KR20230159938A - Method for analyzing bio-signal - Google Patents

Abstract

According to an embodiment of the present disclosure, a method of automating the process of constructing a biosignal analysis model by determining a preprocessing function and an artificial neural network according to the characteristics of the biosignal when analyzing biosignals is disclosed. Specifically, according to the present disclosure, a computing device utilizes a design model to determine one or more variables among variables related to an analysis method of a biological signal, and utilizes the design model to determine one or more variables based on the determined one or more variables. A biometric signal analysis model is dynamically configured, and the biosignal is analyzed using the dynamically configured biosignal analysis model.

Description

Biosignal analysis method {METHOD FOR ANALYZING BIO-SIGNAL}

The present invention relates to a method of analyzing biological signals, and more specifically, automates the process of constructing a biological signal analysis model by dynamically determining preprocessing functions and artificial neural networks according to the characteristics of the biological signals in analyzing biological signals. It's about how to do it.

With the rapid development of artificial intelligence technology in recent years, artificial neural networks are being used for automated analysis in various fields. In particular, research is being actively conducted on automated frameworks that explore optimized artificial neural networks according to input data and derive analysis results.

In the field of biosignal processing, a lot of research is being done on ways to identify biosignal characteristics and diagnose diseases using artificial neural network technology such as CNN (Convolutional Neural Network).

However, biological signals inherently have irregular measurement times or irregular data shapes, and unstable elements such as noise exist during the measurement process. Therefore, in order to successfully analyze biological signals using an artificial neural network, a preprocessing method such as noise removal suitable for the signal and an artificial neural network model suitable for analyzing the signal must be selected depending on the type of signal and measurement environment. Therefore, models for analyzing biological signals need to be designed differently for each analysis.

In this way, redesigning the entire framework, including preprocessing and analysis models, for biosignal analysis each time requires a lot of trial and error, so it consumes a lot of time and resources, and there is a need to mobilize professional manpower. Therefore, there is a demand in the art for a method in which a preprocessing method and analysis model optimized for input biological signals are selected by automating the overall framework for analyzing biological signals using an artificial neural network.

US Patent Publication 2021-0295163 (2021. 09. 23.) discloses a method for automatically searching neural network architecture.

The present disclosure was made in response to the above-described background technology, and uses a design model, which is an artificial intelligence model, to determine the most appropriate variable among several variables for analyzing the input biosignal, and to determine the biosignal constructed based on the determined variable. The purpose is to create an automated framework for analyzing biological signals by analyzing the biological signals through an analysis model.

According to an embodiment of the present disclosure for realizing the above-described problem, a method for analyzing biological signals is disclosed. The method is performed by a computing device, comprising: utilizing a design model to determine one or more variables among variables related to an analysis method of a biological signal; The method may include dynamically constructing a biosignal analysis model based on the determined one or more variables using the design model, and analyzing the biosignal using the dynamically configured biosignal analysis model.

In an alternative embodiment, determining one or more variables associated with how to analyze the biosignal includes: determining a preprocessing function to be used to analyze the biosignal; and determining an architecture to be used to analyze the biosignal.

In an alternative embodiment, the preprocessing function includes: a filtering function; normalization function; interpolation function; Alternatively, it may include at least one of a data augmentation function.

In an alternative embodiment, the architecture includes a Convolutional Neural Network (CNN); Long Short-Term Memory (LSTM); Or it may include at least one of a transformer.

In an alternative embodiment, the architectures may have at least some weights shared between each individual architecture.

In an alternative embodiment, the design model includes: receiving a biological signal from the design model; determining one or more variables among variables related to an analysis method of the biosignal using the design model; Using the design model, dynamically constructing a biosignal analysis model based on the determined one or more variables; analyzing the biosignal using the dynamically configured biosignal analysis model; and determining a reward of the design model based on a result analyzed by the biological signal analysis model.

In an alternative embodiment, utilizing the design model to dynamically construct a biosignal analysis model based on the determined one or more variables includes utilizing positional encoding, wherein the positional encoding Encoding is information about the currently entered variable; Information about the input location of the variable; and information about the range within which each variable can be determined.

In an alternative embodiment, the range of variables that can be determined related to the method of analyzing the biosignal may be limited by the design model.

In alternative embodiments, the range of the variable may be limited to a different range depending on the nature of the biosignal and the field in which the biosignal will be used.

According to an embodiment of the present disclosure for realizing the above-described object, a computer program for analyzing biological signals is disclosed. The above program is, An operation of determining one or more variables related to an analysis method of a biological signal using the design model; Using the design model, dynamically constructing a biosignal analysis model based on the one or more variables determined; and analyzing the biological signal based on the dynamically configured biological signal analysis model.

According to an embodiment of the present disclosure for realizing the above-described problem, a computing device for analyzing biological signals is disclosed. The computing device includes a processor including one or more cores; a network unit that receives biological signals; Includes memory, The one or more processors: Using a design model, determine one or more variables among variables related to an analysis method of a biological signal, using the design model, dynamically construct a biosignal analysis model based on the determined one or more variables, and dynamically configure the dynamic signal analysis model based on the determined one or more variables. The biosignal is analyzed based on a biosignal analysis model composed of.

The present disclosure can determine an optimized preprocessing function and analysis model for analyzing input biological signals and provide results of analyzing the biological signals.

The following drawings attached to be used in explaining the embodiments of the present disclosure are only some of the embodiments of the present disclosure, and for those skilled in the art (hereinafter referred to as “ordinary skilled in the art”), Other drawings can be obtained based on these drawings without effort leading to new inventions.
1 is a block diagram of a computing device that performs an operation for analyzing biological signals according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
Figure 3 is a flowchart of a method illustrating a process of analyzing biological signals according to an embodiment of the present disclosure.
Figure 4 is a conceptual diagram showing a method for training a design model according to an embodiment of the present disclosure.
Figure 5 is a conceptual diagram showing a biosignal analysis model according to an embodiment of the present disclosure.
FIG. 6 is a conceptual diagram illustrating positional encoding of a variable selection module according to an embodiment of the present disclosure.
7 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

The present disclosure utilizes a design model, which is an artificial intelligence model, to determine the most appropriate preprocessing function and architecture to analyze the input biosignal, and a biosignal analysis model constructed based on the determined preprocessing function and architecture analyzes the biosignal to analyze the biosignal. A method of creating a framework that automates the signal analysis process is disclosed.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “when it contains only A,” “when it contains only B,” or “when it is a combination of A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present disclosure is not limited to the embodiments presented herein. This disclosure is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

In this disclosure, network function, artificial neural network, and neural network may be used interchangeably.

Meanwhile, “biological signals” used throughout the detailed description and claims of the present disclosure include electrocardiogram (ECG), electroencephalogram (EEG), electromyogram (EMG), galvanic skin response (GSR), It may refer to a record of measuring signs indicating the activity of the human body, such as electrooculography (EOG), electroretinogram (ERG), and electronic medical record (EMR), but the present disclosure is not limited to this. No.

Meanwhile, “variable” in the present disclosure may refer to a preprocessing function that can convert biological signals into a form that is easy to process, an architecture for analyzing biological signals and diagnosing diseases, and each hyperparameter that constitutes the architecture. For example, the preprocessing function may include various types of filtering functions, normalization functions, interpolation functions, or data augmentation functions, and the architecture may include general artificial neural network models for signal analysis, such as convolutional neural networks, long-term memory, and transformers. , Hyperparameters that make up the architecture may include kernel size (in the case of convolutional neural networks), movement interval (in the case of convolutional neural networks), skip connection, number of layers, hidden dimension (in the case of transformers), etc.

1 is a block diagram of a computing device that performs an operation for analyzing biological signals according to an embodiment of the present disclosure.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for learning neural networks, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. Calculations can be performed.

At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

According to an embodiment of the present disclosure, the processor 110 may acquire a biosignal. The biosignal may be data measured from a separate biosignal measurement device connected to the computing device and received through the network unit 150, or may be data stored in the memory 130, but the present disclosure is not limited to this.

The processor 110 may use a design model to determine variables for analyzing the acquired biosignal from a pool of certain variables. The pool of variables may be differently limited by the processor 110 depending on the type of biosignal to be analyzed and the type of task to be achieved. For example, one of five filtering functions may be used as preprocessing of ECG data to diagnose disease A, but one of three filtering functions may be used as preprocessing of ECG data for diagnosing disease B.

The processor 110 may determine a preprocessing function that is determined to be most appropriate for processing the corresponding biosignal. The present disclosure can separately add information about each preprocessing function using positional encoding. For example, in the design model of the present disclosure, when constructing a biosignal analysis model by sequentially determining preprocessing functions, information values such as the properties of the preprocessing function and the location and range of each preprocessing function are used to dynamically configure the biometric analysis model. It can be included in the process.

If both the preprocessing function and the artificial neural network architecture are determined in one model, the learning process of the design model may become unstable due to differences in the properties of the two different elements. By introducing the concept of positional encoding into the learning process of the design model, the present disclosure can help the model recognize the preprocessing function decision part and the artificial neural network architecture decision part separately, and thus the design model and the design model are composed. The performance of the biosignal analysis model can be maintained stably.

In conclusion, the present disclosure solves the instability of learning that may occur by including the part that determines the appropriate preprocessing function and the part that determines the appropriate architecture in the learning of the design model through positional encoding, and can effectively learn the design model. .

In order to construct a biosignal analysis model, the processor 110 may determine an artificial neural network architecture and hyperparameters of the architecture that are determined to be most suitable for analysis of the biosignal. For example, when analyzing electrocardiogram data (ECG) for the purpose of reading heart disease, the design model can determine the most suitable transformer for ECG analysis among the types of architecture as the architecture for analysis. And the design model can determine various hyperparameters of the transformer architecture (skip connection, number of artificial neural network layers, hidden dimensions), etc. Here, each hyper-parameter may fall within a range adjusted according to electrocardiogram data, which is a biosignal.

The processor 110 may include positional encoding in the process of determining variables for bio-signal analysis. Positional encoding is used as an input to the model by adding additional information to the embedding vector of each input to obtain information about the location of each input, for an artificial neural network model that receives all inputs simultaneously regardless of the order of the inputs, such as a transformer. It means the technology to For example, when the biosignal analysis model constructed by the present disclosure is constructed through sequential variable selection, information on each currently determined variable, the location of the currently determined variable, and the selection range of the currently determined variable are provided. It can be reflected in the model construction process through sional encoding. A detailed description of positional encoding will be described later with reference to FIG. 6.

The processor 110 may configure a biosignal analysis model for biosignal analysis based on variables determined by the design model. For example, the processor selects one of three filtering functions, selects one of four normalization functions, selects one of five interpolation functions, selects one of six data augmentation functions, and , And when a transformer is determined as the architecture for analysis, the biosignal analysis model may be an artificial neural network in which the preprocessing function and architecture thus determined are combined sequentially or in other ways.

The design model is a model that can be reinforced by the processor 110. When variables are determined using the design model and a biosignal analysis model is constructed, the biosignal analysis model analyzes the input biosignal and provides the result. It can be fed back to the design model as a reward of the reinforcement learning model. Reinforcement learning design requires an appropriate definition of reward, and various means can be used to define reward. For example, the reward may be ROC (Receiver Operating Characteristics), which has been conventionally used in reinforcement learning in the biosignal field, or it may be a measurement value used in reinforcement learning in the language processing field, but the present disclosure is not limited to this.

In the process of learning a design model, architecture blocks, that is, algorithms such as convolutional neural network, long-term memory, and transformer, can share weights with each other. By sharing weights, design models can dramatically reduce the amount of massive computation required for training.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure includes Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( A variety of wired communication systems can be used, such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and Local Area Network (LAN).

In addition, the network unit 150 presented in this specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), and SC-FDMA ( A variety of wireless communication systems can be used, such as Single Carrier-FDMA) and other systems.

In the present disclosure, the network unit 150 may use any type of wired or wireless communication system.

The techniques described herein can be used in the networks mentioned above, as well as other networks.

Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural network (CNN), recurrent neural network (RNN), auto encoder, Generative Adversarial Networks (GAN), and Long Short-Term Memory. ; LSTM), Transformer, restricted Boltzmann machine (RBM), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN) It may include etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the training data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer are used. It can be applied.

Figure 3 is a flowchart of a method illustrating a process of analyzing biological signals according to an embodiment of the present disclosure.

In step S310, the processor 110 may use the design model to determine variables related to the analysis method of the biological signal. At this time, variables related to the method of analyzing the biological signal may include a preprocessing function for preprocessing the biological signal and an artificial neural network architecture block for analyzing the biological signal. At this time, the preprocessing functions may be some of the filtering functions, some of the normalization functions, some of the interpolation functions, or It can be several of the data augmentation functions, and the artificial neural network architecture block is a convolutional neural network, long-term memory, transformer, etc. in each artificial neural network block, such as the size of the kernel, number of moves (stride), skip connection, number of layers, etc. May contain elements.

Processor 110 selects each of these variables: one of the filtering functions, one of the normalization functions, one of the interpolation functions, one of the data augmentation functions, and one of the hyperparameters of the selected artificial neural network architecture. Variables related to the analysis method can be determined by sequentially selecting one variable, but the present disclosure is not limited to this determination method.

The criteria by which the processor 110 selects each item may vary depending on the type of biosignal input to the design model and the purpose to be achieved by analyzing the biosignal.

In step S320, the design model can automatically configure a biosignal analysis model, which is a child model of the design model, based on the variables determined in step S310, without separate input from the user. If the processor 110 decides to select one variable from each item using the design model, the biosignal analysis model formed by the design model includes an artificial neural network in the form of sequentially connecting the selected items. It could be a model.

In step S330, the biosignal analysis model, which is a child model of the design model, can analyze the input biosignal and derive the result. For example, a biosignal analysis model can analyze biosignals by going through processes such as noise filtering, normalization, interpolation, and data augmentation on biosignals and then using a transformer artificial neural network with each hyperparameter determined.

Figure 4 is a conceptual diagram showing a method for training a design model according to an embodiment of the present disclosure.

The design model 400 includes a variable selection module 410 and a biosignal analysis model 420 constructed by the design model. The variable selection module may limit the range 411 of variables that can be selected, depending on the type of biological signal and the purpose for analysis. In the present disclosure, by limiting the range of variables that can be selected by the design model 400, the amount of required calculations can be reduced and the biosignal analysis model 420 can be efficiently constructed. The variable selection module 410 can dynamically construct a biological signal analysis model 420, which is a child model, from variables with a limited range depending on the type of biological signal and the purpose for analysis.

The biosignal analysis model 420, which is a child model constructed by the design model, analyzes the biosignal and defines the reward 421 of an artificial neural network in the form of reinforcement learning based on the analysis results to determine the variable selection module 410. ) can be fed back. Afterwards, the variable selection module 410 learns based on the input compensation to construct the next biosignal analysis model.

Compensation 421 defined by the biosignal analysis model 420 may be defined in various forms. In addition to ROC (Receiver Operating Characteristics), which has been used in conventional studies analyzing biological signals using artificial neural networks, it has separate purposes such as factors for evaluating the performance of artificial neural networks used in natural language processing modeling to improve learning efficiency. The reward can be defined using elements of the reinforcement learning model being trained.

Figure 5 is a conceptual diagram showing a biosignal analysis model according to an embodiment of the present disclosure.

A biosignal analysis model constructed by a design model may be a model in which several preprocessing functions and several artificial neural network architectures are sequentially connected. Each preprocessing function and architecture can dynamically change depending on the design model, type of biological signal, and purpose of analysis. The architecture used in the biosignal analysis model can be selected as the most suitable architecture for analyzing the biosignal each time the model is constructed, and the design model can configure the hyperparameters of each architecture as variables.

FIG. 6 is a conceptual diagram illustrating positional encoding of a variable selection module according to an embodiment of the present disclosure.

Generally, in natural language processing, since the word order of each word is entered sequentially in a sentence, each word has its own position information and can be well analyzed using a recurrent neural network. .

However, artificial neural network architectures such as Transformers, in contrast to recurrent artificial neural networks or convolutional artificial neural networks, do not contain information about relative positions in their vectorized inputs, so they encode and add information about the positions to the input vectors. You can enter information. This positional encoding process can also be learned by an artificial neural network.

Taking this into consideration, the present disclosure uses the positional encoding characteristics of the transformer architecture, which has achieved great results in natural language analysis, in the area of biosignal analysis. The variable selection module 600 adds positional encoding 620 information in which the characteristics of the variables are vectorized to the biosignal input 610, including the properties of each variable and the relative position of the variables with respect to the configured biosignal analysis model. It may include information such as the selection range of the currently determined variable. This information can be expressed in the form of a vector 630 containing information about each preprocessing function and each architecture.

By introducing positional encoding into the area of biosignal analysis, the present disclosure can enable the biosignal analysis model constructed by the design model to include information about the properties and positions of each component constituting the model.

If the reinforcement learning process is designed to simultaneously learn two heterogeneous elements, such as a preprocessing function and an artificial neural network architecture, the model's learning process may be unstable and the performance of the learned model may be low. In this disclosure, by introducing the element of positional encoding, the model recognizes the difference between the part that determines the preprocessing function and the part that determines the artificial neural network architecture during the learning process, thereby improving the design model compared to the case of learning without positional encoding. It can be learned stably. As a result, performance can be improved by effectively learning the design model constituting the biosignal analysis model using the method exemplified in this disclosure.

7 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Meanwhile, according to an embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that change during the neural network learning process may include weights that change at the start of the learning cycle and/or weights that change during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, the data structure including the weights of the neural network may include weights that are changed during the neural network learning process and/or the data structure including the weights for which neural network learning has been completed. Therefore, the above-mentioned weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

7 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has generally been described above as being capable of being implemented by a computing device, those skilled in the art will understand that the present disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or in hardware and software. It will be well known that it can be implemented as a combination.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media, such as the like, may also be used in the example operating environment and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as via the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (9)

A method performed by one or more processors of a computing device for analysis of biosignals, comprising:
Using the design model, determining one or more variables among variables related to an analysis method of biosignals;
Using the design model, dynamically constructing a biosignal analysis model based on the determined one or more variables; and
analyzing the biosignal using the dynamically configured biosignal analysis model;
Including,
method.
According to claim 1,
The step of determining one or more variables among the variables related to the analysis method of the biological signal,
determining a preprocessing function to be used to analyze the biosignal; and
determining an architecture to be used to analyze the biosignal;
Including,
method.
According to claim 2,
The architecture is,
At least some weights are shared between each individual architecture,
method.
According to claim 1,
The design model is,
receiving biological signals from the design model;
determining one or more variables among variables related to an analysis method of the biosignal using the design model;
Using the design model, dynamically constructing a biosignal analysis model based on the determined one or more variables;
analyzing the biosignal using the dynamically configured biosignal analysis model; and
determining a reward for the design model based on results analyzed by the biosignal analysis model;
Reinforcement learning based on
method.
According to claim 1,
Using the design model, the step of dynamically constructing a biosignal analysis model based on the determined one or more variables includes utilizing positional encoding,
The positional encoding is,
Information about the currently entered variable;
Information about the input location of the variable; and
Information about the range over which each variable can be determined;
Including,
method.
According to claim 1,
Variables related to the analysis method of the biological signals are,
The range of variables that can be determined is limited by the design model,
method.
According to claim 6,
The range of the variable may be limited to a different range depending on the properties of the biosignal and the field in which the biosignal will be used.
method.
A computer program stored on a computer-readable storage medium containing instructions for causing a computing device to perform operations, the operations comprising:
An operation of determining one or more variables related to an analysis method of a biological signal using the design model;
Using the design model, dynamically constructing a biosignal analysis model based on the one or more variables determined; and
Analyzing the biological signal using the dynamically configured biological signal analysis model;
Including,
A computer program stored on a computer-readable storage medium.
As a computing device,
A processor including one or more cores;
A network unit that receives biological signals; and
Memory;
Including,
The processor,
Using the design model, determine one or more variables related to the analysis method of the biosignal,
Using the design model, dynamically constructing a biosignal analysis model based on the one or more variables determined,
Analyzing the biosignal using the dynamically configured biosignal analysis model,
Computing device.

Images