Intelligent wearing garment for cardiopulmonary exercise and multi-modal analysis system
By adopting high-precision clock synchronization circuits and multimodal analysis algorithms in cardiopulmonary movement intelligent clothing, the complexity of multi-sensor integration and data fusion is solved, precise monitoring and detailed evaluation of cardiopulmonary movement is realized, and data analysis is improved. Accuracy and user experience.
Patent Information
- Application Number
- CN202411035412.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing smart cardiopulmonary exercise clothing has complexity and stability problems in multi-sensor integration and multi-modal data fusion modeling, making it difficult to accurately monitor and comprehensive evaluation of cardiopulmonary exercise, especially in terms of noise processing and data effectiveness. .
A smart wearable clothing and multimodal analysis system for cardiopulmonary movement was designed. Through scientific sensor layout and hardware integration, a high-precision clock synchronization circuit is used to realize the synchronous acquisition and transmission of multi-sensor data, and the data is combined with a multimodal analysis algorithm. Preprocessing and modeling, including data processing of inertial measurement units, electrocardiogram sensors, and axle goniometers, uses deep learning models for human behavior recognition and adaptive updates.
It realizes efficient and accurate monitoring and analysis of cardiopulmonary movements, ensures the synchronization and effectiveness of sensor data, provides detailed cardiopulmonary health and exercise parameters evaluation, and improves the accuracy of user experience and data analysis.
Smart Images

Figure CN118924286A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to wearable technology, multimodal human body data fusion and cardiopulmonary exercise application fields, and in particular to a cardiopulmonary exercise intelligent wearable clothing and a multimodal analysis system. Background Art
[0002] At present, most daily health and sports wearable devices are in the form of single data category testing, such as smart bracelets, pressure detection shoes, etc., which lack comprehensive perception of multiple human physiological and sports data. The development of smart wearable clothing based on multimodal data fusion is one of the main solutions for this application. However, one of the main challenges facing smart clothing technology for cardiopulmonary exercise is the complexity of multi-sensor integration and multimodal data fusion modeling, which limits the reliability and accuracy of smart clothing monitoring cardiopulmonary exercise. Existing technologies have stability problems in sensor layout, large-scale data transmission and multimodal modeling, and cannot achieve accurate monitoring of cardiopulmonary exercise function.
[0003] On the other hand, establishing a cardiopulmonary exercise analysis system with multimodal data fusion also faces many difficulties and challenges. Since cardiopulmonary exercise requires monitoring and analysis of multiple physiological parameters, the system needs to synchronously process a large amount of different types of data. However, existing technologies have bottlenecks in achieving synchronous data acquisition, processing, fusion and analysis, making it difficult to achieve a comprehensive and accurate assessment of cardiopulmonary exercise, and it is difficult to use professional respiratory monitoring equipment to obtain accurate parameters during daily exercise. In addition, in the fusion of different sensor data, how to effectively remove noise and ensure data validity and reliability is also an urgent problem to be solved.
[0004] To this end, the present invention aims to provide a cardiopulmonary exercise intelligent wearable clothing and a multimodal analysis system to solve the above problems. Summary of the invention
[0005] The purpose of the present invention is to solve the above problems and to design a smart wearable cardiopulmonary exercise clothing and a multimodal analysis system, which can realize efficient exercise information monitoring and cardiopulmonary status analysis through effective sensor arrangement for cardiopulmonary exercise function testing.
[0006] In order to achieve the above object, the technical solution of the present invention is as follows:
[0007] The present invention provides a cardiopulmonary exercise intelligent wearable clothing and a multimodal analysis system, wherein the wearable clothing comprises an intelligent wearable clothing and a plurality of sensors, wherein the sensors are fixedly arranged in the interlayer of the clothing by sewing;
[0008] The smart wearable clothing comprises a top and shorts, wherein the layer of the top in contact with the human body is the inner layer of the top, and the side of the wearable clothing away from the human body is the outer layer of the top; the layer of the shorts in contact with the human body is the inner layer of the shorts, and the side of the wearable clothing away from the human body is the outer layer of the shorts;
[0009] The plurality of sensors include five inertial measurement unit sensors IMU, two electrocardiogram sensors ECG and three pairs of rotation axis goniometers. The five inertial measurement unit sensors are fixed at the lower edge of the left sleeve, the lower edge of the right sleeve, the middle of the abdomen and the front side of the left bottom edge and the front side of the right bottom edge of the shorts; the two electrocardiogram sensors are fixedly arranged in the middle and left side of the chest of the wearable suit, and the rotation axis goniometers are fixedly arranged in the inner layer of the upper chest, middle chest and abdomen of the wearable suit.
[0010] In this solution, the wearable clothing includes a top and shorts, both of which are made of sweat-absorbing and quick-drying tight fabrics, ensuring the fit and comfort of wearing, while also having excellent breathability. In terms of sensor integration, the hardware integration solution of the present invention realizes data acquisition, time synchronization and data transmission of multiple sensors through scientific design and advanced technology, ensuring the efficiency and accuracy of cardiopulmonary exercise status monitoring. The inertial measurement unit sensor can obtain data from accelerometers, gyroscopes and magnetometers, providing rich information for comprehensive motion analysis. Its data sampling frequency is 60Hz, ensuring that subtle changes in movement are captured. The ECG sensor can obtain ECG data with a sampling frequency of 500Hz. High-frequency sampling ensures the fine capture of ECG signals, especially during strenuous exercise, and can provide accurate cardiac electrical activity data. The goniometer can obtain multi-axis angle data with a sampling frequency of 100Hz, which is mainly used to monitor the angle changes of the chest during breathing.
[0011] An elastic band is provided on one side of the inner layer of the clothes where the sensors are arranged, and a plurality of the sensors are fixed in the elastic cloth grooves through the elastic bands, so that they can be stably fixed on the bodies of users with different body shapes and postures.
[0012] All sensors are connected to the data integration center module through data cables in the form of wired connection, and the transmission line is arranged in the interlayer of the clothes. The data integration center module completes the charging of multiple sensors and the reception, integration, processing and transmission of multiple sensor data. The silicone slot is designed to be lightweight and does not affect the user's movement, while providing good protection.
[0013] The integrated multi-sensor solves the problem of time alignment and data synchronization acquisition of different types of sensors at the hardware level, including: time alignment and data synchronization between five inertial measurement unit sensors, time alignment and data synchronization between two electrocardiogram sensors, and time alignment and data synchronization between three axle goniometers.
[0014] A multimodal analysis system for cardiopulmonary exercise intelligent wearable clothing, the analysis system comprising a multi-sensor integration system and a multimodal analysis algorithm;
[0015] The multi-sensor integration system adopts a high-precision clock synchronization circuit, and distributes the main clock signal of the data integration center module to each sensor node, ensuring that the data of several sensors are on the same time axis; the time alignment of several sensors is achieved by distributing a unified clock signal, realizing synchronous recording during collection.
[0016] A high-precision clock synchronization circuit is used to distribute the master clock signal to each sensor node to ensure that the data of each sensor is on the same time axis. The time alignment of the five inertial measurement unit sensors is achieved by distributing a unified clock signal, and the data of each sensor is recorded synchronously during acquisition. The data synchronization of the two ECG sensors and the three axis goniometers is also achieved through a similar method to ensure that the data of all sensors can accurately match the timestamp during data transmission.
[0017] The multimodal analysis system includes preprocessing the acquired sensor data, and then implementing multimodal modeling based on the processed data. The modeling integrates these data parameters and is ultimately used for personalized analysis of the user's cardiopulmonary indicators under different activity states. The modeling includes cardiopulmonary health analysis modeling and human behavior modeling;
[0018] The data preprocessing includes data segmentation and separate processing of different types of sensors;
[0019] In this solution, each sensor is segmented in seconds at different acquisition frequencies. The segmented data is preprocessed separately according to the characteristics of different types of data: extended Kalman filtering is performed on the inertial measurement unit data, low-pass filtering is performed on the ECG data, and baseline removal and band-pass filtering are performed on the axle goniometer data;
[0020] The cardiopulmonary analysis model includes modeling and analysis of ECG parameters and axle goniometer data;
[0021] In this solution, two-lead ECG data is used to calculate ECG parameters during activities, including heart rate and arrhythmia; a rotating axis goniometer is used to fit the rise and fall of the chest to calculate respiratory parameters. Three rotating axis goniometers cover the entire chest of the user, sense the rise and fall of the chest during breathing during activities, and obtain accurate angle changes. Through data fitting and feature extraction, a respiratory curve is modeled to calculate respiratory parameters during activities, including respiratory rate, inhalation time, exhalation time, respiratory time, tidal volume, minute ventilation, average inspiratory flow, average expiratory flow, and duty cycle;
[0022] The human behavior recognition model uses inertial sensor unit data to perform hierarchical human behavior recognition;
[0023] In this solution, the processed inertial measurement unit data is used to identify the user's specific activities in a hierarchical form: first, dynamic and static classification is performed based on the threshold to distinguish whether the current behavior is dynamic or static, and further classification models are selected based on the results of the threshold classification. The second layer uses a pre-trained deep learning model to identify specific activities, which is divided into a dynamic deep learning model and a static deep learning model, which recognize dynamic activities and static activities respectively to determine the user's specific activities at this time. At the same time, the system will also adaptively update the model based on the uniqueness of the user to improve the effect. The adaptive update includes online re-learning of the model based on the differences between the user and the pre-trained human behavior model; and generating more data through a generative model based on the user's data to solve the problem of inaccurate classification caused by insufficient data when the user first uses it.
[0024] Compared with the prior art, this solution has the following beneficial effects:
[0025] The present invention uses multiple inertial measurement units to sense the whole-body motion information of the human body, and combines multiple electrocardiogram sensors and goniometers to comprehensively obtain the cardiopulmonary status during activities; the problem is solved through hardware integration, and the data of multiple sensors can be synchronized and transmitted efficiently and accurately, ensuring the precise monitoring and analysis of cardiopulmonary status and motion information; users can choose offline or online recording methods according to their needs, so as to conveniently and flexibly manage and analyze motion data. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 Schematic diagram of the smart wearable cardiopulmonary exercise clothing in an embodiment of the present invention;
[0027] Figure 2 It is an algorithm flow chart of the system in the embodiment of the present invention.
[0028] In the figure: 1. Inertial measurement unit sensor; 2. ECG sensor; 3. Axle goniometer; 4. Data integration center module; 5. Data cable; 6. Inner layer of wearable suit. DETAILED DESCRIPTION
[0029] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution of the present invention will be further described in detail below in conjunction with the embodiments of the present invention and the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will be described in detail below in conjunction with the embodiments.
[0031] Example:
[0032] The solution provided by the embodiment of the present invention is as described in the above invention content, which provides a cardiopulmonary exercise smart wearable clothing and a multimodal analysis system. After the user puts on the clothing, the system is started, and different sensors simultaneously collect data, complete the timestamp alignment in the form of a clock circuit, and transmit it to the data center through wired transmission. In the data center, the data is first segmented and signal processed, and then the pre-processed data is transmitted to the mobile device as wireless gateway data to achieve multimodal data modeling and analysis.
[0033] Users can choose offline or online recording mode according to their needs, which allows for convenient and flexible management and analysis of sports data.
[0034] If you use the offline recording method, that is, when you are not connected to the mobile terminal software, the collected data will be automatically saved in the data integration center. The data integration center has a built-in memory that can save a certain amount of data for users to analyze and view later. The stored data can be exported through the USB interface, or synchronized to the device the next time you connect to the mobile terminal device.
[0035] When using the online recording method, the data from the data integration center is transmitted to the mobile device in real time through the Bluetooth wireless gateway. The application on the mobile device receives and analyzes the data in real time and outputs the real-time analysis results. The data from the inertial measurement unit will be adaptively trained through the hierarchical human behavior recognition model for agility recognition and classification of movements. These models are implemented through the adaptive hierarchical algorithm designed above, which can automatically identify different movement patterns, such as running, walking, jumping, etc., and count the duration and proportion of each movement, so as to provide a detailed movement analysis report. Due to the different sampling frequencies of different sensors, different types of data are integrated into one data packet in the form of seconds when the clock circuit is used for timestamp alignment.
[0036] The data of the inertial measurement unit sensor 1 will be used to build a classifier and adaptive model update through the above-designed adaptive hierarchical algorithm model for user personalized motion recognition and classification. Specifically, the pre-processed motion data can be used to identify different motion patterns, such as running, walking, jumping, etc., through the above-trained classification model, and provide a detailed motion analysis report. At the same time, according to the individual differences of different users (including body shape and sports preferences, etc.) and the degree of matching with the recognition algorithm, the adaptive model is updated to make the system personalized to the user. The adaptive update includes online updating of the classifier according to the differences between the user and the pre-trained human behavior model; and based on the acquisition of new user data, solving the classification error problem caused by insufficient data when the user first uses it.
[0037] The data from ECG sensor 2 will be used to calculate ECG parameters, including heart rate and arrhythmia. Heart rate can reflect exercise intensity and heart function status. By monitoring changes in heart rate, the user's physical fitness level and training effect can be evaluated. Arrhythmia refers to abnormal heart rhythm, including tachycardia, bradycardia or irregular heartbeat, which may affect the effective circulation of blood. During exercise, arrhythmia monitoring can help detect potential heart problems in a timely manner, prevent serious heart events, and ensure the safety of users.
[0038] The angle change data of the three rotating shaft goniometers 3 are processed, feature extracted and fitted, and then used to fit the breathing curve of the chest cavity, and then calculate detailed breathing parameters, including: breathing rate, inhalation time, exhalation time, breathing time, tidal volume, minute ventilation, average inhalation flow, average expiratory flow and duty cycle. These parameters can help evaluate the user's respiratory health status, especially during exercise, to monitor breathing changes in real time.
[0039] After the user completes the exercise, the overall exercise data is uploaded to the cloud. The cloud server can store and analyze the data for a long time and provide users with personalized health reports. For example, the overall heart rate changes of the user in a single complete exercise, whether there are any abnormalities, and suggestions for the user's breathing method during exercise based on the heart rate and breathing rate; for all individual exercises, the changes in the user's physiological parameters during exercise over time are given, and guidance suggestions are given.
[0040] The above specific embodiments are merely explanations of the present invention and are not limitations of the present invention. After reading this specification, those skilled in the art may make modifications to the embodiments without any creative contribution as needed. However, such modifications are protected by the patent law as long as they are within the scope of the claims of the present invention.
Claims
1. A smart wearable cardiopulmonary exercise garment, Its characteristics are: The wearable clothing includes smart wearable clothing and a number of sensors; The smart wearable clothing comprises a top and shorts, wherein the layer of the top in contact with the human body is the inner layer (6) of the top, and the side of the wearable clothing away from the human body is the outer layer of the top; the layer of the shorts in contact with the human body is the inner layer of the shorts, and the side of the wearable clothing away from the human body is the outer layer of the shorts; A lightweight silicone groove is provided on one side of the outer layer of the jacket, a data integration center module (4) is provided inside the lightweight silicone groove, and a plurality of the sensors are connected to the data integration center module (4) via data lines (5).
2. A multi-modal analysis system for smart wearable cardiopulmonary exercise. Its characteristics are: The analysis system comprises a multi-sensor integrated system and a multi-modal analysis algorithm; The multimodal analysis algorithm includes human behavior modeling and cardiopulmonary health analysis modeling; The human behavior modeling is based on the data processed by the inertial measurement unit and uses a hierarchical network to identify the specific activities of the user: first, dynamic and static classification is performed through thresholds, and then the specific activities are identified using a pre-trained dynamic deep learning model and a static deep learning model respectively. At the same time, the system will also adaptively update the model based on the uniqueness of the user; The cardiopulmonary health analysis modeling is based on processed ECG data and axle goniometer (3) data, and uses two-lead ECG data to calculate ECG parameters during activities, including: heart rate and arrhythmia; uses the axle goniometer (3) to fit the rise and fall of the chest to calculate breathing parameters, and three axle goniometers (3) cover the entire chest of the user, sense the rise and fall of the chest during natural breathing in daily activities, and obtain angle changes. Through breathing curve fitting and feature extraction, a breathing curve is modeled to calculate breathing parameters during activities, and the breathing parameters during activities include breathing frequency, inhalation time, exhalation time, breathing time, tidal volume, minute ventilation, average inspiratory flow, average expiratory flow and duty cycle.
3. The cardiopulmonary exercise smart wearable clothing according to claim 1, Its characteristics are: The plurality of sensors include five inertial measurement unit sensors (1) IMU, two electrocardiogram sensors (2) ECG and three pairs of rotation axis goniometers (3), wherein the five inertial measurement unit sensors (1) are fixed on the lower edge of the left sleeve, the lower edge of the right sleeve, the middle of the abdomen and the front side of the lower edge of the left trousers and the front side of the lower edge of the right trousers of the top; the two electrocardiogram sensors (2) are fixedly arranged on the middle and left side of the chest of the wearable clothing, and the rotation axis goniometers (3) are fixedly arranged in the inner interlayer of the upper chest, middle chest and abdomen of the wearable clothing.
4. The cardiopulmonary exercise smart wearable clothing as claimed in claim 3, Its characteristics are: A plurality of the sensors are fixed in the elastic cloth grooves via elastic bands, and the axle angle meter (3), the electrocardiogram sensor (2) and the inertial measurement unit sensor (1) can be stably fixed on the bodies of users of different body shapes and postures.
5. The cardiopulmonary exercise smart wearable clothing according to claim 1, Its characteristics are: A plurality of the sensors are connected to a data integration center module (4) via data lines (5).
6. A multi-modal analysis system for cardiopulmonary exercise smart wearable clothing as claimed in claim 2, Its characteristics are: The multimodal analysis system adopts a high-precision clock synchronization circuit, and distributes the master clock signal to each sensor node through the data integration center module (4), ensuring that the data of several sensors are on the same time axis; the time alignment of several sensors is achieved by distributing a unified clock signal, thereby achieving synchronous recording during collection.
Citation Information
Patent Citations
Wearable cardio-pulmonary function evaluation equipment
CN110801220A
Intelligent wearable electrocardio-respiration detection garment
CN116616786A
Smart clothing system and method based on multi-sensing information fusion
CN117426758A
Human movement monitor , analysis and feedback device based on clothing
CN207071088U
Motion Pattern Recognition Using Wearable Motion Sensors
US20210026440A1
Cited By
Intelligent wearable system and LED content display social garment based on AI identification
CN119336173A
Smart wearable system based on AI recognition and LED content display social service
CN119336173B
Multi-modal wearable sensing data real-time analysis method based on layered architecture
CN120089403A
Exercise load monitoring and intelligent feedback clothing-mounted system
CN120853805A
Hierarchical architecture-based real-time analysis method for multi-modal wearable sensor data
WO2026188793A1
