Skin electric signal decomposition method and device, electronic equipment and storage medium
By identifying the extreme points unaffected by SCR in the skin electrical signal decomposition method, and fitting the skin electrical conductance level curve using cubic spline interpolation, the problem of unstable separation between skin electrical conductance response and level in the prior art is solved, achieving a highly efficient and accurate separation effect.
Patent Information
- Application Number
- CN202511173922.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-21
- Publication Date
- 2025-11-07
AI Technical Summary
Existing methods for separating skin conductance response (SCR) and skin conductance level (SCL) are computationally intensive, time-consuming, and unstable, and are prone to underestimation or overestimation.
Based on the original waveform curve of the EDA signal, the extreme points or near-extreme points that are not affected by the SCR response or whose influence is within a predetermined range are determined as target points. The skin conductance level backup curve is obtained by fitting the curve using cubic spline interpolation and then corrected to obtain the skin conductance response (SCR) component curve.
It achieves efficient and accurate separation of skin conductance response from skin conductance level, obtaining more accurate skin conductance level and response component curves, and reducing computational complexity.
Smart Images
Figure CN120899219A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of physiological signal processing, in particular to a skin electrical signal decomposition method. The present application also relates to a skin electrical signal decomposition device, an electronic device and a computer readable storage medium. BACKGROUND
[0002] The skin electrical activity (EDA) signal is an electrical manifestation of the sympathetic innervation of sweat glands. EDA can be used in psychophysiology (including emotional or cognitive stress) research and pathophysiological applications, such as assessing fatigue, pain, drowsiness, exercise recovery, diagnosis of epilepsy, neuropathy, depression, etc. The emergence of new EDA devices and applications has promoted the development of new signal processing techniques, creating more and more measurement methods derived from EDA mathematics. EDA not only contains information about slow changes (tension components) represented by the average value, but also contains information about rapid or episodic changes in the signal.
[0003] The envelope line is used to describe the skin electrical signal, and after the upper and lower boundaries of the skin electrical signal fluctuation are found, they are connected to form an envelope line; the EDA signal usually contains two signal estimation components: the baseline level corresponding to the normal state of skin conductivity and the skin conductivity response; in the EDA signal decomposition process, the skin conductivity response needs to be separated from the baseline level. The existing separation method has a large amount of calculation, takes a long time, and is sensitive to violations, causing unstable estimation components, for example, there may be underestimation of the skin conductivity level (SCL) and overestimation of the skin conductivity response (SCR).
[0004] Therefore, how to more accurately and efficiently separate the skin conductivity response from the skin conductivity level is a problem to be solved. SUMMARY
[0005] The present application provides a skin electrical signal decomposition method, a skin electrical signal decomposition device, an electronic device and a computer readable storage medium to solve the problem that the existing method cannot efficiently and accurately separate the skin conductivity response from the skin conductivity level.
[0006] In order to solve or partially solve the above technical problems, according to an aspect of the present application, a skin electrical signal decomposition method is provided, comprising: Based on the original waveform curve of the EDA signal, a target point for estimating the skin conductivity level is determined, the target point being an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR response or affected by the SCR response within a predetermined range; Based on the target point, a skin conductivity level standby curve is obtained by fitting; The skin conductance level (SCL) component curve is obtained by modifying the skin conductance level standby curve, and the skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0007] In an embodiment, based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined, including: obtaining a pre-processed EDA signal; determining a plurality of local minimum points of the original waveform curve of the EDA signal, and taking the plurality of local minimum points as candidate points for estimating the skin conductance level; screening the plurality of local minimum points to obtain the target point.
[0008] In an embodiment, screening the plurality of local minimum points to obtain the target point includes: taking any local minimum point in the plurality of local minimum points as a target local minimum point, determining a left local minimum point and a right local minimum point with an amplitude not less than the amplitude corresponding to the point, and obtaining a first distance between the point and the left local minimum point and a second distance between the point and the right local minimum point, respectively; if the first distance or the second distance is greater than a preset distance threshold, determining the target local minimum point as the target point.
[0009] In an embodiment, determining a plurality of local minimum points of the original waveform curve of the EDA signal includes: filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length to obtain a minimum signal amplitude; determining a plurality of points in the original waveform curve of the EDA signal with an amplitude of the minimum signal amplitude as the plurality of local minimum points.
[0010] In an embodiment, the obtaining a pre-processed EDA signal includes: performing noise reduction processing on the original waveform curve of the EDA signal to obtain the pre-processed EDA signal.
[0011] In an embodiment, based on the target point, a skin conductance level standby curve is fitted and obtained, including: filling a sequence composed of each of the target points according to a predetermined node distribution strategy to obtain a target sequence; adopting a cubic spline interpolation method to fit the points in the target sequence to obtain the skin conductance level standby curve.
[0012] In an embodiment, modifying the skin conductance level standby curve includes: The skin conductance level reserve curve is corrected by overshoot correction or undershoot correction.
[0013] In one embodiment, the method further comprises: separating a single skin conductance response (SCR) from a skin conductance response (SCR) component curve, and calculating a parameter feature of the single skin conductance response (SCR).
[0014] According to another aspect of the present application, there is provided a skin electrical signal decomposition apparatus, comprising: a target point selection unit configured to determine a target point for estimating a skin conductance level based on an original waveform curve of an EDA signal, the target point being an extreme point or an approximate extreme point on the original waveform curve which is not affected by or affected by a skin conductance response (SCR) within a predetermined range; a reserve curve obtaining unit configured to obtain a skin conductance level reserve curve based on the target point; a component curve obtaining unit configured to correct the skin conductance level reserve curve to obtain a skin conductance level (SCL) component curve, and to obtain a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve.
[0015] According to another aspect of the present application, there is also provided an electronic device comprising a processor and a memory; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the above method.
[0016] According to another aspect of the present application, there is also provided a computer readable storage medium having stored thereon one or more computer instructions, which are executed by a processor to implement the above method.
[0017] Compared with the prior art, the present application has the following advantages: The skin electrical signal decomposition method provided in the application comprises: determining a target point for estimating a skin conductance level based on an original waveform curve of an EDA signal, the target point being an extreme point or an approximate extreme point on the original waveform curve which is not affected by a SCR reaction or affected by the SCR reaction within a predetermined range; obtaining a skin conductance level standby curve based on the target point fitting; correcting the skin conductance level standby curve to obtain a skin conductance level (SCL) component curve, and obtaining a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve. In the method, the target point for estimating the skin conductance level is determined based on the original waveform curve of the EDA signal, and the target point is an extreme point or an approximate extreme point on the original waveform curve which is not affected by the SCR reaction or affected by the SCR reaction within a predetermined range. Therefore, the target point determined for estimating the skin conductance level matches the change of the skin conductance level (SCL) (the skin conductance level (SCL) of the EDA signal usually changes slowly), the skin conductance level standby curve obtained based on the target point fitting is more accurate, so that the finally obtained skin conductance level (SCL) component curve and the skin conductance response (SCR) component curve are more accurate, and the implementation process of the method is mainly based on the original waveform curve of the EDA signal, without the aid of a complex algorithm, so that the skin conductance response can be efficiently separated from the skin conductance level. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 is a flowchart of the skin electrical signal decomposition method provided in the application; Figure 2 is a unit block diagram of the skin electrical signal decomposition device provided in the application; Figure 3 is a logic structure schematic diagram of the electronic device provided in the application. DETAILED DESCRIPTION
[0019] In the following description, many specific details are set forth in order to provide a thorough understanding of the application. However, the application can be practiced without the specific details set forth in this description, in other manners consistent with the spirit of the application. Those skilled in the art can make similar modifications without departing from the spirit of the application, and therefore the application is not limited to the specific implementations disclosed below.
[0020] For the EDA signal decomposition process, in order to accurately and efficiently decompose the EDA signal, the application provides a skin electrical signal decomposition method, a skin electrical signal decomposition device corresponding to the method, an electronic device, and a computer readable storage medium. The embodiments provided below will be described in detail.
[0021] The first embodiment of the present application provides a skin electrical signal decomposition method, and the application subject of the method can be a computing device for performing EDA signal decomposition. Figure 1 The flowchart of the skin electrical signal decomposition method provided by the first embodiment of the present application is as follows Figure 1 The method provided by the present embodiment is described in detail. The embodiments described below are used to explain the principles of the method and are not limited in actual use.
[0022] As shown in Figure 1 The skin electrical signal decomposition method provided by the present embodiment includes the following steps: S101, determining a target point for estimating a skin conductance level (SCL) based on an original waveform curve of an EDA signal.
[0023] This step is used to determine a target point for estimating a skin conductance level according to an original waveform curve of an EDA signal. The skin conductance level (SCL) is used to represent the gradual level in the skin conductance, and the skin conductance response (SCR) is used to represent the instantaneous and rapid fluctuations in the skin conductance. The original waveform curve is used to represent the change of the conductivity with time, and the ordinate of each point on the original waveform curve is the conductivity, and the abscissa is the time. The target point refers to an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR response or is affected by the SCR response within a predetermined range.
[0024] In the present embodiment, the target point can be determined in the following manner: First, obtain a preprocessed EDA signal. Specifically, the original waveform curve of the EDA signal can be denoised by low-pass filtering to obtain the preprocessed EDA signal.
[0025] Secondly, determine a plurality of local minimum points of the original waveform curve of the EDA signal, and take the plurality of local minimum points as candidate points for estimating the skin conductance level. Specifically, a minimum signal amplitude can be obtained by filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length, and then a plurality of points with the minimum signal amplitude in the original waveform curve of the EDA signal are determined as a plurality of local minimum points.
[0026] Finally, the plurality of local minimum points are screened to obtain the target point. Specifically, any one of the plurality of local minimum points is taken as a target local minimum point, left and right local minimum points with amplitudes not less than the amplitude corresponding to the target local minimum point are determined, and a first distance between the target local minimum point and the left local minimum point and a second distance between the target local minimum point and the right local minimum point are obtained respectively (the distances are time intervals); if the first distance or the second distance is greater than a preset distance threshold, the target local minimum point is determined as the target point. For example, the first distance is L1, the second distance is L2, and the preset distance threshold is T1; if L1 or L2 is greater than the threshold T1, the target local minimum point is determined as the target point.
[0027] In S102, a skin conductance level standby curve is obtained based on the target point.
[0028] After the target point used for estimating the skin conductance level (SCL) is determined in the above step, the skin conductance level standby curve is obtained based on the target point in this step.
[0029] Specifically, the sequence composed of the target points can be filled according to a predetermined node distribution strategy to obtain a target sequence. For example, the sequence composed of the target points is filled with a time scale T1 as a threshold to ensure that the maximum distance between adjacent points in the sequence is not greater than T1. If the length between adjacent target points is less than or equal to T1, a new value does not need to be inserted between the two points. If the length between the adjacent two target points is greater than T1, a new value is inserted at a position in the original waveform curve of the EDA signal where the slope between the adjacent target points is closest to 0. The points in the target sequence are fitted by using a cubic spline interpolation method to obtain the skin conductance level standby curve. The cubic spline interpolation method constructs a smooth function through a piecewise cubic polynomial. The function can fit a smooth curve with the same length as the original waveform curve through all given nodes, which is taken as the skin conductance level standby curve.
[0030] In S103, the skin conductance level standby curve is corrected to obtain a skin conductance level (SCL) component curve, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0031] After the skin conductance level standby curve is obtained in the above step, the skin conductance level standby curve is corrected to obtain a skin conductance level (SCL) component curve in this step, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0032] In the embodiment, the correction of the skin conductance level standby curve can be specifically as follows: using an existing envelope correction method (for example, the MPCI method) to correct the skin conductance level standby curve in terms of overshoot or undershoot, for example, searching for an overshoot part of the skin conductance level standby curve and removing the part so that the fitting curve is as close as possible to the original signal.
[0033] In the embodiment, the skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve by directly subtracting the amplitudes of the two curves, for example, the sequence of the conductance rate changing with time in the original waveform curve is [1 2 2 2 1], the sequence of the conductance rate changing with time in the SCL component curve is [0 0 0 0 0], and the subtraction of the two sequences results in [1 2 2 2 1] which is the SCR component.
[0034] In the embodiment, a single skin conductance response (SCR) can also be separated from the SCR component curve, and the parameter characteristics of the single skin conductance response (SCR) are calculated. For example, the single SCR is separated from the SCR component by using an orthogonal matching pursuit method, and the position, amplitude, duration, area and other parameter characteristics of each SCR are calculated.
[0035] The skin electrical signal decomposition method provided in the embodiment includes the following steps: determining a target point for estimating the skin conductance level based on an original waveform curve of an EDA signal, the target point being an extreme point or an approximate extreme point on the original waveform curve which is not affected by the SCR response or affected by the SCR response within a predetermined range; fitting the target point to obtain a skin conductance level standby curve; correcting the skin conductance level standby curve to obtain a skin conductance level (SCL) component curve, and obtaining a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve. In the method, the target point for estimating the skin conductance level is determined based on the original waveform curve of the EDA signal, and the target point is an extreme point or an approximate extreme point on the original waveform curve which is not affected by the SCR response or affected by the SCR response within a predetermined range. Therefore, the determined target point for estimating the skin conductance level matches the change of the skin conductance level (SCL) (the skin conductance level (SCL) of the EDA signal usually changes slowly), the skin conductance level standby curve obtained by fitting the target point is more accurate, so that the finally obtained skin conductance level (SCL) component curve and the skin conductance response (SCR) component curve are more accurate, and the implementation process of the method is mainly based on the original waveform curve of the EDA signal without the aid of complex algorithms, so that the skin conductance response can be efficiently separated from the skin conductance level.
[0036] The above embodiment provides a skin electrical signal decomposition method. Correspondingly, another embodiment of the present application also provides a skin electrical signal decomposition device. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple. For details of the related technical features, please refer to the corresponding description of the above method embodiment. The following description of the device embodiment is only illustrative.
[0037] For reference Figure 2 To understand this embodiment, Figure 2 The unit block diagram of the skin electrical signal decomposition device provided in this embodiment is shown in Figure 2 The skin electrical signal decomposition device provided in this embodiment includes: A target point selection unit 201 is configured to determine a target point for estimating skin conductance level based on an original waveform curve of an EDA signal, wherein the target point refers to an extreme point or an approximate extreme point on the original waveform curve which is not affected by SCR reaction or affected by SCR reaction within a predetermined range. A backup curve obtaining unit 202 is configured to obtain a skin conductance level backup curve based on the target point. A component curve obtaining unit 203 is configured to correct the skin conductance level backup curve to obtain a skin conductance level (SCL) component curve, and obtain a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve.
[0038] Determine a target point for estimating skin conductance level based on an original waveform curve of an EDA signal, wherein the target point refers to an extreme point or an approximate extreme point on the original waveform curve which is not affected by SCR reaction or affected by SCR reaction within a predetermined range. Obtain a skin conductance level backup curve based on the target point. Correct the skin conductance level backup curve to obtain a skin conductance level (SCL) component curve, and obtain a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve.
[0039] In an embodiment, determining a target point for estimating skin conductance level based on an original waveform curve of an EDA signal includes: Obtain a preprocessed EDA signal. Determine a plurality of local minimum points of the original waveform curve of the EDA signal, and take the plurality of local minimum points as candidate points for estimating skin conductance level. Screen the plurality of local minimum points to obtain the target point.
[0040] In an embodiment, the target point is obtained by screening the plurality of local minimum points, comprising: taking any local minimum point in the plurality of local minimum points as a target local minimum point, determining a left local minimum point and a right local minimum point with an amplitude no less than that of the target local minimum point, and obtaining a first distance between the target local minimum point and the left local minimum point and a second distance between the target local minimum point and the right local minimum point, respectively; if the first distance or the second distance is greater than a preset distance threshold, determining the target local minimum point as the target point.
[0041] In an embodiment, the plurality of local minimum points of the original waveform curve of the EDA signal are determined, comprising: filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length to obtain a minimum signal amplitude; determining a plurality of points in the original waveform curve of the EDA signal with the minimum signal amplitude as the plurality of local minimum points.
[0042] In an embodiment, the pre-processed EDA signal is obtained, comprising: performing noise reduction processing on the original waveform curve of the EDA signal to obtain the pre-processed EDA signal.
[0043] In an embodiment, the skin conductance level standby curve is obtained based on the target point, comprising: filling the sequence composed of the target points according to a predetermined node distribution strategy to obtain a target sequence; fitting the points in the target sequence using a cubic spline interpolation method to obtain the skin conductance level standby curve.
[0044] In an embodiment, the skin conductance level standby curve is corrected, comprising: using the MPCI method to correct the overshoot of the skin conductance level standby curve.
[0045] In an embodiment, the method further comprises: separating a single skin conductance response (SCR) from a skin conductance response (SCR) component curve, and calculating and obtaining a parameter feature of the single skin conductance response (SCR).
[0046] In the above embodiment, a skin electrical signal decomposition method and a skin electrical signal decomposition device are provided. In addition, another embodiment of the present application provides an electronic device. Since the electronic device embodiment is basically similar to the method embodiment, the description is relatively simple. For details of the related technical features, please refer to the corresponding description of the above-provided method embodiment. The following description of the electronic device embodiment is only illustrative. The electronic device embodiment provided by the present application comprises the following: For reference Figure 3 To understand the present embodiment, Figure 3 The schematic diagram of the electronic device provided by the present embodiment is shown in the following figure.
[0047] As Figure 3 shown, the electronic device provided by the present embodiment comprises a processor 301 and a memory 302. The memory 302 is used to store computer instructions for data processing. When the computer instructions are read and executed by the processor 301, the following operations are performed: Based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined. The target point refers to an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR reaction or affected by the SCR reaction within a predetermined range. Based on the target point, a skin conductance level backup curve is obtained by fitting. The skin conductance level backup curve is corrected to obtain a skin conductance level (SCL) component curve, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0048] Based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined. The target point refers to an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR reaction or affected by the SCR reaction within a predetermined range. Based on the target point, a skin conductance level backup curve is obtained by fitting. The skin conductance level backup curve is corrected to obtain a skin conductance level (SCL) component curve, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0049] In an embodiment, based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined, comprising: Obtaining a pre-processed EDA signal; Determining a plurality of local minimum points of the original waveform curve of the EDA signal, and taking the plurality of local minimum points as candidate points for estimating the skin conductance level. Screening the plurality of local minimum points to obtain the target point.
[0050] In an embodiment, the screening the plurality of local minimum points to obtain the target point comprises: Taking any local minimum point in the plurality of local minimum points as a target local minimum point, determining a left local minimum point and a right local minimum point with an amplitude not less than the amplitude corresponding to the target local minimum point, and obtaining a first distance between the target local minimum point and the left local minimum point and a second distance between the target local minimum point and the right local minimum point, respectively. If the first distance or the second distance is greater than a preset distance threshold, the target local minimum point is determined as the target point.
[0051] In an embodiment, the determining the plurality of local minimum points of the original waveform curve of the EDA signal comprises: Filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length to obtain a minimum signal amplitude. Determining a plurality of points with the minimum signal amplitude in the original waveform curve of the EDA signal as the plurality of local minimum points.
[0052] In an embodiment, the obtaining the preprocessed EDA signal comprises: Performing noise reduction processing on the original waveform curve of the EDA signal to obtain the preprocessed EDA signal.
[0053] In an embodiment, the fitting the target point to obtain a skin conductance level standby curve comprises: Filling a sequence composed of the target points according to a predetermined node distribution strategy to obtain a target sequence. Fitting the points in the target sequence using a cubic spline interpolation method to obtain the skin conductance level standby curve.
[0054] In an embodiment, the correcting the skin conductance level standby curve comprises: Using an MPCI method to correct the overshoot of the skin conductance level standby curve.
[0055] In an embodiment, the method further comprises: separating a single skin conductance response (SCR) from a skin conductance response (SCR) component curve, and calculating and obtaining a parameter feature of the single skin conductance response (SCR).
[0056] In the above embodiments, a skin electrical signal decomposition method, a skin electrical signal decomposition device, and an electronic device are provided. In addition, another embodiment of the present application provides a computer readable storage medium for implementing the above skin electrical signal decomposition method. The computer readable storage medium embodiment provided by the present application is described simply. For related parts, please refer to the corresponding description of the above method embodiments. The following described embodiments are only illustrative.
[0057] The computer readable storage medium provided by the embodiment has computer instructions stored thereon, and the instructions are executed by a processor to implement the following steps: Based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined, the target point being an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR reaction or affected by the SCR reaction within a predetermined range; Based on the target point, a skin conductance level backup curve is fitted; The skin conductance level backup curve is corrected to obtain a skin conductance level (SCL) component curve, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0058] Based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined, the target point being an extreme point or an approximate extreme point on the original waveform curve that is not affected by the SCR reaction or affected by the SCR reaction within a predetermined range; Based on the target point, a skin conductance level backup curve is fitted; The skin conductance level backup curve is corrected to obtain a skin conductance level (SCL) component curve, and a skin conductance response (SCR) component curve is obtained based on the original waveform curve and the skin conductance level (SCL) component curve.
[0059] In an embodiment, based on the original waveform curve of the EDA signal, a target point for estimating the skin conductance level is determined, comprising: Obtaining a preprocessed EDA signal; Determining a plurality of local minimum points of the original waveform curve of the EDA signal, and taking the plurality of local minimum points as candidate points for estimating the skin conductance level; Screening the plurality of local minimum points to obtain the target point.
[0060] In an embodiment, screening the plurality of local minimum points to obtain the target point comprises: determining a left-side local minimum point and a right-side local minimum point with an amplitude no less than the amplitude corresponding to the target local minimum point, and obtaining a first distance between the target local minimum point and the left-side local minimum point and a second distance between the target local minimum point and the right-side local minimum point, respectively; determining the target local minimum point as the target point if the first distance or the second distance is greater than a preset distance threshold.
[0061] In an embodiment, the method further includes determining a plurality of local minimum points of the original waveform curve of the EDA signal, including: filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length to obtain a minimum signal amplitude; determining a plurality of points in the original waveform curve of the EDA signal with an amplitude of the minimum signal amplitude as the plurality of local minimum points.
[0062] In an embodiment, the method further includes obtaining the preprocessed EDA signal, including: performing noise reduction processing on the original waveform curve of the EDA signal to obtain the preprocessed EDA signal.
[0063] In an embodiment, the method further includes fitting the target points to obtain a skin conductance level standby curve, including: filling the sequence composed of the target points according to a predetermined node distribution strategy to obtain a target sequence; fitting the points in the target sequence using a cubic spline interpolation method to obtain the skin conductance level standby curve.
[0064] In an embodiment, the method further includes correcting the skin conductance level standby curve, including: correcting the skin conductance level standby curve for overshoot using an MPCI method.
[0065] In an embodiment, the method further includes separating a single skin conductance response (SCR) from a skin conductance response (SCR) component curve and calculating a parameter feature of the single skin conductance response (SCR).
[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0067] The memory can include non-persistent memory in the computer readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer readable media.
[0068] 1. Computer-readable media includes permanent and non-permanent, removable and non-removable media can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only compact discs read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition in this paper, computer-readable media does not include non-transitory computer-readable media (transitory media), such as modulated data signals and carriers.
[0069] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as a method, system or computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0070] Although the present application is disclosed with reference to the preferred embodiments above, it is not intended to limit the present application, and any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application should be defined by the scope defined by the claims of the present application.
Claims
1. A method of skin electrical signal decomposition, characterized by, The method comprises: determining a target point for estimating skin conductance level based on an original waveform curve of an EDA signal, the target point being a local extreme point or a similar local extreme point on the original waveform curve that is not affected by or is affected within a predetermined range by a SCR reaction; fitting a skin conductance level backup curve based on the target point; correcting the skin conductance level backup curve to obtain a skin conductance level (SCL) component curve, and obtaining a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve.
2. The method of claim 1, wherein, The method comprises: obtaining a preprocessed EDA signal; determining a plurality of local minimum points of an original waveform curve of the EDA signal, and taking the plurality of local minimum points as candidate points for estimating skin conductance level; screening the plurality of local minimum points to obtain the target point.
3. The method of claim 2, wherein, The method comprises: taking any local minimum point in the plurality of local minimum points as a target local minimum point, determining a left local minimum point and a right local minimum point with an amplitude not less than that of the target local minimum point, and obtaining a first distance between the target local minimum point and the left local minimum point and a second distance between the target local minimum point and the right local minimum point; if the first distance or the second distance is greater than a preset distance threshold, determining the target local minimum point as the target point.
4. The method of claim 2, wherein, The method comprises: filtering the original waveform curve of the EDA signal using a minimum value filter with a preset window length to obtain a minimum signal amplitude; determining a plurality of points with the minimum signal amplitude in the original waveform curve of the EDA signal as the plurality of local minimum points.
5. The method of claim 2, wherein, The method comprises: performing noise reduction processing on the original waveform curve of the EDA signal to obtain the preprocessed EDA signal.
6. The method of claim 1, wherein, The method comprises: filling a sequence composed of the target points according to a predetermined node distribution strategy to obtain a target sequence; fitting the points in the target sequence using a cubic spline interpolation method to obtain the skin conductance level backup curve.
7. The method of claim 1, wherein, The method comprises: performing overshoot correction or undershoot correction on the skin conductance level backup curve.
8. The method of claim 1, wherein, The method further comprises: separating a single skin conductance response (SCR) from the skin conductance response (SCR) component curve, and calculating a parameter feature of the single skin conductance response (SCR).
9. A skin electrical signal resolving apparatus, characterized by, The device comprises: a target point selection unit configured to determine a target point for estimating skin conductance level based on an original waveform curve of an EDA signal, the target point being a local extreme point or a similar local extreme point on the original waveform curve that is not affected by or is affected within a predetermined range by a SCR reaction; a backup curve obtaining unit configured to fit a skin conductance level backup curve based on the target point; and a correction unit configured to correct the skin conductance level backup curve to obtain a skin conductance level (SCL) component curve, and obtain a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve. A component curve obtaining unit is configured to correct the skin conductance level baseline curve, obtain a skin conductance level (SCL) component curve, and obtain a skin conductance response (SCR) component curve based on the original waveform curve and the skin conductance level (SCL) component curve.
10. An electronic device, comprising: comprising a processor and a memory; wherein The memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1-8.
11. A computer readable storage medium having stored thereon one or more computer instructions, wherein, The instructions are executed by the processor to implement the method according to any one of claims 1-8.