Method and apparatus for detecting abnormal biological signals

Abstract

This invention provides a method for detecting abnormal biological signals. [Solution] A method and apparatus for detecting abnormal biological signals includes the steps of: generating a plurality of sample data by randomly extracting frames having a first data length from raw data including biological signal data; generating a plurality of unit data by extracting frames having a second data length from the sample data in chronological order; generating a training dataset based on the plurality of unit data; and generating an abnormal biological signal detection model by training an artificial intelligence model with the training dataset.

Description

Technical Field

[0001] The present invention relates to a method and apparatus for detecting abnormal biological signals, and more particularly, to a method and apparatus for generating a model for detecting abnormal biological signals, and also to a method and apparatus for detecting abnormal biological signals by monitoring biological signals using the generated model.

Background Art

[0002] An artificial neural network mimics a biological neural network, but they are learned by a large number of input data and are used for estimating or approximating results that are difficult to derive by general techniques. An artificial neural network includes interconnected neuron layers that exchange signals, and synapses have weights that can be tuned based on learning or experience. In order to train an artificial neural network, high-quality learning data is required, and the performance of the artificial neural network can vary depending on the learning data.

[0003] On the other hand, heart disease accounts for a high proportion of the main causes of death at home and abroad. In particular, unexpected sudden death due to suffocation accidents during the sleep of infants most frequently occurs in infants aged 2 to 4 months. Also, as the rate of solitary death gradually increases, the need to reduce social costs through the prevention and management of solitary death is increasing.

[0004] The above background art is technical information that the inventor possessed for the derivation of the present invention or acquired during the derivation process of the present invention, and it cannot necessarily be said that it is publicly known technology that was publicly disclosed to the general public before the filing of the present invention.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The purpose of this disclosure is to provide a method and apparatus for detecting abnormal biological signals. The problems that this disclosure seeks to solve are not limited to the technical problems described above, and other technical problems not described will be clearly understood by a person with ordinary skill in the art from the description of the invention and will be further understood from embodiments of this disclosure. It will also be understood that the problems and advantages that this disclosure seeks to solve can be achieved by the means and combinations thereof shown in the claims. [Means for solving the problem]

[0006] As a means to solve the aforementioned technical problems, a first aspect of this disclosure provides a method for detecting abnormal biological signals, which includes the steps of: generating a plurality of sample data by randomly extracting frames having a first data length from raw data including biological signal data; generating a plurality of unit data by extracting frames having a second data length from the sample data in chronological order; generating a training dataset based on the plurality of unit data; and generating an abnormal biological signal detection model by training an artificial intelligence model on the training dataset.

[0007] A second aspect of this disclosure provides a device for detecting abnormal biological signals, which includes a memory storing at least one program and a processor that performs calculations by executing the at least one program, wherein the processor randomly extracts frames having a first data length from raw data including biological signal data to generate a plurality of sample data, extracts frames having a second data length from the sample data in chronological order to generate a plurality of unit data, generates a training dataset based on the plurality of unit data, and generates an abnormal biological signal detection model by training an artificial intelligence model on the training dataset.

[0008] A third aspect of this disclosure can provide a computer-readable recording medium that stores a program for performing the method of the first aspect on a computer.

[0009] A fourth aspect of the present disclosure provides a neuromorphic device for realizing a neural network that detects abnormal biological signals, comprising at least one processor for driving the neural network and an on-chip memory including a crossbar array circuit that receives instructions from the at least one processor and performs in-memory operations, wherein the at least one processor receives input data collected by a sensor, inputs the input data to the neural network which has been trained based on predetermined training data to detect the abnormal biological signals, the input data includes biological signals and noise signals, and the neural network includes an input layer into which the input data is input, one or more hidden layers for extracting features of the input data, and an output layer that outputs an output signal.

[0010] A fifth aspect of the present disclosure provides a method for detecting an abnormal biological signal using a neural network, comprising the steps of: receiving input data collected by a sensor; and inputting the input data into a neural network trained on predetermined training data to detect the abnormal biological signal, wherein the input data includes a biological signal and a noise signal; and the neural network includes an input layer into which the input data is input, one or more hidden layers for extracting features of the input data; and an output layer for outputting the abnormal biological signal.

[0011] A sixth aspect of this disclosure can provide a computer-readable recording medium that stores a program for performing the method of the fifth aspect on a computer.

[0012] In addition to those, other methods, other apparatuses for realizing the present invention, and computer-readable recording media containing programs for performing the said methods can be further provided.

[0013] Other aspects, features, and advantages not described herein will become apparent from the attached drawings, claims, and the following detailed description of the invention. [Effects of the Invention]

[0014] According to the aforementioned problem-solving means of this disclosure, it is possible to prevent and manage unintentional sudden death or death in isolation caused by suffocation accidents during sleep in infants and young children, thereby reducing social costs.

[0015] Furthermore, the problem-solving method described in this disclosure minimizes misrecognition of abnormal biological signals, which significantly increase social costs, and enables the construction of highly accurate machine learning models.

[0016] The effects of the embodiments are not limited to those described above, and any other effects not described will be clearly understood by those with ordinary skill in the art from the description of the present invention. [Brief explanation of the drawing]

[0017] [Figure 1] This diagram illustrates the architecture of a fully-connected neural network (FCNN) according to one embodiment of the present invention. [Figure 2] This is an illustrative diagram for comparing a von Neumann structure and a CIM (Computing-In-Memory) structure according to one embodiment of the present invention. [Figure 3] This is an illustrative diagram for comparing a von Neumann structure and a CIM (Computing-In-Memory) structure according to one embodiment of the present invention. [Figure 4] This figure shows a neural network according to one embodiment of the present invention. [Figure 5] This is an illustrative diagram of an environment for detecting abnormal biological signals according to one embodiment of the present invention. [Figure 6] This is an illustrative diagram of an environment for detecting abnormal biological signals according to one embodiment of the present invention. [Figure 7] It is a diagram for explaining load data according to an embodiment of the present invention. [Figure 8] It is a diagram for explaining a method of generating a plurality of sample data according to an embodiment of the present invention. [Figure 9] It is a diagram for explaining a method of generating a plurality of unit data according to an embodiment of the present invention. [Figure 10] It is a diagram for explaining a method of generating a plurality of unit data according to an embodiment of the present invention. [Figure 11] It is a diagram for explaining a method of generating a learning data set according to an embodiment of the present invention. [Figure 12] It is a diagram for explaining a method of generating a learning data set according to an embodiment of the present invention. [Figure 13] It is a diagram for explaining a method of generating a learning data set according to an embodiment of the present invention. [Figure 14] It is a graph showing the result of training an artificial intelligence model with a learning data set according to an embodiment of the present invention. [Figure 15] It is a block diagram of a device for detecting an abnormal biological signal according to an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0018] In explaining the present invention, when it is determined that a specific explanation of related known technologies obscures the gist of the present invention, the detailed explanation may be omitted, and unless otherwise specifically defined, all terms used in this specification have the same meaning as generally understood by those having ordinary knowledge in the technical field to which the present invention pertains.

[0019] Phrases such as "according to an embodiment", "relating to an embodiment", and "by the realization of an embodiment" in this specification do not necessarily all indicate the same embodiment.

[0020] Since embodiments can be modified in various ways and may take many forms, some embodiments are illustrated and described in detail in the drawings. However, this should not be understood as limiting the embodiments to any particular form of disclosure, but rather as including all modifications, equivalents, or substitutes that fall within the concept and technical scope of the embodiments. The terms used in this specification are for illustrative purposes only and are not intended to limit the embodiments.

[0021] The terminology used in the embodiments has been selected as widely used and general terms as possible, taking into account the functions of these embodiments. However, this may vary depending on the intentions of engineers in the technical field to which the embodiments belong, precedents, and the emergence of new technologies. In certain cases, the applicant may have arbitrarily selected some terms, in which case their meaning will be described in detail in the relevant section. Therefore, the terminology used in the embodiments should not be merely names of terms, but should be defined based on the meaning of those terms and the overall content of the embodiments.

[0022] Some embodiments of this disclosure can be represented by functional block configurations and various processing steps. Some or all of such functional blocks can be implemented by various numbers of hardware and / or software configurations that perform a particular function. For example, a functional block of this disclosure can be implemented by one or more microprocessors or by a circuit configuration for a given function.

[0023] Furthermore, for example, the functional blocks of this disclosure can be implemented in various programming or scripting languages. Functional blocks can also be implemented in algorithms that run on one or more processors. In addition, this disclosure may employ prior art for electronic environment configuration, signal processing, and / or data processing.

[0024] Terms such as "database," "element," "means," and "configuration" can be used broadly and are not limited to mechanical and physical configurations. Furthermore, terms such as "-part" and "-module" as described in the specification refer to a unit that processes at least one function or operation, which can be implemented in hardware or software, or a combination of hardware and software.

[0025] The connecting lines or members shown in the drawings between components are merely illustrative examples of functional and / or physical or circuit connections. In actual devices, connections between components can be represented by various alternative or additional functional, physical, or circuit connections.

[0026] Furthermore, while ordinal terms such as "first," "second," etc., used herein may be used to describe various components, the components themselves should not be limited by these terms. The terms are used solely for the purpose of distinguishing one component from another.

[0027] Furthermore, some components in the drawings may be shown with slightly exaggerated sizes or proportions. Additionally, components shown in one drawing may not be shown in other drawings.

[0028] Throughout the specification, “Embodiments” are arbitrary classifications that facilitate the description of the invention in this disclosure, and each embodiment does not need to be mutually exclusive. For example, a configuration disclosed in one embodiment can be applied to and / or implemented in other embodiments, and can be applied to and / or implemented with modifications without departing from the scope of this disclosure.

[0029] Furthermore, the terms used in this disclosure are for illustrative purposes only and do not limit the embodiments. In this disclosure, singular forms include plural forms unless otherwise specified.

[0030] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings, so as to be easily implemented by a person with ordinary skill in the art. However, embodiments of the present disclosure can be realized in a variety of different forms and are not limited to the embodiments described herein.

[0031] The present invention will now be described in detail based on the above and with reference to the drawings.

[0032] Neuromorphic chips are hardware that mimics human brain function by generating circuits that mimic the morphology of neurons. In other words, a neuromorphic chip is a computer chip that mimics the structure of the nervous system.

[0033] Neuromorphic chips, composed only of the circuits necessary for neural network computation, can achieve gains of hundreds of times or more in terms of power, area, and speed. Unlike conventional computers, the human brain does not consume much power even when processing large amounts of data, so neuromorphic chips can conserve energy by mimicking this brain operation by arranging structures that connect neurons and synapses in parallel and disconnecting them when not processing data.

[0034] For example, in conventional computers with a von Neumann architecture, data is processed sequentially as it is input, making it excellent for executing precisely crafted programs. However, it suffers from problems such as limited power consumption and low efficiency in areas like pattern recognition and real-time recognition.

[0035] In contrast, neuromorphic chips use analog operation, where various states change progressively, rather than digital data such as 0s and 1s. In other words, the parallel-configured artificial neurons operate in an event-driven manner without clock operation. Therefore, they can efficiently process unstructured characters, speech, and images that conventional computers have difficulty intuitively recognizing. Specifically, by distributing neurons (nerve cells) and synapses (connecting lines) using silicon transistor circuits and memory elements, data can be processed in parallel.

[0036] In one embodiment, when input data such as images, sounds, or electromagnetic waves are input to a neuromorphic chip, predetermined output data can be output by performing calculations within the neuromorphic chip on the input data. The predetermined output data may include the recognition results of sounds / images / electromagnetic waves based on feature classification of the input data. For example, when an electromagnetic wave signal is input as input data, the predetermined output data may include the recognition results of the electromagnetic wave, which classifies whether or not the input data contains an abnormal signal that has been learned in advance.

[0037] On the other hand, the data input to the neuromorphic chip is not limited to the aforementioned images, sounds, or electromagnetic waves, but may also include various forms of data such as video and text.

[0038] One embodiment of a neuromorphic device can be realized with an edge AI chip. Edge AI refers to the technology of executing AI algorithms on hardware devices using edge computing, which is based on data generated by the system. AI processing is mainly performed in cloud-based data centers that require enormous computing capacity, so it is highly dependent on servers. In contrast, using edge AI, the execution of AI algorithm calculations is performed locally, so the dependence on the cloud (server) is reduced, communication costs are reduced, and privacy is protected because sensitive personal information is not sent to the cloud. Therefore, by configuring a neuromorphic device with an edge AI chip, it is possible to reduce costs and improve security, as well as realize a highly responsive system because the calculations are processed immediately within the same hardware.

[0039] In the following description, the device for detecting abnormal biological signals according to one embodiment of the present invention may be the neuromorphic device described above. That is, the neuromorphic device described above can function as a device for detecting abnormal biological signals according to one embodiment of the present invention.

[0040] Figure 1 is a diagram illustrating the architecture of a fully-connected neural network (FCNN) according to one embodiment of the present invention.

[0041] Referring to Figure 1, a fully connected layer, or FCNN, is a layer in a convolutional neural network where all neurons in one layer are connected to all neurons in the next layer. It is used to classify data using a flattened matrix in the form of a one-dimensional array.

[0042] In FCNN, each node has a value, and each neuron has a weight and a bias. When moving from one layer to another, the node value of the next layer is obtained by multiplying the weight of each node by the bias. If this calculated value satisfies certain conditions, the output value obtained through an activation function is input as the node value of the next layer and activated. If this calculated value does not satisfy the conditions, an activation function intervenes to deactivate the node.

[0043] Therefore, since the output value differs depending on the type of activation function, it is important to use the appropriate activation function as needed. Typical examples include the ReLU function and the Softmax function.

[0044] Since FCNN can only accept one-dimensional array data as input, a drawback is that if the input data is a three-dimensional image consisting of length, width, and channels (color), it must be flattened into one-dimensional data before being input to the FCNN. In other words, because the spatial information of the image is ignored, it has the disadvantage of not being able to extract features embedded in the shape. Therefore, FCNN is highly useful when the input data can be realized as one-dimensional array data, such as electromagnetic wave data. According to one embodiment, the neural network described later may be an FCNN.

[0045] Figures 2 and 3 are illustrative diagrams illustrating a comparison between a von Neumann structure and a CIM (Computing-In-Memory) structure according to one embodiment of the present invention.

[0046] Referring to Figure 2, the von Neumann structure is a computer structure proposed by John von Neumann, and is a typical three-stage structure of a stored-program computer consisting of main memory, a central processing unit, and an input / output device.

[0047] The von Neumann architecture has the advantage of greatly improving versatility in computing devices because, when changing tasks, hardware (such as wires) does not need to be rearranged, and only the software (program) needs to be changed. However, because it involves sequentially executing a sequence of instructions, each instruction consisting of operations that change values ​​in designated memory locations, it causes serious problems in the design of high-speed computers. This is known as the von Neumann bottleneck phenomenon.

[0048] To solve the von Neumann bottleneck phenomenon, alternatives have been proposed, such as the Harvard architecture, which divides memory into parts where instructions are stored and parts where data is stored; the CIM architecture, which performs not only data storage but also data computation in memory; and neuromorphic computing, which uses an integrated circuit in the form of an artificial neural network that mimics the brain structure of higher animals, with many units that combine computation and memory functions connected in parallel in a network, and then operates each unit in an event-driven manner.

[0049] Referring to Figure 3, it can be seen that the CIM structure consists of a processor and memory with computing capabilities.

[0050] Unlike the conventional von Neumann architecture, where all data in memory is moved to the processor for calculations, the CIM architecture performs calculations in memory when a processor instruction is received, and only the result data is sent to the processor. This eliminates the need to move large amounts of data, effectively resolving the aforementioned von Neumann bottleneck phenomenon. It also has the advantage of significantly reducing power consumption.

[0051] A neural network according to one embodiment of the present invention can perform calculations using only on-chip memory, without using external memory. For example, the neural network can perform calculations on each layer using only on-chip memory in a CIM-based manner, without using external memory (e.g., off-chip memory), thereby performing calculations without memory updates while processing input signals. Specifically, the neural network can perform CIM-based calculations with each memory cell directly connected to the processor.

[0052] However, CIM (Computer-Input Memory) may have limitations in memory capacity and power consumption of computing devices compared to common memory such as RAM (Random Access Memory). Therefore, producing high-performance CIM chips may require new hardware structures, which can increase manufacturing costs. Thus, the CIM structure may be advantageous for performing relatively small amounts of computation or simple calculations. In contrast, a neural network according to one embodiment of the present invention may be composed of memory capable of multi-bit implementation in order to overcome the shortcomings of such CIM structures. For example, the neural network may be composed of memory capable of implementing 7 bits 128 analog memory states. By configuring the neural network with a large capacity, unlike common CIM chips which exhibit problems such as heat generation and performance degradation, it is possible to process a huge amount of data with low power and high performance even during long-term use.

[0053] On the other hand, on-chip memory can be realized by a crossbar array circuit. That is, the crossbar array can receive instructions from the processor and perform calculations, and CIM calculations can be achieved by integrating memory elements with a crossbar array structure into the on-chip memory. As an example, the processor can detect abnormal biological signals by receiving input data collected by a sensor, driving a neural network circuit trained based on predetermined training data, and receiving the abnormal biological signals output by the neural network circuit. Specifically, the processor can detect abnormal biological signals by inputting input data into the neural network. The configuration of the neural network and the training data for generating the abnormal biological signal detection model realized by the neural network will be described in detail below.

[0054] Figure 4 shows a neural network according to one embodiment of the present invention.

[0055] Referring to Figure 4, in one embodiment, the neural network may include an input layer 410 into which input data 400 is input, one or more hidden layers 420, 430, 440 that extract features from the input data 400, and an output layer 450 that outputs an output signal 460. Here, the input layer 410, one or more hidden layers 420, 430, 440, and the output layer 450 may represent the layers of the fully connected CNN described above.

[0056] In one embodiment, the neural network can classify input data 400 into one of three categories: normal biological signals, abnormal biological signals, and noise. Specifically, the neural network may include an input layer 410 for classifying the input data 400, one or more hidden layers 420, 430, 440, and an output layer 450.

[0057] In one embodiment, the input layer 410 of the neural network may be input data 400 which includes biosignals and noise signals. The biosignals are signals generated by the movement of the human body, and the noise signals may include simple movements of the monitored object that are not the biosignals being monitored (e.g., breathing or heartbeats) (e.g., turning over in bed), as well as movements of non-monitoring objects such as people or companion animals in the vicinity.

[0058] In one embodiment, the hidden layers 420, 430, and 440 of the neural network can extract or classify features of the input data 400 by reflecting weights in the input data 400. Therefore, the more hidden layers 420, 430, and 440 there are, the more sophisticated the processing of the input data 400 can be, improving the functionality of the algorithm.

[0059] In one embodiment, the output layer 450 of the neural network can output whether the input data 400 corresponds to a normal biological signal, an abnormal biological signal, or noise, based on the features extracted by at least one hidden layer 420, 430, or 440. That is, the output layer 450 can output as an output signal whether the neural network classified the input data 400 as a normal biological signal, an abnormal biological signal, or noise.

[0060] Figures 5 and 6 are illustrative diagrams of an environment for detecting abnormal biological signals according to one embodiment of the present invention.

[0061] Referring to Figure 5, the device 1 for detecting abnormal biological signals (hereinafter referred to as "device") can communicate with sensor 2 and one or more external control devices 31, 32, 33, and 34.

[0062] For example, device 1 can receive input data collected by sensor 2.

[0063] Furthermore, when an abnormal biological signal is detected, device 1 can transmit an emergency signal to an external control system including at least one of the following: a control center 31, a government office 32, an external terminal 33, and an external server 34.

[0064] In one embodiment, biosignals and noise signals included in the input data can be collected by sensor 2.

[0065] The change in the rib cage due to human respiration is at the 4-12 mm level, and the change in the rib cage due to heartbeat is at the 0.6-2 mm level. Therefore, in one embodiment, sensor 2 may be a millimeter-wave radar (mmWave Radar) whose radio wave wavelength band is in the millimeter (mm) band, or whose radio wave frequency band is in the 24 GHz-77 GHz range. However, the radio wave wavelength band and frequency band of sensor 2 are not limited to the embodiments described above, and the type of radar is not limited to a millimeter-wave radar.

[0066] Here, sensor 2 can collect characteristics related to the shape or movement of a human body being monitored by emitting radio waves to the human body being monitored and receiving the radio waves that have been reflected back from the surface of the body. Therefore, sensor 2 can collect changes in the rib cage caused by the breathing or heartbeat of the human body being monitored.

[0067] Referring to Figure 6, in one embodiment, the device 1 may include a communication unit (not shown) that uses at least one communication protocol, such as a Serial Peripheral Interface (SPI) 12, a Digital Video Port (DVP), a Parallel Serial Peripheral Interface (PSPI), an Inter-Integrated Circuit (I2C), a General Purpose Input / Output (GPIO), a Pulse Width Modulation (PWM), an Inter-IC Sound (I2S), and a Universal Asynchronous Receiver / Transmitter (UART) 13.

[0068] The serial peripheral interface 12 is a synchronous serial communication protocol for communication between multiple peripheral devices and a microcontroller or microprocessor. The serial peripheral interface 12 can be used to exchange data between a single device 1 and multiple slave devices such as a sensor 2 or external memory 21, according to one embodiment. The general-purpose asynchronous transceiver 13 is a form of serial communication protocol used to transmit data asynchronously. The general-purpose asynchronous transceiver 13 can be used for serial communication between device 1 and peripheral devices such as an external terminal 33, according to one embodiment.

[0069] As an example, device 1 can receive biosignals and noise signals related to the movement of the thoracic cage of a human body 600 collected by sensor 2 by communicating with sensor 2 using serial peripheral interface 12.

[0070] Furthermore, device 1 can send and receive data to and from the external memory 21 by communicating with the external memory 21 using the serial peripheral interface 12. The external memory 21 can store at least one signal from the normal biological signal, abnormal biological signal, and noise of the human body 600 detected by device 1.

[0071] However, in order for device 1 to communicate with sensor 2 and / or external memory 21, it may use at least one communication protocol or communication device other than the serial peripheral interface 12, such as DVP (Digital Video Port), PSPI (Parallel Serial Peripheral Interface), general-purpose asynchronous transceiver (UART), I2C (Inter-Integrated Circuit), GPIO (General Purpose Input / Output), and PWM (Pulse Width Modulation). That is, device 1 may include a communication unit (not shown) that uses at least one communication protocol of DVP (Digital Video Port), PSPI (Parallel Serial Peripheral Interface), general-purpose asynchronous transceiver (UART), I2C (Inter-Integrated Circuit), GPIO (General Purpose Input / Output), and PWM (Pulse Width Modulation).

[0072] In one embodiment, the device 1 can transmit an emergency signal to an external terminal 33 or the like using a general-purpose asynchronous transceiver 13. Here, the external terminal 33 is merely one embodiment, and it goes without saying that it can also transmit emergency signals to the aforementioned control center 31, government office 32, and external server 34. The external terminal 33 may also be a pre-configured parent's terminal. The emergency signal can be transmitted to the external terminal 33 in the form of text, images, audio, notifications, etc.

[0073] However, in order for device 1 to communicate with an external terminal 33, it may use at least one peripheral interface other than the general-purpose asynchronous transceiver 13, such as GPIO (General Purpose Input / Output), I2C (Inter-Integrated Circuit), I2S (Inter-IC Sound), and PWM (Pulse Width Modulation). That is, device 1 may include a communication unit (not shown) that uses at least one communication protocol of GPIO, I2C, I2S, and PWM.

[0074] However, the communication protocol and peripheral interface described above are merely one embodiment, and the method by which device 1 communicates with sensor 2, external memory 21, external terminal 33, etc., is not limited to these.

[0075] In one embodiment, the device 1 is installed in a predetermined space and monitors the biological signals of a human body 600. When an abnormal biological signal is detected from the human body 600, it transmits an emergency signal to a pre-configured external terminal 33, enabling immediate response to the emergency situation. This helps prevent accidental suffocation accidents among infants and deaths of elderly people living alone.

[0076] Figure 7 illustrates raw data based on one embodiment of the present invention.

[0077] An apparatus according to one embodiment of the present invention may be a neuromorphic device including a neural network, and may be an artificial intelligence model trained based on predetermined training data. In other words, an abnormal biological signal detection model may be implemented in a neuromorphic device.

[0078] Here, the specified training data may be generated based on raw data. The specified training data can be generated by processing the raw data according to the following explanation.

[0079] In one embodiment, the raw data may include normal biological signal data 710, abnormal biological signal data 720, and noise data 730.

[0080] In the following explanation, we will assume that biological signals are respiratory signals, but this is merely for the sake of explanation; biological signals can include various signals from the human body, including heartbeat signals.

[0081] Normal biosignal data 710 is data that measures only normal respiratory signals. For example, it may be a predetermined amount of data collected from a monitored subject whose sensor is breathing normally. Similarly, abnormal biosignal data 720 may be data that measures unstable respiration, such as when respiratory distress occurs. For example, it may be a predetermined amount of data collected from a monitored subject whose sensor is breathing abnormally. Here, the predetermined amount can be changed depending on the embodiment, such as 3 hours and 20 minutes or 10 hours.

[0082] The noise data 730 may be 3 hours and 20 minutes of data measuring signals other than the biological signals of the monitored subject, such as the movement of the monitored subject or the movement of the observer or companion animal. By generating training data not only for normal and abnormal biological signals but also for noise, higher performance can be achieved when the product is actually applied.

[0083] For example, the amounts of normal biological signal data 710, abnormal biological signal data 720, and noise data 730 may be the same. Therefore, the model can be appropriately trained on normal / abnormal biological signals and noise, achieving high performance. However, the amounts of each data may differ, and the amounts of each data are not limited to the embodiments described above.

[0084] In one embodiment, each raw data may include in-phase raw data ("I-data" in Figure 7) and phase-shifted raw data ("Q-data" in Figure 7). For example, the phase-shifted raw data may be quadrature data. In-phase raw data can mean the real part of a raw data represented as a complex number, and phase-shifted raw data can mean the imaginary part of a raw data represented as a complex number. In-phase raw data and phase-shifted raw data can be used together to represent other dimensions of a complex signal.

[0085] Figure 8 illustrates a method for generating multiple sample data according to one embodiment of the present invention.

[0086] The devices described in Figures 1 to 7 refer to neuromorphic devices that detect abnormal biological signals. However, the devices that generate abnormal biological signal detection models realized by neuromorphic devices (hereinafter referred to as "model generation devices") can refer to devices that generate or process training data for training the abnormal biological signal detection model.

[0087] In one embodiment, the model generation device can extract multiple frames from the raw data to generate multiple sample data 800. Here, the model generation device can extract multiple frames having a first data length 801 from the raw data.

[0088] For example, the first data length 801 could be 30 seconds. Assuming the raw data length 802 is 3 hours and 20 minutes, and the raw data is sampled at 20 Hz, there could be 240,000 data points corresponding to the raw data length 802, and 600 data points corresponding to the first data length 801, which is 30 seconds.

[0089] In one embodiment, the model generation device can randomly extract multiple frames from the raw data. That is, instead of sequentially extracting data points, it can randomly extract multiple frames having a first data length 801. Furthermore, the model generation device can extract a predetermined number of frames (for example, 2000) to generate a predetermined number of sample data 800.

[0090] On the other hand, if the raw data includes in-phase raw data and moving-phase raw data, the model generator can generate multiple in-phase sample data 800 by randomly extracting frames having a first data length 801 from the in-phase raw data. Furthermore, the model generator can generate multiple moving-phase sample data 810 by extracting frames having a first data length 801 from the moving-phase raw data so that they correspond to the signals of the multiple in-phase sample data 800. That is, the in-phase sample data 800 can be randomly extracted, and the moving-phase sample data 810 can extract the signal at the time point corresponding to the in-phase sample data 800. As an example, the model generator can extract moving-phase raw data and frames shifted by the phase difference of the in-phase raw data from the moving-phase sample data 800 to generate moving-phase sample data 810 so that they correspond to the signals of the in-phase sample data 800.

[0091] Figures 9 and 10 illustrate a method for generating multiple unit data according to one embodiment of the present invention.

[0092] Referring to Figure 9, multiple unit data points 900 to 990 generated from sample data having a first data length of 801 are shown.

[0093] In one embodiment, the model generation device can generate a plurality of unit data 900 to 990 by extracting frames having a second data length 901 from sample data in chronological order. For example, the second data length 901 may be 7.5 seconds. If the first data length 801 of the sample data is 30 seconds and there are 600 data points for the first data length 801 due to a data sampling period of 20 Hz, then there may be 150 data points for the second data length 901.

[0094] In one embodiment, the model generation device can sequentially extract frames having a second data length 901 such that they overlap by a third data length 902 between a plurality of unit data points 900 to 990. Specifically, the model generation device can extract a first frame 900 containing the first data point, and then extract a second frame 910 such that it overlaps with the first frame 900 by a third data length 902. Similarly, the model generation device can extract a third frame (not shown) such that it overlaps with the second frame 910 by a third data length 902.

[0095] For example, the third data length 902 could be 5 seconds. If the second data length 901 is 7.5 seconds, the model generator can move by a length of 2.5 seconds during the extraction of each frame to extract the next frame. Here, if the second data length 901 has 150 data points, the third data length 902 could have 100 points, and a total of 10 frames are extracted, so 10 sets of multiple unit data 900-990 can be generated. Also, since multiple unit data 900-990 are generated for each sample data, the number of unit data corresponding to one raw data can be generated by multiplying the number of sample data (e.g., 2000) by the number of unit data generated from each sample data (e.g., 10). Figure 9 shows that 10 sets of unit data 900-990 are generated, but the number of multiple unit data 900-990 can be varied depending on the third data length 902.

[0096] In one embodiment, the multiple sample data may include multiple in-phase sample data and multiple moving-phase sample data. Therefore, the model generation device can generate multiple in-phase unit data corresponding to the multiple in-phase sample data and multiple moving-phase unit data corresponding to the multiple moving-phase sample data. That is, the model generation device can generate multiple in-phase unit data for each of the in-phase sample data and generate multiple moving-phase unit data for each of the moving-phase sample data.

[0097] In one embodiment, the model generation device can convert the generated unit data into frequency components. For example, the model generation device can perform a Fast Fourier Transform (FFT) on the generated unit data.

[0098] Referring to Figure 10, multiple unit data 1010 to 1100 converted to frequency components are shown.

[0099] In one embodiment, the model generation device can convert multiple in-phase unit data into frequency components and multiple moving-phase unit data into frequency components.

[0100] Figures 11-13 illustrate a method for generating a training dataset according to one embodiment of the present invention.

[0101] Referring to Figure 11, multiple unit data points 1100 to 1190 are shown.

[0102] In one embodiment, the model generation device can generate a training dataset based on a plurality of unit data 1100 to 1190. Specifically, the model generation device can synthesize the plurality of unit data 1100 to 1190, which have been converted into frequency components, in the order in which they are extracted.

[0103] This allows us to generate one training data point corresponding to one sample data point. The reason for combining multiple unit data points 1100-1190 that have already been generated by superimposing them on each other is that if the signal contains signals such as the delta function, we can check whether it is noise or not by looking at whether there is continuity with the adjacent unit data points and reflect this in the training data.

[0104] Referring to Figure 12, multiple in-phase unit data 1100-1190 and multiple shifted phase unit data 1101-1191 are shown.

[0105] In one embodiment, the model generation device can combine multiple in-phase unit data 1100-1190 and multiple moving-phase unit data 1101-1191 by crossing them. Combining by crossing them means combining them sequentially such that the first moving-phase unit data 1101 is placed after the first in-phase unit data 1100, the second in-phase unit data 1110 is placed after the first moving-phase unit data 1101, and the second moving-phase unit data 1111 is placed after the second in-phase unit data 1110. Similarly, the third in-phase unit data 1120 and the third moving-phase unit data 1121 can be placed after the second moving-phase unit data 1111, and depending on the number of unit data, the last in-phase unit data 1190 and the last moving-phase unit data 1191 can be placed last.

[0106] Referring to Figure 13, the raw data includes normal biological signal data, abnormal biological signal data, and noise data. Therefore, the model generation device can generate normal biological signal learning data 1310 from the normal biological signal data 710, abnormal biological signal learning data 1320 from the abnormal biological signal data 720, and noise signal learning data 1330 from the noise data 730.

[0107] Multiple sample data and multiple unit data may be generated for normal biological signal data, abnormal biological signal data, and noise data, respectively. For example, a model generation device can generate N (e.g., 2000) in-phase sample data 800 and N (e.g., 2000) moving-phase sample data 810 from normal biological signal data 710.

[0108] Furthermore, since multiple unit data (not shown) generated from one sample data 800 are further synthesized into one training data, N (for example, 2000) normal biological signal training data 1310, abnormal biological signal training data 1320, and noise signal training data 1330 can also be generated.

[0109] In one embodiment, the training dataset generated by the model generation device may include normal biological signal training data 1310, abnormal biological signal training data 1320, and noise signal training data 1330.

[0110] On the other hand, in one embodiment, the model generation device can generate an abnormal biological signal detection model by training an artificial intelligence model with a training dataset.

[0111] Figure 14 is a graph showing the results of training an artificial intelligence model with a training dataset according to one embodiment of the present invention.

[0112] In one embodiment, the model generation device can adjust the parameters of the artificial intelligence model using a training dataset. Here, the artificial intelligence model may be a machine learning model.

[0113] Referring to Figure 14, it can be seen that the training loss function and validation loss function of a machine learning model change as shown in Figure 14 as the number of training iterations (epochs) on the training dataset increases. The training loss function (train_loss) is a value that indicates the loss of the training dataset, and the training loss function decreases as the machine learning model makes more accurate predictions on the training dataset. The validation loss function (val_loss) is a value that indicates the loss of new data that the machine learning model has not seen before (i.e., validation data), and the validation loss function decreases as the machine learning model becomes more generalized.

[0114] In one embodiment, the model generation device can select the machine learning model with the lowest loss function and the highest model accuracy, and determine it as the abnormal biological signal detection model.

[0115] The resulting abnormal biological signal detection model is implemented using a neural network. The processor in the neuromorphic device inputs the input data collected by the sensor into the abnormal biological signal detection model, and can then detect abnormal biological signals based on the output of the abnormal biological signal detection model.

[0116] Figure 15 is a block diagram of a device for detecting abnormal biological signals according to one embodiment of the present invention.

[0117] Referring to Figure 15, the device 1500 may include a communication unit 1510, a processor 1520, and a DB 1530. Only components relevant to the embodiment are shown in the device 1500 in Figure 15. Therefore, it will be understood by those ordinary skill in the art that other general-purpose components may be included in addition to the components shown in Figure 15.

[0118] The communication unit 1510 may include one or more components that enable wired / wireless communication with an external server or external device. For example, the communication unit 1510 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown). In one embodiment, the communication unit 1510 can use at least one communication protocol, such as Serial Peripheral Interface (SPI) and Universal Asynchronous Transceiver (UART). Also in one embodiment, the communication unit 1510 can communicate with sensors, external memory, and external control devices.

[0119] DB1530 is hardware that stores various types of data processed within the device 1500, and can store programs for processing and controlling the processor 1520.

[0120] The DB1530 includes RAM (random access memory) such as DRAM (dynamic random access memory) and SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), CD-ROM, Blu-ray or other optical disc storage, HDD (hard disk drive), SSD (solid state drive), or flash memory.

[0121] The processor 1520 controls the overall operation of the device 1500. For example, the processor 1520 can control the input unit (not shown), display (not shown), communication unit 1510, DB1530, etc., by executing a program stored in DB1530. The processor 1520 can control the operation of the device 1500 by executing a program stored in DB1530.

[0122] The processor 1520 can control at least part of the operation of the device for detecting abnormal biological signals or the model generation device described above in Figures 1 to 14.

[0123] The processor 1520 can be implemented using at least one of the following: ASICs (application-specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, microcontrollers, microprocessors, or other electrical units for performing functions.

[0124] In one embodiment, the device 1500 may be a server. The server can be implemented as a computer device or a group of computer devices that communicate over a network to provide instructions, code, files, content, services, etc. The server can receive data necessary to optimize the neural network model and optimize the neural network model based on the received data.

[0125] On the other hand, embodiments of the present invention can be realized in the form of a computer program that can be executed on a computer by various components, and such a computer program can be recorded on a computer-readable medium. Here, the medium includes magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical recording media such as floptical disks; and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, and flash memory.

[0126] On the other hand, the computer program may be specifically designed and configured for the present invention, or it may be publicly known and available to those skilled in the field of computer software. Examples of computer programs include not only machine code generated by a compiler, but also high-level language code executed by a computer using an interpreter or the like.

[0127] According to one embodiment, the methods according to various embodiments of the present disclosure can be provided in a computer program product. The computer program product can be traded as a commodity between a seller and a buyer. The computer program product can be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or through an application store (e.g., Play Store). TM The computer program product can be distributed online (e.g., by download or upload) via a network or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated on a storage medium readable by equipment such as the memory of a manufacturer's server, an application store server, or an intermediary server.

[0128] With respect to the steps constituting the method according to the present invention, unless otherwise stated, the steps may be performed in any order that suits them. The present invention is not necessarily limited to the order in which the steps are described above. All use of examples or exemplary terms in the present invention is solely for the purpose of illustrating the invention in detail, and the scope of the present invention is not limited by such examples or exemplary terms unless otherwise limited by the claims. Furthermore, those skilled in the art will understand that the present invention can be constructed within the scope of the claims or their equivalents with various modifications, combinations, and changes, depending on the design conditions and factors.

[0129] Therefore, the concept of the present invention should not be limited to the embodiments described above, and it can be said that not only the scope of the appended claims, but also all scopes equivalent to or equivalently modified from those claims, fall within the scope of the concept of the present invention.

Claims

1. A step of generating multiple sample data by randomly extracting frames having a first data length from raw data including biological signal data, The steps include: extracting frames having a second data length from the aforementioned sample data in chronological order to generate a plurality of unit data; A step of generating a training dataset based on the aforementioned plurality of unit data, The step includes generating an abnormal biological signal detection model by training an artificial intelligence model on the aforementioned training dataset, The aforementioned plurality of sample data and the plurality of unit data are generated for the normal biological signal data, abnormal biological signal data, and noise data contained in the raw data, respectively. A method for detecting abnormal biological signals, wherein the training dataset includes normal biological signal training data generated from normal biological signal data, abnormal biological signal training data generated from abnormal biological signal data, and noise signal training data generated from noise data.

2. The step of generating the aforementioned multiple unit data is: A method for detecting an abnormal biological signal according to claim 1, comprising the step of sequentially extracting frames having the second data length such that they overlap by a third data length between the plurality of unit data.

3. The step of generating the aforementioned multiple unit data is: A method for detecting an abnormal biological signal according to claim 1, comprising the step of converting the generated plurality of unit data into frequency components.

4. The step of generating the aforementioned training dataset is: A method for detecting an abnormal biological signal according to claim 3, comprising the step of synthesizing the converted plurality of unit data in the order in which they were extracted.

5. The aforementioned raw data is Includes in-phase raw data and phase-shifted raw data, The step of generating the aforementioned multiple sample data is: The steps include: randomly extracting frames having the first data length from the in-phase raw data to generate a plurality of in-phase sample data; A method for detecting an abnormal biological signal according to claim 4, comprising the step of generating a plurality of moving phase sample data by extracting frames having a first data length from the moving phase raw data so that they correspond to the signals of each of the plurality of in-phase sample data.

6. The step of generating the aforementioned training dataset is: A method for detecting an abnormal biological signal according to claim 5, comprising the step of cross-referencing and synthesizing a plurality of in-phase unit data corresponding to the plurality of in-phase sample data and a plurality of moving-phase unit data corresponding to the plurality of moving-phase sample data.

7. The step of generating the abnormal biological signal detection model is: The steps include adjusting the parameters of the artificial intelligence model using the aforementioned training dataset, A method for detecting an abnormal biological signal according to claim 1, comprising the step of generating the abnormal biological signal detection model based on the adjusted number of times (epochs) and the accuracy of the artificial intelligence model.

8. The aforementioned abnormal biological signal detection model is This is realized with neuromorphic devices. The neuromorphic device is At least one processor that drives the abnormal biological signal detection model, It includes a crossbar array circuit that receives instructions from the at least one processor and performs in-memory operations, The aforementioned at least one processor is The input data collected by the sensor is input to the abnormal biological signal detection model. A method for detecting an abnormal biological signal according to claim 1, wherein an abnormal biological signal is detected based on the output of the abnormal biological signal detection model.

9. Memory containing at least one program, A processor that performs calculations by executing the aforementioned at least one program, The aforementioned processor, Multiple sample data sets are generated by randomly extracting frames with a first data length from raw data containing biological signal data. Frames having a second data length are extracted from the aforementioned sample data in chronological order to generate multiple unit data. A training dataset is generated based on the aforementioned multiple unit data, An abnormal biological signal detection model is generated by training an artificial intelligence model on the aforementioned training dataset. The aforementioned plurality of sample data and the plurality of unit data are generated for the normal biological signal data, abnormal biological signal data, and noise data contained in the raw data, respectively. The device for detecting abnormal biological signals includes, as the training dataset, normal biological signal training data generated from normal biological signal data, abnormal biological signal training data generated from abnormal biological signal data, and noise signal training data generated from noise data.

10. A computer-readable recording medium that stores a program for executing the method according to claim 1 on a computer.

Images