CN113017649A - Electroencephalogram activity identification method and device, electronic equipment and medium - Google Patents
Electroencephalogram activity identification method and device, electronic equipment and medium Download PDFInfo
- Publication number
- CN113017649A CN113017649A CN202110211205.4A CN202110211205A CN113017649A CN 113017649 A CN113017649 A CN 113017649A CN 202110211205 A CN202110211205 A CN 202110211205A CN 113017649 A CN113017649 A CN 113017649A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- frequency
- frequency activity
- activity
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Abstract
The application discloses an electroencephalogram activity identification method, an electroencephalogram activity identification device, electronic equipment and a medium. In the application, electroencephalograms can be acquired and preprocessed; detecting a high frequency activity event in the pre-processed electroencephalogram; if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events; and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity. By applying the technical scheme of the application, whether the high-frequency activity events exist in the intracranial electroencephalogram of the user can be automatically detected, and the state type of the user is judged by determining the brain area which generates the high-frequency activity at the earliest time through extracting the time sequence process of each high-frequency activity event. Thereby avoiding the defects of time and labor consumption in the interpretation process of the intracranial electroencephalogram and the limitation of the types and the number of post-processing technologies in the related technologies.
Description
Technical Field
The present application relates to data processing technologies, and in particular, to a method and an apparatus for recognizing brain electrical activity, an electronic device, and a medium.
Background
Electroencephalography is an important, irreplaceable method of studying brain science and brain diseases, including scalp electroencephalography and intracranial electroencephalography. Generally, in order to capture effective information, it is necessary to acquire a brain electrical signal recorded for a long time and then perform recognition of brain electrical activity by means of manual visual analysis of a doctor. However, the electroencephalogram determination process with high lead number, high sampling rate and long time is complex and burdensome, not only is time-consuming, but also is limited by the experience level, knowledge accumulation and physical state of the doctor, and the accuracy rate is difficult to guarantee.
Disclosure of Invention
The embodiment of the application provides an electroencephalogram activity identification method, an electroencephalogram activity identification device, an electronic device and a medium, wherein according to one aspect of the embodiment of the application, the provided electroencephalogram activity identification method is characterized by comprising the following steps:
acquiring an electroencephalogram and preprocessing the electroencephalogram;
detecting a high frequency activity event in the pre-processed electroencephalogram;
if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events;
and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
Further, the acquiring and preprocessing electroencephalograms comprises:
re-referencing the electroencephalogram;
eliminating power frequency noise interference of the re-referenced electroencephalogram by adopting a first Hertz notch filter to obtain a first processed electroencephalogram;
and eliminating the baseline wandering interference of the first processed electroencephalogram by adopting a second Hertz high-pass filter to obtain a second processed electroencephalogram.
Further, the detecting high frequency activity events in the pre-processed electroencephalogram comprises:
segmenting the second processed electroencephalogram into a first number of segmented electroencephalograms;
performing band-pass filtering on each electroencephalogram of the segments to obtain a band-pass signal corresponding to each electroencephalogram of the segments;
slicing the band pass signal of each of the electroencephalograms into a second number of sub-bands and frequency normalizing the signal of each sub-band;
extracting band-pass envelopes from the frequency-normalized sub-bands to obtain a band-pass envelope value corresponding to each sub-band;
and determining a high-frequency activity event according to the band-pass envelope value.
Further, the determining a high frequency activity event from the band pass envelope values comprises:
if detecting a sub-band of which the duration time of the band-pass envelope value is greater than the preset envelope threshold value is not less than the discharge time threshold value, determining the sub-band as a high-frequency activity event;
and if the interval time of two adjacent high-frequency activity events is less than the first time period, combining the two high-frequency activity events into one high-frequency activity event.
Further, the obtaining a prescreening signal of high-frequency activity according to the high-frequency activity event includes:
counting the number of high frequency activity events in each lead;
selecting the leads with the number meeting a first preset standard of the high-frequency activity events as high-frequency activity leads;
the electroencephalogram signal of each high-frequency active lead is divided into a second number of segment electroencephalogram signals respectively;
calculating the number of high-frequency activity events in each segment of electroencephalogram signal; and combining the number of the segment electroencephalogram signals meeting a second preset standard to obtain the preliminary screening signal of the high-frequency activity.
Further, the calculating the time sequence relationship of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity includes:
acquiring a time-frequency diagram of the primary screening signal, and calculating the frequency spectrum centroid of each segment of electroencephalogram signal;
determining the time position of each frequency spectrum centroid in the corresponding time-frequency diagram as the generation time of the high-frequency activity event of each lead in the corresponding segment electroencephalogram signal;
and sequencing the generation time of the high-frequency activity events to obtain the time sequence relation of the high-frequency activity events.
Further, after the time sequence relationship of each high-frequency activity event is calculated according to the preliminary screening signal of the high-frequency activity, the method further includes:
and clustering and displaying the high-frequency activity events of each segment of electroencephalogram signal.
According to another aspect of the embodiments of the present application, there is provided an electroencephalogram activity recognition apparatus, including:
an acquisition module configured to acquire an electroencephalogram and perform preprocessing;
a detection module configured to detect high frequency activity events in the pre-processed electroencephalogram;
the generating module is configured to obtain a preliminary screening signal of the high-frequency activity according to the high-frequency activity events if the number of the high-frequency activity events is not less than two;
and the calculation module is configured to calculate the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
According to another aspect of the embodiments of the present application, there is provided an electronic device including:
a memory for storing executable instructions; and
and the display is used for displaying with the memory to execute the executable instructions so as to complete the operation of any one of the electroencephalogram activity identification methods.
According to a further aspect of the embodiments of the present application, there is provided a computer-readable storage medium for storing computer-readable instructions, which when executed, perform the operations of any one of the brain electrical activity recognition methods described above.
By applying the technical scheme of the application, whether the high-frequency activity events exist in the intracranial electroencephalogram signals of the user can be automatically detected, and the time sequence process of each high-frequency activity event can be extracted to determine the brain area which generates the high-frequency activity at the earliest time, so that the electroencephalogram interpretation efficiency and accuracy are greatly improved.
The technical solution of the present application is further described in detail by the accompanying drawings and examples.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description, serve to explain the principles of the application.
The present application may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:
fig. 1 is a schematic diagram of an electroencephalogram activity recognition method proposed in the present application;
FIG. 2 is a schematic diagram of a prescreening signal for high frequency activity according to one embodiment of the present application;
FIG. 3 is a schematic diagram of the location of the spectral centroid in the prescreened signal according to one embodiment of the present application;
FIG. 4 is a schematic diagram of a clustered display of high frequency activity events, according to one embodiment of the present application;
fig. 5 is a schematic structural diagram of an electrical brain activity recognition device according to the present application;
fig. 6 is a schematic structural diagram of an electroencephalogram activity identification electronic device according to the present application.
Detailed Description
Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present application unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In addition, technical solutions between the various embodiments of the present application may be combined with each other, but it must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination of technical solutions should be considered to be absent and not within the protection scope of the present application.
It should be noted that all the directional indicators (such as upper, lower, left, right, front and rear … …) in the embodiment of the present application are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is changed accordingly.
The following describes a method for performing brain electrical activity recognition according to an exemplary embodiment of the present application with reference to fig. 1-2. It should be noted that the following application scenarios are merely illustrated for the convenience of understanding the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
The application also provides an electroencephalogram activity identification method, an electroencephalogram activity identification device, a target terminal and a medium.
Fig. 1 schematically shows a flow chart of an electroencephalogram activity recognition method according to an embodiment of the present application. As shown in fig. 1, the method includes:
and S101, acquiring an electroencephalogram and preprocessing the electroencephalogram.
First, electroencephalography in the related art is an important and irreplaceable method for studying brain science and brain diseases. For example, in the related art, it is possible to determine whether a user affects the working or living state of the user due to the presence of a problem such as epilepsy from the electroencephalogram.
The electroencephalogram may include a scalp electroencephalogram and an intracranial electroencephalogram, here optionally an intracranial electroencephalogram. It will be appreciated that intracranial electroencephalography can accurately locate the site of origin of a seizure and to some extent the course and extent of the spread of the seizure. Therefore, one or more electroencephalograms of the user to be detected can be selected to be obtained to serve as the basis for the electroencephalogram activity identification and judgment.
The method comprises the steps of acquiring intracranial electroencephalogram (including ECoG and SEEG) signals of a user by adopting an electroencephalogram amplifier according to clinical standards, wherein the sampling rate range can be more than 2000Hz, and the lead number range can be 40-200. The monitoring time can be one day or more than one week. This is not limited in this application.
Further, the preprocessing performed on the electroencephalogram includes:
re-referencing the electroencephalogram;
eliminating power frequency noise interference of the re-referenced electroencephalogram by adopting a first Hertz notch filter to obtain a first processed electroencephalogram;
and eliminating the baseline wandering interference of the first processed electroencephalogram by adopting a second Hertz high-pass filter to obtain a second processed electroencephalogram.
S102, detecting high-frequency activity events in the preprocessed electroencephalogram.
The method specifically comprises the following steps:
segmenting the second processed electroencephalogram into a first number of segmented electroencephalograms;
performing band-pass filtering on each electroencephalogram of the segments to obtain a band-pass signal corresponding to each electroencephalogram of the segments;
slicing the band pass signal of each of the electroencephalograms into a second number of sub-bands and frequency normalizing the signal of each sub-band;
extracting band-pass envelope processing is carried out on the frequency-normalized sub-bands, and a band-pass envelope value corresponding to each sub-band is obtained;
and determining a high-frequency activity event according to the band-pass envelope value.
Optionally, if a sub-band is detected, where the duration of the band pass envelope value greater than the preset envelope threshold is not less than the discharge time threshold, determining that the sub-band is a high-frequency activity event; otherwise, no high-frequency activity event exists;
and if the interval time of two adjacent high-frequency activity events is less than the first time period, combining the two high-frequency activity events into one high-frequency activity event.
Thus, the present application can detect whether or not the electroencephalogram includes electroencephalograms (i.e., high-frequency activity events) reflected as high-frequency activity and the number thereof.
S103, if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events.
The method specifically comprises the following steps:
counting the number of high frequency activity events in each lead;
selecting the leads with the number meeting a first preset standard of the high-frequency activity events as high-frequency activity leads;
the electroencephalogram signal of each high-frequency active lead is divided into a second number of segment electroencephalogram signals respectively;
calculating the number of high-frequency activity events in each segment of electroencephalogram signal; and combining the number of the segment electroencephalogram signals meeting a second preset standard to obtain the preliminary screening signal of the high-frequency activity.
And S104, calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
The method specifically comprises the following steps:
acquiring a time-frequency diagram of the primary screening signal, and calculating the frequency spectrum centroid of each segment of electroencephalogram signal;
determining the time position of each frequency spectrum centroid in the corresponding time-frequency diagram as the generation time of the high-frequency activity event of each lead in the corresponding segment electroencephalogram signal;
and sequencing the generation time of the high-frequency activity events to obtain the time sequence relation of the high-frequency activity events.
Optionally, when it is detected that there are multiple discharges (i.e., high-frequency activity events) at multiple positions in the electroencephalogram, the application may further obtain time points of the respective discharge positions and sequence the discharge positions to obtain a discharge position with the earliest occurrence time, so as to determine the brain area state of the user to be detected.
Further, after the time sequence relation of each high-frequency activity event is obtained through calculation, the high-frequency activity events of each segment of electroencephalogram signal are clustered and displayed.
According to the electroencephalogram interpretation method and device, whether high-frequency activity events exist in intracranial electroencephalograms of a user can be automatically detected, the time sequence process of each high-frequency activity event can be extracted, the brain area which generates high-frequency activity at the earliest time is determined, and therefore the electroencephalogram interpretation efficiency and accuracy are greatly improved.
An electroencephalogram activity identification method according to an embodiment of the present application is described below with reference to fig. 2-4, taking an intracranial electroencephalogram as an example.
First, an intracranial electroencephalogram is collected and pre-processed.
The preprocessing specifically comprises re-reference, power frequency removal and drift removal processing. The heavy reference comprises a single electrode heavy reference (monopolarreference), a bipolar reference (bipolar reference), a laplacian heavy reference (laplacian reference), a global heavy reference (common average reference), and other heavy reference methods. The power frequency removal processing may employ a notch filter of 50Hz and/or a multiple of 50Hz (i.e., a first Hz) to remove power frequency noise interference, so as to obtain a first processed electroencephalogram after the power frequency noise removal. The de-drift process may use a high pass filter no greater than 1.6Hz (usually 0.1Hz, 0.5Hz, 0.53Hz, 1Hz, 1.6Hz, etc., i.e., the second Hz) to solve the baseline drift phenomenon in the de-power frequency intracranial electroencephalogram signals, and obtain the second processed electroencephalogram.
Then, determining whether a high frequency activity event is present in the second processed electroencephalogram, including:
the second processed electroencephalogram is segmented into a plurality of segmented electroencephalograms, each segmented electroencephalogram corresponding to an electroencephalogram of a short-time segment. The length of the time segment may be determined based on the memory limitations of the computer performing the processing, e.g. 200 seconds, whereby the memory requirements of the computer may be reduced.
And performing band-pass filtering on each section electroencephalogram by using a third-order FIR (finite impulse response) filter to obtain a band-pass signal corresponding to each section electroencephalogram. The lower frequency limit of the band-pass filter is usually 60-80Hz, and the upper frequency limit is 250-500 Hz.
The band pass signal of each segmented electroencephalogram is sliced into a second number of sub-bands, each sub-band ranging, for example, from 20Hz, and the signal of each sub-band is frequency normalized to obtain a normalized frequency signal for each segmented electroencephalogram. The normalization formula is as follows:
wherein, represents xBandCorresponding to the sub-band signal, xminCorresponding to the minimum value, x, of the subband signalmaxCorresponding to the maximum value, x, of the subband signalnormBandCorresponding to a frequency energy normalized signal.
And extracting band-pass envelopes from the frequency-normalized sub-bands to obtain a band-pass envelope value corresponding to each sub-band. Wherein for wideband signals a smoothing method can be used and for narrowband signals a hilbert transform can be used. The formula of the hilbert transform is as follows:
wherein, x (t) represents the intracranial electroencephalogram signal after band-pass filtering, t represents a time sampling point, and the band-pass envelope value of the electroencephalogram signal is obtained through Hilbert transformation
And determining a high-frequency activity event according to the band-pass envelope value. The detection criteria for high frequency activity events are: a) the band-pass envelope value exceeds the envelope Threshold value ThresholdHFA(ii) a b) The time for exceeding the envelope threshold, i.e. the time for discharging, is not less than the discharge time threshold tHFA(ii) a c) If the interval time of two high-frequency activity events is less than the interval threshold tgapThen combine into oneA high frequency activity event. Wherein a single channel threshold mean is set1And a global threshold mean2Obtaining an envelope Threshold value ThresholdHFA：
ThrgSholdHFA＝max(median1，median2)
If the number of the detected high-frequency activity events is greater than 2, acquiring a preliminary screening signal of the high-frequency activity, which specifically comprises the following steps:
counting the number of high-frequency activity events in each lead, and selecting the lead of which the number meets a first preset standard as the high-frequency activity lead. The first preset criterion is, for example: the number of high frequency activity events ranks top 50% from large to small.
And respectively dividing the electroencephalogram signal of each high-frequency active lead into a second number of segment electroencephalogram signals, wherein the segment electroencephalogram signals are electroencephalogram signals corresponding to a short-time window, and the short-time window is 300ms-2s for example.
And calculating the number of high-frequency activity events in each segment of electroencephalogram signal, and combining the segment electroencephalogram signals of which the number meets a second preset standard to obtain a prescreened signal of the high-frequency activity. The second preset criterion is, for example: the number of high frequency activity events ranks 70% top from large to small.
Therefore, band-pass signals of the intracranial brain electricity of the high-frequency activity short-time window of the high-frequency activity leads are extracted and spliced together to obtain the prescreening signals of the high-frequency activity as shown in figure 2.
And finally, calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity, wherein the time sequence relation comprises the following steps:
acquiring a time-frequency diagram of each primary screening signal, and calculating the frequency spectrum centroid of each segment of electroencephalogram signal;
determining the time position of each frequency spectrum centroid in the corresponding time-frequency diagram as the generation time of the high-frequency activity event of each lead in the corresponding segment electroencephalogram signal;
and sequencing the generation time of the high-frequency activity events to obtain the time sequence relation of the high-frequency activity events.
The time-frequency diagram of each prescreened signal is obtained in the following manner: firstly, performing time-frequency decomposition on the primary screening signal of each high-frequency moving brain wave (for example, wavelet transform, short-time Fourier transform and other methods can be adopted, for the short-time Fourier transform, one reference is set as a Hamming window, the block size is 0.05 times of the sampling rate, the overlapping size is 80% of the block size, the number of points of the Fourier transform is the same as the block size, and the sampling rate is 0.05 times.
Normalizing the time-frequency diagram obtained after short-time Fourier transform, wherein the normalization formula is as follows:
wherein x isspecTime-frequency, x, representing the prescreened signalmeanRepresenting the time-frequency mean, sigma, of the prescreened signalspecStandard deviation, x, representing the time-frequency of the prescreened signalnormIs a normalized time-frequency diagram.
In addition, the time-frequency graph after normalization can be subjected to Gaussian smoothing to obtain the time-frequency graph after smoothing. And a frequency range can be further selected (for example, the frequency range can be 30-300 Hz), so that a time-frequency graph of high-frequency activity is obtained.
The application obtains the frequency spectrum centroid according to the following formula:
where w represents frequency, STFT is Short Time Fourier Transform (STFT), STFT (n, w) represents the Fourier Transform at sample point n;
wherein the content of the first and second substances,
the nature of the Fourier transform is the inner product, which can be understood as x (n) at e-iwnAnd then the components of the signal at each sample point at w are added together. x (n) at the sample pointSignal amplitude at n, w (n-m) denotes a windowing function, e-iwnTrigonometric functions representing different frequencies;
as shown in fig. 3, the time position of the spectral centroid in the corresponding time-frequency plot represents the generation time instant of each high frequency activity event within the short time window. And sequencing the generation time of each high-frequency activity brain wave so as to determine the time sequence relation of each high-frequency activity brain wave.
The high frequency activity timing of each short time window can be further subjected to cluster analysis and displayed. The high frequency activity sequences gathered into the same category represent higher similarity of high frequency activity, i.e. mean the same template sequence, as shown in fig. 4.
Optionally, in another embodiment based on the foregoing method of the present application, after calculating a time sequence relationship of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity, the method includes:
and determining the corresponding brain area as the brain area with the earliest high-frequency activity according to the electrode or the electrode group corresponding to the high-frequency activity event with the earliest generation time.
Further, the status category of the detected user can be determined according to the brain area status.
Optionally, when it is determined that there are multiple (at least two) discharge positions (corresponding to the high-frequency active brain waves) in the electroencephalogram, the method obtains the discharge time points of the positions, labels the discharge position with the earliest occurrence time (i.e., the brain region to which the first high-frequency active brain wave corresponds), and uses the discharge position as the brain region state of the user to be detected, so as to determine the state category of the user.
In the application, electroencephalograms can be acquired and preprocessed; detecting the number of high frequency activity events in the preprocessed electroencephalogram; if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events; and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity. By applying the technical scheme of the application, whether the high-frequency activity events exist in the intracranial electroencephalogram of the user can be automatically detected, and the state type of the user is judged by determining the brain area which generates the high-frequency activity at the earliest time through extracting the time sequence process of each high-frequency activity event. Thereby avoiding the defects of time and labor consumption in the interpretation process of the intracranial electroencephalogram and the limitation of the types and the number of post-processing technologies in the related technologies.
In another embodiment of the present application, as shown in fig. 5, the present application further provides an electroencephalogram activity recognition apparatus. The system comprises an acquisition module 201, a detection module 202, a generation module 203 and a calculation module 204, wherein,
an acquisition module 201 configured to acquire an electroencephalogram and perform preprocessing;
a detection module 202 configured to detect high frequency activity events in the pre-processed electroencephalogram;
a generating module 203 configured to obtain a prescreening signal of the high-frequency activity according to the high-frequency activity events if the number of the high-frequency activity events is not less than two;
and the calculating module 204 is configured to calculate a time sequence relationship of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
In the application, electroencephalograms can be acquired and preprocessed; detecting the number of high frequency activity events in the preprocessed electroencephalogram; if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events; and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity. By applying the technical scheme of the application, whether the high-frequency activity events exist in the intracranial electroencephalogram of the user can be automatically detected, and the state type of the user is judged by determining the brain area which generates the high-frequency activity at the earliest time through extracting the time sequence process of each high-frequency activity event. Thereby avoiding the defects of time and labor consumption in the interpretation process of the intracranial electroencephalogram and the limitation of the types and the number of post-processing technologies in the related technologies.
FIG. 6 is a block diagram illustrating a logical structure of an electronic device in accordance with an exemplary embodiment. For example, the electronic device 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium, such as a memory, including instructions executable by a processor of an electronic device to perform the method for brain electrical activity recognition described above, the method comprising: acquiring an electroencephalogram and preprocessing the electroencephalogram; detecting a number of high frequency activity events in the preprocessed electroencephalogram; if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events; and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity. Optionally, the instructions may also be executable by a processor of the electronic device to perform other steps involved in the exemplary embodiments described above. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided an application/computer program product including one or more instructions executable by a processor of an electronic device to perform the above-described brain electrical activity recognition method, the method comprising: acquiring an electroencephalogram and preprocessing the electroencephalogram; detecting a number of high frequency activity events in the preprocessed electroencephalogram; if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events; and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity. Optionally, the instructions may also be executable by a processor of the electronic device to perform other steps involved in the exemplary embodiments described above.
Those skilled in the art will appreciate that the schematic diagram 6 is merely an example of the computer device 30 and does not constitute a limitation of the computer device 300, and may include more or less components than those shown, or combine certain components, or different components, e.g., the computer device 30 may also include input output devices, network access devices, buses, etc.
The Processor 302 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor 302 may be any conventional processor or the like, the processor 302 being the control center for the computer device 30 and connecting the various parts of the overall computer device 30 using various interfaces and lines.
The modules integrated by the computer device 300 may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by hardware related to computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. An electroencephalogram activity recognition method, characterized by comprising:
acquiring an electroencephalogram and preprocessing the electroencephalogram;
detecting a high frequency activity event in the pre-processed electroencephalogram;
if the number of the high-frequency activity events is not less than two, acquiring a primary screening signal of the high-frequency activity according to the high-frequency activity events;
and calculating the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
2. The method of claim 1, wherein the acquiring and pre-processing electroencephalograms comprises:
re-referencing the electroencephalogram;
eliminating power frequency noise interference of the re-referenced electroencephalogram by adopting a first Hertz notch filter to obtain a first processed electroencephalogram;
and eliminating the baseline wandering interference of the first processed electroencephalogram by adopting a second Hertz high-pass filter to obtain a second processed electroencephalogram.
3. The method of claim 2, wherein the detecting high frequency activity events in the pre-processed electroencephalogram comprises:
segmenting the second processed electroencephalogram into a first number of segmented electroencephalograms;
performing band-pass filtering on each electroencephalogram of the segments to obtain a band-pass signal corresponding to each electroencephalogram of the segments;
slicing the band pass signal of each of the electroencephalograms into a second number of sub-bands and frequency normalizing the signal of each sub-band;
extracting band-pass envelope processing is carried out on the frequency-normalized sub-bands, and a band-pass envelope value corresponding to each sub-band is obtained;
and determining a high-frequency activity event according to the band-pass envelope value.
4. The method of claim 3, wherein said determining high frequency activity events from the band pass envelope values comprises:
if detecting a sub-band of which the duration time of the band-pass envelope value is greater than the preset envelope threshold value is not less than the discharge time threshold value, determining the sub-band as a high-frequency activity event;
and if the interval time of two adjacent high-frequency activity events is less than the first time period, combining the two high-frequency activity events into one high-frequency activity event.
5. The method of claim 1, wherein the obtaining a prescreened signal of high frequency activity based on the high frequency activity event comprises:
counting the number of high frequency activity events in each lead;
selecting the leads with the number meeting a first preset standard of the high-frequency activity events as high-frequency activity leads;
the electroencephalogram signal of each high-frequency active lead is divided into a second number of segment electroencephalogram signals respectively;
calculating the number of high-frequency activity events in each segment of electroencephalogram signal; and combining the number of the segment electroencephalogram signals meeting a second preset standard to obtain the preliminary screening signal of the high-frequency activity.
6. The method of claim 5, wherein the calculating the time sequence relationship of the high frequency activity events according to the prescreening signals of the high frequency activities comprises:
acquiring a time-frequency diagram of the primary screening signal, and calculating the frequency spectrum centroid of each segment of electroencephalogram signal;
determining the time position of each frequency spectrum centroid in the corresponding time-frequency diagram as the generation time of the high-frequency activity event of each lead in the corresponding segment electroencephalogram signal;
and sequencing the generation time of the high-frequency activity events to obtain the time sequence relation of the high-frequency activity events.
7. The method of claim 1 or 6, wherein after calculating the time sequence relationship of each high frequency activity event according to the preliminary screening signal of the high frequency activity, the method further comprises:
and clustering and displaying the high-frequency activity events of each segment of electroencephalogram signal.
8. An electroencephalogram activity recognition apparatus, comprising:
an acquisition module configured to acquire an electroencephalogram and perform preprocessing;
a detection module configured to detect high frequency activity events in the pre-processed electroencephalogram;
the generating module is configured to obtain a preliminary screening signal of the high-frequency activity according to the high-frequency activity events if the number of the high-frequency activity events is not less than two;
and the calculation module is configured to calculate the time sequence relation of each high-frequency activity event according to the preliminary screening signal of the high-frequency activity.
9. An electronic device, comprising:
a memory for storing executable instructions; and the number of the first and second groups,
a processor for displaying with the memory to execute the executable instructions to perform the operations of the brain electrical activity recognition method of any one of claims 1-7.
10. A computer-readable storage medium storing computer-readable instructions that, when executed, perform the operations of the brain electrical activity recognition method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110211205.4A CN113017649A (en) | 2021-02-25 | 2021-02-25 | Electroencephalogram activity identification method and device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110211205.4A CN113017649A (en) | 2021-02-25 | 2021-02-25 | Electroencephalogram activity identification method and device, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113017649A true CN113017649A (en) | 2021-06-25 |
Family
ID=76461713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110211205.4A Pending CN113017649A (en) | 2021-02-25 | 2021-02-25 | Electroencephalogram activity identification method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113017649A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070197930A1 (en) * | 2006-02-17 | 2007-08-23 | Mika Sarkela | Detection of epileptiform activity |
| CN105919568A (en) * | 2016-05-24 | 2016-09-07 | 北京千安哲信息技术有限公司 | Gabor transformation based method and device for extracting and analyzing breathing and heartbeat signals |
| CN105962914A (en) * | 2016-05-24 | 2016-09-28 | 北京千安哲信息技术有限公司 | Respiration and heartbeat signal separation method and device based on blind source separation |
| US9533159B2 (en) * | 2013-08-30 | 2017-01-03 | Cardiac Pacemakers, Inc. | Unwanted stimulation detection during cardiac pacing |
| WO2018102815A1 (en) * | 2016-12-02 | 2018-06-07 | Thomas Jefferson University | Signal processing method for distinguishing and characterizing high-frequency oscillations |
| CN111772585A (en) * | 2020-07-13 | 2020-10-16 | 清华大学 | Data extraction method for epileptic abnormal group activities in interval intracranial electroencephalogram signals |
-
2021
- 2021-02-25 CN CN202110211205.4A patent/CN113017649A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070197930A1 (en) * | 2006-02-17 | 2007-08-23 | Mika Sarkela | Detection of epileptiform activity |
| US9533159B2 (en) * | 2013-08-30 | 2017-01-03 | Cardiac Pacemakers, Inc. | Unwanted stimulation detection during cardiac pacing |
| CN105919568A (en) * | 2016-05-24 | 2016-09-07 | 北京千安哲信息技术有限公司 | Gabor transformation based method and device for extracting and analyzing breathing and heartbeat signals |
| CN105962914A (en) * | 2016-05-24 | 2016-09-28 | 北京千安哲信息技术有限公司 | Respiration and heartbeat signal separation method and device based on blind source separation |
| WO2018102815A1 (en) * | 2016-12-02 | 2018-06-07 | Thomas Jefferson University | Signal processing method for distinguishing and characterizing high-frequency oscillations |
| CN111772585A (en) * | 2020-07-13 | 2020-10-16 | 清华大学 | Data extraction method for epileptic abnormal group activities in interval intracranial electroencephalogram signals |
Non-Patent Citations (1)
| Title |
|---|
| 孙博: "癫痫病灶准确定位中脑电高频振荡节律检测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)医药卫生科技辑(月刊)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110338786B (en) | Epileptic discharge identification and classification method, system, device and medium | |
| CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
| JP5271718B2 (en) | How to identify fetal and maternal ECGs across multiple time segments | |
| Chang et al. | Detection of eye blink artifacts from single prefrontal channel electroencephalogram | |
| Aarabi et al. | Automated neonatal seizure detection: a multistage classification system through feature selection based on relevance and redundancy analysis | |
| US6591132B2 (en) | Artifact detection in encephalogram data using an event model | |
| JP2019055173A (en) | Cascaded binary classifier for identifying rhythms in single-lead electrocardiogram (ecg) signal | |
| CN110141218B (en) | Electrocardiosignal classification method, electrocardiosignal classification device, program product and storage medium | |
| CN108158578A (en) | Noise segments recognition methods, ECG signal processing method and processing device | |
| CN105796096A (en) | Heart rate variability analysis method, heart rate variability analysis system and terminal | |
| CN108742697B (en) | Heart sound signal classification method and terminal equipment | |
| CN106923820B (en) | Electrocardiosignal artifact identification method and electrocardiosignal artifact identification device | |
| EP3616605A1 (en) | Non-invasive detection of coronary heart disease from short single-lead ecg | |
| CN114767087B (en) | Multi-target respiratory frequency estimation method, device, equipment and storage medium | |
| CN112494031A (en) | Respiration rate calculation method and device | |
| DE102016204397A1 (en) | CLASSIFICATION OF A TIME SERIES SIGNAL AS VENTRICULAR EXTRASYSTOLE | |
| Mondal et al. | Boundary estimation of cardiac events S1 and S2 based on Hilbert transform and adaptive thresholding approach | |
| CN104983415B (en) | The heart claps the method and device of identification | |
| CN109009079A (en) | User Status detection system and method, computer equipment, computer storage medium | |
| CN108937920B (en) | Ventricular fibrillation signal detection method and system and ventricular fibrillation detection device | |
| CN113017649A (en) | Electroencephalogram activity identification method and device, electronic equipment and medium | |
| CN104545890B (en) | A kind of personal identification method and device based on electrocardiosignal | |
| Becerra et al. | Stochastic analysis and classification of 4-area cardiac auscultation signals using Empirical Mode Decomposition and acoustic features | |
| Hamidah et al. | Effective heart sounds detection method based on signal's characteristics | |
| CN113768520B (en) | Training method and device for electroencephalogram detection model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210730 Address after: 100084 b201c-1, 3rd floor, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing Applicant after: Beijing innovation Zhiyuan Technology Co.,Ltd. Address before: B201d-1, 3rd floor, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing 100083 Applicant before: Beijing Zhiyuan Artificial Intelligence Research Institute |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211209 Address after: Room 0106-687, floor 1, No. 26, Shangdi Information Road, Haidian District, Beijing 100080 Applicant after: Lingxi medical technology (Beijing) Co.,Ltd. Address before: 100084 b201c-1, 3rd floor, building 8, yard 1, Zhongguancun East Road, Haidian District, Beijing Applicant before: Beijing innovation Zhiyuan Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |