CN114169361A - Biological signal marking method, device, equipment and storage medium - Google Patents
Biological signal marking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114169361A CN114169361A CN202111331759.4A CN202111331759A CN114169361A CN 114169361 A CN114169361 A CN 114169361A CN 202111331759 A CN202111331759 A CN 202111331759A CN 114169361 A CN114169361 A CN 114169361A
- Authority
- CN
- China
- Prior art keywords
- signal
- target
- mutation point
- biological
- biological 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
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000035772 mutation Effects 0.000 claims abstract description 210
- 230000009471 action Effects 0.000 claims abstract description 38
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000004806 packaging method and process Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 abstract description 2
- 238000003062 neural network model Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 27
- 238000012545 processing Methods 0.000 description 17
- 238000012937 correction Methods 0.000 description 16
- 230000008859 change Effects 0.000 description 12
- 230000033001 locomotion Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
Abstract
The embodiment of the application provides a biological signal marking method, a biological signal marking device, biological signal marking equipment and a storage medium, wherein the method comprises the following steps: identifying a target signal mutation point in the original biological signal by using a preset sliding window, wherein the preset sliding window is used for extracting signal data with a first preset time length from the original biological signal, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal; extracting a target biological signal from an original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process that a human body executes a target action; and selecting the label information and packaging the label information and the target biological signal in a data packet to obtain biological signal sample data. The method can quickly and accurately obtain the biological signal sample data for training the neural network model.
Description
Technical Field
The disclosed embodiments relate to the technical field of biological signal identification, and more particularly, to a biological signal marking method, device, equipment and storage medium.
Background
Human biological signals, such as myoelectricity, electroencephalogram, electrooculogram, etc., are unsteady alternating-current signals, which generate signal waveforms carrying different characteristic information during relaxation and various actions.
In the field of human body biological signal recognition, an original signal needs to be collected first, generally, when the original signal is collected, operations of periodically and alternately carrying out a relaxation state and a target action state are generally adopted, so that effective signals in the original signal are extracted and labeled, namely, action behaviors corresponding to a certain section of signal data are obtained, and training sample data is formed and used for a deep learning network.
In order to improve the robustness of the deep learning network, it is necessary to add as many and accurate samples as possible. At present, effective signal extraction and labeling require researchers to manually extract and label by using some auxiliary tools, a great deal of time and energy are consumed, the effective signal extraction and labeling are easily influenced by personal subjective factors of the extraction personnel, and the problems that the accurate demarcation point confirmation is inaccurate and the like are introduced.
Disclosure of Invention
An object of the present disclosure is to provide a new technical solution for bio-signal marking to quickly and accurately identify a target signal in an original signal, thereby generating bio-signal sample data for a deep learning network.
According to a first aspect of the present disclosure, there is provided an embodiment of a method of bio-signal marking, comprising:
identifying a target signal mutation point in the original biological signal by using a preset sliding window, wherein the preset sliding window is used for extracting signal data with a first preset time length from the original biological signal, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal;
extracting a target biological signal from an original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process that a human body executes a target action;
and selecting the label information and packaging the label information and the target biological signal in a data packet to obtain biological signal sample data.
Optionally, the target signal discontinuity comprises at least one signal discontinuity, and the identifying the target signal discontinuity in the original biosignal using the preset sliding window comprises:
acquiring first signal data and second signal data which are adjacent in time sequence from the original biological signal according to a first increment window length on the basis of a preset sliding window, wherein the generation time of the second signal data is later than that of the first signal data;
acquiring a first characteristic value of the first signal data, and acquiring a second characteristic value of the second signal data;
under the condition that the absolute value of the difference value between the first characteristic value and the second characteristic value is larger than a first preset threshold value, acquiring a middle value of a time range corresponding to second signal data as a first signal mutation point to be determined;
under the condition that the first to-be-determined signal mutation point meets a preset condition, determining the first to-be-determined signal mutation point as a first signal mutation point;
and obtaining a target signal mutation point according to the first signal mutation point.
Optionally, the determining that the first to-be-determined signal discontinuity point is the first signal discontinuity point when the first to-be-determined signal discontinuity point meets the preset condition includes:
acquiring a third characteristic value of third signal data before a first to-be-determined signal mutation point and acquiring a fourth characteristic value of fourth signal data after the first to-be-determined signal mutation point, wherein the third signal data and the fourth signal data are signal data with a second preset time length, and the second preset time length is less than the first preset time length;
and under the condition that the absolute value of the difference value between the third characteristic value and the fourth characteristic value is larger than a second preset threshold value, determining the first to-be-determined signal abrupt change point as the first signal abrupt change point.
Optionally, the extracting the target bio-signal from the original bio-signal according to the target signal mutation point includes:
extracting signal data of third preset time before and after a first signal mutation point from the original biological signal to serve as a first biological signal, wherein the first biological signal is generated in the process that a human body is in a relaxed state and a target action is executed once;
and obtaining the target biological signal according to the first biological signal.
Optionally, after obtaining the target bio-signal, the method further comprises:
acquiring a fifth characteristic value of all signals before a first signal mutation point and acquiring a sixth characteristic value of half signals before the first signal mutation point from the first biological signals;
and under the condition that the absolute value of the difference value of the fifth characteristic value and the sixth characteristic value is larger than a third preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
Optionally, the method further comprises:
under the condition that the absolute value of the difference value between the fifth characteristic value and the sixth characteristic value is not larger than a third preset threshold value, acquiring seventh characteristic values of all signals after the first signal mutation point from the first biological signal;
and under the condition that the absolute value of the difference value of the fifth characteristic value and the seventh characteristic value is not larger than a fourth preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
Optionally, the target signal mutation points include at least one signal mutation point, and the target biological signals include at least one biological signal corresponding to the at least one signal mutation point respectively; after obtaining the target bio-signal, the method further comprises:
acquiring any biological signal from the target biological signal as a second biological signal, and acquiring a second signal mutation point corresponding to the second biological signal from the target signal mutation point;
taking the difference value between the second signal mutation point and the preset sliding window duration and the first increment window length as an initial time point;
reducing the length of the first increment window to obtain the length of a second increment window;
acquiring fifth signal data and sixth signal data which are adjacent in time sequence from the starting time point in the original biological signal based on a preset sliding window and according to the length of a second increment window;
under the condition that the absolute value of the difference value between the eighth characteristic value of the fifth signal data and the ninth characteristic value of the sixth signal data is larger than a first preset threshold, obtaining the starting time corresponding to the sixth signal data, and updating a second signal mutation point according to the starting time, the duration of a preset sliding window and the length of a second increment window; and the number of the first and second groups,
extracting signal data of each third preset time length before and after the updated second signal mutation point from the original biological signal so as to update the signal data in the second biological signal;
and updating the target biological signal according to the updated second biological signal.
Optionally, the raw bio-signal comprises a dc bias signal;
prior to the step of identifying the target signal discontinuity in the raw bio-signal using a preset sliding window, the method further comprises:
acquiring a signal mean value of an original biological signal as a direct current offset component;
and removing the direct current bias signal included in the original biological signal according to the direct current bias component.
According to a second aspect of the present disclosure, there is provided an embodiment of a bio-signal marking device, comprising:
the signal mutation point identification module is used for identifying a target signal mutation point in the original biological signal by using a preset sliding window, wherein the preset sliding window is a sliding window with a first preset duration, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal;
the biological signal extraction module is used for extracting a target biological signal from the original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process of biologically executing a target action;
and the marking module is used for taking the action information of the target action as a label of the target biological signal so as to obtain biological signal sample data.
According to a third aspect of the present disclosure, there is provided an embodiment of an electronic device, comprising the apparatus according to the second aspect of the present specification, or comprising:
a memory for storing executable instructions;
a processor for performing the method according to the first aspect of the present description under control of the executable computer program.
According to a fourth aspect of the present disclosure, there is provided one embodiment of a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program readable by a computer for performing the method according to the first aspect of the present specification when the computer program is read by the computer.
One beneficial effect of the embodiments of the present disclosure is that, according to the embodiments of the present disclosure, for an original signal to be analyzed, an electronic device may identify signal data in the original biological signal by using a preset window without relying on manual work to obtain a target signal mutation point reflecting a human action state mutation; and then, extracting a target biological signal generated in the process of executing a target action by a human body from the original biological signal according to the target signal mutation point, and quickly and accurately obtaining biological signal sample data by selecting the label information and packaging the label information and the target biological signal in a data packet.
Other features of the present description and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description, serve to explain the principles of the specification.
Fig. 1 is a schematic diagram of an original signal provided by an embodiment of the present disclosure.
Fig. 2 is a schematic flow chart of a biosignal marking method according to an embodiment of the disclosure.
Fig. 3 is a schematic diagram of an original signal after removing a dc offset signal according to an embodiment of the present disclosure.
Fig. 4 is a schematic flowchart of acquiring a target signal mutation point according to an embodiment of the present disclosure.
Fig. 5 is a schematic diagram of a preset sliding window step provided in the embodiment of the present disclosure.
Fig. 6 is a schematic diagram of a first target signal discontinuity point provided by an embodiment of the present disclosure.
Fig. 7a is a schematic flowchart of a first mutation point error correction process according to an embodiment of the disclosure.
Fig. 7b is a flowchart illustrating a second mutation point error correction process according to an embodiment of the disclosure.
Fig. 8 is a schematic diagram of a second target signal discontinuity point provided by an embodiment of the present disclosure.
Fig. 9 is a schematic flowchart of a mutation point correction process provided in the embodiment of the present disclosure.
FIG. 10 is a schematic diagram of a critical signal discontinuity provided by embodiments of the present disclosure.
Fig. 11 is a schematic diagram of a third target signal discontinuity point provided by an embodiment of the present disclosure.
Fig. 12 is a block schematic diagram of a bio-signal marking device provided in an embodiment of the present disclosure.
Fig. 13 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure 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 invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, 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.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
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.
< method examples >
Generally, after an original biological signal of a human body is acquired, since the original biological signal does not include label information of a target action performed by the human body, the original biological signal cannot be directly input to a neural network for learning and classification, and the target biological signal in the original biological signal, that is, signal data generated in a process of the target action performed by the human body, needs to be screened and labeled before being used. In order to facilitate neural network learning, the target biological signal obtained by extraction and the label need to be packaged into biological signal sample data.
Please refer to fig. 1, which is a schematic diagram of an original signal provided by an embodiment of the present disclosure. As shown in fig. 1, in the human biological signal acquisition process, due to factors such as motion intervals, motion dynamics, and skin movement, target biological signals reflecting target motions may be distributed dispersedly and have different signal amplitudes, and some artifact signals may be introduced, so that when the target biological signals in the original biological signals are identified and analyzed based on a manual method to generate biological signal sample data, time and labor are wasted, and the accuracy is not high. In order to solve the problem, in the embodiment of the disclosure, after acquiring an original biological signal of a human body, based on a characteristic that a biological signal generated by the human body in a relaxed state and when a target action is performed usually has a sudden change, and the biological signal before a signal sudden change point usually tends to be stable, and the biological signal after the signal sudden change point usually increases signal characteristics which tend to be stable again, the original biological signal is automatically identified and analyzed by the electronic device to generate biological signal sample data for neural network learning.
Please refer to fig. 2, which is a schematic flow chart of a bio-signal marking method according to an embodiment of the present disclosure, where the embodiment may be implemented by an electronic device, and the electronic device may be a server or a terminal device, and is not limited herein.
As shown in fig. 2, the method for marking a biological signal of the present embodiment includes steps S2100 to S2300, which will be described in detail below.
Step S2100, identifying a target signal mutation point in the original biological signal by using a preset sliding window, wherein the preset sliding window is used for extracting signal data with a first preset duration from the original biological signal, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal; and executing step S2200, namely extracting a target biological signal from the original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process that the human body executes the target action.
As shown in fig. 1, when a human biological signal is actually collected, since the human biological signal is an astable ac signal, a dc bias voltage is usually superimposed on the skin of a human body to collect a complete ac signal waveform for the convenience of collecting by an electronic device. Therefore, before the original biological signal of the human body is collected and analyzed, the electronic device is required to remove the direct current bias signal superimposed in the original biological signal so as to avoid the interference of the direct current bias signal on the identification result.
That is, in one embodiment, in the case that the original bio-signal contains a dc offset signal, after the step S2100 is implemented, the method further includes: acquiring a signal mean value of an original biological signal as a direct current offset component; removing the DC bias signal included in the original bio-signal according to the DC bias component.
The treatment can be used in particular toThe following equation is expressed: xnew＝X–(∑(Xi) N) is calculated. Specifically, for an ac signal with a dc offset signal, the dc offset component of the dc offset signal is actually the average of the entire signal, and thus subtracting the average of the entire signal from the original biosignal removes the dc offset signal, leaving only the ac signal.
Please refer to fig. 3, which is a schematic diagram of an original signal after removing a dc offset signal according to an embodiment of the present disclosure. As shown in fig. 3, after removing the dc offset signal from the original signal shown in fig. 1 based on the above formula, an ac signal with a center based on 0v can be obtained. By removing the direct current bias signal in the original biological signal through the method, the interference of the direct current bias signal on the analysis result can be avoided, and the accuracy of the result is improved.
Please refer to fig. 4, which is a schematic flow chart of obtaining a mutation point of a target signal according to an embodiment of the disclosure. As shown in fig. 4, in one embodiment, the target signal discontinuity may include at least one signal discontinuity, and the identifying the target signal discontinuity in the original bio-signal using the preset sliding window includes: step S4100, acquiring first signal data and second signal data which are adjacent in time sequence from an original biological signal according to a first increment window length based on a preset sliding window, wherein the generation time of the second signal data is later than that of the first signal data; step S4200, acquiring a first eigenvalue of the first signal data, and acquiring a second eigenvalue of the second signal data; step S4300, when the absolute value of the difference value between the first characteristic value and the second characteristic value is greater than a first preset threshold, acquiring a middle value of a time range corresponding to the second signal data as a first signal mutation point to be determined; step S4400, determining the first signal mutation point to be determined as a first signal mutation point under the condition that the first signal mutation point to be determined meets a preset condition; and a step S4500 of obtaining a target signal mutation point according to the first signal mutation point.
In this embodiment, the determining that the first to-be-determined signal discontinuity point is the first signal discontinuity point when the first to-be-determined signal discontinuity point satisfies the preset condition includes: acquiring a third characteristic value of third signal data before a first to-be-determined signal mutation point and acquiring a fourth characteristic value of fourth signal data after the first to-be-determined signal mutation point, wherein the third signal data and the fourth signal data are signal data with a second preset time length, and the second preset time length is less than the first preset time length; and under the condition that the absolute value of the difference value between the third characteristic value and the fourth characteristic value is larger than a second preset threshold value, determining the first to-be-determined signal abrupt change point as the first signal abrupt change point.
Specifically, after removing the dc bias signal in the original bio-signal, according to the characteristic that the amplitude of the bio-signal generated during the human body performing the target motion, such as blinking, shaking, waving, etc., is much larger than the amplitude of the bio-signal generated when the human body is in a relaxed state, as shown in fig. 5, two pieces of signal data sequentially connected in front and back time sequence, i.e., the first signal data and the second signal data, are intercepted from the original bio-signal one by one with a preset sliding window of a first preset duration, such as 200ms, i.e., the time window as a time window, and with a first increment window length, such as 20ms, as a first increment window of one step, so as to retrieve the original bio-signal, and by comparing the magnitudes of the characteristic values of the first signal data and the second signal data, the target signal mutation point in the original bio-signal can be obtained, the characteristic value of the first signal data and the second signal data may be an average value, an effective value, or a variance, and in the embodiment of the present disclosure, the characteristic value is exemplified as the average value.
After obtaining the target signal mutation point, in an embodiment, the extracting the target biosignal from the original biosignal according to the target signal mutation point includes: extracting signal data of third preset time before and after a first signal mutation point from the original biological signal to serve as a first biological signal, wherein the first biological signal is generated in the process that a human body is in a relaxed state and a target action is executed once; and obtaining a target biological signal according to the first biological signal.
In this embodiment, the third preset time period may be 1s, and of course, the value may also be set according to needs, and is not particularly limited herein.
Please refer to fig. 6, which is a schematic diagram of a first target signal discontinuity point according to an embodiment of the present disclosure. As shown in fig. 6, for the original signal shown in fig. 3 after the dc offset signal is removed, 14 target signal discontinuities can be quickly calculated by the above method.
It should be noted that, in the embodiment of the present disclosure, specific values of the first preset duration, the first increment window length, the first preset threshold, and the second preset threshold may be set as needed, and are not particularly limited herein. In addition, in this embodiment, if the original biological signal includes a plurality of channels, each channel may be identified and analyzed by using a corresponding number of preset sliding windows, and the detailed processing procedure is not described herein again. In addition, in specific implementation, if an absolute value of a difference between characteristic values, such as an average value, of the first signal data and the second signal data is not greater than a first preset threshold, it may be determined that the human biological signal does not undergo a sudden change within a time range corresponding to the first signal data and the second signal data, that is, an action performed by the human body does not undergo a sudden change, and at this time, the preset sliding window may be moved according to a length of the first incremental window to continue to search for a signal mutation point in the original biological signal; or, under the condition that the absolute value of the difference between the characteristic values of the first signal data and the second signal data is greater than the first preset threshold, after the first to-be-determined signal mutation point is obtained, in order to improve the accuracy of the result, preset time durations before and after the first to-be-determined signal mutation point, for example, 200ms characteristic values of the signal data, may be compared again, if the difference between the two characteristic values is small, the signal mutation point may be determined as a false signal, and if the difference between the two characteristic values is large, the signal mutation point is indicated to be relatively accurate, and the to-be-determined signal mutation point may be used as one of the target signal mutation points.
Referring to fig. 6, according to the amplitude fluctuation of each signal discontinuity in fig. 6, the 13 th signal discontinuity is an interference signal discontinuity, that is, an erroneous signal discontinuity, and in order to avoid errors caused by the interference signal discontinuity, the method may further correct the signal discontinuity in the target signal discontinuity and the bio-signal in the target bio-signal by the following steps.
Please refer to fig. 7a, which is a schematic flow chart of a first mutation point error correction process provided in the embodiment of the present disclosure, where the error correction process includes: step S7100, acquiring fifth characteristic values of all signals before a first signal mutation point from the first biological signal, and acquiring sixth characteristic values of half signals before the first signal mutation point; step S7200, determining the first signal mutation point as an error signal mutation point under the condition that the absolute value of the difference value between the fifth characteristic value and the sixth characteristic value is larger than a third preset threshold value, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
In addition, please refer to fig. 7b, which is a schematic flow chart of a second error correction processing provided in the embodiment of the present disclosure, where the error correction processing includes: step S7300, acquiring a seventh eigenvalue of all signals after the first signal mutation point from the first biological signal under the condition that the absolute value of the difference between the fifth eigenvalue and the sixth eigenvalue is not larger than a third preset threshold; step S7400, determining the first signal discontinuity as an erroneous signal discontinuity, removing the first signal discontinuity from the target signal discontinuity, and removing the first biosignal from the target biosignal, if the absolute value of the difference between the fifth characteristic value and the seventh characteristic value is not greater than a fourth preset threshold value.
That is, the original biological signal is a biological signal generated when the human body cycle is from a relaxed state to a target action, and therefore, after the target signal mutation point and the target biological signal are obtained through the above preliminary identification analysis, because the target biological signal includes signal data of a preset duration before and after each signal mutation point, in the biological signal corresponding to each signal mutation point, the biological signal data including the relaxed state and the biological signal data when the target action is executed are all included, therefore, for each biological signal in the target biological signal, the characteristic value of the signal data before the corresponding signal mutation point can be compared first, if the biological signal tends to be stable, that is, the absolute value of the difference is small, the biological signal corresponding to the relaxed state is indicated, and the preliminary judgment that the signal mutation point and the corresponding effective biological signal are identified correctly can be made. After the preliminary judgment, the characteristic values of the signal data before and after the signal mutation point can be further compared again, if the difference value between the two values is larger, the signal mutation point and the effective biological signal corresponding to the signal mutation point are correct, otherwise, the signal mutation point and the effective biological signal can be determined to have errors and need to be discarded.
In particular, at least one error correction process may be used to correct the signal discontinuities of the target signal discontinuities and the biological signals of the target biological signals, and the error correction process is not limited herein.
Please refer to fig. 8, which is a schematic diagram of a second target signal mutation point according to an embodiment of the disclosure. As shown in fig. 8, through the above processing, the abrupt change point of the interference signal in fig. 6 can be accurately removed, so as to improve the accuracy of the result.
Referring to fig. 8, as shown in fig. 8, the target signal discontinuity may include at least one signal discontinuity, and the target bio-signal may include at least one bio-signal corresponding to the at least one signal discontinuity, and as shown in fig. 8, the signal discontinuity obtained through the above processing may have an inaccurate demarcation point position, so in an embodiment of the present disclosure, a correction processing for the signal discontinuity is further provided, as shown in fig. 9, which is a schematic flow chart of the discontinuity correction processing provided in the embodiment of the present disclosure. As shown in fig. 9, the correction process specifically includes the steps of: s9100, acquiring any biological signal from the target biological signals as a second biological signal, and acquiring a second signal mutation point corresponding to the second biological signal from the target signal mutation point; step S9200, taking the difference value between the second signal mutation point and the preset sliding window duration and the first incremental window length as an initial time point; step S9300, reducing the length of the first incremental window to obtain the length of a second incremental window; step S9400, in the original biological signal, acquiring fifth signal data and sixth signal data which are adjacent in time sequence from the starting time point based on a preset sliding window and according to the length of a second increment window; step S9500, under the condition that the absolute value of the difference value between the eighth characteristic value of the fifth signal data and the ninth characteristic value of the sixth signal data is larger than a first preset threshold, acquiring a starting time corresponding to the sixth signal data, and updating a second signal mutation point according to the starting time, the preset sliding window duration and the second increment window length; extracting signal data of each third preset time length before and after the updated second signal mutation point from the original biological signal so as to update the signal data in the second biological signal; in step S9600, the target bio-signal is updated according to the updated second bio-signal.
In particular, in order to increase the processing speed, when the target signal discontinuity is obtained from the original biosignal, the first increment window length is generally set to be relatively long, that is, a relatively long increment window is set, and due to the window span problem, in some limit cases, the calculation error of one increment window length is most likely to occur. Please refer to fig. 10, which is a schematic diagram of a critical signal discontinuity point according to an embodiment of the present disclosure. As shown in fig. 10, the 3 rd time window is just before the critical point of the signal mutation, which results in that the mutation point cannot be detected in the time window 3, and the mutation point can only be detected in the time window 4, but it is possible that the mutation point is located at the beginning or the end of the last incremental window, therefore, in order to more accurately locate the real mutation point position, after the target signal mutation point is obtained, the incremental window length can be adjusted, that is, the second incremental window length smaller than the first incremental window length can be obtained by reducing the first incremental window length, so as to finely adjust the demarcation point position of the signal mutation point according to the second incremental window length, and further extract the signal data from the original bio-signal again according to the finely adjusted signal mutation point, so as to update the bio-signal corresponding to the signal mutation point, and further according to the updated bio-signal, and updating the target biological signal and improving the accuracy of the result.
In specific implementation, when the second signal discontinuity point is updated according to the start time, the preset duration of the sliding window, and the second incremental window length, the following formula may be specifically used: the updated second signal discontinuity is obtained as the start time + (duration of the preset sliding window — second incremental window length/2).
Please refer to fig. 11, which is a schematic diagram of a third target signal mutation point according to an embodiment of the disclosure. As shown in fig. 11, the position of the boundary point of the 12 th signal discontinuity in fig. 8 can be optimized by the above-described correction processing.
After step S2200, step S2300 is executed to select the tag information and package the tag information and the target bio-signal in a data packet, so as to obtain the bio-signal sample data.
Specifically, after the target biological signal is obtained according to the above steps, since the motion information of the target motion executed by the human body is determined in the process of acquiring the original biological signal, the motion information of the target motion can be obtained in advance, and after the electronic device extracts the effective target biological signal from the original biological signal, the motion information is used as the label of each effective biological signal in the target biological signal, so that the biological signal sample data for neural network learning can be conveniently, quickly and accurately obtained.
It should be noted that, in the specific implementation, since the signal mutation point of each effective biological signal in the target biological signal can also be obtained through the above processing, the biological signal in the target biological signal can also be labeled with fine granularity according to each signal mutation point, that is, the signal data before the signal mutation point corresponding to each biological signal is labeled as a relaxed state, and the signal data after the signal mutation point is labeled as action information of the target action.
To sum up, the biological signal marking method provided by the embodiment of the present disclosure may identify, by using a preset window, signal data in an original biological signal to obtain a target signal mutation point reflecting a human action state mutation, without relying on manual work, for the original signal to be analyzed; and then, extracting a target biological signal generated in the process of executing a target action by a human body from the original biological signal according to the target signal mutation point, and quickly and accurately obtaining biological signal sample data by selecting the label information and packaging the label information and the target biological signal in a data packet.
< apparatus embodiment >
Corresponding to the above method embodiment, fig. 12 is a block schematic diagram of a bio-signal marking device provided in the embodiment of the present disclosure. As shown in fig. 12, the bio-signal marking apparatus 100 may include: a signal mutation point identification module 110, a biological signal extraction module 120 and a marking module 130.
The signal mutation point identification module 110 is configured to identify a target signal mutation point in an original biological signal by using a preset sliding window, where the preset sliding window is a sliding window with a first preset duration, and the target signal mutation point is a time point in the original biological signal, where the time point reflects a human body action state mutation.
In one embodiment, the apparatus 100 further comprises a dc offset signal removing module, configured to, before the step of identifying the target signal mutation point in the original biological signal by using the preset sliding window, obtain a signal mean of the original biological signal as a dc offset component; and removing the direct current bias signal included in the original biological signal according to the direct current bias component.
In one embodiment, the target signal discontinuity includes at least one signal discontinuity, and the signal discontinuity identification module 110, when identifying the target signal discontinuity in the original bio-signal using a preset sliding window, may be configured to: acquiring first signal data and second signal data which are adjacent in time sequence from the original biological signal according to a first increment window length on the basis of a preset sliding window, wherein the generation time of the second signal data is later than that of the first signal data; acquiring a first characteristic value of the first signal data, and acquiring a second characteristic value of the second signal data; under the condition that the absolute value of the difference value between the first characteristic value and the second characteristic value is larger than a first preset threshold value, acquiring a middle value of a time range corresponding to second signal data as a first signal mutation point to be determined; under the condition that the first to-be-determined signal mutation point meets a preset condition, determining the first to-be-determined signal mutation point as a first signal mutation point; and obtaining a target signal mutation point according to the first signal mutation point.
In one embodiment, in a case that the first to-be-determined signal discontinuity satisfies a preset condition, the signal discontinuity identification module 110, when determining that the first to-be-determined signal discontinuity is the first signal discontinuity, may be configured to: acquiring a third characteristic value of third signal data before a first to-be-determined signal mutation point and acquiring a fourth characteristic value of fourth signal data after the first to-be-determined signal mutation point, wherein the third signal data and the fourth signal data are signal data with a second preset time length, and the second preset time length is less than the first preset time length; and under the condition that the absolute value of the difference value between the third characteristic value and the fourth characteristic value is larger than a second preset threshold value, determining the first to-be-determined signal abrupt change point as the first signal abrupt change point.
The biological signal extracting module 120 is configured to extract a target biological signal from an original biological signal according to a target signal mutation point, where the target biological signal includes signal data generated during a target action executed by a living being.
In one embodiment, the bio-signal extraction module 120, when extracting the target bio-signal from the original bio-signal according to the target signal mutation point, may be configured to: extracting signal data of third preset time before and after a first signal mutation point from the original biological signal to serve as a first biological signal, wherein the first biological signal is generated in the process that a human body is in a relaxed state and a target action is executed once; and obtaining the target biological signal according to the first biological signal.
In one embodiment, the apparatus 100 further comprises a first error correction module configured to: acquiring a fifth characteristic value of all signals before a first signal mutation point and acquiring a sixth characteristic value of half signals before the first signal mutation point from the first biological signals; and under the condition that the absolute value of the difference value of the fifth characteristic value and the sixth characteristic value is larger than a third preset threshold value, determining the first signal discontinuity point as an error signal discontinuity point, and removing the first signal discontinuity point from the target signal discontinuity point.
In one embodiment, the apparatus 100 further comprises a second error correction module for removing the first bio-signal from the target bio-signal; under the condition that the absolute value of the difference value between the fifth characteristic value and the sixth characteristic value is not larger than a third preset threshold value, acquiring seventh characteristic values of all signals after the first signal mutation point from the first biological signal; and under the condition that the absolute value of the difference value of the fifth characteristic value and the seventh characteristic value is not larger than a fourth preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
In one embodiment, the target signal mutation point comprises at least one signal mutation point, and the target biological signal comprises at least one biological signal corresponding to the at least one signal mutation point; the apparatus 100 further comprises a correction module for: acquiring any biological signal from the target biological signal as a second biological signal, and acquiring a second signal mutation point corresponding to the second biological signal from the target signal mutation point; taking the difference value between the second signal mutation point and the preset sliding window duration and the first increment window length as an initial time point; reducing the length of the first increment window to obtain the length of a second increment window; acquiring fifth signal data and sixth signal data which are adjacent in time sequence from the starting time point in the original biological signal based on a preset sliding window and according to the length of a second increment window; under the condition that the absolute value of the difference value between the eighth characteristic value of the fifth signal data and the ninth characteristic value of the sixth signal data is larger than a first preset threshold, obtaining the starting time corresponding to the sixth signal data, and updating a second signal mutation point according to the starting time, the duration of a preset sliding window and the length of a second increment window; extracting signal data of each third preset time length before and after the updated second signal mutation point from the original biological signal so as to update the signal data in the second biological signal; and updating the target biological signal according to the updated second biological signal.
The marking module 130 is configured to select tag information and package the tag information and a target biological signal in a data packet to obtain biological signal sample data.
< apparatus embodiment >
Corresponding to the above method embodiment, please refer to fig. 13, which is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.
As shown in fig. 13, the electronic device 200 comprises a processor 210 and a memory 220, the memory 220 is used for storing an executable computer program, and the processor 210 is used for executing the bio-signal marking method according to any of the above method embodiments according to the control of the computer program.
In one embodiment, the processor 210 may be configured to: identifying a target signal mutation point in the original biological signal by using a preset sliding window, wherein the preset sliding window is used for extracting signal data with a first preset time length from the original biological signal, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal; extracting a target biological signal from an original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process that a human body executes a target action; and selecting the label information and packaging the label information and the target biological signal in a data packet to obtain biological signal sample data.
In one embodiment, the process 210 may be used to: acquiring first signal data and second signal data which are adjacent in time sequence from the original biological signal according to a first increment window length on the basis of a preset sliding window, wherein the generation time of the second signal data is later than that of the first signal data; acquiring a first characteristic value of the first signal data, and acquiring a second characteristic value of the second signal data; under the condition that the absolute value of the difference value between the first characteristic value and the second characteristic value is larger than a first preset threshold value, acquiring a middle value of a time range corresponding to second signal data as a first signal mutation point to be determined; under the condition that the first to-be-determined signal mutation point meets a preset condition, determining the first to-be-determined signal mutation point as a first signal mutation point; and obtaining a target signal mutation point according to the first signal mutation point.
In one embodiment, the processor 210 may be configured to: extracting signal data of third preset time before and after a first signal mutation point from the original biological signal to serve as a first biological signal, wherein the first biological signal is generated in the process that a human body is in a relaxed state and a target action is executed once; and obtaining the target biological signal according to the first biological signal.
In one embodiment, the processor 210 may be further configured to: acquiring a fifth characteristic value of all signals before a first signal mutation point and acquiring a sixth characteristic value of half signals before the first signal mutation point from the first biological signals; and under the condition that the absolute value of the difference value of the fifth characteristic value and the sixth characteristic value is larger than a third preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
In one embodiment, the target signal mutation point comprises at least one signal mutation point, and the target biological signal comprises at least one biological signal corresponding to the at least one signal mutation point; the processor 210 may be further configured to: acquiring any biological signal from the target biological signal as a second biological signal, and acquiring a second signal mutation point corresponding to the second biological signal from the target signal mutation point; taking the difference value between the second signal mutation point and the preset sliding window duration and the first increment window length as an initial time point; reducing the length of the first increment window to obtain the length of a second increment window; acquiring fifth signal data and sixth signal data which are adjacent in time sequence from the starting time point in the original biological signal based on a preset sliding window and according to the length of a second increment window; under the condition that the absolute value of the difference value between the eighth characteristic value of the fifth signal data and the ninth characteristic value of the sixth signal data is larger than a first preset threshold, obtaining the starting time corresponding to the sixth signal data, and updating a second signal mutation point according to the starting time, the duration of a preset sliding window and the length of a second increment window; extracting signal data of each third preset time length before and after the updated second signal mutation point from the original biological signal so as to update the signal data in the second biological signal; and updating the target biological signal according to the updated second biological signal.
The modules of the bio-signal marking device 100 may be implemented by the processor 210 in the present embodiment executing a computer program stored in the memory 220, or may be implemented by other circuit structures, which is not limited herein.
< computer-readable storage Medium embodiment >
The present embodiments provide a computer-readable storage medium having stored therein an executable command, which when executed by a processor, performs the method described in any of the method embodiments of the present specification.
One or more embodiments of the present description may be a system, method, and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the specification.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations for embodiments of the present description may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), can execute computer-readable program instructions to implement various aspects of the present description by utilizing state information of the computer-readable program instructions to personalize the electronic circuit.
Aspects of the present description are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the description. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present description. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.
The foregoing description of the embodiments of the present specification has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the application is defined by the appended claims.
Claims (11)
1. A method of marking a biological signal, comprising:
identifying a target signal mutation point in an original biological signal by using a preset sliding window, wherein the preset sliding window is used for extracting signal data with a first preset duration from the original biological signal, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal;
extracting a target biological signal from the original biological signal according to the target signal mutation point, wherein the target biological signal comprises signal data generated in the process that a human body executes a target action;
selecting label information and packaging the label information and the target biological signal in a data packet to obtain biological signal sample data.
2. The method of claim 1, wherein the target signal discontinuity comprises at least one signal discontinuity, and wherein identifying the target signal discontinuity in the raw biosignal using the preset sliding window comprises:
acquiring first signal data and second signal data which are adjacent in time sequence from the original biological signal according to a first increment window length on the basis of the preset sliding window, wherein the generation time of the second signal data is later than that of the first signal data;
acquiring a first characteristic value of the first signal data, and acquiring a second characteristic value of the second signal data;
under the condition that the absolute value of the difference value between the first characteristic value and the second characteristic value is larger than a first preset threshold value, acquiring a middle value of a time range corresponding to the second signal data as a first to-be-determined signal mutation point;
determining the first signal mutation point to be determined as a first signal mutation point under the condition that the first signal mutation point to be determined meets a preset condition;
and obtaining the target signal mutation point according to the first signal mutation point.
3. The method of claim 2, wherein the determining that the first to-be-determined signal discontinuity is a first signal discontinuity if the first to-be-determined signal discontinuity satisfies a preset condition comprises:
acquiring a third characteristic value of third signal data before the first to-be-determined signal mutation point and acquiring a fourth characteristic value of fourth signal data after the first to-be-determined signal mutation point, wherein the third signal data and the fourth signal data are signal data with a second preset time length, and the second preset time length is smaller than the first preset time length;
and under the condition that the absolute value of the difference value between the third characteristic value and the fourth characteristic value is larger than a second preset threshold value, determining the first to-be-determined signal mutation point as a first signal mutation point.
4. The method of claim 2, wherein extracting the target bio-signal from the original bio-signal according to the target signal mutation point comprises:
extracting signal data of third preset time lengths before and after the first signal mutation point from the original biological signals to serve as first biological signals, wherein the first biological signals are generated in the process that a human body is in a relaxed state and the target action is executed once;
and obtaining the target biological signal according to the first biological signal.
5. The method of claim 4, wherein after obtaining the target bio-signal, the method further comprises:
acquiring a fifth characteristic value of all signals before the first signal mutation point and acquiring a sixth characteristic value of half signals before the first signal mutation point from the first biological signal;
and under the condition that the absolute value of the difference value of the fifth characteristic value and the sixth characteristic value is larger than a third preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
6. The method of claim 5, further comprising:
under the condition that the absolute value of the difference value between the fifth characteristic value and the sixth characteristic value is not larger than the third preset threshold value, acquiring a seventh characteristic value of all signals after the first signal mutation point from the first biological signal;
and under the condition that the absolute value of the difference value of the fifth characteristic value and the seventh characteristic value is not larger than a fourth preset threshold value, determining the first signal mutation point as an error signal mutation point, removing the first signal mutation point from the target signal mutation point, and removing the first biological signal from the target biological signal.
7. The method of claim 1, wherein the target signal mutation point comprises at least one signal mutation point, and the target bio-signal comprises at least one bio-signal corresponding to the at least one signal mutation point; after obtaining the target bio-signal, the method further comprises:
acquiring any biological signal from the target biological signals as a second biological signal, and acquiring a second signal mutation point corresponding to the second biological signal from the target signal mutation point;
taking the difference value between the second signal mutation point and the duration of the preset sliding window and the length of the first incremental window as an initial time point;
reducing the length of the first increment window to obtain a second increment window length;
acquiring fifth signal data and sixth signal data which are adjacent in time sequence in the original biological signal from the starting time point based on the preset sliding window according to the length of the second increment window;
under the condition that the absolute value of the difference value between the eighth characteristic value of the fifth signal data and the ninth characteristic value of the sixth signal data is larger than a first preset threshold, obtaining the starting time corresponding to the sixth signal data, and updating the second signal mutation point according to the starting time, the duration of the preset sliding window and the length of the second incremental window; and the number of the first and second groups,
extracting signal data of third preset time length before and after the updated second signal mutation point from the original biological signal so as to update the signal data in the second biological signal;
updating the target bio-signal according to the updated second bio-signal.
8. The method of claim 1, wherein the raw bio-signal comprises a dc bias signal;
before the step of identifying a target signal discontinuity in the raw bio-signal using a preset sliding window, the method further comprises:
acquiring a signal mean value of the original biological signal as a direct current offset component;
removing the DC bias signal included in the original bio-signal according to the DC bias component.
9. A biosignal marking device, comprising:
the signal mutation point identification module is used for identifying a target signal mutation point in an original biological signal by using a preset sliding window, wherein the preset sliding window is a sliding window with a first preset duration, and the target signal mutation point is a time point reflecting human body action state mutation in the original biological signal;
a biological signal extraction module, configured to extract a target biological signal from the original biological signal according to the target signal mutation point, where the target biological signal includes signal data generated in a process in which the living being performs a target action;
and the marking module is used for selecting label information and packaging the label information and the target biological signal in a data packet to obtain biological signal sample data.
10. An electronic device comprising the apparatus of claim 9, or comprising:
a memory for storing executable instructions;
a processor for performing the method according to any one of claims 1-8 under control of the executable computer program.
11. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program readable for execution by a computer, the computer program being adapted to perform the method according to any one of claims 1-8 when read by the computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111331759.4A CN114169361A (en) | 2021-11-11 | 2021-11-11 | Biological signal marking method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111331759.4A CN114169361A (en) | 2021-11-11 | 2021-11-11 | Biological signal marking method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114169361A true CN114169361A (en) | 2022-03-11 |
Family
ID=80478796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111331759.4A Pending CN114169361A (en) | 2021-11-11 | 2021-11-11 | Biological signal marking method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114169361A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102174706A (en) * | 2011-01-05 | 2011-09-07 | 刘文祥 | Semiconductor sequence body |
| CN110432885A (en) * | 2019-09-11 | 2019-11-12 | 东北大学 | A kind of photoplethysmographic noise remove method |
| CN111339545A (en) * | 2020-03-20 | 2020-06-26 | 苏州链原信息科技有限公司 | Method for generating data tag, electronic device and computer storage medium |
| CN111415644A (en) * | 2020-03-26 | 2020-07-14 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio comfort degree prediction method and device, server and storage medium |
| CN113505632A (en) * | 2021-05-12 | 2021-10-15 | 杭州回车电子科技有限公司 | Model training method, model training device, electronic device and storage medium |
-
2021
- 2021-11-11 CN CN202111331759.4A patent/CN114169361A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102174706A (en) * | 2011-01-05 | 2011-09-07 | 刘文祥 | Semiconductor sequence body |
| CN110432885A (en) * | 2019-09-11 | 2019-11-12 | 东北大学 | A kind of photoplethysmographic noise remove method |
| CN111339545A (en) * | 2020-03-20 | 2020-06-26 | 苏州链原信息科技有限公司 | Method for generating data tag, electronic device and computer storage medium |
| CN111415644A (en) * | 2020-03-26 | 2020-07-14 | 腾讯音乐娱乐科技（深圳）有限公司 | Audio comfort degree prediction method and device, server and storage medium |
| CN113505632A (en) * | 2021-05-12 | 2021-10-15 | 杭州回车电子科技有限公司 | Model training method, model training device, electronic device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| RUISHAN DU, ET AL: "Automatic mutation feature identification from well logging curves based on sliding t test algorthm", 《CLUSTER COMPUTING》, 15 March 2018 (2018-03-15), pages 14193 - 14200, XP036932770, DOI: 10.1007/s10586-018-2267-z * |
| 吴杰康，等: "基于独立分量分析的电力系统瞬时电压畸变信号判别方法", 《电网技术》, 31 March 2009 (2009-03-31), pages 1 - 8 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103903B (en) | Acoustic model training method and device based on artificial intelligence and storage medium | |
| Wu et al. | Modified multiscale entropy for short-term time series analysis | |
| US8490056B2 (en) | Automatic identification of subroutines from test scripts | |
| CN109063587B (en) | Data processing method, storage medium and electronic device | |
| CN104503593A (en) | Control information determination method and device | |
| KR101561464B1 (en) | Collected data sentiment analysis method and apparatus | |
| CN108090043B (en) | Error correction report processing method and device based on artificial intelligence and readable medium | |
| CN111511269A (en) | Decoding a person's visual attention from an electroencephalogram signal | |
| CN110245232B (en) | Text classification method, device, medium and computing equipment | |
| CN107273883B (en) | Decision tree model training method, and method and device for determining data attributes in OCR (optical character recognition) result | |
| Li et al. | Time series classification with discrete wavelet transformed data | |
| CN112270168A (en) | Dialogue emotion style prediction method and device, electronic equipment and storage medium | |
| CN114298050A (en) | Model training method, entity relation extraction method, device, medium and equipment | |
| CN112507090A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111145903A (en) | Method and device for acquiring vertigo inquiry text, electronic equipment and inquiry system | |
| CN109902582B (en) | Action classification method and device, storage medium and terminal equipment | |
| CN109101956B (en) | Method and apparatus for processing image | |
| CN110865721B (en) | Action data marking device, method and non-transitory computer readable storage medium | |
| CN114169361A (en) | Biological signal marking method, device, equipment and storage medium | |
| CN107894837A (en) | Dynamic sentiment analysis model sample processing method and processing device | |
| US9183649B2 (en) | Automatic tuning of value-series analysis tasks based on visual feedback | |
| CN110400560B (en) | Data processing method and device, storage medium and electronic device | |
| Zhou et al. | Threshold selection and adjustment for online segmentation of one-stroke finger gestures using single tri-axial accelerometer | |
| US20220207382A1 (en) | Apparatus and method for refining data and improving performance of behavior recognition model by reflecting time-series characteristics of behavior | |
| CN105139038A (en) | Electromyographic signal mode identification method |
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 |