Method for generating training images for use in training an image-based artificial intelligence model for analyzing images obtained from multi-channel one-dimensional signals and an apparatus for carrying out the same

The method generates diverse training images for AI models analyzing multi-channel one-dimensional signals, improving performance by adapting to varied output formats and ensuring robustness against format changes.

JP2024542787AActive Publication Date: 2024-11-15SEOUL NAT UNIV HOSPITAL
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024533031
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-12-01
Filing Date
2022-12-02
Publication Date
2024-11-15
Estimated Expiration
2042-12-02

AI Technical Summary

Technical Problem

Existing artificial intelligence models trained on a single output format for two-dimensional images of multi-channel one-dimensional signals struggle to analyze images in different formats, leading to low performance and inability to adapt to format changes in new products or updates.

Method used

A method and apparatus for generating large-scale training images with varied output formats by selecting deformation and output formats, determining grid scales, and representing waveforms on a two-dimensional plane, using a computing device to process multi-channel one-dimensional signals.

Benefits of technology

Enables the generation of two-dimensional signal images in various formats, enhancing the performance of artificial intelligence models by addressing out-of-distribution issues and ensuring robust analysis across different image formats.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024542787000001_ABST
    Figure 2024542787000001_ABST
Patent Text Reader

Abstract

The embodiment relates to a training image generating method and an apparatus for performing the same, which generate a training signal based on source signal information, select at least one output format from a plurality of preset output formats to determine an output format of a training image, determine an output interval for each channel of the training signal based on a length of a time interval of a waveform of the determined output format, select a scale for each axis to determine a grid scale of the training image, display a grid pattern on a two-dimensional plane according to the determined grid scale, set a reference position of a waveform content of the training signal based on at least one of the determined output interval for each channel and the determined grid scale, and display the waveform content and signal indicator of the training signal on the two-dimensional plane on which the grid pattern is displayed.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The embodiments relate to a training image generation technique, e.g., a training image generation technique capable of generating a large number of training images with a variety of image formats and signal patterns, used to train an image-based artificial intelligence model that analyzes images obtained from multi-channel one-dimensional signals, and an apparatus for implementing the same. [Background technology]

[0002] Biosignals such as electrocardiograms and electroencephalograms are generally measured in the form of one-dimensional signals. At this time, the measured signal is embodied as a numerical value in the time domain measured in the corresponding channel, and is generally expressed in a numerical array structure of C×T type. The measured numerical value is stored in the aforementioned numerical array structure and used.

[0003] The signal data values ​​are difficult for a human reader to understand as they are, so they are displayed on paper or on a device screen as a two-dimensional image output in which waveforms are drawn for each channel in a format that is easy for humans to understand.

[0004] However, there are many different formats for 2D image output, and even if the 2D image output is used for the same purpose, the format may be very different depending on the product.

[0005] Let us assume that we are developing an artificial intelligence model that analyzes signal information displayed as a two-dimensional image output result. If this artificial intelligence model is trained using training images with one output format, the artificial intelligence model will not be able to analyze target images with other output formats and will have low analytical performance.

[0006] Therefore, in order for an AI model to learn to have high analytical performance, it is necessary to prepare training images with as many different output formats as possible. However, it is practically very difficult to prepare a large number of training images for sufficient learning using only existing images of existing products in use. In particular, there is a limitation in that it is completely unable to prepare for future changes such as the launch of new products or updates to existing products that use new output formats. Summary of the Invention [Problem to be solved by the invention]

[0007] In one aspect, an exemplary embodiment of the present application aims to provide a training image generation method and apparatus that can generate large-scale training images with a variety of image formats and signal patterns in order to solve problems that arise when training 2D images in only one format without considering the diversity of formats, for example, a training image generation technique used to train an image-based artificial intelligence model that analyzes images obtained from multi-channel 1-dimensional signals, and a method and apparatus for implementing the same. [Means for solving the problem]

[0008] In an embodiment of the present application, there is provided a training image generation method executed by a computing device including a processor and a memory, for example, for training an image-based artificial intelligence model that analyzes images obtained from a multi-channel one-dimensional signal, the training image generation method including the steps of: generating a training signal based on source signal information including a multi-channel one-dimensional signal; selecting at least one output format from a plurality of preset output formats to determine an output format of the training image; determining an output interval for each channel of the training signal based on the length of the time interval of the waveform of the determined output format; selecting an axis-specific scale to determine a grid scale of the training image; displaying a grid pattern on a two-dimensional plane according to the determined grid scale; setting a reference position of the waveform content of the training signal based on at least one of the determined channel-specific output interval and the determined grid scale; and displaying the waveform content and signal indicator of the training signal on the two-dimensional plane on which the grid pattern is displayed. A computer-readable recording medium having recorded thereon a program for executing the training image generation method, or a computer program stored on a computer-readable recording medium, is provided.

[0009] In addition, an embodiment of the present application provides a training image generation device including: an acquisition unit that acquires a source signal; and an image generation unit that includes a processor and a memory; wherein the image generation unit receives source signal information received by the acquisition unit and executes the aforementioned training image generation method. Effect of the Invention

[0010] In one aspect, embodiments of the present application may provide a training data set that can be used to develop artificial intelligence that generates various types of 2D signal images from a source signal, such as a multi-channel 1D signal, and analyzes the 2D signal images with superior performance.

[0011] By utilizing the above-mentioned various types of 2D signal images, it is possible to solve problems that arise when training only one type without taking into account the diversity of the types, such as the out-of-distribution problem, or the problem of analysis being incorrect even when the type changes slightly.

[0012] The invention according to the embodiments of the present application can be expanded and applied not only to signals in the medical and bio fields, but also to signal analysis in other industrial fields in which two-dimensional images are analyzed based on one-dimensional signals.

[0013] The effects of the present application are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims. [Brief description of the drawings]

[0014] In order to more clearly describe the exemplary embodiments of the present application, the drawings necessary for the description of the embodiments are briefly introduced below. It should be understood that the following drawings are only intended to describe the embodiments of the present specification, and are not intended to be limiting. In addition, for the sake of clarity, some elements may be shown in the following drawings to which various modifications such as exaggeration and omission have been applied. [Figure 1] 1 is a flow diagram of a training image generation method used to train an image-based artificial intelligence model for analyzing images obtained from a multi-channel one-dimensional signal, according to one aspect of the present application. [Diagram 2] 2 is a schematic diagram of source signal information according to an embodiment of the present application; [Diagram 3] FIG. 2 is a schematic diagram of a training signal according to an embodiment of the present application. [Figure 4] FIG. 2 is a schematic diagram of an output format according to one embodiment of the present application. [Diagram 5] FIG. 2 is a schematic diagram of a grating scale according to one embodiment of the present application. [Figure 6] FIG. 13 is a diagram showing how a grid pattern is displayed according to one embodiment of the present application. [Figure 7] FIG. 2 is a schematic diagram of the result of displaying the waveform content and signal indicators of a training signal on a two-dimensional plane with a grid pattern according to one embodiment of the present application. [Figure 8] FIG. 2 is a schematic diagram of additional information according to one embodiment of the present application; [Figure 9] FIG. 4 is a block diagram of an apparatus for executing the training image generation method according to another aspect of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Some embodiments of the present application will be described in detail below with reference to the exemplary drawings. When referring to components in each drawing, the same components may be referred to by the same reference numerals as much as possible even if they are shown in different drawings. In addition, when describing the present embodiment, if it is determined that a specific description of related publicly known configurations or functions may obscure the gist of the present technical idea, the detailed description may be omitted.

[0016] In this specification, when "comprises," "has," "consists of," and the like are used, other parts may be added unless "only" is used. When an element is expressed in the singular, it may include a plural unless otherwise expressly stated.

[0017] In addition, in describing components of this application, terms such as first, second, A, B, (a), (b), etc. may be used. Unless otherwise specified, these terms are merely used to distinguish the components from other components, and are not intended to limit the essence, order, procedure, number, etc. of the components.

[0018] As used herein, "learning" is a term that refers to performing machine learning through procedural computing.

[0019] As used herein, network refers to a neural network of a machine learning algorithm or model.

[0020] In this specification, terms such as "unit," "module," "apparatus," or "system" are intended to refer to a combination of not only hardware but also software driven by the hardware. For example, the hardware may be a data processing device including a central processing unit (CPU), a graphic processing unit (GPU), or other processor. In addition, software may refer to a running process, an object, an executable, a thread of execution, a program, etc.

[0021] In this specification, multi-channel is defined to mean one or more channels, and does not exclude the case where there is only one channel.

[0022] In certain embodiments, the training image generation method used to train an image-based artificial intelligence model to analyze two-dimensional images obtained from a multi-channel one-dimensional signal may be performed by a computing device including at least one processor and a memory.

[0023] The computing device is configured to receive and process signal data from an external device (eg, a signal measurement device).

[0024] FIG. 1 is a flow diagram of a method for generating training images used to train an image-based artificial intelligence model for analyzing images obtained from a multi-channel one-dimensional signal, according to one aspect of the present application.

[0025] Referring to FIG. 1, the training image generating method (hereinafter, referred to as training image generating method) includes a step of generating / modulating a training signal based on source signal information (S100).

[0026] FIG. 2 is a schematic diagram of source signal information according to an embodiment of the present application, and FIG. 3 is a schematic diagram of a training signal according to an embodiment of the present application.

[0027] Referring to FIG. 2, the source signal information may include one-dimensional signals for each channel measured through one or more channels attached to the subject's body. For example, the input source signal may be an array in the form of channel x time (C x T). The source signal may have a numeric array. As shown in FIG. 2, the source signal information may include 12 one-dimensional electrocardiogram signals measured through 12 lead channels.

[0028] The source signal information may include an analog source signal, a measurement value (eg, a digital value) of the source signal.

[0029] In addition, the source signal information may further include source additional information other than the signal, such as subject information of the source signal (identification information, age, gender, readout information, etc.), source scale indicator, source channel indicator, and source lattice scale.

[0030] Such a source signal is utilized as a source for generating training signals. Multiple training signals may be generated from a single source signal.

[0031] In one embodiment, the step (S100) may include the steps of: selecting at least one transformation function from a plurality of predefined transformation functions; and transforming the source signal into a training signal using the selected transformation function.

[0032] A modification function is a function that modifies an input signal into another signal. Such signal modification may be treated as a pre-processing step of the training image generation process. The modification function may be, for example, a signal pre-processing function aimed at removing various forms of noise or at randomly modifying the input signal itself.

[0033] Each of the plurality of transformation functions comprises one or more transformation elements that perform a transformation function. In some embodiments, the transformation elements may represent signal attributes of the input signal that are to be transformed. The number of transformation functions (f n 1 ) are predefined and stored. The subscript n indicates that there are n functions, and the superscript is a number to distinguish it from other functions, which will be described later.

[0034] In a particular embodiment, the transformation function (f n 1 ) deformation element vector (P n 1 ) may include m factors, each of which is a transformation element P nm 1 (where n is a transformation function identifier and m is an element identifier). nm 1 ) may correspond to unique input information processing properties. n 1 ), each deformation element (P nm 1 ) is the setting value of the signal processing attribute and the signal is transformed. For example, the transformation function (f n 1 ) is the denoising function, the deformation factor (P nm 1 ) corresponds to a signal processing attribute that specifies (sets) certain characteristics of the noise removal process.

[0035] The signal processing attributes may include, for example, ways of processing, modifying, or removing (replacing the signal magnitude with a fixed value such as 0) the signal magnitude, waveform, frequency range, frequency distribution, signal rise time, time range, and / or other signal attributes, and this may be performed separately for each channel, or may be applied commonly to a group of channels or to all channels.

[0036] In a specific embodiment, the transformation elements of the transformation function may be embodied as hyperparameters. When one transformation function includes multiple transformation elements, the multiple transformation elements may be represented as a hyperparameter vector, where the vector values ​​are the transformation element values. Then, each transformation function may be associated with its own hyperparameter vector.

[0037] A training signal may be generated using such a transformation function (S100). n 1 ) is a signal obtained by receiving a source signal (e.g., an electrocardiogram signal, X) and transforming it into a signal X'=f n 1 (X, P nm 1 In addition, when the transformation element value is changed, the signal attribute is realized with a changed value in a corresponding manner, and finally, a signal with changed signal attribute is generated (S100).

[0038] In one embodiment, the step of selecting at least one transformation function may select one of the plurality of transformation functions according to a 1-1 probability distribution preset for the set of the plurality of transformation functions, or may select two or more transformation functions from the plurality of transformation functions.

[0039] The first-1 probability distribution defines the probability of selecting a particular transformation function(s) to generate training images from among a plurality of transformation functions.

[0040] In one embodiment, the first probability distribution may be defined by selecting one transformation function out of n. For example, the first probability distribution may have a multinomial distribution. In this case, the source signal is subjected to a single transformation process.

[0041] In another embodiment, the 1-1st probability distribution may be defined by selecting two or more transformation functions out of n. For example, the 1-1st probability distribution may have a binomial distribution. In this case, different transformations may be selected in duplicate and used to generate the training signal. Then, the source signal is multi-transformed using the selected multiple transformation functions.

[0042] In an alternative embodiment, the 1-1 probability distribution may be an arbitrary specified initial probability distribution that is optimized through training, as will be described in more detail below.

[0043] The selected transformation function may be used as is, or the transformation factor values ​​of the selected transformation function may be changed to generate the training signal (S100). The selected transformation function may be adjusted by inputting a new value for at least one transformation factor as an input argument.

[0044] In one embodiment, the step of transforming the source signal into a training signal using a selected transformation function may include the steps of: changing at least one transformation factor value of the selected transformation function to a new value; and generating a signal reflecting a signal attribute modified according to the modified transformation factor value as the training signal. The modification of the transformation factor value may be performed based on a probability distribution.

[0045] In one embodiment, a 1-2nd probability distribution may be set for each transformation element. If the number of transformation elements is m, m 1-2nd probability distributions are defined and assigned. For each transformation element of the transformation function selected according to the 1-1st probability distribution, the existing transformation element value may be changed to a new value selected according to the 1-2nd probability distribution preset for the transformation element. The changed new value is reflected in the source signal to generate a new training signal.

[0046] The first-second probability distribution defines a probability distribution in which each transformation element of the transformation function is assigned an individual value from the entire range of values ​​that it can have. In a specific embodiment, the first-second probability distribution may include a Gaussian (normal) distribution, a gamma distribution, an exponential distribution, a uniform distribution, a chi-square distribution as a continuous probability distribution, a binomial distribution, a negative binomial distribution, an initial lower distribution, a Poisson distribution, and a multinomial distribution and / or a multivariate distribution for a number of transformation elements as a discrete probability distribution. The same or different first-second probability distribution may be set for each transformation element. In addition to the parametric approach method of extracting a transformation element with a specific type of probability distribution defined as above, a transformation element may be randomly extracted without assuming a specific distribution.

[0047] In one embodiment, when the transformation element is embodied as numerical data, the first-second probability distribution may be a continuous probability distribution such as Gaussian (normal) distribution, Gamma distribution, exponential distribution, uniform distribution, or chi-square distribution, and the new value of the transformation element is a value selected from the continuous probability distribution.

[0048] In one embodiment, when the transformation element is embodied as binary variable data, the first-second probability distribution may be a binomial distribution, a negative binomial distribution, an initial lower distribution, or a Poisson distribution, which are discrete probability distributions. The binary variable data may be expressed as a first binary value indicating "yes" or a second binary value indicating "no". The new value of the transformation element is a value selected according to the discrete probability distribution.

[0049] In one embodiment, if the transformation element is embodied as a categorical variable, the first-second probability distribution may be a multinomial probability distribution, and the new value of the transformation element is a value selected according to the multinomial probability distribution.

[0050] In some embodiments, the set of transformation elements forming the transformation function may include at least some transformation elements that are correlated with each other. If the transformation element changed to a new value is correlated with other transformation elements, the first-second probability distribution set for the other correlation transformation elements may be a multivariate probability distribution. Then, the values ​​of the other correlation transformation elements are changed to new values ​​selected according to the predefined multivariate probability distribution.

[0051] In addition to the parametric approach method for extracting the deformation factors with the specific form of probability distribution defined as described above, the deformation factors may be randomly extracted without assuming a specific distribution.

[0052] In an alternative embodiment, the first-second probability distribution may be an optimized version of any specified initial probability distribution through training, as will be described in more detail below.

[0053] As shown in FIG. 3, a portion of the generated training signal is displayed on a two-dimensional planar frame of the training image.

[0054] Referring back to FIG. 1, the training image generating method includes the step of determining an output object format of the training image by selecting at least one output object format from a plurality of preset output object formats (S200).

[0055] FIG. 4 is a schematic diagram of an output format according to one embodiment of the present application.

[0056] 4, the output format defines a structure for arranging output components of a training image on a two-dimensional plane frame. The plurality of output formats may be associated with output components of different aspects. In a specific embodiment, the plurality of output formats may include an output format defining a type of waveform, an output format defining an arrangement position of waveform, an output format defining a position of a waveform display area, and / or an output format defining a position of an additional information display area.

[0057] The waveform type may include a channel number.

[0058] The arrangement position of the waveform indicates in what order and at what position the waveforms for each channel are arranged, and may include the arrangement order.

[0059] The position of the waveform display area may include the coordinate range of the area (eg, grid area) in which the waveform is displayed.

[0060] The position of the additional information display area includes the coordinate range of an area in which additional information other than the waveform is displayed. The additional information may include subject information of the waveform (e.g., age, sex), waveform analysis, scale information of the waveform, etc.

[0061] The waveform display area and the additional information display area may be separate from each other or may at least partially overlap each other.

[0062] Each of the multiple output formats is composed of one or more format elements that constitute the layout structure of the output format. Therefore, like the transformation function based on the transformation elements, the output format may also be expressed as a function composed of format elements. n (n is a natural number equal to or greater than 1) output format functions (f n 2 ) are predefined and stored, where the subscript n is a letter indicating that there are n functions, and the superscript is a number to distinguish the function from other functions described above and below.

[0063] In a particular embodiment, the output form function (f n 2 ) of the form vector (P n 2 ) may include m factors, each of which is a formal element P nm 2 (where n is the output form function identifier, and m is the element identifier). nm 2 ) corresponds to the placement target defined in the output format, i.e., the output component.

[0064] In one embodiment, the format elements may include channel number, channel order, position of the waveform display area, position of the additional display area, vertical spacing between each waveform, horizontal spacing between individual waveforms, and / or length of the time interval of the waveforms, etc. For example, an output format format element that defines the position of the waveform display area may include the position of the waveform display area on a two dimensional plane, etc.

[0065] When a form element has a particular value, an output element corresponding to the form element is embodied on the output form with the particular value and is represented on the training image.

[0066] Similar to the transformation function, the formal elements of the output formal function may be embodied as hyperparameters. When one output formal function includes multiple transformation elements, the multiple formal elements may be represented as a hyperparameter vector, where the vector values ​​are the formal element values. Then, each output formal function may be associated with its own hyperparameter vector.

[0067] In one embodiment, the step of selecting at least one output form function (S200) may select any one output form function according to a 2-1st predetermined probability distribution for the set of the plurality of preset output forms, or may select two or more output form functions from the plurality of output form functions.

[0068] The second-first probability distribution defines the probability of selecting a particular output form function (or functions) to generate training images from among a plurality of output form functions. Selecting an output form function according to the second-first probability distribution is similar to selecting a transform according to the first-first probability distribution.

[0069] In one embodiment, the 2-1st probability distribution may be defined by selecting an output product type function out of n. For example, the 2-1st probability distribution may have a multinomial distribution.

[0070] In another embodiment, the 2-1st probability distribution may be defined by selecting two or more output object form functions out of n. For example, the 2-1st probability distribution may have a binomial distribution. In this case, different output object form functions may be overlapped and used to generate training images.

[0071] In an alternative embodiment, the 2-1 probability distribution may be an optimized version of any specified initial probability distribution through training, as will be described in more detail below.

[0072] The selected output type may be used as is, or the values ​​of the form elements of the selected output type may be changed to determine the output type for the training images (S200). The selected output type function may receive a new value for at least one form element as an input argument to adjust the function of the output type function.

[0073] In one embodiment, the step of selecting at least one output type from a plurality of preset output types and determining the output type of the training image (S200) may include the steps of: changing at least one form element value of the form elements constituting the selected output type to a new value; and determining the output type having the changed form element value as the output type of the training image. The value of the form element may be changed based on a probability.

[0074] In one embodiment, a 2-2nd probability distribution may be set for each form element. If the number of form elements is m, m 2-2nd probability distributions are defined and assigned. For each of the form elements of the output form function selected according to the 2-1st probability distribution, the existing form element value may be changed to a new value selected according to the 2-2nd probability distribution preset for the output form function. The output form reflecting the changed new value is used to generate a training image.

[0075] The second-second probability distribution defines a probability distribution in which each formal element of the output formal function is assigned an individual value from the entire range of values ​​that it can have. In a specific embodiment, the second-second probability distribution may include a Gaussian (normal) distribution, a gamma distribution, an exponential distribution, a uniform distribution, a chi-square distribution as a continuous probability distribution, a binomial distribution, a negative binomial distribution, an initial lower distribution, a Poisson distribution, a multinomial distribution, and / or a multivariate distribution for a number of transformation elements as a discrete probability distribution. The same or different second-second probability distribution may be set for each formal element. In addition to the parametric approach method of extracting a formal element with a specific type of probability distribution defined as above, a formal element may be randomly extracted without assuming a specific distribution.

[0076] In one embodiment, when the form element is embodied as numeric data, the 2-2 probability distribution may be a continuous probability distribution such as Gaussian (normal) distribution, Gamma distribution, exponential distribution, uniform distribution, or chi-square distribution, and the new value of the form element is a value selected from the continuous probability distribution.

[0077] In one embodiment, when the formal element is embodied as binary variable data, the 2-2 probability distribution may be a binomial distribution, a negative binomial distribution, an initial lower distribution, or a Poisson distribution, which are discrete probability distributions. The binary variable data may be expressed as a second binary value indicating "yes" or a second binary value indicating "no". The new value of the formal element is a value selected according to the discrete probability distribution.

[0078] In one embodiment, if the formal element is embodied as a categorical variable, the second probability distribution may be a multinomial probability distribution, and the new value of the formal element is a value selected according to the multinomial probability distribution.

[0079] In some embodiments, the set of format elements forming the output format function may include at least some format elements that are correlated with each other. If the format element changed to a new value is correlated with other format elements, the second-second probability distribution set for the other correlated format elements may be a multivariate probability distribution. Then, the values ​​of the other correlated format elements are changed to new values ​​selected according to the predefined multivariate probability distribution.

[0080] In addition to the parametric approach for extracting form elements with a specific type of probability distribution defined as described above, form elements may be randomly extracted without assuming a specific distribution.

[0081] In an alternative embodiment, the 2-2 probability distribution may be an optimized version of any specified initial probability distribution through training, as will be described in more detail below.

[0082] In this way, an output format having form factor values ​​modified according to the second-second probability distribution is provided as an output format for generating the training images (S200).

[0083] Referring again to FIG. 1, the training image generating method includes a step of determining an output interval for each channel of the training signal based on the length of the time interval of the waveform of the determined output type (S300), and a step of determining a grid scale of the training image by selecting a scale for each axis (S400).

[0084] The step of determining an output interval for each channel of the training signal (S300) may include the steps of: selecting at least one of a start point and an end point of the output interval for each channel to be output to the training image within the entire length of the received source signal; and calculating the channel interval based on the length of a time interval of a waveform and the selected point within a format element of the selected output format.

[0085] Generally, only a portion of all signals measured is output to an image. The total length of the output section is determined as the time section of the waveform among the format attributes of the output type determined in step S200 (S300).

[0086] The start point or end point is selected from a range including the entire time interval of the determined waveform among the entire interval of the generated training signal.

[0087] The selection range of the start points may be a range from the rising point of the training signal to a point extended in the negative time direction by the time period of the waveform determined in step S200 from the falling point of the training signal. In one example, if the entire period of the training signal is [0, Ω] and the time period of the waveform is w, the distribution of the start points may be [0, Ω-w]. In this case, the end point is a point where the time period of the waveform determined is extended in the positive time direction from the selected start point.

[0088] The selection range of the end point may be the opposite of the selection range of the start point, and the selection range of the end point may be a range from the falling edge of the training signal to a point extended in the positive time direction by the time period of the determined waveform from the rising edge of the training signal. In one example, the distribution of the end points may be [w, Ω]. In this case, the start point is a point extended in the negative time direction by the time period of the determined waveform from the selected end point.

[0089] In one embodiment, the start point or the end point may be a point selected from a selection range for each point according to a third probability distribution preset in advance, the third probability distribution defining a probability distribution in which an individual value is assigned from a selection range for each point.

[0090] The third probability distribution may be a Gaussian (normal) distribution, a uniform distribution, or a chi-square distribution as a continuous probability distribution. When a start point is selected by the uniform probability distribution or the like, an end point may be automatically selected and an output interval may be determined from a training signal.

[0091] In some embodiments, the multiple channels may include synchronized channels, where at least some of the channels have the same output duration. In other embodiments, the multiple channels may be unsynchronized channels, where the output durations of the multiple channels are different from each other.

[0092] By performing the operation of step S300, the waveform content to be displayed on the training image over the entire section of the training signal is determined.

[0093] The step of determining the grid scale of the training image (S400) may be determined by selecting a horizontal axis unit scale and / or a vertical axis unit scale of a coordinate system displaying the training signal.

[0094] FIG. 5 is a schematic diagram of a grating scale according to one embodiment of the present application.

[0095] Referring to FIG. 5, in a grid scale, the horizontal axis (or x-axis) represents time and the vertical axis (or y-axis) represents signal measurements.

[0096] In some embodiments, the step of selecting a horizontal axis unit scale and / or a vertical axis unit scale may include the step of selecting any one of a plurality of horizontal axis unit scales according to a preset 4-1 probability distribution over an entirety of a plurality of preset horizontal axis unit scales; and / or the step of selecting any one of a plurality of vertical axis unit scales according to a preset 4-2 probability distribution over an entirety of a plurality of preset vertical axis unit scales.

[0097] Similar to the 1-1 probability distribution, the 4-1 and 4-2 probability distributions may have a multinomial distribution. Then, a training signal is displayed on the training image in selected horizontal and / or vertical axis units.

[0098] Referring again to FIG. 1, the training image generating method includes a step (S500) of displaying a grid pattern on a two-dimensional plane according to the grid scale determined in the step (S400).

[0099] FIG. 6 shows a grid pattern representation according to one embodiment of the present application.

[0100] Referring to FIG. 6, the grating pattern according to the grating scale is a pattern in which gratings are arranged in units of the grating scale for each axis determined in step S400 (S500).

[0101] In an embodiment, the step of displaying the grid pattern on a two-dimensional plane (S500) may include the step of selecting one grid pattern format from a plurality of preset grid pattern formats.

[0102] The grid pattern format defines a grid pattern using a unique display line hierarchy and / or a unique display line design of the pattern. The hierarchy may indicate, for example, a large section, a medium section, a small section, and the like.

[0103] Similarly to the output object form function, each of the multiple grid pattern forms consists of one or more pattern elements that form the grid pattern form. Therefore, similar to the output object form function, the grid pattern form may also be expressed as a function consisting of pattern elements. n (n is a natural number equal to or greater than 1) grid pattern form functions (f n 3 ) are predefined and stored, where the subscript n is a letter indicating that there are n functions, and the superscript is a number to distinguish the function from other functions described above and below.

[0104] In a particular embodiment, the grid pattern form function (f n 3 ) pattern vector (P n 3 ) may include m factors, each of which is a pattern element P nm 3 (where n is a lattice pattern format function identifier, and m is an element identifier). nm 2 ) corresponds to the pattern components defined by the lattice pattern type function.

[0105] In one embodiment, the pattern elements may include the pattern of the display lines of the lattice pattern (various display formats for displaying imaginary lines such as solid lines / dotted lines / double lines), thickness, color, etc. The color may be realized by RGB values, CMYK channel values, etc.

[0106] When a pattern element has a specific value, a pattern element corresponding to the pattern element is embodied in the grid pattern format with the specific value and is represented on the training image.

[0107] Similar to the output type function, the pattern elements of the lattice pattern type function may be embodied as hyperparameters. When one lattice pattern type function includes multiple pattern elements, the multiple pattern elements may be expressed as a hyperparameter vector, where the vector value is the pattern element value. Then, each lattice pattern type function may be associated with its own hyperparameter vector.

[0108] In an embodiment, the step of selecting one of the plurality of grid pattern types may select one of the grid pattern types according to a preset 5-1st probability distribution.

[0109] The 5-1 probability distribution defines the probability of selecting a particular lattice pattern type from the entire set of lattice pattern type functions to generate training images. Selecting an output product type function according to the 5-1 probability distribution is similar to selecting a transform according to the 1-1 probability distribution.

[0110] In one embodiment, the 5-1st probability distribution may be defined by selecting a lattice pattern type function out of n. For example, the 5-1st probability distribution may have a multinomial distribution.

[0111] In an alternative embodiment, the 5-1 probability distribution may be an optimized version of any specified initial probability distribution through training, as will be described in more detail below.

[0112] The selected grid pattern type may be used as is, or the values ​​of the pattern elements of the selected grid pattern type may be changed to determine the grid pattern type for the training images (S500). The selected grid pattern type may adjust the function of the grid pattern type function by inputting a new value for at least one pattern element as an input argument.

[0113] In one embodiment, the step of representing the lattice pattern on a two-dimensional plane (S500) may include the steps of adjusting pattern element values ​​of the selected lattice pattern type; and determining the lattice pattern type having the adjusted pattern element values ​​as the lattice pattern type of the training image. The values ​​of the pattern elements may be changed based on a probability.

[0114] In one embodiment, a 5-2 probability distribution may be set for each pattern element. If the number of pattern elements is m, m 5-2 probability distributions are defined and assigned. For each pattern element of the lattice pattern type function selected according to the 5-1 probability distribution, the existing pattern element value may be changed to a new value selected according to the 5-2 probability distribution preset for the lattice pattern type function. The lattice pattern type reflecting the changed new value is used to generate a training image.

[0115] The 5-2 probability distribution defines a probability distribution in which an individual value is assigned from the entire range of values ​​that each pattern element of the lattice pattern type function can have. In a specific embodiment, the 5-2 probability distribution may include a Gaussian probability distribution, a uniform probability distribution, a continuous uniform probability distribution, a normal distribution, a chi-square distribution, a binomial probability distribution, a multinomial probability distribution, and / or a multivariate probability distribution. The same or different 5-2 probability distributions may be set for each pattern element.

[0116] In one embodiment, when the pattern element is embodied as numerical data, the probability distribution of 5-2 may be a Gaussian (normal) distribution, a gamma distribution, an exponential distribution, a uniform distribution, or a chi-square distribution as a continuous probability distribution, and the new value of the pattern element is a value selected from the continuous probability distribution.

[0117] In one embodiment, when the pattern element is embodied as binary variable data, the 5-2 probability distribution may be a binomial distribution, a negative binomial distribution, an initial lower distribution, or a Poisson distribution, which are discrete probability distributions. The binary variable data may be expressed as a second binary value indicating "yes" or a second binary value indicating "no". The new value of the pattern element is a value selected according to the discrete probability distribution.

[0118] In some embodiments, the set of pattern elements forming the grid pattern type function may include at least some pattern elements that are correlated with each other. If the pattern element changed to a new value is correlated with other pattern elements, the 5-2nd probability distribution set for the other correlated pattern elements may be a multivariate probability distribution. Then, the values ​​of the other correlated pattern elements are changed to a new value selected according to a predefined multivariate probability distribution.

[0119] The grid pattern is then displayed on a two-dimensional plane in an adjusted grid pattern format based on the selected grid pattern format.

[0120] In an alternative embodiment, the 5-2 probability distribution may be optimized through training from any specified initial probability distribution, as described in more detail below.

[0121] Referring again to FIG. 1, the training image generating method includes a step (S600) of setting a reference position of the waveform content of the training signal determined in step (S300) based on at least one of the output type determined in step (S200), the channel-specific output interval determined in step (S300), and the grid scale determined in step (S400); and a step (S700) of displaying the waveform content and signal indicators of the training signal on the two-dimensional plane on which the grid pattern is displayed in step (S500).

[0122] In step S200, the positions of the training signals for each channel and the positions of the output object arrangement structure are calculated on a two-dimensional plane forming a frame of the training image. In step S300, the contents of the waveform to be displayed in the training image are determined.

[0123] According to the grid scale determined in step S400, coordinates of measurement values ​​for the waveform content in the training signal are calculated (S600). The coordinates of the measurement values ​​are positions on a two-dimensional plane and define where the waveform content of which channel is located. The coordinates of the measurement values ​​are calculated as coordinate values ​​based on the grid pattern.

[0124] The calculated training signal measurements may be utilized as reference coordinates for the waveform content of the training signal. FIG. 7 is a schematic diagram of the result of displaying the waveform content and signal indicators of a training signal on a two-dimensional plane with a grid pattern according to one embodiment of the present application.

[0125] Referring to FIG. 7, the step of displaying the waveform content and signal identifier of the training signal on a two-dimensional plane on which a grid pattern is displayed (S700) may display the waveform content and signal identifier of each channel of the training signal on the two-dimensional plane on which the pattern is displayed based on the reference position.

[0126] In one embodiment, the step of representing the waveform content of each channel of the training signal on the two-dimensional plane on which the grid pattern is represented (S700) based on the reference position may include the steps of: defining a representation function for graphically expressing the waveform content of the training signal for each channel based on the reference position; and representing the waveform content and signal identifier of the training signal using the defined representation function.

[0127] The above notation function (f n 4 ) is the reference coordinate of the training signal and one or more representation vectors (P nm 4) is based on the notation vector (P n 4 ) may include m factors, each of which is a representation element P nm 4 (where n is the notation function identifier and m is the element identifier). Incidentally, here, the subscript n is a letter indicating that there are n functions, and the superscript is a number to distinguish it from the other functions mentioned above.

[0128] The reference coordinates of the training signal may include coordinates of measurements of the waveform content of the training signal calculated to match a grid pattern, such as a coordinate on the horizontal axis of the signal and a coordinate on the vertical axis.

[0129] The notation element (P nm 4 ) defines the design of the waveform and the signal identifiers. The notation elements consist of a first group related to the design of the waveform and a second group related to the design of the signal identifiers.

[0130] The first group of notation elements may include a waveform, a thickness, a hue, etc. The hue may be represented by an RGB value, a CMYK channel value, etc.

[0131] The signal indicators include a channel indicator and a scale indicator. The second group of notation elements may include the position, pattern, font, color, thickness of the character (or line), etc. of the indicator. The position of the indicator is indicated as a relative position from the training signal being represented.

[0132] Such definition may be made in response to user input or may be preset.

[0133] The representation function may be used to represent the waveform content of the training signal on a two-dimensional plane, and a channel indicator and a scale indicator may be represented within a certain distance from the waveform of the training signal (S700).

[0134] If the representation element values ​​are adjusted, the waveform content, channel indicator, and scale indicator of the training signal may be represented on the two-dimensional plane to reflect the adjusted representation element values ​​(S700).

[0135] In one embodiment, the step of representing the waveform content and signal identifier of the training signal using the defined representation function may include the steps of adjusting values ​​of representation elements of the representation function; and representing the channel-by-channel waveform content of the training signal on the two-dimensional plane on which the grid pattern is represented, reflecting the adjusted representation element values. The values ​​of the representation elements may be changed based on a probability.

[0136] In one embodiment, a sixth probability distribution may be set for each notation element. If the number of notation elements is m, m fifth probability distributions are defined and assigned. For each notation element of the notation function selected according to the sixth probability distribution, an existing notation element value may be changed to a new value selected according to the sixth probability distribution preset for that notation element. A training image is displayed on a two-dimensional plane in a notation format reflecting the changed new value.

[0137] The sixth probability distribution defines a probability distribution in which each representation element of the representation function is assigned an individual value from the entire range of values ​​that it can have. In a specific embodiment, the sixth probability distribution may include a Gaussian (normal) distribution, a uniform distribution, a chi-square distribution as a continuous probability distribution, a binomial distribution, a negative binomial distribution, an initial lower distribution, a Poisson distribution as a discrete probability distribution, and a multinomial distribution and / or a multivariate probability distribution for a number of variant elements. The same or different sixth probability distribution may be set for each representation element. In addition to the parametric approach method of extracting representation elements with a specific form of probability distribution defined as above, representation elements may be randomly extracted without assuming a specific distribution.

[0138] In one embodiment, when the notation element is embodied as numerical data, the sixth probability distribution may be a Gaussian (normal) distribution, a uniform distribution, a continuous uniform probability distribution, a normal distribution, or a chi-square distribution as a continuous probability distribution, and the new value of the notation element is a value selected from the continuous probability distribution.

[0139] In one embodiment, when the representation element is embodied as binary variable data, the sixth probability distribution may be a binomial distribution, a negative binomial distribution, an initial lower distribution, or a Poisson distribution, which are discrete probability distributions. The binary variable data may be expressed as a second binary value indicating "yes" or a second binary value indicating "no". A new value of the representation element is a value selected according to the discrete probability distribution.

[0140] In one embodiment, if the representation element is embodied as a categorical variable, the sixth probability distribution may be a multinomial probability distribution, and the new value of the representation element is then a value selected according to the multinomial probability distribution.

[0141] In some embodiments, the set of notation elements forming the notation function may include at least some notation elements that are correlated with each other. If the notation element changed to a new value is correlated with other notation elements, the sixth probability distribution set for the other notation elements having the correlation may be a multivariate probability distribution. Then, the values ​​of the other notation elements having the correlation are changed to the new value selected according to the predefined multivariate probability distribution. Then, the waveform contents and signal identifiers of the training signal are displayed on a two-dimensional plane in a display format having the changed values ​​(S700).

[0142] In an alternative embodiment, the sixth probability distribution may be an optimized version of any specified initial probability distribution through training, as described in more detail below.

[0143] The training image generating method also includes the step of further representing additional information and / or scale information of the training signal (S800).

[0144] FIG. 8 is a schematic diagram of additional information according to one embodiment of the present application.

[0145] 8, the additional information of the training signal is the original attributes of the training signal, similar to the source additional information. The additional information of the training signal may be embodied in text indicating age, sex, measurement location, measurement time, or waveform analysis.

[0146] In one embodiment, the step of displaying the additional information of the training signal may include a step of selecting and displaying additional information text arbitrarily selected from predefined additional information texts. The display position of the additional information text is based on the output format determined in step S300.

[0147] In some other embodiments, the side information of the training signal may be source side information, in which case the side information of the training signal and the side information of the source signal are identical.

[0148] The scale information is information describing the grid scale determined in step S400, and may be embodied as a symbol, a picture, or text that represents the grid scale. The display position of the scale information also depends on the output format determined in step S200.

[0149] In an embodiment, the step of representing the scale information may include the steps of: selecting one of a plurality of preset scale notation methods; and representing the scale information in the selected scale notation method.

[0150] In an embodiment, the step of selecting one of a plurality of preset scale notation schemes may include selecting one of a plurality of preset scale notation schemes according to a seventh probability distribution.

[0151] The seventh probability distribution may be defined in a 1 in n manner. For example, the seventh probability distribution may have a multinomial distribution.

[0152] The training image generating method may further include the step of further modifying the generated training image (S900).

[0153] The step (S900) may include the steps of: selecting at least one image augmentation function from a plurality of preset image augmentation functions; and further transforming the training image using the selected image augmentation function.

[0154] The image dilation function may consist of multiple dilation factors, which may include a type of deformation, a frequency, an intensity, and / or an epoch number.

[0155] The step of selecting the expansion function is similar to the step of selecting the transformation function. In one embodiment, the step of selecting the expansion function may select one image expansion function from among the transformation functions according to an eighth probability distribution preset for the set of the plurality of image expansion functions, or may select two or more image expansion functions from among the plurality of image expansion functions.

[0156] The eighth probability distribution defines the probability of selecting a particular image expansion function(s) to generate training images from the universe of image expansion functions.

[0157] In one embodiment, the eighth probability distribution may be defined in a manner of selecting an image expansion function 1 out of n. For example, the eighth probability distribution may have a multinomial distribution.

[0158] In another embodiment, the eighth probability distribution may be defined by selecting two or more image expansion functions out of n. For example, the eighth probability distribution may have a binomial distribution.

[0159] The training image generating method may further include converting the generated training image data into a tensor of W×H×C' type (S1000), where W is the width of the image, H is the height of the image, and C' is the number of color channels (C'=1 in case of monochrome). When a multi-channel one-dimensional signal of C×T real array type is input to the source signal, the training image generating method may generate training images and output the resultant converted into a three-dimensional real array of W*h*C type.

[0160] In the alternative embodiment, the probability distribution may be an arbitrary specified initial probability distribution that is optimized through training.

[0161] As previously mentioned, the hyper-parameter vector may include binomial, multinomial, and numerical data.

[0162] The binomial data is selected according to the binomial distribution. As described above, the selection according to the binomial distribution may be performed more than once. The label data for the binomial data is embodied as a multilabel choice in which one or more items are selected as "yes."

[0163] The multinomial data is selected according to a multinomial distribution. As described above, the selection according to the multinomial distribution may be performed alone. Then, the label data for the multinomial data is implemented by a single label choice.

[0164] Numerical data is selected according to a probability distribution having a limited or unlimited range. Such a probability distribution may include a Gaussian (normal) distribution, a gamma distribution, an exponential distribution, a uniform distribution, a chi-square distribution, etc., as a continuous probability distribution. As mentioned above, the selection according to the uniform distribution is to select a real number having a limited or unlimited range.

[0165] The elements embodied in the data format may correspond to hyperparameters of a machine learning model and may be targets for optimization.

[0166] Such hyperparameters may be optimized in the process of training an image-based artificial intelligence model that utilizes the generated training images to analyze multi-channel one-dimensional signal images.

[0167] The hyperparameters are optimized with the following goals: a) improving accuracy on the trained AI text dataset, b) improving robustness against domain shifts and adversarial attacks, and c) improving the embedding quality of the latent vectors (i.e., minimizing the distance in the latent space between identical concepts).

[0168] The optimization of the hyperparameters may be performed through optimization algorithms such as, but not limited to, Grid search, Random search, Gaussian process, and Tree-structured Parzen Estimator (TPE).

[0169] According to another aspect of the present application, the training image generation method may be performed by a component configured to receive and process data.

[0170] FIG. 9 is a block diagram of an apparatus for executing the training image generating method according to another aspect of the present application.

[0171] Referring to FIG. 9, the apparatus includes an acquisition unit 10; and an image generation unit 100.

[0172] The acquisition unit 10 acquires a source signal from a device capable of measuring a source signal such as a multi-channel one-dimensional signal. For example, the acquisition unit 10 can acquire an electrocardiogram signal directly or indirectly from an electrocardiogram measuring device attached to a part of a body of a subject to measure an electrocardiogram signal, which is a multi-channel one-dimensional signal of the subject (user).

[0173] The acquisition unit 10 may be connected to receive information from an electrocardiogram measuring device that measures an electrocardiogram signal of the subject via a sensor attached to a part of the subject's body, and the acquisition unit 10 may then directly acquire the electrocardiogram signal from the electrocardiogram measuring device.

[0174] The sensor may be attached to a part of the body of the subject to measure the electrocardiogram signal of the subject (user). The electrocardiogram signal acquired from the sensor and the electrocardiogram signal measuring device may be converted into a digital signal via an analog-digital converter (ADC). In addition, the electrocardiogram measuring device (not shown) may measure a biosignal when it is determined that the user's body is in contact with the touch panel for a predetermined time or more. According to another embodiment, the acquiring unit 10 may acquire not only an electrocardiogram signal (raw signal) but also an electrocardiogram image that is output on paper or an image and visualized based on an already acquired electrocardiogram signal.

[0175] The acquisition unit 10 may be connected to receive information from an electrocardiogram measuring device that measures an electrocardiogram signal of the subject via a sensor attached to a part of the subject's body, and the acquisition unit 10 may then directly acquire the electrocardiogram signal from the electrocardiogram measuring device.

[0176] Alternatively, the acquisition unit 10 may be connected to an external device so as to perform wired or wireless electrical communication. In this case, the acquisition unit 10 may acquire electrocardiogram signal data from electrocardiogram signal data previously acquired or stored in the external device. The external device may be connected to an electrocardiogram measuring device itself, or may acquire electrocardiogram signal data via another external device connected to the electrocardiogram measuring device. Therefore, the acquisition of electrocardiogram signal data by the acquisition unit 10 from an external device may be treated as indirect acquisition of an electrocardiogram signal.

[0177] Source signal information measured through one or more channels is acquired by the acquisition unit 10. The source signal information may include an analog source signal, digital source signal information, or a source image representing a source signal.

[0178] The image generating unit 100 is a computing device including a processor and a memory, and may perform steps (S100 to S800) of the training image generating method of FIG. 1 upon receiving source signal information received by the acquiring unit 10.

[0179] In one embodiment, the image generating unit 100 may be embodied as a server. The acquiring unit 10 may be a device (e.g., a user terminal or a signal input device) connected to the server for inputting data.

[0180] In this case, the server is a number of computer systems or computer software implemented as a network server, and can provide various information by configuring it as a website. Here, the network server means a computer system and computer software (network server program) that is connected to a subordinate device that can communicate with other network servers via a computer network such as a private intranet or the Internet, receives a request to execute a task, executes the task accordingly, and provides the execution result. However, in addition to such a network server program, it should be interpreted as a broad concept including a series of application programs that operate on the network server and, in some cases, various databases that are built inside. For example, when various databases are included, the server is configured to use external database information such as a cloud, and in this case, the server can connect to an external database server (e.g., a cloud server) through operation to communicate data.

[0181] The training image generating method and the operation of the apparatus for performing the same according to the embodiments described above may be embodied at least in part in a computer program and recorded in a computer-readable recording medium, for example, with a program product comprising a computer-readable medium including program code, which may be executed by a processor to perform any or all of the steps, operations, or processes described.

[0182] The computer may be any device that may be or may be integrated into a desktop computer, laptop computer, notebook, smartphone, or similar computing device. A computer is a device that has one or more alternative special purpose processors, memory, storage space, and networking components (either wireless or wired). The computer may run an operating system such as, for example, a Microsoft Windows compatible operating system, Apple OSX or iOS, a Linux distribution, or Google's Android OS.

[0183] The computer-readable recording medium includes all kinds of recording devices in which computer-readable data is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. The computer-readable recording medium may also be distributed among computer systems connected via a network, and computer-readable code may be stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for implementing the present embodiment should be easily understood by those skilled in the art to which the present embodiment pertains.

[0184] The present invention has been described above with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will understand that various modifications and variations of the embodiments are possible based on the above. However, such modifications should be considered to be within the technical scope of the present invention. Therefore, the true technical scope of the present invention should be determined by the technical ideas of the appended claims. [Industrial Applicability]

[0185] The present invention relates to a training image generation technique used to train an image-based artificial intelligence model and an apparatus for implementing the same, and can be applied to signal analysis in a variety of industrial fields in which two-dimensional images are analyzed based on signals in the medical and bio fields and other one-dimensional signals.

Claims

1. 1. A method for generating training images, performed by a computing device including a processor and a memory, comprising: generating a training signal based on the source signal information; determining an output format of the training image by selecting at least one output format from a plurality of preset output formats; determining an output interval for each channel of the training signal based on the length of a time interval of the waveform of the determined output type; selecting a scale for each axis to determine a grid scale for the training images; representing the grid pattern on a two-dimensional plane according to the determined grid scale; setting a reference position of the waveform content of the training signal based on at least one of the determined channel-by-channel output interval and the determined grid scale; and and displaying the waveform content and signal identifier of the training signal on a two-dimensional plane on which a grid pattern is displayed. A training image generation method comprising:

2. The step of generating a training signal based on source signal information includes: selecting at least one transformation function from a plurality of predetermined transformation functions; and Transforming the source signal into a training signal using a selected transformation function; The training image generating method according to claim 1 , wherein the transformation function is composed of one or more transformation elements which indicate transformation of a signal processing attribute of the input signal, and each transformation element corresponds to a signal processing attribute.

3. Modifying the signal processing attributes includes manipulating, changing, or removing one or more of a signal magnitude, a waveform, a frequency range, a frequency distribution, a signal rise time, and a signal time range; 3. The method of claim 2, wherein modifying the signal processing attributes is performed on a per-channel basis, on a group of channels, or on the entire channel basis.

4. The step of selecting at least one transformation function from the plurality of transformation functions comprises: Selecting one of the plurality of transformation functions according to a first-first probability distribution preset for the set of the plurality of transformation functions, or selecting two or more of the plurality of transformation functions, When selecting one of N transformation functions, the first probability distribution is a multinomial distribution; 3. The method of claim 2, wherein when two or more transformation functions are selected from among N, the first probability distribution is a binomial distribution.

5. The step of transforming the source signal into the training signal using the selected transformation function comprises: changing at least one transformation element value of the transformation elements constituting the selected transformation function to a new value; and Then, generating a signal reflecting the signal processing attributes modified in accordance with the modified transformation factor values ​​as a training signal; 3. The training image generating method according to claim 2, wherein the new value is a value selected according to a first-second probability distribution preset for the deformation element.

6. If the transformation element is embodied as numerical data, the new value of the transformation element is a value selected according to a continuous probability distribution; When the transformation element is embodied as binary variable data, the new value of the transformation element is a value selected according to a discrete probability distribution; 6. The method of claim 5, wherein when the deformation factor is implemented as a categorical variable, the new value of the deformation factor is a value selected according to a multinomial probability distribution.

7. The set of transformation elements forming the transformation function includes at least some transformation elements that are correlated with each other, 6. The method of claim 5, wherein if the deformation element changed to a new value is correlated with other deformation elements, the values ​​of the other correlated deformation elements are changed to a new value selected according to a predefined multivariate probability distribution.

8. The step of determining the output format of the training image by selecting at least one output format from a plurality of preset output formats includes: selecting one output type according to a second-first predetermined probability distribution for the set of the plurality of preset output types, or selecting two or more output types from the plurality of output types; When selecting one output type out of N, the second-1st probability distribution is a multinomial distribution; 2. The method of claim 1, wherein when two or more transformation functions are selected from among N transformation functions, the second-1st probability distribution is a binomial distribution.

9. determining an output format of the training image by selecting at least one output format from a plurality of preset output formats, changing at least one form element value of the form elements of the selected output form to a new value; and determining an output type having the modified form factor values ​​as an output type of the training images; each of the plurality of output formats comprises one or more format elements that define a layout structure of the output format; 9. The method of claim 8, wherein the new value is a value selected according to a 2-2 probability distribution preset for the form element.

10. If the form element is embodied as numeric data, the new value of the form element is a value selected according to a continuous probability distribution; If the formal element is embodied as binary variable data, the new value of the formal element is a value selected according to a discrete probability distribution; 10. The method of claim 9, wherein when the formal elements are embodied as categorical variables, the new values ​​of the formal elements are values ​​selected according to a multinomial probability distribution.

11. The set of form elements forming the output form includes at least some form elements that are correlated with each other; 10. The method of claim 9, wherein if the form element changed to a new value has a correlation with other form elements, the values ​​of the other correlated form elements are changed to a new value selected according to a predefined multivariate probability distribution.

12. determining an output section for each channel of a training signal based on a length of a time section of a waveform of the determined output type, selecting at least one of a start point and an end point of an output section for each channel to be output to the training image within the entire length of the received source signal; and 2. The method of claim 1, further comprising the step of calculating the output interval for each channel based on a length of a time interval of a waveform and a selected point among format elements of a selected output type.

13. The start point or the end point is a point selected from a selection range for each point according to a third probability distribution preset therefor, the third probability distribution defines a probability distribution in which individual values ​​are specified from a selection range for a start point and an end point; the selection range of the start point is a range from the rising point of the training signal to a point extended in the negative time direction by the determined time period of the waveform from the falling point of the training signal, 13. The training image generating method according to claim 12, wherein the selection range of the end point is a range from the falling point of the training signal to a point extended in a positive time direction by a time period of the determined waveform from the rising point of the training signal.

14. The step of selecting a scale for each axis and determining a grid scale for the training image includes: selecting one of the plurality of horizontal axis unit scales according to a fourth-1st predetermined probability distribution over all of the plurality of predetermined horizontal axis unit scales; or selecting one of the plurality of vertical axis unit scales according to a fourth-second predetermined probability distribution over all of the plurality of predetermined vertical axis unit scales; 2. The training image generating method according to claim 1, wherein the probability distributions 4-1 and 4-2 have a multinomial distribution.

15. The step of displaying the grid pattern on a two-dimensional plane according to the determined grid scale includes: selecting one of the plurality of grid pattern types according to a (5-1)th predetermined probability distribution for the set of the plurality of preset grid pattern types; 2. The training image generating method according to claim 1, wherein the 5-1st probability distribution is a multinomial distribution.

16. The step of representing the grid pattern on a two-dimensional plane according to the determined grid scale includes: adjusting the pattern element values ​​of the selected grid pattern type; and determining a grid pattern type having the adjusted pattern element values ​​as the grid pattern type of the training images; Each of the plurality of grid pattern types comprises one or more pattern elements that define a grid pattern with a line hierarchy of the pattern or a unique line design of the pattern; 16. The method of claim 15, wherein the adjusted values ​​are values ​​selected according to a 5-2nd probability distribution preset for the form elements.

17. When the pattern element is embodied as numerical data, the adjusted value of the pattern element is a value selected according to a continuous probability distribution, 17. The method of claim 16, wherein when the pattern elements are embodied as binary variable data, the adjusted values ​​of the pattern elements are values ​​selected according to a discrete probability distribution.

18. The set of pattern elements in the grid pattern form includes at least some pattern elements that are correlated with each other, 17. The method of claim 16, wherein if the pattern element adjusted to a new value is correlated with other pattern elements, the values ​​of the other correlated pattern elements are adjusted to a new value selected according to a predefined multivariate probability distribution.

19. 2. The training image generating method according to claim 1, wherein the reference position of the waveform content of the training signal includes coordinates of measurement values ​​of the training signal, which are calculated as coordinate values ​​based on the grid pattern.

20. The step of displaying the waveform content and the signal identifier of the training signal on a two-dimensional plane having a lattice pattern includes: defining a representation function for graphically expressing the waveform content of the training signal for each channel based on the reference position; representing the waveform content and signal identifiers of the training signal using the defined representation function; 2. The method of claim 1, wherein the representation function is based on reference coordinates of the training signal and one or more representation elements, the representation elements defining a waveform design or a signal indicator design.

21. The step of expressing the waveform content and the signal identifier of the training signal using the defined expression function includes: adjusting the values ​​of the representation elements of the representation function; and displaying the waveform content of each channel of the training signal on the two-dimensional plane on which the grid pattern is displayed, reflecting the adjusted display element values; 21. The method of claim 20, wherein the adjusted value is a value selected according to a sixth probability distribution preset for the notation element.

22. If the representation element is embodied as numeric data, the adjusted value of the representation element is a value selected according to a continuous probability distribution, When the representation element is embodied as binary variable data, the adjusted value of the representation element is a value selected according to a discrete probability distribution; 22. The method of claim 21, wherein when the representation element is embodied as categorical variable data, the adjusted value of the representation element is a value selected according to a multinomial probability distribution.

23. The set of notation elements forming the notation function includes at least some notation elements that are correlated with each other, 22. The method of claim 21, wherein if the notation element adjusted to a new value has a correlation with another notation element, the value of the other notation element having the correlation is adjusted to a new value selected according to a predefined multivariate probability distribution.

24. 2. The method of claim 1, wherein the method is used to train an image-based artificial intelligence model for analyzing images obtained from a multi-channel one-dimensional signal.

25. A computer program stored on a medium for performing, in combination with hardware, the training image generating method according to any one of claims 1 to 24.

26. A training image generating device, comprising: An acquisition unit for acquiring a source signal; and an image generating unit including a processor and a memory; A training image generating device, characterized in that the image generating unit receives source signal information received by the acquiring unit, and executes the training image generating method according to any one of claims 1 to 24.

Citation Information

Patent Citations

  • Block copy producing device

    JP1994282060A

  • Abnormality detector and abnormality detection method

    JP2020191050A

  • System and method for identifying cardiac arrhythmias with deep neural networks

    US20200178825A1

  • Encoding electrocardiographic data

    US20230388520A1