Heart rate and oxygen saturation measurement device based on deep learning
A technology of measurement equipment and deep learning network, applied in the field of heart rate and blood oxygen saturation measurement equipment, can solve the problem of inaccurate measurement results, and achieve the effect of speeding up calculation speed, good tolerance, and improving accuracy
Active Publication Date: 2021-03-02
天津惊帆科技有限公司
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the influence of factors such as the skin color of the measurement site, temperature, fat and thin, and ambient light, the collected PPG signal often has a lot of noise, resulting in inaccurate measurement results
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The heart rate and blood oxygen saturation measurement device proposed by the present invention includes a PPG signal processing unit, which contains a deep learning network model, and the heart rate and blood oxygen saturation are predicted by means of the deep learning network model, such as Figure 1 to Figure 3 As shown, the deep learning network model adopts a multi-task learning method, that is, the two prediction tasks share the convolutional layer, and use different fully connected layers for the final prediction. The model structure is a sequentially connected five-layer convolutional neural network layer. , there is a gated linear unit between the convolutional neural network layers, and the formula of the gated linear unit is as follows:
[0031] H=A*sigmoid(B)
[0032] Where H is the output, and A and B are half the number of channels of the input. The form of multiplication is point-by-point multiplication. Using such a gated linear unit simplifies gradie...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
PPG is photoplethysmography. The specific method is to shoot the LED light to the skin, use the photosensitive sensor to receive the light that is reflected or transmitted after being absorbed by the skin tissue, and convert the electrical signal obtained by the photosensitive sensor into a digital signal. Get the final PPG signal. Since oxyhemoglobin and hemoglobin have different light absorption characteristics, the traditional method uses two wavelengths of light to measure the intensity of the reflected light AC signal, and then calculates the ratio of oxyhemoglobin to hemoglobin based on the absorption characteristics of the two types of light. The invention proposes a heart rate and blood oxygen saturation measurement device based on deep learning and PPG signals. The device uses two types of light to obtain two PPG signals, and simultaneously processes the PPG signals with the help of a deep learning network model in the device, thereby predicting the human body. heart rate and oxygen saturation. The device has a good tolerance to noise, and can accurately measure heart rate and blood oxygen in both resting and exercising states.
Description
technical field [0001] The invention relates to the field of heart rate and blood oxygen saturation measuring equipment, in particular to a heart rate and blood oxygen saturation measuring device based on deep learning and PPG signals. Background technique [0002] Heart rate is an important indicator to measure the health status of the human body, and it can objectively reflect the working state of the human heart. Detecting the heart rate can detect the health status of the human body, prevent cardiovascular diseases, and can also evaluate the exercise state during exercise. ECG signal, pulse sensor signal, PPG signal, etc. can be used to detect human heart rate. Since ECG signals and pulse sensors are inconvenient to wear and are easily affected by exercise, PPG signals have become the most effective method for portable heart rate measurement. In addition, according to the different absorption coefficients of oxyhemoglobin and hemoglobin on light waves, the PPG signal c...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/024A61B5/1455
CPCA61B5/02416A61B5/14551A61B5/72A61B5/7264
Inventor 张进东丁立明崔久莉刘文江刘金海
Owner 天津惊帆科技有限公司