrometer output intensities may be provided to a trained machine learning computational model for outputting a concentration of an analyte in the sample. For example, the analyte concentration logic 1006 of the spectrometer support module 1000 may perform the operations of 2104.

[0048] The concentration of the analyte in the sample may be output at 2106. For example, the output logic 1008 of the spectrometer support module 1000 may perform the operations of 2106.

[0049] 15 , an array of spectrometer output intensities for a sample may be generated at 2202. Different ones of the spectrometer output intensities in the array may be associated with data representing different amounts of deflection. For example, spectrometer intensity logic 1002 of spectrometer support module 1000 may perform the operations of 2202.

[0050] At 2204, a concentration of the analyte in the sample may be generated based on the received sequence of spectrometer output intensities. For example, the analyte concentration logic 1006 of the spectrometer support module 1000 may perform the operations of 2204.

[0051] A feature relevance indicator associated with one or more of the concentration of the analyte in the sample and the spectrometer output intensity may be output at 2206. For example, the output logic 1008 of the spectrometer support module 1000 may perform the operations of 2206.

[0052] 16 , an array of spectrometer output intensities for a sample may be generated at 2302. Different ones of the spectrometer output intensities in the array may be associated with data representing different amounts of deflection. For example, spectrometer intensity logic 1002 of spectrometer support module 1000 may perform the operations of 2302.

[0053] At 2304, a concentration of the analyte in the sample may be generated based on the received sequence of spectrometer output intensities without the need for a user to select one or more of the data representing the amount of deflection prior to generating the concentration of the analyte. For example, the analyte concentration logic 1006 of the spectrometer support module 1000 may perform the operations of 2304.

[0054] The concentration of the analyte in the sample may be output at 2306. For example, the output logic 1008 of the spectrometer support module 1000 may perform the operation of 2306.

[0055] 17 , an array of spectrometer output intensities of a calibration sample may be generated for each of a plurality of calibration samples of an analyte at different known concentrations at 2402. Different ones of the spectrometer output intensities in the array may be associated with data representing different amounts of deflection. For example, spectrometer intensity logic 1002 of spectrometer support module 1000 may perform the operations of 2402.

[0056] At 2404, the pre-trained machine learning computational model may be re-trained using a plurality of known concentrations of the analyte in the calibration samples and a plurality of associated sequences of spectrometer output intensities to output a concentration of the analyte in the target sample based on the input sequence of spectrometer output intensities of the target sample. Alternatively, at 2404, a pre-processing method may be generated (e.g., to perform normalization as described above) for use with the pre-trained machine learning computational model. For example, the training logic 1004 of the spectrometer support module 1000 may perform the operations of 2404.

[0057] At 2406, the retrained machine learning computational model may be used as a calibration model of the analyte for a subsequent spectrometer operation. Alternatively, at 2406, the pre-processing method generated at 2404 may be executed with the pre-trained machine learning computational model as a calibration model of the analyte for a subsequent spectrometer operation. For example, the analyte concentration logic 1006 of the spectrometer support module 1000 may perform the operations of 2406.

[0058] The spectrometer-assisted methods disclosed herein may include interactions with a human user (e.g., via a user local computing device 5020 discussed herein with reference to FIG. 20). These interactions may include providing information to the user (e.g., information regarding the operation of a spectrometer such as spectrometer 5010 of FIG. 20, information regarding the sample being analyzed, or information regarding other tests or measurements performed by the spectrometer, information retrieved from a local or remote database, or other information) or providing the user with options to enter commands (e.g., to control the operation of a spectrometer such as spectrometer 5010 of FIG. 20 or to control the analysis of data generated by the spectrometer), queries (e.g., to a local or remote database), or other information. In some embodiments, these interactions may be implemented through a graphical user interface (GUI) including a visual display on a display device (e.g., display device 4010 discussed herein with reference to FIG. 19 ) that provides output to the user and / or prompts the user to provide input (e.g., via one or more input devices such as a keyboard, mouse, trackpad, or touch screen, included in other I / O devices 4012 discussed herein with reference to FIG. 19 ). The spectrometer support systems disclosed herein may include any suitable GUI for interaction with a user. In some embodiments, the output logic 1008 may provide any of the GUIs disclosed herein.

[0059] 18 illustrates an exemplary GUI 3000 that may be used in implementing some or all of the assistance methods disclosed herein, according to various embodiments. As described above, the GUI 3000 may be provided on a display device (e.g., the display device 4010 discussed herein with reference to FIG. 19) of a computing device (e.g., the computing device 4000 discussed herein with reference to FIG. 19) of a spectrometer assistance system (e.g., the spectrometer assistance system 5000 discussed herein with reference to FIG. 20), and a user may interact with the GUI 3000 using any suitable input device (e.g., any of the input devices included in the other I / O devices 4012 discussed herein with reference to FIG. 19) and input technology (e.g., cursor movement, motion capture, face recognition, gesture detection, voice recognition, button activation, etc.).

[0060] GUI 3000 may include a data display area 3002, a data analysis area 3004, a spectrometer control area 3006, and a settings area 3008. The particular number and arrangement of areas shown in Figure 18 is merely illustrative, and any number and arrangement of areas, including any desired characteristics, may be included in GUI 3000.

[0061] The data display area 3002 may display data generated by a spectrometer (e.g., spectrometer 5010 discussed herein with reference to FIG. 20). For example, the data display area 3002 may display an output intensity signal from the spectrometer (which may be background corrected or otherwise processed by spectrometer intensity logic 1002).

[0062] The data analysis area 3004 may display the results of the data analysis (e.g., the results of analyzing the data illustrated in the data display area 3002 and / or other data). For example, the data analysis area 3004 may display the concentration of an analyte of interest in the sample (e.g., as determined by the analyte concentration logic 1006 according to any of the embodiments disclosed herein), one or more feature relevance indicators (e.g., as determined by the analyte concentration logic 1006 according to any of the embodiments disclosed herein), or any other suitable information. In some embodiments, the data display area 3002 and the data analysis area 3004 may be combined within the GUI 3000 (e.g., to include the data output from the spectrometer and some analysis of the data in a common graph or area).

[0063] The spectrometer control area 3006 may include options that allow a user to control a spectrometer (e.g., spectrometer 5010 discussed herein with reference to FIG. 20). For example, the spectrometer control area 3006 may include options for initiating or otherwise controlling analysis of a sample by the spectrometer.

[0064] The settings area 3008 may include options that enable a user to control features and functions of the GUI 3000 (and / or other GUIs) and / or perform common computing operations related to the data display area 3002 and the data analysis area 3004 (e.g., saving data such as analyte concentrations and / or feature relevance indicators on a storage device such as storage device 4004 as discussed herein with reference to FIG. 19, transmitting data such as analyte concentrations and / or feature relevance indicators to another user, displaying data, etc.).

[0065] As mentioned above, the spectrometer assistance module 1000 may be implemented by one or more computing devices. FIG. 19 is a block diagram of a computing device 4000 that may perform some or all of the spectrometer assistance methods disclosed herein, according to various embodiments. In some embodiments, the spectrometer assistance module 1000 may be implemented by a single computing device 4000 or multiple computing devices 4000. Furthermore, as discussed below, the computing device 4000 (or multiple computing devices 4000) that implements the spectrometer assistance module 1000 may be part of one or more of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 of FIG. 20. In some embodiments, the processor 14, the memory 15, and the I / O unit 16 may be part of the computing device 4000.

[0066] Although the computing device 4000 of FIG. 19 is illustrated as having several components, any one or more of these components may be omitted or duplicated as appropriate for the application and setting. In some embodiments, some or all of the components included in the computing device 4000 may be mounted on one or more motherboards and encapsulated in a housing (e.g., comprising plastic, metal, and / or other materials). In some embodiments, some of these components may be fabricated on a single system-on-a-chip (SoC) (e.g., an SoC may include one or more processing devices 4002 and one or more storage devices 4004). Additionally, in various embodiments, computing device 4000 may not include one or more of the components illustrated in FIG. 19, but may include interface circuitry (not shown) for coupling to one or more components using any suitable interface (e.g., a Universal Serial Bus (USB) interface, a High-Definition Multimedia Interface (HDMI), a Controller Area Network (CAN) interface, a Serial Peripheral Interface (SPI) interface, an Ethernet interface, a wireless interface, or any other suitable interface). For example, computing device 4000 may not include display device 4010, but may include display device interface circuitry (e.g., connectors and driver circuitry) to allow display device 4010 to be coupled.

[0067] The computing device 4000 may include a processing device 4002 (e.g., one or more processing devices). As used herein, the term "processing device" may refer to any device or portion of a device that processes electronic data from registers and / or memory and converts the electronic data into other electronic data that may be stored in registers and / or memory. The processing device 4002 may include one or more digital signal processors (DSPs), application specific integrated circuits (ASICs), central processing units (CPUs), graphics processing units (GPUs), cryptographic processors (dedicated processors that execute cryptographic algorithms in hardware), server processors, or any other suitable processing devices.

[0068] The computing device 4000 may include a storage device 4004 (e.g., one or more storage devices). The storage device 4004 may include one or more memory devices, such as random access memory (RAM) (e.g., static RAM (SRAM) devices, magnetic RAM (MRAM) devices, dynamic RAM (DRAM) devices, resistive RAM (RRAM) devices, or conductive-bridging RAM (CBRAM) devices), hard-drive-based memory devices, solid-state memory devices, network drives, cloud drives, or any combination of memory devices. In some embodiments, the storage device 4004 may include memory that shares a die with the processing device 4002. In such embodiments, the memory may be used as a cache memory and may include, for example, embedded dynamic random-access memory (eDRAM) or spin transfer torque magnetic random-access memory (STT-MRAM). In some embodiments, the storage device 4004 may include a non-transitory computer-readable medium having instructions that, when executed by one or more processing devices (e.g., the processing device 4002), cause the computing device 4000 to perform any suitable method, or portion thereof, of the methods disclosed herein.

[0069] The computing device 4000 may include an interface device 4006 (e.g., one or more interface devices 4006). The interface device 4006 may include one or more communication chips, connectors, and / or other hardware and software to manage communications between the computing device 4000 and other computing devices. For example, the interface device 4006 may include circuitry to manage wireless communications to transfer data to and from the computing device 4000. The term "wireless" and its derivatives may be used to describe circuits, devices, systems, methods, techniques, communication channels, etc. that may communicate data through the use of modulated electromagnetic radiation over a non-solid medium. This term does not imply that the associated devices do not include any wiring, although in some embodiments they may not. The circuitry included in the interface device 4006 for managing wireless communications may implement any of a number of wireless standards or protocols, including, but not limited to, Wi-Fi (IEEE 802.11 family), Institute for Electrical and Electronic Engineers (IEEE) standards, including the IEEE 802.16 standard (e.g., the IEEE 802.16-2005 Amendment), the Long-Term Evolution (LTE) project (e.g., the Advanced LTE project, the Ultra-Mobile Broadband (UMB) project (also referred to as "3GPP2"), etc.), with any amendments, updates, and / or revisions.In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate in accordance with a Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Universal Mobile Telecommunications System (UMTS), High Speed ​​Packet Access (HSPA), Evolved HSPA (E-HSPA), or LTE network. In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate in accordance with an Enhanced Data for GSM Evolution (EDGE), GSM EDGE Radio Access Network (GERAN), Universal Terrestrial Radio Access Network (UTRAN), or Evolved UTRAN (E-UTRAN). In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate according to Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Digital Enhanced Cordless Telecommunications (DECT), Evolution-Data Optimized (EV-DO), and derivatives thereof, as well as any other wireless protocols designated as 3G, 4G, 5G, and beyond. In some embodiments, the interface device 4006 may include one or more antennas (e.g., one or more antenna arrays) for receiving and / or transmitting wireless communications.

[0070] In some embodiments, the interface device 4006 may include circuitry for managing wired communications, such as electrical, optical, or any other suitable communication protocol. For example, the interface device 4006 may include circuitry supporting communications according to Ethernet technology. In some embodiments, the interface device 4006 may support both wireless and wired communications, and / or support multiple wired and / or multiple wireless communications protocols. For example, a first set of circuits of the interface device 4006 may be dedicated to short-range wireless communications, such as Wi-Fi or Bluetooth, and a second set of circuits of the interface device 4006 may be dedicated to long-range wireless communications, such as global positioning system (GPS), EDGE, GPRS, CDMA, WiMAX, LTE, EV-DO, or others. In some embodiments, the first set of circuits of the interface device 4006 may be dedicated to wireless communications, and the second set of circuits of the interface device 4006 may be dedicated to wired communications.

[0071] The computing device 4000 may include a battery / power circuit 4008. The battery / power circuit 4008 may include one or more energy storage devices (e.g., batteries or capacitors) and / or circuitry for coupling components of the computing device 4000 to an energy source separate from the computing device 4000 (e.g., AC line power).

[0072] The computing device 4000 may include a display device 4010 (e.g., multiple display devices). The display device 4010 may include any visual indicator, such as a head-up display, a computer monitor, a projector, a touch screen display, a liquid crystal display (LCD), a light emitting diode display, or a flat panel display.

[0073] The computing device 4000 may include other input / output (I / O) devices 4012. The other I / O devices 4012 may include, for example, one or more audio output devices (e.g., a speaker, a headset, an earpiece, an alarm, etc.), one or more audio input devices (e.g., a microphone or microphone array), a location device (e.g., a GPS device that communicates with a satellite-based system to receive the location of the computing device 4000, as is known in the art), an audio codec, a video codec, a printer, sensors (e.g., a thermocouple or other temperature sensor, a humidity sensor, a pressure sensor, a vibration sensor, an accelerometer, a gyroscope, etc.), an image capture device such as a camera, a cursor control device such as a keyboard, a mouse, a stylus, a trackball, or a touchpad, a barcode reader, a Quick Response (QR) code reader, or a radio frequency identification (RFID) reader.

[0074] The computing device 4000 may have any suitable form factor for the application and setting, such as a handheld or mobile computing device (e.g., a cell phone, a smartphone, a mobile Internet device, a tablet computer, a laptop computer, a netbook computer, an ultrabook computer, a personal digital assistant (PDA), an ultra-mobile personal computer, etc.), a desktop computing device, or a server computing device, or other networked computing component.

[0075] One or more computing devices implementing any of the spectrometer-assisted modules or methods disclosed herein may be part of a spectrometer-assisted system. FIG. 20 is a block diagram of an exemplary spectrometer-assisted system 5000 in which some or all of the spectrometer-assisted methods disclosed herein may be performed, according to various embodiments. The spectrometer-assisted modules and methods disclosed herein (e.g., the spectrometer-assisted module 1000 of FIG. 3 and the methods of FIGS. 13-17) may be implemented by one or more of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 of the spectrometer-assisted system 5000. In some embodiments, the spectrometer measurement system 10 of FIG. 1 may be part of the spectrometer-assisted system 5000.

[0076] Any of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may include any of the embodiments of the computing device 4000 discussed in this specification with reference to FIG. 19, and any of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may take the form of any suitable of the embodiments of the computing device 4000 discussed in this specification with reference to FIG. 19.

[0077] The spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may each include a processing device 5002, a storage device 5004, and an interface device 5006. The processing device 5002 may take any suitable form, including any of the forms of the processing devices 4002 discussed herein with reference to Figure 6, and the processing devices 5002 included in different ones of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may take the same form or different forms. The storage device 5004 may take any suitable form, including any of the forms of the storage devices 5004 discussed herein with reference to Figure 6, and the storage devices 5004 included in different ones of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may take the same form or different forms. The interface device 5006 may take any suitable form, including any of the forms of the interface devices 4006 discussed herein with reference to FIG. 6, and the interface devices 5006 included in different ones of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may take the same or different forms.

[0078] The spectrometer 5010, the user local computing device 5020, the service local computing device 5030, and the remote computing device 5040 may communicate with other elements of the spectrometer-assisted system 5000 via communication paths 5008. The communication paths 5008 may communicatively couple the interface devices 5006 of different ones of the elements of the spectrometer-assisted system 5000 (e.g., according to any of the communication techniques discussed herein with reference to the interface device 4006 of the computing device 4000 of FIG. 19 ) as shown, and may be wired or wireless communication paths. Although the particular spectrometer-assisted system 5000 depicted in FIG. 20 includes communication paths between each pair of the spectrometer 5010, the user local computing device 5020, the service local computing device 5030, and the remote computing device 5040, this "fully coupled" implementation is merely illustrative, and in various embodiments, various ones of the communication paths 5008 may not be present. For example, in some embodiments, the service local computing device 5030 may not have a direct communications path 5008 between its interface device 5006 and the interface device 5006 of the spectrometer 5010, and instead may communicate with the spectrometer 5010 via a communications path 5008 between the service local computing device 5030 and the user local computing device 5020, and a communications path 5008 between the user local computing device 5020 and the spectrometer 5010.

[0079] The spectrometer 5010 may include any suitable spectrometer, such as an inductively coupled plasma optical emission spectrometer (ICP-OES), a mass spectrometer, or any other suitable spectrometer.

[0080] The user local computing device 5020 may be a computing device that is local to a user of the spectrometer 5010 (e.g., according to any of the embodiments of the computing device 4000 discussed herein). In some embodiments, the user local computing device 5020 may also be local to the spectrometer 5010, but need not be, e.g., a user local computing device 5020 in a user's home or office may be remote from the spectrometer 5010 but communicate with the spectrometer 5010 such that the user may control and / or access data from the spectrometer 5010 using the user local computing device 5020. In some embodiments, the user local computing device 5020 may be a laptop, smartphone, or tablet device. In some embodiments, the user local computing device 5020 may be a portable computing device.

[0081] The service local computing device 5030 may be a computing device that is local to an entity that services the spectrometer 5010 (e.g., according to any of the embodiments of the computing device 4000 discussed herein). For example, the service local computing device 5030 may be local to the manufacturer of the spectrometer 5010 or a third-party service company. In some embodiments, the service local computing device 5030 may communicate with the spectrometer 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., via a direct communication path 5008 or via multiple "indirect" communication paths 5008, as discussed above) and receive data regarding the operation of the spectrometer 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., results of self-tests of the spectrometer 5010, calibration coefficients used by the spectrometer 5010, measurements of sensors associated with the spectrometer 5010, etc.). In some embodiments, the service local computing device 5030 may communicate with the spectrometer 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., via a direct communication path 5008 or via multiple "indirect" communication paths 5008, as discussed above) and transmit data to the spectrometer 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., updating programmed instructions such as firmware in the spectrometer 5010, initiating the execution of a test or calibration sequence for the spectrometer 5010, updating programmed instructions such as software in the user's local computing device 5020 or the remote computing device 5040, etc.).A user of the spectrometer 5010 may utilize the spectrometer 5010 or the user local computing device 5020 to communicate with the service local computing device 5030 to report problems with the spectrometer 5010 or the user local computing device 5020, request a visit from a technician to improve the operation of the spectrometer 5010, order consumables or replacement parts related to the spectrometer 5010, or for other purposes.

[0082] The remote computing device 5040 may be a computing device (e.g., according to any of the embodiments of computing device 4000 discussed herein) that is remote from the spectrometer 5010 and / or the user local computing device 5020. In some embodiments, the remote computing device 5040 may be included in a data center or other large-scale server environment. In some embodiments, the remote computing device 5040 may include network-attached storage (e.g., as part of the storage device 5004). The remote computing device 5040 may store data generated by the spectrometer 5010, perform analysis of the data generated by the spectrometer 5010 (e.g., according to programmed instructions), facilitate communications between the user local computing device 5020 and the spectrometer 5010, and / or facilitate communications between the service local computing device 5030 and the spectrometer 5010.

[0083] In some embodiments, one or more of the elements of the spectrometer support system 5000 illustrated in FIG. 20 may not be present. Furthermore, in some embodiments, more than one of various ones of the elements of the spectrometer support system 5000 of FIG. 20 may be present. For example, the spectrometer support system 5000 may include multiple user local computing devices 5020 (e.g., different user local computing devices 5020 associated with different users or at different locations). In another example, the spectrometer support system 5000 may include multiple spectrometers 5010 all in communication with a service local computing device 5030 and / or a remote computing device 5040, in such an embodiment, the service local computing device 5030 may monitor these multiple spectrometers 5010 or the service local computing device 5030 may trigger updates or other information may be "broadcast" to the multiple spectrometers 5010 simultaneously. Different ones of the spectrometers 5010 in the spectrometer support system 5000 may be located near each other (e.g., in the same room) or far from each other (e.g., on different floors of a building, in different buildings, in different cities, etc.). In some embodiments, the spectrometers 5010 may be coupled to an Internet-of-Things (IoT) stack that allows command and control of the spectrometers 5010 via web-based applications, virtual or augmented reality applications, mobile applications, and / or desktop applications. Any of these applications may be accessed by a user operating a user local computing device 5020 in communication with the spectrometers 5010 by an intervening remote computing device 5040. In some embodiments, the spectrometers 5010 may be sold by a manufacturer as part of a local spectrometer computing unit 5012 along with one or more associated user local computing devices 5020.

[0084] In some embodiments, different ones of the spectrometers 5010 included in the spectrometer-aided system 5000 may be different types of spectrometers 5010, for example, one spectrometer 5010 may be a mass spectrometer and another spectrometer 5010 may be an optical spectrometer. In some such embodiments, the remote computing device 5040 and / or the user local computing device 5020 may combine data from the different types of spectrometers 5010 included in the spectrometer-aided system 5000.

[0085] The following paragraphs provide various examples of the embodiments disclosed herein.

[0086] Example A1 is a spectrometer support device including first logic for generating, for each of a plurality of calibration samples of an analyte of different known concentrations, an array of spectrometer output intensities of the calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for training a machine learning computational model using the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities, and outputting a concentration of the analyte in the target sample based on an input array of spectrometer output intensities of the target sample; and third logic for using the trained machine learning computational model as a calibration model for the analyte for subsequent spectrometer operations.

[0087] Example A2 includes the subject matter of example A1 and further specifies that the spectrometer is an optical spectrometer, and the data representative of the different amounts of polarization is data representative of different wavelengths of radiation.

[0088] Example A3 includes the subject matter of example A1 and further specifies that the spectrometer is a mass spectrometer and that the data representative of different amounts of deflection is data representative of different mass to charge ratios.

[0089] Example A4 includes the subject matter of any of Examples A1-3 and further specifies that the analyte is a single element.

[0090] Example A5 includes the subject matter of any of Examples A1-4, and further specifies that the tensors input to the machine learning computational model include spectrometer output intensities at different amounts of deflection.

[0091] Example A6 includes the subject matter of any of Examples A1-5, and further specifies that the tensors input to the machine learning computational model include ratios of different ones of the spectrometer output intensities at different amounts of deflection.

[0092] Example A7 includes the subject matter of any of Examples A1-6, and further specifies that the array of spectrometer output intensities of the calibration sample is an array of background-corrected output intensities.

[0093] Example A8 includes the subject matter of any of Examples A1-7 and further specifies that the calibration sample is a first calibration sample, the analyte is a first analyte, the machine learning computational model is a first machine learning computational model, the first logic is for generating, for each of a plurality of second calibration samples of different known concentrations of a second analyte, an array of spectrometer output intensities of the second calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, where the second analyte is different from the first analyte, the second logic uses the plurality of known concentrations of the second analyte in the second calibration samples and the associated plurality of arrays of spectrometer output intensities to train the second machine learning computational model, and output a concentration of the second analyte in the target sample based on the input array of spectrometer output intensities of the target sample, and the third logic uses the trained second machine learning computational model as a calibration model for the second analyte for subsequent spectrometer operations.

[0094] Example A9 includes the subject matter of Examples A1-8 and further specifies that for each of a plurality of calibration samples of different known concentrations of the analyte, the array of calibration sample spectrometer output intensities includes three or more output intensities.

[0095] Example A10 includes the subject matter of any of Examples A1-9, and further specifies that for one or more of the multiple calibration samples of the analyte of different known concentrations, the array of spectrometer output intensities of the calibration samples includes at least one saturated spectrometer output intensity.

[0096] Example BI1 is a spectrometer support device that includes first logic for generating an array of spectrometer output intensities of a sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection, second logic for providing the received array of spectrometer output intensities to a trained machine learning computational model, where the trained machine learning computational model is for outputting a concentration of an analyte in the sample, and third logic for outputting the concentration of the analyte in the sample.

[0097] Example BI2 includes the subject matter of example BI1 and further specifies that the spectrometer is an optical spectrometer and that the data representative of the different amounts of polarization is data representative of different wavelengths of radiation.

[0098] Example BI3 includes the subject matter of example BI1 and further specifies that the spectrometer is a mass spectrometer and that the data representative of different amounts of deflection is data representative of different mass to charge ratios.

[0099] Example BI4 includes the subject matter of any of Examples BI1-3 and further specifies that the analyte is a single element.

[0100] Example BI5 includes the subject matter of any of Examples BI1-BI4, and further specifies that the array of sample spectrometer output intensities is an array of background-corrected output intensities.

[0101] Example BI6 includes the subject matter of any of Examples BI1-BI5, and further specifies that the array of spectrometer output intensities for the sample includes three or more output intensities.

[0102] Example BI7 includes the subject matter of any of Examples BI1-BI6, and further specifies that the array of spectrometer output intensities for the sample includes at least one saturated spectrometer output intensity.

[0103] Example BI8 includes the subject matter of any of examples BI1-BI7, and further specifies that the third logic outputs, to a display device, a feature relevance indicator associated with one or more of the spectrometer output intensities.

[0104] Example BI9 includes the subject matter of Example BI8 and further demonstrates that the feature relevance indicator associated with the spectrometer output intensity indicates that the spectrometer output intensity was more important than other of the spectrometer output intensities to determining the concentration of the analyte in the sample.

[0105] Example BI10 includes the subject matter of any of Examples BI8-9 and further demonstrates that a feature relevance indicator associated with the two spectrometer output intensities indicates that the combination of the two spectrometer output intensities was more important to determining the concentration of the analyte in the sample than other combinations of the spectrometer output intensities.

[0106] Example BI11 includes the subject matter of Example BI10 and further demonstrates that the feature relevance indicator associated with the two spectrometer output intensities indicates that the ratio of the two spectrometer output intensities was more important than other ratios of the spectrometer output intensities to determining the concentration of the analyte in the sample.

[0107] Example BI12 includes the subject matter of any of Examples BI8-BI11, and further specifies that the feature relevance indicator includes a list of specific data representing different amounts of deflection associated with specific spectrometer output intensities.

[0108] Example BI13 includes the subject matter of Example BI12 and further specifies that the feature relevance indicator includes a list of wavelengths that are more important than other wavelengths to determining the concentration of an analyte in a sample.

[0109] Example BI14 includes the subject matter of example BI12 and further specifies that the feature relevance indicator includes a list of mass to charge ratios that are more important than other mass to charge ratios to determining the concentration of an analyte in a sample.

[0110] Example BI15 includes the subject matter of any of Examples BI1-BI4, and further specifies that the third logic outputs the concentration of the analyte in the sample to a display device.

[0111] Example BII1 is a spectrometer support device including first logic for generating an array of spectrometer output intensities of a sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for generating a concentration of an analyte in the sample based on the received array of spectrometer output intensities; and third logic for outputting a feature association indicator associated with the concentration of the analyte in the sample and one or more of the spectrometer output intensities.

[0112] Example BII2 includes the subject matter of example BII1 and further specifies that the spectrometer is an optical spectrometer and that the data representative of different amounts of polarization is data representative of different wavelengths of radiation.

[0113] Example BII3 includes the subject matter of Example BII1 and further specifies that the spectrometer is a mass spectrometer and that the data representative of different amounts of deflection is data representative of different mass to charge ratios.

[0114] Example BII4 includes the subject matter of any of Examples BII1-3 and further specifies that the analyte is a single element.

[0115] Example BII5 includes the subject matter of any of Examples BII1-4, and further specifies that the array of sample spectrometer output intensities is an array of background-corrected output intensities.

[0116] Example BII6 includes the subject matter of any of Examples BII1-5, and further specifies that the array of spectrometer output intensities for the sample includes three or more output intensities.

[0117] Example BII7 includes the subject matter of any of Examples BII1-6, and further specifies that the array of sample spectrometer output intensities includes at least one saturated spectrometer output intensity.

[0118] Example BII8 includes the subject matter of any of Examples BII1-7 and further demonstrates that the feature relevance indicator associated with the spectrometer output intensity indicates that the spectrometer output intensity was more important than other of the spectrometer output intensities to determining the concentration of the analyte in the sample.

[0119] Example BII9 includes the subject matter of any of Examples BII1-8 and further demonstrates that the feature relevance indicator associated with the two spectrometer output intensities indicates that the combination of the two spectrometer output intensities was more important to determining the concentration of the analyte in the sample than other combinations of the spectrometer output intensities.

[0120] Example BII10 includes the subject matter of Example BII9 and further demonstrates that the feature relevance indicator associated with the two spectrometer output intensities indicates that the ratio of the two spectrometer output intensities was more important to determining the concentration of the analyte in the sample than other ratios of the spectrometer output intensities.

[0121] Example BII11 includes the subject matter of any of Examples BII1-10, and further specifies that the feature relevance indicator includes a list of specific data representing different amounts of deflection associated with specific spectrometer output intensities.

[0122] Example BII12 includes the subject matter of Example BII11 and further demonstrates that the feature relevance indicator includes a list of wavelengths that are more important than other wavelengths to determining the concentration of an analyte in a sample.

[0123] Example BII13 includes the subject matter of Example BII11 and further specifies that the feature relevance indicator includes a list of mass to charge ratios that are more important than other mass to charge ratios to determining the concentration of an analyte in a sample.

[0124] Example BII14 includes the subject matter of any of Examples BII1-13, and further specifies that the third logic outputs the concentration of the analyte in the sample to a display device.

[0125] Example BIII1 is a spectrometer output device including first logic for generating an array of spectrometer output intensities for a sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for generating a concentration of an analyte in the sample based on the received array of spectrometer output intensities without requiring a user to select one or more of the data representing the amounts of deflection prior to generating the concentration of the analyte in the sample; and third logic for outputting the concentration of the analyte in the sample.

[0126] Example BIII2 includes the subject matter of Example BIII1 and further specifies that the spectrometer is an optical spectrometer and the data representative of different amounts of polarization is data representative of different wavelengths of radiation.

[0127] Example BIII3 includes the subject matter of Example BIII1 and further specifies that the spectrometer is a mass spectrometer and that the data representative of different amounts of deflection is data representative of different mass to charge ratios.

[0128] Example BIII4 includes the subject matter of any of Examples BIII1-3 and further specifies that the analyte is a single element.

[0129] Example BIII5 includes the subject matter of any of Examples BIII1-4, further specifying that the array of sample spectrometer output intensities is an array of background-corrected output intensities.

[0130] Example BIII6 includes the subject matter of any of Examples BIII1-5, further specifying that the array of spectrometer output intensities for the sample includes three or more output intensities.

[0131] Example BIII7 includes the subject matter of any of Examples BIII1-6, further specifying that the array of sample spectrometer output intensities includes at least one saturated spectrometer output intensity.

[0132] Example BIII8 includes the subject matter of any of Examples BIII1-7, and further specifies that the third logic outputs, to a display device, a feature relevance indicator associated with one or more of the spectrometer output intensities.

[0133] Example BIII9 includes the subject matter of Example BIII8 and further demonstrates that the feature relevance indicator associated with the spectrometer output intensity indicates that the spectrometer output intensity was more important than other of the spectrometer output intensities to determining the concentration of the analyte in the sample.

[0134] Example BIII10 includes the subject matter of any of Examples BIII8-9, and further specifies that the feature relevance indicator associated with the two spectrometer output intensities indicates that the combination of the two spectrometer output intensities was more important than other combinations of spectrometer output intensities to determining the concentration of the analyte in the sample.

[0135] Example BIII11 includes the subject matter of Example BIII10 and further demonstrates that the feature relevance indicator associated with the two spectrometer output intensities indicates that the ratio of the two spectrometer output intensities was more important than other ratios of the spectrometer output intensities to determining the concentration of the analyte in the sample.

[0136] Example BIII12 includes the subject matter of any of Examples BIII8-11, and further specifies that the feature relevance indicator includes a list of specific data representing different amounts of deflection associated with specific spectrometer output intensities.

[0137] Example BIII13 includes the subject matter of Example BIII12 and further specifies that the feature relevance indicator includes a list of wavelengths that are more important to determining the concentration of an analyte in a sample than other wavelengths.

[0138] Example BIII14 includes the subject matter of Example BIII12 and further specifies that the feature relevance indicator includes a list of mass to charge ratios that are more important than other mass to charge ratios to determining the concentration of the analyte in the sample.

[0139] Example BIII15 includes the subject matter of any of Examples BIII1-14, and further specifies that the third logic outputs the concentration of the analyte in the sample to a display device.

[0140] Example C1 is a spectrometer support device including: first logic for generating, for each of a plurality of calibration samples of an analyte of different known concentrations, an array of spectrometer output intensities of the calibration sample, where different ones of the spectrometer output intensities in the array are associated with data representing different amounts of deflection; second logic for using the plurality of known concentrations of the analyte in the calibration samples and the associated plurality of arrays of spectrometer output intensities to retrain a pre-trained machine learning computational model or to generate a pre-processing method for use with the pre-trained machine learning computational model to output a concentration of the analyte in the target sample based on an input array of spectrometer output intensities of the target sample; and third logic for using the re-trained machine learning computational model or to execute the pre-processing method with the pre-trained machine learning computational model as a calibration model of the analyte for subsequent spectrometer operation.

[0141] Example C2 includes the subject matter of example C1 and further specifies that the spectrometer is an optical spectrometer, and the data representative of different amounts of polarization is data representative of different wavelengths of radiation.

[0142] Example C3 includes the subject matter of example C1 and further specifies that the spectrometer is a mass spectrometer and that the data representative of different amounts of deflection is data representative of different mass to charge ratios.

[0143] Example C4 includes the subject matter of any of Examples C1-3 and further specifies that the analyte is a single element.

[0144] Example C5 includes the subject matter of any of Examples C1-4, and further specifies that the tensors input to the machine learning computational model include spectrometer output intensities at different amounts of deflection.

[0145] Example C6 includes the subject matter of any of Examples C1-5, and further specifies that the tensors input to the machine learning computational model include ratios of different ones of the spectrometer output intensities at different amounts of deflection.

[0146] Example C7 includes the subject matter of any of Examples C1-6, and further specifies that the array of spectrometer output intensities of the calibration sample is an array of background-corrected output intensities.

[0147] Example C8 includes the subject matter of any of Examples C1-7, and further specifies that the spectrometer is a first spectrometer, and the pre-trained machine learning computational model was trained using data generated by a second spectrometer different from the first spectrometer.

[0148] Example C9 includes the subject matter of example C8 and further specifies that the amount of data from the first spectrometer used to retrain the pre-trained machine learning computational model is less than the amount of data from the second spectrometer used to pre-train the machine learning computational model.

[0149] Example C10 includes the subject matter of any of Examples C1-9, and further specifies that for each of a plurality of calibration samples of different known concentrations of the analyte, the array of spectrometer output intensities of the calibration samples includes three or more output intensities.

[0150] Example C11 includes the subject matter of any of Examples C1-10, and further specifies that for one or more of the multiple calibration samples of the analyte of different known concentrations, the array of spectrometer output intensities of the calibration samples includes at least one saturated spectrometer output intensity.

[0151] Example C12 includes the subject matter of any of Examples C1-11, and further specifies that the second logic is for retraining a subset of parameters of a pre-trained machine learning computational model.

[0152] Example C13 includes the subject matter of any of Examples C1 to C12, and further specifies that the second logic is for retraining only the final layer of the pre-trained machine learning computational model.

[0153] Example D includes any of the spectrometer support modules disclosed herein.

[0154] Example E includes any of the spectrometer-assisted methods disclosed herein.

[0155] Example F includes any of the GUIs disclosed herein.

[0156] Example G includes any of the spectrometer-assisted computing devices and systems disclosed herein.

[0157] Example H includes a spectrometer system that includes any of the spectrometer support modules or devices disclosed herein.

[0158] Example I includes a spectrometer system configured to perform any of the spectrometer-assisted methods disclosed herein.

[0159] For purposes of this disclosure, the phrases "A and / or B" and "A or B" mean (A), (B), or (A and B). For purposes of this disclosure, the phrases "A, B, and / or C" and "A, B, or C" mean (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C). Although some elements may be referred to in the singular (e.g., a "processing device"), any suitable element may be represented by multiple instances of that element, and vice versa. For example, a set of operations described as being performed by a processing device may be implemented with different ones of the operations performed by different processing devices.

[0160] This description uses the phrases "one embodiment," "various embodiments," and "several embodiments," each of which may refer to one or more of the same or different embodiments. Additionally, terms such as "comprising," "including," and "having" used with respect to embodiments of the present disclosure are synonymous. When used to describe a range of dimensions, the phrase "between X and Y" represents a range that includes X and Y. As used herein, an "apparatus" may refer to any individual device, a collection of devices, a portion of a device, or a collection of portions of devices. The drawings are not necessarily drawn to scale.

Claims

1. 1. A spectrometer support device, comprising: first logic for generating an array of spectrometer output intensities for a sample, different ones of the spectrometer output intensities in the array being associated with data representing different amounts of deflection; second logic for providing the received sequence of spectrometer output intensities and at least one ratio between a spectrometer output intensity associated with one deflection amount and a spectrometer output intensity associated with a different deflection amount to a trained machine learning computational model, the trained machine learning computational model for outputting a concentration of an analyte in the sample; and third logic for outputting a concentration of the analyte in the sample.

2. 2. The spectrometer aided apparatus of claim 1, wherein the spectrometer is an optical spectrometer and the data representative of different amounts of polarization is data representative of different wavelengths of radiation.

3. 2. The spectrometer support apparatus of claim 1, wherein the spectrometer is a mass spectrometer and the data representative of different amounts of deflection is data representative of different mass to charge ratios.

4. The spectrometer-assisted apparatus of any one of claims 1 to 3, wherein the analyte is a single element.

5. A spectrometer support apparatus according to any one of claims 1 to 3, wherein the array of spectrometer output intensities for the sample comprises three or more output intensities.

6. 1. A method for determining an analyte concentration from a spectrometer output intensity, comprising: generating an array of spectrometer output intensities for a sample, different ones of the spectrometer output intensities in the array being associated with data representing different amounts of deflection; providing data representative of at least some of the received sequences of spectrometer output intensities to a trained machine learning computational model, the trained machine learning computational model for outputting a concentration of an analyte in the sample, the data provided to the trained machine learning computational model including at least one ratio between a spectrometer output intensity associated with one amount of deflection and a spectrometer output intensity associated with a different amount of deflection; and outputting the concentration of the analyte in the sample.

7. 7. The method of claim 6, further comprising generating a feature relevance indicator associated with one or more of the spectrometer output intensities based on the output of the trained machine learning computational model.

8. 8. The method of claim 7, wherein the feature relevance indicator associated with a spectrometer output intensity indicates that the spectrometer output intensity was more important than others of the spectrometer output intensities to determining a concentration of the analyte in the sample.

9. 8. The method of claim 7, wherein the feature relevance indicator associated with two spectrometer output intensities indicates that a combination of the two spectrometer output intensities was more important to determining a concentration of the analyte in the sample than other combinations of spectrometer output intensities.

10. 10. The method of claim 9, wherein the feature relevance indicator associated with the two spectrometer output intensities indicates that a ratio of the two spectrometer output intensities was more important to determining a concentration of the analyte in the sample than other ratios of spectrometer output intensities.

11. The method of any one of claims 7 to 10, wherein generating the feature relevance indicator comprises performing linear regression feature relevance, logistic regression feature relevance, or decision tree feature relevance.

12. A method according to any one of claims 7 to 10, wherein the feature relevance indicator comprises a list of wavelengths which are more important than other wavelengths in determining the concentration of the analyte in the sample.

13. A method according to any one of claims 7 to 10, wherein the feature relevance indicator comprises a list of mass to charge ratios which are more important than other mass to charge ratios in determining the concentration of the analyte in the sample.

14. 1. A spectrometer system comprising: a spectrometer support module, the spectrometer support module comprising: first logic for generating an array of spectrometer output intensities for a sample, different ones of the spectrometer output intensities in the array being associated with data representing different amounts of deflection; second logic for providing at least a ratio of spectrometer output intensities associated with different amounts of deflection to a trained machine learning computational model, the trained machine learning computational model for outputting a concentration of an analyte in the sample; and third logic for outputting a concentration of the analyte in the sample.

15. 15. The spectrometer system of claim 14, wherein the third logic is for outputting the concentration of the analyte in the sample to a display device.

Images