Multi-parameter biosensing intelligent monitoring armband device and health monitoring method thereof

Abstract

The invention relates to a multi-parameter biosensing intelligent monitoring armband device, and belongs to the technical field of wearable health monitoring equipment, and the device comprises a muscle force sensing module which is used for detecting and collecting pressure generated by user muscles and pressure change data; the myoelectricity sensing module is used for detecting and collecting electric signals generated by muscle activities of the user; the muscle oxygen sensing module is used for detecting and collecting muscle oxygen saturation data of the user; the data processing unit is used for receiving and processing information from the muscle force sensing module, the myoelectricity sensing module and the muscle oxygen sensing module so as to generate multi-dimensional sensing data; the communication module is used for sending the multi-dimensional sensing data to external equipment; the arm band is used for fixing the muscle force sensing module, the myoelectricity sensing module and the muscle oxygen sensing module in the middle of the brachioradial muscle, and an electrode of the myoelectricity sensing module is fixed to the muscle belly center of the radial wrist flexor muscle. The invention further relates to a health monitoring method.

Description

Technical Field

[0001] The present invention belongs to the technical field of wearable health monitoring equipment and relates to a multi-parameter biosensor intelligent monitoring armband device and a health monitoring method thereof. Background Art

[0002] With the advancement of science and technology and the improvement of people's health awareness, biosensor technology has been widely used in health monitoring, sports tracking and medical diagnosis. The significant defects of existing monitoring equipment in terms of comprehensive functions, data accuracy, and wearing comfort have seriously restricted its in-depth development and wide application in the field of health monitoring. Therefore, exploring and developing new biosensor devices that can overcome these technical obstacles has become an urgent need for the development of the industry. Single function has become a major bottleneck restricting its wide application. Most biosensor devices on the market only focus on monitoring a single or a few physiological indicators, such as heart rate or step count, and cannot fully cover all key physiological data that users may be concerned about, such as blood pressure, blood oxygen saturation, body temperature changes, and muscle activity status. This limitation not only limits users' comprehensive understanding of their personal health status, but also hinders its in-depth application in professional sports training, disease prevention, and daily health management. Signal interference and motion artifact problems have long plagued the industry and users. In dynamic environments, especially when performing high-intensity or complex exercises, sensors are susceptible to external interference, resulting in a decrease in the quality of collected physiological signals and even misleading data. At the same time, due to technical limitations, existing devices often have difficulty in achieving precise control and fixation of sensor positions, making it particularly difficult to monitor physiological signals for specific muscle groups, further reducing the accuracy and reliability of the data. In addition, inconvenience in wearing and poor comfort are also issues that cannot be ignored by existing technologies. Many devices are designed irrationally or made of improper materials, causing users to feel uncomfortable after wearing them for a long time, and even affecting their normal activities, which greatly reduces users' willingness and compliance. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a multi-parameter biosensor intelligent monitoring armband device and a health monitoring method thereof.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] In one aspect, a multi-parameter biosensing intelligent monitoring armband device comprises:

[0006] Muscle force sensing module: used to detect and collect the pressure and pressure change data generated by the user's muscles;

[0007] Myoelectric sensing module: used to detect and collect electrical signals generated by the user's muscle activity;

[0008] Muscle oxygen sensing module: used to detect and collect the user's muscle oxygen saturation data;

[0009] Data processing unit: used for receiving and processing information from the muscle force sensing module, the myoelectric sensing module and the muscle oxygen sensing module to generate multi-dimensional sensing data;

[0010] Communication module: used to send the multi-dimensional sensing data to an external device;

[0011] Armband: used to fix the muscle force sensing module, electromyography sensing module and muscle oxygen sensing module in the middle of the brachioradialis muscle, wherein the electrode of the electromyography sensing module is fixed in the center of the belly of the radial flexor carpi.

[0012] Furthermore, the data processing unit is used to pre-process the muscle strength, electromyography and muscle oxygen data, and then perform feature extraction and feature fusion respectively; finally, the fused features are classified using a support vector machine to identify different muscle states, and a health score is calculated based on the classification results and feature values ​​to evaluate the user's health status; the health score is compared with a warning threshold, and a warning is triggered when the health score is lower than the threshold.

[0013] Furthermore, the muscle oxygen sensing module is a spectral sensor that estimates muscle oxygen saturation by emitting and receiving red light and near-infrared light and utilizing the specific absorption spectra of reduced hemoglobin and oxygenated hemoglobin in the blood in the red and infrared regions.

[0014] Furthermore, it also includes a power supply module for supplying power to the muscle strength sensing module, the electromyography sensing module, the muscle oxygen sensing module, the data processing unit and the communication module.

[0015] Furthermore, the armband is an adjustable armband, which applies pressure to the wearing part by manually or automatically controlling the air pressure.

[0016] In another aspect, the present invention provides a multi-parameter biosensor intelligent monitoring armband health detection method, comprising the following steps:

[0017] S1: Collect arm muscle pressure and pressure change data, electromyographic signals, and muscle oxygen saturation data;

[0018] S2: preprocess the collected data;

[0019] S3: extract the electromyographic signal features, muscle force signal features and muscle oxygen signal features respectively;

[0020] S4: Different weights are given to the electromyographic signal, muscle force signal and muscle oxygen signal according to their importance, and weighted fusion is performed on the features;

[0021] S5: Use support vector machine to classify the fused features to identify different muscle states;

[0022] S6: Calculate a health score based on the classification result and the feature value to evaluate the user's health status;

[0023] S7: Set warning thresholds, monitor health scores in real time, and trigger warnings when the scores are lower than the thresholds.

[0024] Further, the preprocessing in step S2 includes:

[0025] For EMG signal preprocessing:

[0026] Filtering: Use a bandpass filter to remove noise;

[0027] Amplification: Strengthening a signal to improve the signal-to-noise ratio;

[0028] Denoising: Apply wavelet transform or median filtering to remove noise from EMG signals;

[0029] For muscle force signal preprocessing:

[0030] Filtering: Use a low-pass filter to remove high-frequency noise;

[0031] Normalization: Normalize the force signal to the percentage of the maximum force;

[0032] For muscle oxygen signal preprocessing:

[0033] Filtering: Use a low-pass filter to remove high-frequency noise;

[0034] Normalization: Normalize the SmO2 values ​​to a range of 0-100%.

[0035] Further, the feature extraction in step S3 includes:

[0036] EMG signal characteristics include:

[0037] Time domain characteristics: root mean square value RMS, average absolute value MAV, waveform length WL;

[0038] Frequency domain features: power spectral density PSD, Fourier transform FFT;

[0039] Time-frequency domain features: wavelet transform coefficients;

[0040] Muscle force signal characteristics include:

[0041] Peak force: maximum force value;

[0042] Average force: the average force value over a period of time;

[0043] Rate of change of force: the rate at which the value of a force changes;

[0044] Muscle oxygen signal characteristics include:

[0045] Average SmO2: average SmO2 value over a period of time;

[0046] SmO2 change rate: the rate at which the SmO2 value changes.

[0047] Furthermore, in step S4, a machine learning algorithm is used to fuse and classify the features.

[0048] The beneficial effects of the present invention are:

[0049] 1. The multi-parameter biosensor intelligent monitoring armband device according to the present invention can monitor a variety of physiological data in real time, thereby improving the comprehensiveness and accuracy of data monitoring.

[0050] 2. The multi-parameter biosensor intelligent monitoring armband device according to the present invention is reasonably designed, comfortable to wear, easy to operate, and suitable for health monitoring and sports tracking in various scenarios.

[0051] 3. The multi-parameter biosensor intelligent monitoring armband device according to the present invention can provide personalized health advice through integrated multiple sensors and data processing algorithms, and trigger an early warning mechanism when necessary to ensure the health and safety of the user.

[0052] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0054] Figure 1 This is a hardware principle block diagram of a multi-parameter biosensor intelligent monitoring armband device according to an embodiment of the present invention;

[0055] Figure 2 This is an overall structural framework diagram of a multi-parameter biosensor intelligent monitoring armband device according to an embodiment of the present invention;

[0056] Figure 3 The figure is a schematic diagram of the specific process of data processing;

[0057] Figure 4 is an overall schematic diagram of a multi-parameter biosensor intelligent monitoring armband device according to an embodiment of the present invention;

[0058] Figure 5 It is a graph of raw data of muscle strength, myoelectricity and muscle oxygen output according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0060] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0061] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0062] The present invention provides a multi-parameter biosensor intelligent monitoring armband device, comprising:

[0063] Muscle force sensing module: used to detect and collect the pressure and pressure change data generated by the user's muscles;

[0064] Myoelectric sensing module: used to detect and collect electrical signals generated by the user's muscle activity;

[0065] Muscle oxygen sensing module: used to detect and collect the user's muscle oxygen saturation data;

[0066] Data processing unit: used for receiving and processing information from the muscle force sensing module, the myoelectric sensing module and the muscle oxygen sensing module to generate multi-dimensional sensing data;

[0067] Communication module: used to send the multi-dimensional sensing data to an external device;

[0068] Armband: used to fix the muscle force sensing module, the electromyographic sensing module and the muscle oxygen sensing module in the middle of the brachioradialis muscle, wherein the electrode of the electromyographic sensing module is fixed in the center of the belly of the radial flexor carpi;

[0069] It also includes a power supply module for supplying power to the muscle strength sensing module, the myoelectric sensing module, the muscle oxygen sensing module, the data processing unit and the communication module.

[0070] Figure 1 This is the hardware principle block diagram of the multi-parameter biosensor intelligent monitoring armband device of the embodiment of the present invention, and the circuit design of each module can be seen. In order to ensure that the circuit board used meets the actual needs, the present invention designs a circuit board. The power module is used to power the single-chip microcomputer used in this device. In the acquisition circuit design of this device, the power module undertakes two important tasks: charging the lithium battery and providing stable 5V and 3.3V voltages for the entire circuit. Among them, the 5V voltage regulator chip provides the required 5V analog input voltage for the ADS1299 of the analog front end, and the 3.3V voltage regulator chip provides the required 3.3V voltage for the digital power supply, data processing unit and wireless communication module of the ADS1299. LTC1983ES6-5 and ME6211A33M3G-N are selected as power supplies, and HX4002-MFC is selected as a voltage stabilization device to ensure the stable supply and regulation of voltage, so that the driving power supply is stable and adjustable under the premise of small size and good performance, which is very suitable for the needs of this device. In addition, the present invention designs a TYPE-C interface and a lithium battery charging chip TP4056 for charging the lithium battery of the circuit board. By turning the power switch to the right, the circuit board can be provided with power from the lithium battery. At the same time, the 5V and 3.3V voltage regulator chips can stabilize the lithium battery voltage at 5V and 3.3V for circuit use.

[0071] The data processing unit is the core module of the device, and the design of this module is the core work of the circuit board design. The present invention selects the STM32F103RET6 chip as the data processing unit. The operational amplifier chip model used in the device is OPA4172IPWR. This chip has the characteristics of wide input voltage range, rail-to-rail output swing, low power supply current, low offset voltage and no inversion, which fully meets the needs of the muscle force sensing module of the device. Since the amplitude of the surface electromyography signal is very small, it is not enough to set only one amplifier, so an operational amplifier is used to achieve two-stage amplification of the signal. The device selects the rail-to-rail operational amplifier ADS1299 produced by ADI. The ADS1299 chip receives the electromyography analog signal and converts it into an 8*24-bit digital signal. In addition, any configuration of the input channel can be selected to generate the output signal. The chip data rate is 250SPS to 16kSPS. In order to collect muscle oxygen signals, the device selects the MAX30102 chip, which is a pulse oxygen saturation and heart rate monitoring module that integrates infrared LEDs and photodetectors. SpO2 and HR are measured by sending infrared and red light to the blood on the skin and then detecting the reflected light. The present invention uses Bluetooth as the transmission mode of the communication module because Bluetooth transmission has low power consumption, low latency, can achieve wireless connection, and is easy to use. Wireless remote data is transmitted to the host computer through the Bluetooth module CH9140. The above is the schematic design of the main module of the acquisition circuit. After testing, the circuit board produced by this design is small in size, low in cost, easy to carry, and fully functional, which basically meets the needs of this device.

[0072] Figure 2It is the overall design structure framework diagram of the multi-parameter biosensor intelligent monitoring armband device of the embodiment of the present invention. It includes the structural design, circuit design and display interface design of the multi-parameter biosensor intelligent monitoring armband device. The structural design part includes muscle force sensor, electromyographic sensor and muscle oxygen sensor. All three sensors need to be designed specifically according to the measured muscle position. For example, the device measures the positions of the brachioradialis, radial wrist flexor, palmaris longus and ulnar wrist flexor at the arms of multiple subjects and then obtains the appropriate position. The circuit design mainly includes the schematic design, PCB part and the lower computer data acquisition program writing part. Finally, there is the display interface part, which pre-processes the collected data and displays it on the computer. Specifically, the muscle force sensing module includes a pressure sensor, which is arranged on the surface in contact with the user's muscles, and is used to measure the pressure changes generated by the muscles to obtain muscle force data. The electromyographic sensing module includes an electromyographic sensor, which is arranged at a position in contact with the user's muscles or nerves, and is used to detect the electrical signals generated by muscle activity. The muscle oxygen sensing module includes a spectral sensor that can emit and receive red light and near-infrared light, and uses the specific absorption spectra of reduced hemoglobin and oxygenated hemoglobin in the blood in the red and infrared light regions (600-1000nm) to estimate muscle oxygen saturation. The fixing device is a strip made of a fabric substrate material, and the acquisition and conditioning module is placed in the middle of the brachioradialis muscle along the extension direction of the brachioradialis muscle to avoid signal interference caused by squeezing. The acquisition system is fixed in the middle of the subject's brachioradialis muscle, and the strip straps are fixed from the brachioradialis muscle, radial flexor carpi, palmaris longus, and ulnar flexor carpi, and the electromyographic electrode is fixed in the center of the muscle belly of the radial flexor carpi.

[0073] like Figure 3 As shown, the data processing unit is used to process and fuse electromyography (EMG), muscle force (Force) and muscle oxygen (SmO2) data to identify muscle status and health status. The algorithm is divided into several main steps: data preprocessing, feature extraction, data fusion and health status assessment.

[0074] 1. Data preprocessing

[0075] EMG signal preprocessing:

[0076] Filtering: Use a bandpass filter (20-450Hz) to remove noise;

[0077] Amplification: Strengthening a signal to improve the signal-to-noise ratio;

[0078] Denoising: Apply wavelet transform or median filtering to remove noise from EMG signals.

[0079] Muscle force signal preprocessing:

[0080] Filtering: Use a low-pass filter (e.g. 5Hz) to remove high-frequency noise;

[0081] Normalize: Normalize the force signal to a percentage of the maximum force.

[0082] Muscle oxygen signal preprocessing:

[0083] Filtering: Use a low-pass filter (e.g. 1Hz) to remove high-frequency noise;

[0084] Normalization: Normalize the SmO2 values ​​to a range of 0-100%.

[0085] 2. Feature extraction

[0086] EMG signal characteristics:

[0087] Time domain characteristics: root mean square value (RMS), mean absolute value (MAV), waveform length (WL);

[0088] Frequency domain features: power spectral density (PSD), Fourier transform (FFT);

[0089] Time-frequency domain features: wavelet transform coefficients.

[0090] Muscle strength signal characteristics:

[0091] Peak force: maximum force value;

[0092] Average force: the average force value over a period of time;

[0093] Rate of change of force: the rate at which the value of a force changes.

[0094] Muscle oxygen signal characteristics:

[0095] Average SmO2: average SmO2 value over a period of time;

[0096] SmO2 change rate: the rate at which the SmO2 value changes.

[0097] 3. Data Fusion

[0098] Weighted fusion: Give different weights to each sensor according to its importance:

[0099] Fused_Feature=w EMG EMG_Feature+w Force Force_Feature+w SmO2 ·SmO2_Feature

[0100] Where W EMG、 W Force、 W SmO2 is the weight, which can be adjusted according to the experimental results.

[0101] Machine Learning Fusion: Use machine learning algorithms to fuse and classify features.

[0102] 4. Health status assessment

[0103] Classification model: A support vector machine (SVM) is used to classify the fused features to identify different muscle states (e.g., normal, fatigue, and injury).

[0104] Health score: A health score is calculated based on the classification results and feature values ​​to evaluate the user's health status.

[0105] 5. Early warning mechanism

[0106] Threshold setting: Set warning thresholds based on health scores.

[0107] Real-time monitoring: monitor the health score in real time and trigger an alert when the score falls below the threshold.

[0108] like Figure 4 As shown, different exercises performed by the wearer of the smart armband device will cause changes in different muscle groups. The sensors in the device are attached to the human skin and can accurately sense these changes. The circuit can record and transmit the changes detected by the sensor. The data is uploaded to the display interface through wireless transmission, and then the wearer's status can be judged based on the test data. Adjusting the device's adjustment belt (manually or automatically adjusted by the system through air pressure) can apply appropriate pressure to the wearing part and relieve muscle fatigue to a certain extent. The data monitored by the sensor can determine whether the wearer needs to stop exercising to prevent fatigue injuries and prevent the occurrence of stress bone injuries.

[0109] Figure 5 It is the raw data graph of muscle strength, electromyography, and muscle oxygen output according to the embodiment of the present invention. According to the embodiment of the present invention, the multi-parameter biosensor intelligent monitoring armband device can output stable electromyography, muscle strength, and muscle oxygen signals. When the subject clenched his fist, the intensity of these three signals was slightly larger than that in the resting state. For the surface electromyography signal, the signal intensity increases with the increase of grip strength. For the muscle strength signal, the change of the grip strength of the four channels has little effect on the signal intensity displayed in the raw data. For muscle oxygen saturation, the rate of change of the signal increases with the increase of grip strength, but the amplitude of the change is not very obvious. The experimental results show that with the increase of grip strength, the amplitude of the surface electromyography signal shows an upward trend, indicating that the degree of muscle recruitment and the intensity of activity increase. The change of muscle strength signal is not obvious, which may be because the change of grip strength mainly affects the recruitment of muscles rather than the contraction force itself. It can be seen from the muscle oxygen saturation curve that when the fist is clenched, the oxygen saturation gradually decreases during the grip duration. After loosening the fist, that is, the rest time between different grip stages, the oxygen saturation rises rapidly. The greater the grip strength, the greater the rate of change of oxygen saturation. The above phenomenon can be explained as follows: during muscle contraction, the oxygen consumption is greater than the oxygen supply, thus reducing the oxygen saturation.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A multi-parameter biosensor intelligent monitoring armband device, characterized in that: include: Muscle force sensing module: used to detect and collect the pressure and pressure change data generated by the user's muscles; Myoelectric sensing module: used to detect and collect electrical signals generated by the user's muscle activity; Muscle oxygen sensing module: used to detect and collect the user's muscle oxygen saturation data; Data processing unit: used for receiving and processing information from the muscle force sensing module, the myoelectric sensing module and the muscle oxygen sensing module to generate multi-dimensional sensing data; Communication module: used to send the multi-dimensional sensing data to an external device; Armband: used to fix the muscle force sensing module, electromyography sensing module and muscle oxygen sensing module in the middle of the brachioradialis muscle, wherein the electrode of the electromyography sensing module is fixed in the center of the belly of the radial flexor carpi.

2. The multi-parameter biosensor intelligent monitoring armband device according to claim 1, characterized in that: The data processing unit is used to preprocess the muscle strength, electromyography and muscle oxygen data, and then perform feature extraction and feature fusion respectively; finally, the fused features are classified using a support vector machine to identify different muscle states, and a health score is calculated based on the classification results and feature values ​​to evaluate the user's health status; the health score is compared with a warning threshold, and a warning is triggered when the health score is lower than the threshold.

3. The multi-parameter biosensor intelligent monitoring armband device according to claim 1, characterized in that: The muscle oxygen sensing module is a spectral sensor that estimates muscle oxygen saturation by emitting and receiving red light and near-infrared light and utilizing the specific absorption spectra of reduced hemoglobin and oxygenated hemoglobin in the blood in the red and infrared regions.

4. The multi-parameter biosensor intelligent monitoring armband device according to claim 1, characterized in that: It also includes a power supply module for supplying power to the muscle strength sensing module, the myoelectric sensing module, the muscle oxygen sensing module, the data processing unit and the communication module.

5. The multi-parameter biosensor intelligent monitoring armband device according to claim 1, characterized in that: The armband is an adjustable armband that applies pressure to the wearing part by manually or automatically controlling the air pressure.

6. A multi-parameter biosensor intelligent monitoring armband health detection method, characterized in that: The following steps are involved: S1: Collect arm muscle pressure and pressure change data, electromyographic signals, and muscle oxygen saturation data; S2: preprocess the collected data; S3: extract the electromyographic signal features, muscle force signal features and muscle oxygen signal features respectively; S4: Different weights are given to the electromyographic signal, muscle force signal and muscle oxygen signal according to their importance, and weighted fusion is performed on the features; S5: Use support vector machine to classify the fused features to identify different muscle states; S6: Calculate a health score based on the classification result and the feature value to evaluate the user's health status; S7: Set warning thresholds, monitor health scores in real time, and trigger warnings when the scores are lower than the thresholds.

7. The multi-parameter biosensor intelligent monitoring armband health detection method according to claim 6 is characterized in that: The pre-processing in step S2 includes: For EMG signal preprocessing: Filtering: Use a bandpass filter to remove noise; Amplification: Strengthening a signal to improve the signal-to-noise ratio; Denoising: Apply wavelet transform or median filtering to remove noise from EMG signals; For muscle force signal preprocessing: Filtering: Use a low-pass filter to remove high-frequency noise; Normalization: Normalize the force signal to the percentage of the maximum force; For muscle oxygen signal preprocessing: Filtering: Use a low-pass filter to remove high-frequency noise; Normalization: Normalize the SmO2 values ​​to a range of 0-100%.

8. The multi-parameter biosensor intelligent monitoring armband health detection method according to claim 6 is characterized in that: The feature extraction in step S3 includes: EMG signal characteristics include: Time domain characteristics: root mean square value RMS, average absolute value MAV, waveform length WL; Frequency domain features: power spectral density PSD, Fourier transform FFT; Time-frequency domain features: wavelet transform coefficients; Muscle force signal characteristics include: Peak force: maximum force value; Average force: the average force value over a period of time; Rate of change of force: the rate at which the value of a force changes; Muscle oxygen signal characteristics include: Average SmO2: average SmO2 value over a period of time; SmO2 change rate: the rate at which the SmO2 value changes.

9. The multi-parameter biosensor intelligent monitoring armband health detection method according to claim 6, characterized in that: In step S4, a machine learning algorithm is also used to fuse and classify the features.

Images