Bracelet fitting detection method based on PPG signal
By performing sliding window detection and weighting processing on the bracelet PPG signal, the problem of difficulty in determining the wearable state in the prior art is solved, and high-accurate wearable state detection and power saving are achieved.
Patent Information
- Application Number
- CN202411236657.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The prior art is difficult to effectively determine the wearable state of the bracelet through the sensor of the wearable device itself, which affects the accuracy of PPG signal acquisition and the saving of equipment power.
Using a bracelet fit detection method based on PPG signal, the three-channel data is obtained, sliding window detection, derivation, and difference are calculated, and the fluctuation value is determined based on the weighted probability value and the preset threshold value to distinguish between loose and tight wear Posting the situation.
It realizes the effective distinction between loose wear and tight fit through changes in PPG signal waveform, improves detection accuracy and saves equipment power.
Smart Images

Figure CN119033353A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a bracelet fit detection method based on PPG signals. Background Art
[0002] Wearable devices represented by smart bracelets have entered people's lives and are used to track people's daily activities, sleep conditions, and eating habits. Usually, wearable devices detect the user's real-time or periodic data on the user's health, exercise, and other data to understand the user's physical condition. By detecting PPG data through photoelectric sensors, the data can be analyzed to obtain some physiological parameter signals of the human body, such as heart rate, blood oxygen saturation, etc. If the bracelet is not worn tightly, it will increase the noise of the collected PPG signal and affect the accuracy of the calculation of physiological signals. The bracelet can also stop collecting signals based on the judgment results to save device power.
[0003] The mainstream technology used in wearable bracelets on the market is the photoplethysmography (PPG) method. The principle is to use the light absorption ability of different tissues of the human body to obtain blood flow information and then obtain some physiological information of the human body. It is mainly divided into transmission type and reflection type. Due to the convenience of structural design, the same-side reflection type is generally used.
[0004] How to use the wearable device's own sensors to determine the wearing status is an urgent problem to be solved. Summary of the invention
[0005] In view of the problems existing in the prior art, the present invention provides a bracelet fit detection method based on PPG signals.
[0006] The technical solution adopted by the present invention is: a bracelet fit detection method based on PPG signal, comprising the following steps: Step 1: Get the PPG signal from the wristband; Step 2: Perform fluctuation detection on the three-channel data of the PPG signal respectively to obtain the fluctuation statistics within a fixed period; Step 3: Weight the statistical results obtained in step 2 to obtain the volatility probability value; Step 4: Obtain the required judgment result according to the fluctuation probability value obtained in step 3 and the preset threshold.
[0007] Furthermore, the fluctuation detection process in step 2 is as follows: The sliding window is used for detection to obtain the data change sequence; Derivative the data change sequence to obtain the data change situation sequence; The data fluctuation value is obtained by taking the difference of the data change sequence; The data fluctuation value is compared with the fluctuation threshold. If it is within the threshold, it is determined to be a fluctuation.
[0008] Furthermore, in step 4, the fluctuation probability value is compared with a preset threshold value. If it is within the preset threshold value, it is determined to be a close fit; if it exceeds the threshold value, it is determined to be loose.
[0009] Furthermore, the weighting process in step 3 is as follows:
[0010] in, Y is the weighted result value, A , B , C are the weighted values corresponding to the red light signal, infrared light signal and green light signal respectively; RED is the fluctuation statistics of the red light signal within a fixed period; IRED is the statistical result of the fluctuation of the near-infrared light signal within a fixed period, GREEN It is the statistical result of the fluctuation of green light in a fixed period.
[0011] Furthermore, the fluctuation threshold determination method is as follows:
[0012] in, is the fluctuation threshold, K 1 , K 2 and K 3 is the difference range when fluctuation occurs under different wearing conditions, a is the preset coefficient value.
[0013] Furthermore, the calculation method of the difference range when fluctuations occur in different wearing states is as follows:
[0014]
[0015]
[0016] in, V 1 , V 2 , V 3 They are the output values in static and close wearing, slipping, and slightly loose wearing without slipping. in, , ,
[0017] in, d1 , d 2 , d 3 They are the PPG sensor output values in the corresponding states respectively; N is the total number of outputs.
[0018] Furthermore, the weighted values corresponding to the red light signal, the infrared light signal and the green light signal are calculated as follows:
[0019] in, M is the corresponding weighted value, j =1 A , j =2 B , j =3 C , is the signal-to-noise ratio of a single-channel signal, is the sum of the signal-to-noise ratios of the three signals, λ j is the wavelength, N j is the total number of data points for each signal, is the sampling rate of a single-channel signal, b is the proportionality coefficient, is the spectral volume pulse wave amplitude.
[0020] Furthermore, the spectrum volume pulse wave amplitude calculation method is as follows:
[0021] in, is the total reflection coefficient corresponding to the wavelength in the diastolic state, is the total reflection coefficient corresponding to the wavelength in the contracted state.
[0022] The beneficial effects of the present invention are: (1) The method of the present invention can effectively distinguish between loose and tight wearing of PPG devices through changes in PPG signal waveforms; (2) The method of the present invention has been tested and has a high accuracy rate. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 It is a schematic diagram of the process of the present invention.
[0024] Figure 2 It is a schematic diagram of the fluctuation detection process in the present invention.
[0025] Figure 3 These are the PPG three-channel signal images collected under different wearing conditions, a is red light, b is infrared light, and c is green light.
[0026] Figure 4 For Figure 3 The three-axis signal diagram collected under the same conditions, a is the X-axis, b is the Y-axis, and c is the Z-axis.
[0027] Figure 5 This is a diagram showing an example of fluctuation detection in an embodiment of the present invention.
[0028] Figure 6 Schematic diagram of the relationship between the spectral volume pulse wave amplitude and wavelength in an embodiment of the present invention, a is the change of the total reflection coefficient corresponding to the wavelength in the diastolic state with the wavelength, and b is the spectral volume pulse wave amplitude value.
[0029] Figure 7 Schematic diagram of test accuracy statistics results in an embodiment of the present invention. DETAILED DESCRIPTION
[0030] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0031] like Figure 1 As shown, a bracelet fit detection method based on PPG signal includes the following steps: Step 1: Get the PPG signal from the wristband; The collected PPG signal is three-channel data (Red, IRed, Green) with a sampling rate of 50 Hz. The length of the sliding window varies according to the sampling rate, and each channel will judge the signal fluctuation during the Tjudge period.
[0032] Step 2: Perform fluctuation detection on the three-channel data of the PPG signal respectively to obtain the fluctuation statistics within a fixed period; Fluctuation detection methods such as Figure 2 As shown, The sliding window is used for detection to obtain the data change sequence; Derivative the data change sequence to obtain the data change situation sequence; The data fluctuation value is obtained by taking the difference of the data change sequence; The data fluctuation value is compared with a preset threshold and if it is within the threshold, it is determined to be a fluctuation.
[0033] The fluctuation threshold is determined as follows:
[0034] in, is the fluctuation threshold, K 1 , K 2 and K 3is the difference range when fluctuation occurs under different wearing conditions, a is the preset coefficient value.
[0035] The calculation method for the difference range when fluctuations occur under different wearing conditions is as follows:
[0036]
[0037]
[0038] in, V 1 , V 2 , V 3 They are the output values in static and close wearing, slipping, and slightly loose wearing without slipping. in, , ,
[0039] in, d 1 , d 2 , d 3 They are the PPG sensor output values in the corresponding states respectively; N is the total number of outputs.
[0040] Step 3: Weight the statistical results obtained in step 2 to obtain the volatility probability value; The weighting process is as follows:
[0041] in, Y is the weighted result value, A , B , C are the weighted values corresponding to the red light signal, infrared light signal and green light signal respectively; RED is the fluctuation statistics of the red light signal within a fixed period; IRED is the statistical result of the fluctuation of the near-infrared light signal within a fixed period, GREEN It is the statistical result of the fluctuation of green light in a fixed period.
[0042] The weighted values corresponding to the red light signal, infrared light signal, and green light signal are calculated as follows:
[0043] in, M is the corresponding weighted value, j =1A , j =2 B , j =3 C , is the signal-to-noise ratio of a single-channel signal, is the sum of the signal-to-noise ratios of the three signals, λ j is the wavelength, N j is the total number of data points for each signal, is the sampling rate of a single-channel signal, b is the proportionality coefficient, is the spectral volume pulse wave amplitude.
[0044] The spectral volume pulse wave amplitude is calculated as follows:
[0045] in, is the total reflection coefficient corresponding to the wavelength in the diastolic state, is the total reflection coefficient corresponding to the wavelength in the contracted state.
[0046] Step 4: Obtain the required judgment result according to the fluctuation probability value obtained in step 3 and the preset threshold.
[0047] The fluctuation probability value is compared with a preset threshold. If it is within the preset threshold, it is determined to be a close fit. If it exceeds the threshold, it is determined to be loose.
[0048] Example The present invention will be further described below in conjunction with specific embodiments.
[0049] A bracelet fit detection method based on PPG signals comprises the following steps: Step 1: Get the PPG signal from the wristband; The collected PPG signal is three-channel data (Red, IRed, Green) with a sampling rate of 50 Hz. The length of the sliding window varies according to the sampling rate, and each channel will judge the signal fluctuation during the Tjudge period.
[0050] Currently, PPG sensors and triaxial accelerometers are usually used to collect corresponding signals. Figure 3 and Figure 4 The collected PPG three-channel signal and three-axis signal diagram are given. Figure 4 It can be seen from the bc box that the waveform changes of the three-axis accelerometer when worn loosely and tightly are consistent in some cases, and the tightness of the wear cannot be judged by the sudden change of the waveform of the three-axis accelerometer. Figure 3The PPG waveform shows obvious waveform differences in different wearing scenarios, so the PPG signal is used as the data source.
[0051] Step 2: Perform fluctuation detection on the three-channel data of the PPG signal respectively to obtain the fluctuation statistics within a fixed period; In this embodiment, the fluctuation detection example is as follows Figure 5 As shown: Use sliding window to detect and get the data change sequence; Confirm the sliding window data length: According to the change frequency of the signal actually collected by the designed wristband device and the sudden change of tightness during the actual use of the wristband, the sampling rate of the device used is 50 Hz, and the time corresponding to one data value is 20 ms, so five data correspond to 100 ms. Therefore, the length of each signal update interval data is 5, and the length of the selected sliding window is 3.
[0052] The buffer is updated once every five data are full, and the five data in the buffer array are slid three times, and the data change of the window length of 3 is obtained each time, and finally the sequence { y 1 , y 2 , y 3}, the number of criteria for judging whether the data set fluctuates changes from 5 to 3.
[0053] Derivative the data change sequence to obtain the data change situation sequence; For the sequence { y 1 , y 2 , y 3} Take the first-order derivative and get the change sequence { y 1 , y 2 , y 3}Data changes of { z 1 , z 2},in z 1 Represents the data changes from Window 1 to Window 2. z 2 Represents the data change from Window 2 to Window 3. At this time, the number of criteria for determining whether the data window data has changed is changed from 3 to 2.
[0054] The data fluctuation value is obtained by taking the difference of the data change sequence; right{ z 1 , z 2} to find the difference. When the difference is greater than a certain threshold, we can conclude that these five data have undergone data fluctuations corresponding to the situation where the bracelet is worn loosely.
[0055] The data fluctuation value is compared with the preset threshold. If it is within the threshold, it is judged as fluctuation. If it is fluctuation, the output record is 1, and if it is not fluctuation, the output is 0; the output result is as follows.
[0056] Red: {0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,…………} IRed: {0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1,…………} Green: {1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1,…………} The total number of single-channel outputs is N The fluctuation threshold is determined as follows:
[0057] in, is the fluctuation threshold, K 1 , K 2 and K 3 is the difference range when fluctuation occurs under different wearing conditions, a is the preset coefficient value. In this embodiment, 7 / 50 is taken. This value is based on the degree of change of the waveform combined with K 1 , K 2 and K 3 Comprehensive judgment is obtained.
[0058] The calculation method for the difference range when fluctuations occur under different wearing conditions is as follows:
[0059]
[0060]
[0061] in, V 1 , V 2 , V 3They are the output values in the states of static close wearing, sliding, and slightly loose wearing but no sliding; the above three values are the PPG output values obtained by obviously close wearing, sliding, and slight sliding detection.
[0062] in, , ,
[0063] in, d 1 , d 2 , d 3 They are the PPG sensor output values in the corresponding states respectively; N is the total number of outputs.
[0064] Step 3: Weight the statistical results obtained in step 2 to obtain the volatility probability value; The weighting process is as follows:
[0065] in, Y is the weighted result value, A , B , C are the weighted values corresponding to the red light signal, infrared light signal and green light signal respectively; RED is the fluctuation statistics of the red light signal within a fixed period; IRED is the statistical result of the fluctuation of the near-infrared light signal within a fixed period, GREEN It is the statistical result of the fluctuation of green light in a fixed period.
[0066] in , , ; n 1 , n 2 , n 3 are the number of fluctuations counted in step 2 for red light, infrared light and green light respectively.
[0067] The weighted values corresponding to the red light signal, infrared light signal, and green light signal are calculated as follows:
[0068] in, M is the corresponding weighted value, j =1 A , j =2 B , j =3 C, is the signal-to-noise ratio of a single-channel signal, is the sum of the signal-to-noise ratios of the three signals, λ j is the wavelength, N j is the total number of data points for each signal, is the sampling rate of a single-channel signal, b is the proportionality coefficient, is the spectral volume pulse wave amplitude, the curve is as follows Figure 6 As shown in b.
[0069] The spectral volume pulse wave amplitude is calculated as follows:
[0070] in, is the total reflection coefficient corresponding to the wavelength in the diastolic state, and its curve is as follows Figure 6 As shown in a, is the total reflection coefficient corresponding to the wavelength in the contracted state.
[0071] Step 4: Obtain the required judgment result according to the fluctuation probability value obtained in step 3 and the preset threshold.
[0072] The fluctuation probability value is compared with a preset threshold. If it is within the preset threshold, it is judged as a tight fit. If it exceeds the threshold, it is judged as a loose fit. For example, in this embodiment, the preset threshold is 50%. If it exceeds 50%, it is judged as a loose fit. Otherwise, it is judged as a tight fit.
[0073] To illustrate the effect of the method of the present invention, five volunteers of different genders and different wrist circumferences were tested by swinging their arms forward and backward and quickly turning their wrists 90 degrees to simulate sports scenes according to the steps of the method of the present invention. Among them, 100 tests under the condition of tight wearing were all judged accurately, with an accuracy rate of 100%; under the condition of loose wearing, the five students made a total of 1 misjudgment, that is, the accuracy rate of 100 loose wearing tests was 99%. The statistical results are as follows Figure 7 shown.
[0074] The three-channel signal obtained by PPG extraction, although the existing bracelet devices all use PPG signals, they only use the physiological information represented by it, and do not use the fluctuation of the signal itself for further processing. The method of the present invention can accurately judge the wearing condition of the bracelet device by processing the three-channel signal, and the accuracy is high.
Claims
1. A wristband fit detection method based on PPG signal, It is characterized in that The following steps are involved: Step 1: Get the PPG signal from the wristband; Step 2: Perform fluctuation detection on the three-channel data of the PPG signal respectively to obtain the fluctuation statistics within a fixed period; Step 3: Weight the statistical results obtained in step 2 to obtain the volatility probability value; Step 4: Obtain the required judgment result according to the fluctuation probability value obtained in step 3 and the preset threshold.
2. According to claim 1, a wristband fit detection method based on PPG signal, It is characterized in that The fluctuation detection process in step 2 is as follows: The sliding window is used for detection to obtain the data change sequence; Derivative the data change sequence to obtain the data change situation sequence; The data fluctuation value is obtained by taking the difference of the data change sequence; The data fluctuation value is compared with the fluctuation threshold. If it is within the threshold, it is determined to be a fluctuation.
3. According to the method for detecting the fit of a wristband based on a PPG signal according to claim 1, It is characterized in that In step 4, the fluctuation probability value is compared with a preset threshold. If it is within the preset threshold, it is determined to be a close fit. If it exceeds the threshold, it is determined to be loose.
4. According to claim 1, a wristband fit detection method based on PPG signal, It is characterized in that The weighting process in step 3 is as follows: in, Y is the weighted result value, A , B , C are the weighted values corresponding to the red light signal, infrared light signal and green light signal respectively; RED is the fluctuation statistical result of the red light signal within a fixed period; IRED is the statistical result of the fluctuation of the near-infrared light signal within a fixed period, GREEN It is the statistical result of the fluctuation of green light in a fixed period.
5. The wristband fit detection method based on PPG signal according to claim 2, It is characterized in that The fluctuation threshold determination method is as follows: in, is the fluctuation threshold, K 1 , K 2 and K 3 is the difference range when fluctuation occurs under different wearing conditions, a is the preset coefficient value.
6. A wristband fit detection method based on PPG signal according to claim 5, It is characterized in that The calculation method of the difference range when fluctuations occur in different wearing states is as follows: in, V 1 , V 2 , V 3 They are the output values in static and close wearing, slipping, and slightly loose wearing without slipping. in, , , in, d 1 , d 2 , d 3 They are the PPG sensor output values in the corresponding states respectively; N is the total number of outputs.
7. The wristband fit detection method based on PPG signal according to claim 4, It is characterized in that The weighted values corresponding to the red light signal, infrared light signal and green light signal are calculated as follows: in, M is the corresponding weighted value, j =1 A , j =2 B , j =3 C , is the signal-to-noise ratio of a single-channel signal, is the sum of the signal-to-noise ratios of the three signals, λ is the wavelength, N j is the total number of data points for each signal, is the sampling rate of a single-channel signal, b is the proportionality coefficient, is the spectral volume pulse wave amplitude.
8. A wristband fit detection method based on PPG signals according to claim 7, It is characterized in that The spectrum volume pulse wave amplitude calculation method is as follows: in, is the total reflection coefficient corresponding to the wavelength in the diastolic state, is the total reflection coefficient corresponding to the wavelength in the contracted state.
Citation Information
Patent Citations
Method and device for generating photoplethysmography signal
CN111297339A
Method and device for generating photoplethysmography signal
CN111297347A
Method for analyzing regularity evaluation information, monitoring device and monitoring system
CN114040705A
Heart rate variability detection method based on smart phone camera
CN114052690A
Blood oxygen detection device based on green light, blood oxygen detection method thereof and medium
CN114073520A
