Electroencephalogram characteristic waveform detection method and device and storage medium

Abstract

The invention relates to an electroencephalogram characteristic waveform detection method and device and a storage medium. The electroencephalogram characteristic waveform detection method comprises the following steps: acquiring electroencephalogram signal data with a preset length; based on the sampling windows of the first preset duration, the second preset duration and the third preset duration, first sampling data, second sampling data and third sampling data are obtained from the electroencephalogram signal data; respectively obtaining a first characteristic waveform, a second characteristic waveform and a third characteristic waveform based on the first sampling data, the second sampling data and the third sampling data; and based on a preset rule, analyzing the first feature waveform, the second feature waveform and the third feature waveform to obtain a target feature waveform.

Description

Method, device and storage medium for detecting electroencephalogram characteristic waveform Technical Field

[0001] The present disclosure relates to, but is not limited to, a method, device, and storage medium for detecting characteristic EEG waveforms. Background Art

[0002] Electroencephalography (EEG) is an electrophysiological monitoring method that records brain waves. Electrodes are placed on the scalp to record the voltage fluctuations generated by the ionic currents of brain neurons. EEG measures the synchronized sum of postsynaptic potentials when numerous pyramidal cells are excited. EEG is primarily used to assist in the diagnosis of brain-related diseases. It is most commonly used to diagnose epilepsy, for which it is one of the gold standards. It can also be used to diagnose sleep disorders, determine the depth of anesthesia, determine the degree of coma, assess cerebrovascular disease, and determine brain death.

[0003] Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a method, device and storage medium for detecting EEG characteristic waveforms.

[0005] According to a first aspect of the present disclosure, a method for detecting an EEG characteristic waveform is provided, the method comprising:

[0006] Obtaining EEG signal data of a preset length;

[0007] Based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, respectively, obtaining first sampling data, second sampling data, and third sampling data from the EEG signal data;

[0008] obtaining a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data, respectively;

[0009] Based on preset rules, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are analyzed to obtain a target characteristic waveform.

[0010] In an exemplary embodiment, the acquiring of first sampling data, second sampling data, and third sampling data from the EEG signal data based on the sampling windows of the first preset time length, the second preset time length, and the third preset time length, respectively, includes:

[0011] Sliding the sampling window of the first preset time length based on a first preset step length, and taking all sampled data within the sampling window of the first preset time length on the EEG signal data as the first sampled data;

[0012] Sliding the sampling window of the second preset time length based on the second preset step length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as the second sampled data;

[0013] Based on a third preset step length, the sampling window of the third preset time length is slid, and all the sampling data within the sampling window of the third preset time length on the EEG signal data is used as the third sampling data.

[0014] In an exemplary embodiment, the first preset duration is less than the second preset duration and less than the third preset duration;

[0015] The preset rules include:

[0016] If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform;

[0017] If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

[0018] In an exemplary embodiment, the EEG characteristic waveform includes: an epileptic waveform, a sleep waveform, a severe waveform, an artifact waveform, a consciousness state waveform and a seizure waveform, wherein the seizure waveform is used to characterize the EEG waveform during an epileptic seizure, and the artifact waveform is used to characterize non-brain-derived interference signals.

[0019] According to a second aspect of the present disclosure, a device for detecting an EEG characteristic waveform is provided, the device comprising:

[0020] A first acquisition module is configured to acquire EEG signal data of a preset length;

[0021] a second acquisition module configured to acquire first sampling data, second sampling data, and third sampling data from the EEG signal data based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, respectively;

[0022] a third acquisition module, configured to respectively obtain a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data;

[0023] The analysis module is configured to analyze the first characteristic waveform, the second characteristic waveform and the third characteristic waveform based on preset rules to obtain a target characteristic waveform.

[0024] In an exemplary embodiment, the second acquisition module is further configured to include:

[0025] Sliding the sampling window of the first preset time length based on a first preset step length, and taking all sampled data within the sampling window of the first preset time length on the EEG signal data as the first sampled data;

[0026] Sliding the sampling window of the second preset time length based on the second preset step length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as the second sampled data;

[0027] Based on a third preset step length, the sampling window of the third preset time length is slid, and all the sampling data within the sampling window of the third preset time length on the EEG signal data is used as the third sampling data.

[0028] In an exemplary embodiment, the first preset duration is less than the second preset duration and less than the third preset duration;

[0029] The preset rules include:

[0030] If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform;

[0031] If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

[0032] In an exemplary embodiment, the EEG characteristic waveform includes: an epileptic waveform, a sleep waveform, a severe waveform, an artifact waveform, a consciousness state waveform and a seizure waveform, wherein the seizure waveform is used to characterize the EEG waveform during an epileptic seizure, and the artifact waveform is used to characterize non-brain-derived interference signals.

[0033] According to a third aspect of the present disclosure, there is provided a device for detecting an EEG characteristic waveform, comprising:

[0034] processor;

[0035] a memory for storing processor-executable instructions;

[0036] The processor is configured to execute the method as described in the first aspect of the embodiment of the present disclosure.

[0037] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of a device, the device is enabled to perform the method as described in the first aspect of the embodiment of the present disclosure.

[0038] The method disclosed in the present invention has the following beneficial effects: the method realizes automatic recognition of the basic characteristic waves of EEG signals through a neural network model, which can be applied to various detection tasks, and by analyzing the characteristic waves in sampling data of different time lengths, the accuracy of characteristic wave detection can be improved.

[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which constitute part of this disclosure, are used to provide a further understanding of the disclosure. The exemplary embodiments of the disclosure and their descriptions are used to explain the disclosure and do not constitute an improper limitation of the disclosure. In the accompanying drawings:

[0041] Fig. 1 is a flow chart of a method for detecting a characteristic EEG waveform according to an exemplary embodiment.

[0042] Fig. 2 is a schematic diagram showing EEG signal data according to an exemplary embodiment.

[0043] Fig. 3 is a block diagram of a device for detecting an EEG characteristic waveform according to an exemplary embodiment.

[0044] FIG4 is a block diagram showing a device for executing a method for detecting a characteristic EEG waveform according to an exemplary embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure. It should be noted that, in the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other.

[0046] In related technologies, there are two main ways to interpret and analyze EEG signals: the first is to rely on doctors to complete it through visual inspection. However, in order to be able to record enough waveforms for various diagnoses, it is usually necessary to continuously record the patient's EEG data for multiple days. The huge amount of EEG data increases the doctor's labor intensity and reduces the detection efficiency. In addition, due to the different interpretations of standards by individual doctors, manual interpretation of EEGs causes a large subjective factor, which affects consistency and leads to reduced consistency in reports. In addition, the popularity of EEG reading technology is poor and the training time is long, which makes it impossible for pediatricians and critical care doctors to correctly interpret the condition in a timely manner. The second method is to use computer technology to automatically identify and analyze the characteristic waves in the EEG signal. Although the automatic analysis technology of EEG signals and the automatic detection technology of related characteristic waveforms can improve detection efficiency and report consistency, reduce the missed detection rate of characteristic waveforms, and have great clinical application value, the detection of characteristic waves in related technologies can usually only be applied to a single task, such as only IED detection or only artifact detection, etc., and cannot complete the detection tasks of multiple characteristic waves at one time. Moreover, the accuracy of different characteristic wave detection schemes varies, and different detection tasks cannot be applied uniformly.

[0047] In an exemplary embodiment of the present disclosure, in order to overcome the problems in the related art, a method for detecting EEG characteristic waveforms is provided. EEG signal data of a preset length is obtained, and based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, first sampling data, second sampling data, and third sampling data are respectively obtained in the EEG signal data. Based on the first sampling data, the second sampling data, and the third sampling data, a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform are respectively obtained. Based on preset rules, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are analyzed to obtain a target characteristic waveform. In the present disclosure, the automatic recognition of the basic characteristic waves of EEG signals is realized through a neural network model, so as to be applied to a variety of detection tasks, and by analyzing the characteristic waves in sampling data of different time lengths, the accuracy of characteristic wave detection can be improved.

[0048] In an exemplary embodiment of the present disclosure, a method for detecting a characteristic EEG waveform is provided. FIG1 is a flow chart of a method for detecting a characteristic EEG waveform according to an exemplary embodiment, as shown in FIG1 , comprising the following steps:

[0049] Step S101, obtaining EEG signal data of a preset length;

[0050] Step S102, based on the sampling windows of the first preset time length, the second preset time length, and the third preset time length, respectively, obtaining first sampling data, second sampling data, and third sampling data from the EEG signal data;

[0051] Step S103, obtaining a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data, respectively;

[0052] Step S104 : analyzing the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform based on preset rules to obtain a target characteristic waveform.

[0053] In step S101, the EEG signal data is a three-dimensional EEG signal view, as shown in FIG2, which is composed of a single sampling slice in a time series. When acquiring the EEG signal, the data of each channel is filtered and arranged according to the single sampling slice in FIG2, where ECG is the electrocardiogram channel, EMG is the electromyography channel, SPO2 is the blood oxygenation channel, and the rest are EEG signals that meet the 10-20 standard. The length of the EEG signal data is a preset length, which is determined by the duration of the EEG signal data and the sampling rate of the EEG signal. The length of the EEG signal data = the duration of the EEG signal data × the sampling rate. For example, if the EEG signal data is 10 seconds and the sampling rate is 512, its length is 5120. Among them, the duration of the EEG signal data can be determined according to actual needs, which is usually related to the doctor's usage habits and the size of the display, for example, greater than 10 seconds and less than 20 seconds. It can also be adjusted according to the viewing requirements.

[0054] In step S102, the first preset duration, the second preset duration, and the third preset duration can be determined according to actual needs, and are different preset durations. For example, the first preset duration is 1 second, the second preset duration is 2 seconds, and the third preset duration is 8 seconds. Based on sampling windows of different durations, different sampled data are obtained from the EEG signal data. Since the durations of the sampling windows are different, the amount of sampled data obtained is also different. Therefore, the amount of data contained in the first sampled data, the second sampled data, and the third sampled data is different.

[0055] In step S103, the first sampling data, the second sampling data, and the third sampling data obtained are respectively input into three different trained 3D neural network models. Through the neural network models, a first characteristic waveform is identified in the first sampling data, a second characteristic waveform is identified in the second sampling data, and a third characteristic waveform is identified in the third sampling data. The three different 3D neural network models all use the same network architecture, but have different input lengths. The input length of the 3D neural network model used for the first sampling data is the product of the first preset time length and the sampling rate, the input length of the 3D neural network model used for the second sampling data is the product of the second preset time length and the sampling rate, and the input length of the 3D neural network model used for the third sampling data is the product of the third preset time length and the sampling rate.

[0056] When training the 3D neural network model, the training sample data used are EEG signals of different durations and the characteristic waveforms contained in the EEG signals, including: epileptiform waveforms, sleep waveforms, severe waveforms, artifact waveforms, consciousness state waveforms, and seizure waveforms. Among them, the seizure waveform is used to characterize the EEG waveform during an epileptic seizure. Therefore, when using the trained 3D neural network model to perform characteristic waveform detection on the EEG signal data, the first characteristic waveform, second characteristic waveform, and third characteristic waveform obtained also include: epileptiform waveforms, sleep waveforms, severe waveforms, artifact waveforms, consciousness state waveforms, and seizure waveforms. Among them, epileptiform waveforms include interictal epileptic discharges (IED) and the ictal-interictal continuum (IIC), seizure waveforms include electroencephalographic seizures (ESz), severe waveforms include periodic discharges (PD) and rhythmic delta activity (RDA), sleep waveforms include slow-wave sleep (slow-wave sleep), that is, the θ and δ waveforms that appear during sleep stages, consciousness state waveforms include the K-complex, the characteristic wave of sleep stage II, and the 8-13Hz α rhythm of electroencephalographic activity that appears repetitively rhythmically in the wakeful state, and artifact waveforms represent various non-brain-derived signals, that is, waveforms caused by external factors.

[0057] In step S104, for EEG signal data of the same length, the characteristic waves identified based on different durations should be characteristic waves of the same type. For example, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all epileptic waveforms. Therefore, when a sleep waveform exists among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, it indicates that there is an erroneous waveform. Therefore, based on the preset rules, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are analyzed to eliminate logical inconsistencies, so that the target characteristic waveform can be obtained more accurately. The preset rules can be any analysis rules that can avoid conflicts among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform.

[0058] In an exemplary embodiment of the present disclosure, EEG signal data of a preset length is obtained, and sampling windows of a first preset time length, a second preset time length, and a third preset time length are respectively obtained in the EEG signal data. Based on the first sampling data, the second sampling data, and the third sampling data, a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform are respectively obtained. Based on preset rules, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are analyzed to obtain a target characteristic waveform. This can realize automatic recognition of basic characteristic waves of EEG signals for application in various detection tasks, and by analyzing characteristic waves in sampling data of different time lengths, the accuracy of characteristic wave detection can be improved.

[0059] In an exemplary embodiment, in step S102, first sampling data, second sampling data, and third sampling data are respectively obtained from the EEG signal data based on sampling windows of the first preset time length, the second preset time length, and the third preset time length, including:

[0060] Based on a first preset step length, sliding a sampling window of a first preset duration, and taking all sampled data within the sampling window of the first preset duration on the EEG signal data as first sampled data;

[0061] Based on a second preset step length, sliding a sampling window of a second preset time length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as second sampled data;

[0062] Based on the third preset step length, a sampling window of a third preset duration is slid, and all sampling data within the sampling window of the third preset duration on the EEG signal data is used as third sampling data.

[0063] The first preset step length, the second preset step length and the third preset step length are determined according to actual needs and can be the same or different. In order to ensure the accuracy of recognition, the preset step length should be determined so that the acquired sampling data covers as much EEG signal data of the preset length as possible, so that more feature data can be extracted when performing feature wave recognition.

[0064] For example, if the preset length of the EEG signal data is 10 seconds of EEG signal data, the sampling window of the first preset time length is a sampling window of 1 second, and the first preset step length is 2 seconds, then the first sampling data is the EEG signal data of the 1st second, the EEG signal data of the 4th second, the EEG signal data of the 7th second, and the EEG signal data of the 10th second.

[0065] In an exemplary embodiment, when the first preset duration is less than the second preset duration and less than the third preset duration, the preset rule includes:

[0066] If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform;

[0067] If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

[0068] Since the first preset time length is less than the second preset time length and less than the third preset time length, the first sampling data only includes a small part of the EEG signal waveform, the data volume is small, and the first characteristic waveform identified by the first sampling data is a waveform in a short time; the third sampling data includes most of the EEG signal waveform, the data volume is large, and the third characteristic waveform identified by the third sampling data is a waveform in a longer time; the second characteristic waveform identified by the second sampling data is between the first characteristic waveform and the second characteristic waveform.

[0069] Taking the first preset time length as 1 second, the second preset time length as 2 seconds, and the third preset time length as 8 seconds as an example: If the characteristic waveform detected within 1 second is an epileptic waveform, and the characteristic waveform detected within 8 seconds is also an epileptic waveform, then it can be mutually confirmed that the identified characteristic waveform is accurate, that is, it indicates that the characteristic waveform in the EEG signal data is an epileptic waveform. Therefore, if the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, then the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform can be used as the target characteristic waveform. If the characteristic waveform detected within 1 second is an epileptic waveform, but the characteristic waveforms detected within 2 seconds and within 8 seconds are both sleep waveforms, since epileptic waveforms and sleep waveforms are mutually exclusive, and the sleep waveform is identified from the longer time period, it indicates that the time period is in a sleep state. It can be considered that the sampling data within 1 second has an error, and the detected waveform is likely a pseudo-error waveform, that is, it indicates that the characteristic waveform in the EEG signal data is a sleep waveform. Therefore, if the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are characteristic waveforms of different types, then the third characteristic waveform can be used as the target characteristic waveform.

[0070] It should be noted that the preset rules can be adjusted according to the mutually exclusive relationship between various basic characteristic waves.

[0071] In an exemplary embodiment of the present disclosure, a device for detecting a characteristic EEG waveform is provided. FIG3 is a block diagram of a device for detecting a characteristic EEG waveform according to an exemplary embodiment. As shown in FIG3 , the device for detecting a characteristic EEG waveform includes:

[0072] A first acquisition module 301 is configured to acquire EEG signal data of a preset length;

[0073] A second acquisition module 302 is configured to acquire first sampling data, second sampling data, and third sampling data from the EEG signal data based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, respectively;

[0074] A third acquisition module 303 is configured to obtain a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data, respectively;

[0075] The analysis module 304 is configured to analyze the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform based on preset rules to obtain a target characteristic waveform.

[0076] In an exemplary embodiment, the second acquisition module 302 is further configured to include:

[0077] Sliding the sampling window of the first preset time length based on a first preset step length, and taking all sampled data within the sampling window of the first preset time length on the EEG signal data as the first sampled data;

[0078] Sliding the sampling window of the second preset time length based on the second preset step length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as the second sampled data;

[0079] Based on a third preset step length, the sampling window of the third preset time length is slid, and all the sampling data within the sampling window of the third preset time length on the EEG signal data is used as the third sampling data.

[0080] In an exemplary embodiment, the first preset duration is less than the second preset duration and less than the third preset duration;

[0081] The preset rules include:

[0082] If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform;

[0083] If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

[0084] In an exemplary embodiment, the EEG characteristic waveform includes: an epileptic waveform, a sleep waveform, a severe waveform, an artifact waveform, a consciousness state waveform and a seizure waveform, wherein the seizure waveform is used to characterize the EEG waveform during an epileptic seizure, and the artifact waveform is used to characterize non-brain-derived interference signals.

[0085] FIG4 is a block diagram showing a device 400 for executing a method for detecting a characteristic EEG waveform according to an exemplary embodiment.

[0086] 4 , apparatus 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input / output (I / O) interface 412 , a sensor component 414 , and a communication component 416 .

[0087] Processing component 402 generally controls the overall operation of device 400, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. Processing component 402 may include one or more processors 420 to execute instructions to perform all or part of the steps of the above-described method. In addition, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.

[0088] The memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc. The memory 404 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0089] The power supply component 406 provides power to the various components of the device 400. The power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 400.

[0090] The multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and / or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0091] The audio component 410 is configured to output and / or input audio signals. For example, the audio component 410 includes a microphone (MIC) that is configured to receive external audio signals when the device 400 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 404 or transmitted via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting audio signals.

[0092] I / O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0093] The sensor assembly 414 includes one or more sensors for providing various aspects of the status assessment of the device 400. For example, the sensor assembly 414 can detect the open / closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400. The sensor assembly 414 can also detect changes in the position of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration / deceleration of the device 400, and temperature changes of the device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0094] The communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices. The device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0095] In an exemplary embodiment, the apparatus 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0096] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by the processor 420 of the apparatus 400 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0097] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the device, enables the device to perform a method for detecting a characteristic EEG waveform, the method including any of the above-mentioned methods for detecting a characteristic EEG waveform.

[0098] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, devices (equipment), or computer program products. Therefore, the present disclosure may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data), including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVDs) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0099] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (devices) and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0100] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0102] In this disclosure, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that an article or device comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such article or device. In the absence of further limitations, an element defined by the phrase "comprising..." does not preclude the presence of additional identical elements in the article or device comprising the element.

[0103] Although the preferred embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present disclosure.

[0104] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include such modifications and variations. Industrial Applicability

[0105] In the present disclosure, a neural network model is used to realize automatic recognition of the basic characteristic waves of EEG signals, which can be applied to various detection tasks. By analyzing the characteristic waves in sampling data of different time lengths, the accuracy of characteristic wave detection can be improved.

Claims

1. A method for detecting a characteristic EEG waveform, characterized in that: The method for detecting the characteristic EEG waveform includes: Obtaining EEG signal data of a preset length; Based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, respectively, obtaining first sampling data, second sampling data, and third sampling data from the EEG signal data; obtaining a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data, respectively; Based on preset rules, the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are analyzed to obtain a target characteristic waveform.

2. The method for detecting characteristic EEG waveform according to claim 1, wherein: The sampling windows based on the first preset time length, the second preset time length, and the third preset time length, respectively obtaining first sampling data, second sampling data, and third sampling data from the EEG signal data, include: Sliding the sampling window of the first preset time length based on a first preset step length, and taking all sampled data within the sampling window of the first preset time length on the EEG signal data as the first sampled data; Sliding the sampling window of the second preset time length based on the second preset step length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as the second sampled data; Based on a third preset step length, the sampling window of the third preset time length is slid, and all the sampling data within the sampling window of the third preset time length on the EEG signal data is used as the third sampling data.

3. The method for detecting characteristic EEG waveform according to claim 1, wherein: The first preset duration is less than the second preset duration and less than the third preset duration; The preset rules include: If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform; If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

4. The method for detecting characteristic EEG waveform according to claim 1, wherein: The EEG characteristic waveforms include: epileptiform waveforms, sleep waveforms, severe waveforms, artifact waveforms, consciousness state waveforms and seizure waveforms, wherein the seizure waveform is used to characterize the EEG waveform during an epileptic seizure, and the artifact waveform is used to characterize non-brain-derived clutter signals.

5. A device for detecting characteristic EEG waveforms, characterized in that: The device for detecting the characteristic EEG waveform comprises: A first acquisition module is configured to acquire EEG signal data of a preset length; a second acquisition module configured to acquire first sampling data, second sampling data, and third sampling data from the EEG signal data based on sampling windows of a first preset time length, a second preset time length, and a third preset time length, respectively; a third acquisition module, configured to respectively obtain a first characteristic waveform, a second characteristic waveform, and a third characteristic waveform based on the first sampling data, the second sampling data, and the third sampling data; The analysis module is configured to analyze the first characteristic waveform, the second characteristic waveform and the third characteristic waveform based on preset rules to obtain a target characteristic waveform.

6. The device for detecting characteristic EEG waveforms according to claim 5, characterized in that: The second acquisition module is further configured to include: Sliding the sampling window of the first preset time length based on a first preset step length, and taking all sampled data within the sampling window of the first preset time length on the EEG signal data as the first sampled data; Sliding the sampling window of the second preset time length based on the second preset step length, and taking all sampled data within the sampling window of the second preset time length on the EEG signal data as the second sampled data; Based on a third preset step length, the sampling window of the third preset time length is slid, and all the sampling data within the sampling window of the third preset time length on the EEG signal data is used as the third sampling data.

7. The device for detecting characteristic EEG waveforms according to claim 5, characterized in that: The first preset duration is less than the second preset duration and less than the third preset duration; The preset rules include: If the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform are all characteristic waveforms of the same type, the first characteristic waveform, the second characteristic waveform, or the third characteristic waveform is used as the target characteristic waveform; If different types of characteristic waveforms exist among the first characteristic waveform, the second characteristic waveform, and the third characteristic waveform, the third characteristic waveform is used as the target characteristic waveform.

8. The device for detecting characteristic EEG waveforms according to claim 1, characterized in that: The EEG characteristic waveforms include: epileptiform waveforms, sleep waveforms, severe waveforms, artifact waveforms, consciousness state waveforms and seizure waveforms, wherein the seizure waveform is used to characterize the EEG waveform during an epileptic seizure, and the artifact waveform is used to characterize non-brain-derived clutter signals.

9. A device for detecting characteristic EEG waveforms, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of a device, The device is enabled to perform the method according to any one of claims 1 to 14.

Images