CN116019443B - Cardiopulmonary resuscitation chest compression compliance detection system and method - Google Patents
Cardiopulmonary resuscitation chest compression compliance detection system and method Download PDFInfo
- Publication number
- CN116019443B CN116019443B CN202211729849.3A CN202211729849A CN116019443B CN 116019443 B CN116019443 B CN 116019443B CN 202211729849 A CN202211729849 A CN 202211729849A CN 116019443 B CN116019443 B CN 116019443B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- pressing
- acceleration
- rescuer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007906 compression Methods 0.000 title claims abstract description 100
- 230000006835 compression Effects 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000002680 cardiopulmonary resuscitation Methods 0.000 title claims description 27
- 238000003825 pressing Methods 0.000 claims abstract description 66
- 230000003993 interaction Effects 0.000 claims abstract description 34
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 19
- 238000005452 bending Methods 0.000 claims abstract description 12
- 238000003860 storage Methods 0.000 claims abstract description 5
- 210000000038 chest Anatomy 0.000 claims description 69
- 230000001133 acceleration Effects 0.000 claims description 49
- 238000006073 displacement reaction Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 210000001562 sternum Anatomy 0.000 claims description 14
- 210000000707 wrist Anatomy 0.000 claims description 14
- 239000000243 solution Substances 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 10
- 230000033001 locomotion Effects 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 230000010354 integration Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 210000002569 neuron Anatomy 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000010146 3D printing Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000001746 injection moulding Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007789 sealing Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000012804 iterative process Methods 0.000 claims 1
- 238000010606 normalization Methods 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 abstract description 3
- 230000001960 triggered effect Effects 0.000 abstract 1
- 230000006872 improvement Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 210000004247 hand Anatomy 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 101100242890 Quaranfil virus (isolate QrfV/Tick/Afghanistan/EG_T_377/1968) PA gene Proteins 0.000 description 2
- 101100247669 Quaranfil virus (isolate QrfV/Tick/Afghanistan/EG_T_377/1968) PB1 gene Proteins 0.000 description 2
- 101100242901 Quaranfil virus (isolate QrfV/Tick/Afghanistan/EG_T_377/1968) PB2 gene Proteins 0.000 description 2
- 101150025928 Segment-1 gene Proteins 0.000 description 2
- 101150082826 Segment-2 gene Proteins 0.000 description 2
- 101150027881 Segment-3 gene Proteins 0.000 description 2
- 101100242902 Thogoto virus (isolate SiAr 126) Segment 1 gene Proteins 0.000 description 2
- 101100194052 Thogoto virus (isolate SiAr 126) Segment 2 gene Proteins 0.000 description 2
- 101100242891 Thogoto virus (isolate SiAr 126) Segment 3 gene Proteins 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000010989 Bland-Altman Methods 0.000 description 1
- 208000010496 Heart Arrest Diseases 0.000 description 1
- 206010049418 Sudden Cardiac Death Diseases 0.000 description 1
- 206010047571 Visual impairment Diseases 0.000 description 1
- 208000008784 apnea Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 208000014221 sudden cardiac arrest Diseases 0.000 description 1
Landscapes
- Percussion Or Vibration Massage (AREA)
Abstract
The invention discloses a multi-dimensional index compliance detection system and method for chest compressions, wherein an auxiliary system consists of an equipment shell, a rubber binding belt, a voice interaction module, an inertia measurement unit module, a microcontroller module, a communication module, a storage module, a touch and display module and a power supply module; the auxiliary method comprises a pressing depth detection method, a pressing frequency detection method, an arm pressing perpendicularity detection method and an elbow bending detection method, so that the pressing depth, the frequency, the arm and elbow gesture normalization of a rescuer are evaluated; according to the auxiliary system, the starting and working states of the auxiliary system are triggered and guided by the rescuer through the voice information, the system guides the rescuer through the voice information, the quality of chest compression is effectively improved, and the auxiliary system is standard, accurate, efficient and intelligent in chest compression medical behaviors.
Description
Technical Field
The invention belongs to the crossing fields of intelligent medical treatment, artificial intelligence, instrument science, computer science, sensor technology, man-machine interaction technology and the like, and particularly relates to a cardiopulmonary resuscitation chest compression compliance detection system and method.
Background
Cardiopulmonary resuscitation (Cardiopulmonary Resuscitation, CPR) is a medical technique for performing treatment of sudden cardiac arrest and apneas, and is one of the most important and fundamental first-aid measures. Cardiopulmonary resuscitation comprises three major aspects: chest compressions, external ventilation, and shock defibrillation. Wherein, chest compression throughout the life of cardiopulmonary resuscitation, after cardiac arrest, the artificial chest compression helps the patient establish extracorporeal circulation, maintain cerebral blood oxygen, and promote blood return to the heart, help the patient resume spontaneous circulation, therefore, chest compression has very important roles in cardiopulmonary resuscitation.
According to the AHA guidelines, the following requirements are made for adult normative chest compressions: 1. the pressing depth is 50-60 mm, and the frequency is 100-120 times/min; 2. after compression, sufficient chest compression release is performed. In addition, the rescuer needs to keep the time balance of pressing and rebound, so that impact pressing is avoided, when the compression is performed, the arms vertically downwards apply pressure to the center of the two breast connecting lines of the sternum of the patient, elbow bending and arm pressing inclination are avoided, and rolling pressing and pushing pressing are avoided;
Many researchers recognize that non-normative problems in chest compressions will affect the curative effect of cardiopulmonary resuscitation, and research and develop chest compression aids. The invention patent CN114983794A designs an external chest compression auxiliary device which is in a flat plate structure, is internally provided with an accelerometer and a pressure sensor and is used for acquiring compression depth and chest elasticity coefficient during external chest compression; when the structure works, the structure needs to be placed between the chest of a patient and the palm of a rescuer; to a certain extent, the sense of realism of contact between the rescuer and the patient is affected, and the touch feeling of the surface material of the pressing auxiliary equipment is always obtained. The invention patent CN114404262A designs wearable cardiopulmonary resuscitation auxiliary equipment, which is similar to a wristwatch structure, and realizes the evaluation of the depth and frequency of pressing during chest compression by taking a mechanical transmission, a gear, a motor and a proximity sensor as basic components, wherein the mechanical structure transmission has certain complexity. Therefore, in order to solve the problems that the quality monitoring dimension of the chest compression medical behavior is small, the interference or the introduction of discomfort to a rescuer is caused by the detection equipment and the clinical application is difficult in the existing chest compression auxiliary equipment, the development of the wearable chest compression multi-dimensional index compliance detection system and method for the rescuer is a work which needs to be developed by the technicians in the field.
Disclosure of Invention
In order to solve the technical problems, the invention provides a cardiopulmonary resuscitation chest compression compliance detection system and method, which aim at the defects that the prior chest compression auxiliary equipment is stuck on the sternum of a patient, or clamped between the left hand and the right hand of a rescuer, or has a complex mechanical structure, can not be used for conveniently participating in chest compression assistance, and has the defects of interference on the touch of the rescuer, discomfort introduction, influence on the judgment of the integrity and accurate force application position of the rib sternum of the rescuer, less detection information and poor convenience and interactivity.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
The invention provides a cardiopulmonary resuscitation chest compression compliance detection system which comprises a central control processing module, an inertia measurement module, a voice interaction module, a touch display module, a power supply module, a communication module and a data storage module, wherein the central control processing module is used for processing the chest compression compliance detection system:
the central control processing module adopts a low-power consumption embedded microprocessor, is responsible for logic control, data operation and algorithm deployment of the whole system, and performs data communication with the inertia measurement module, the voice interaction module, the touch display module, the power supply module, the communication module and the data storage module;
The inertial measurement module is an integrated unit composed of an accelerometer, a gyroscope and a magnetometer, and can be used for measuring triaxial inertial data of a system attachment body, wherein the triaxial inertial data comprises acceleration, angular velocity and attitude quaternion, the inertial measurement module has a data preprocessing function and transmits inertial data acquired in real time to the central control processing module through a data transmission bus, and the voice interaction module comprises a voice interaction controller, a microphone and a micro loudspeaker;
the voice interaction controller deploys a voice interaction instruction and a voice model in a required cardiopulmonary resuscitation scene, and the voice interaction module perceives the voice instruction sent by a rescuer in the environment through a microphone and gives the rescuer guidance comments and real-time feedback correction through a micro-speaker;
The touch display module consists of a miniature touch screen and a touch driving and display driving circuit, an auxiliary system is configured through the touch display module before chest compression begins, and after chest compression is completed, the touch display module is used for checking compression index detection statistical information;
The power supply module consists of a power supply conversion module, a battery and a charging module and is responsible for supplying and discharging of the whole system;
the communication module comprises wired communication and wireless communication and is used for transmitting data of the nodes to network equipment or PC equipment; the data storage module is used for storing the IMU data for implementing acquisition and the information related to the chest compression process state data.
As an auxiliary system of the invention, further improvement is as follows: the auxiliary system is matched with the shell and the rubber binding belt, the shell is formed by 3D printing, injection molding or die processing, a necessary man-machine interaction interface and an interface are reserved for the shell, the modules are installed in the shell in a sealing mode, and the rubber binding belt is used for connecting the shell and the wrist of a rescuer.
As an auxiliary system of the invention, further improvement is as follows: the low-power consumption embedded microprocessor is a single-core or multi-core processor.
As an auxiliary system of the invention, further improvement is as follows: the touch display module is matched with the voice interaction module to perform audio-visual feedback when chest compression is applied.
As an auxiliary system of the invention, further improvement is as follows: the data storage module selects the TF memory card as external storage equipment.
The invention provides a method for detecting a compliance detection system for chest compressions during cardiopulmonary resuscitation, which comprises the following specific steps:
S1: the data acquisition and segmentation of the wrist strap IMU node are carried out, and the microcontroller acquires the data output by the IMU through the UART communication interface, segments the data and adds the segmented data into a data window;
S2: carrying out coordinate transformation on the acceleration under the obtained carrier system by using the attitude quaternion;
S3: selecting acceleration in the vertical direction after coordinate transformation, performing trapezoidal value integral calculation, and then inputting a calculation result into a 0.3Hz Baud Wo Sigao pass filter to remove trend items, so as to obtain speed in the vertical direction;
s4: dividing the speed in the vertical direction into a speed curve section of a pressing stage and a rebound stage;
S5: detecting the pressing depth, and performing trapezoidal value integration on the segmented curve in the pressing and rebound stage to obtain the depth of the pressing and rebound stage;
s6: according to the fixed sampling rate and the number of data points of the speed curve obtained by segmentation in the step S4, the time consumed by pressing and rebound can be solved;
s7: a linear displacement sensor is arranged in the chest of the dummy model, and the sternum depression distance actually generated when the sternum of the dummy is pressed is acquired;
S8: obtaining a continuous pressing displacement curve, and carrying out curve characteristic identification based on peak detection and frequency domain analysis;
s9: according to the curve characteristics, solving the reference depth, frequency and time spent in the pressing and rebound processes;
S10: comparing the solution values of S9, S6 and S5 with a reference value, performing error correction by using a machine learning method,
To obtain more accurate compression depth and frequency information;
S11: and inputting the pitch angle as a characteristic vector into a long-short-term memory artificial neural network LSTM, performing sequence identification, and detecting arm compliance through an arm pressing verticality detection method and an elbow bending detection method.
As a further improvement of the method of the present invention, the method for transforming the coordinates of the acceleration obtained under the carrier system by using the attitude quaternion in the step S2 is as follows:
For the acceleration for implementing acquisition, based on the gesture quaternion, the triaxial acceleration of coordinate transformation to a geographic coordinate system is solved, and the method is based on the following algorithm:
pbody＝[0,abx,aby,abz]T
pworld＝q·pbody·q-1＝q·pbody·q*/||q||2
Wherein a bx,aby,abz is the triaxial acceleration under the IMU carrier coordinate system, p body is a virtual quaternion, the acceleration under the carrier system is described, q is the attitude quaternion under the world coordinate system obtained by IMU measurement, p world is the acceleration quaternion under the world coordinate system, and because the acceleration quaternion is also a virtual quaternion, the triaxial acceleration under the world coordinate system can be obtained by taking the imaginary part of the acceleration quaternion, and the triaxial acceleration is northeast day.
As a further improvement of the method of the present invention, the pressing depth detection method at the pressing stage of step S5 is as follows: based on the following formula:
Where a' is the bias after subtracting the gravitational acceleration, a noise is the wide-band measurement noise, A (t), V (t) and D (t) are the ideal acceleration, velocity and displacement caused by motion;
And (3) carrying out trapezoidal numerical integration again in the small section of the speed curve section of the pressing stage and the rebound stage, and solving to obtain a motion displacement Distance of the pressing and rebound process in each period, wherein the sampling rate Sample and the speed sequence Length obtained by the segmentation are known, so that the time t and the speed v of the pressing and rebound process and the average frequency f of each minute are obtained by solving:
t＝Length/Sample
v＝Distance/t
Where N is the cumulative number of compressions, t 1 is the time spent in the compression process, t 2 is the time spent in the rebound process, and a machine learning regression algorithm is introduced to correct the compression depth error, a linear regression model is applied to correct the error between the compression depth solution and the reference value, considering a set of datasets { (x i,yi), i=1, 2, …, N }, where x i is the reference depth, y i is the solution depth, the linear regression model is based on the following form:
y＝xTβ+ε
Where ε N (0, σ 2), the error variable σ 2 and the parameter vector β need to be based on existing datasets, their parameters are determined by training and iteration.
As a further improvement of the method of the present invention, the arm pressing perpendicularity detection method and the elbow bending detection method of step S11 are as follows:
In order to identify the compliance of arms and elbows of a rescuer when the rescuer applies pressure, wearing an IMU node on the wrist of the rescuer, continuously observing a pitching angle, and recording standard pressing data for a certain period of time, wherein the included angle between the arms and the horizontal plane is a threshold value for judging whether the arms and the horizontal plane are in compliance or not; arm inclination pressing data, namely an included angle between the arm and the horizontal plane is between lambda 1 and lambda 2, and lambda 1 and lambda 2 are thresholds for judging whether compliance exists or not; elbow bending press data, i.e. the elbow remains unlocked during the press, elbow angle bending changes and the elbow applies force, the data set obtained above will be used as feature observation and model training data;
Classifying the categories of the model training data sequence by using LSTM, wherein the LSTM can take a point set in a certain moment of the current sampling point history as input, and mine the categories of the characteristics of the sequence formed by the continuous point sets;
the LSTM neural network structure consists of a sequence input layer, a LSTM layer, a full connection layer, a softmax layer and a classification layer; the input layer receives the input sequence as a feature vector, the number of input layers is set to 1, the lstm layer sets the number of hidden layer neurons, and the output mode is set to sequence output when the pitch angle is used as the feature vector. Outputting a class to which a section of sequence belongs through the full connection layer, the softmax layer and the classification layer;
training using adam algorithm, calculating exponential moving average of gradient, exponential moving average of gradient square:
where β 1、β2 is the gradient descent factor and the mean square gradient descent factor, adam updates the network parameters using a moving average:
before the model training process, the number of neurons and the corresponding solver parameters in the algorithm formula are adjusted, the numerical value of the MSE of the verification set and an MSE graph in the iteration process are observed, and when the MSE is not converged any more, the identification effect is optimal. MSE measures the same descriptive statistics between predicted values and truth labels:
Wherein n is the number of feature vectors, y i and Respectively a predicted value and a true value.
Compared with the prior art, the invention has the beneficial effects that:
1. Compared with the prior auxiliary equipment which is directly placed on the sternum of a patient or clamped between left and right hands of a rescuer, the auxiliary system disclosed by the invention is worn on the wrist of the rescuer, so that the touch sense of the rescuer is not disturbed and uncomfortable to be introduced.
2. In the method, the existing double integral solving pressing depth method is improved, algorithm optimization is introduced, solving errors of pressing depth are reduced, and the accuracy of the system can meet the requirement of 50-60 mm pressing depth measurement;
3. besides the monitoring of main-stream chest compression auxiliary equipment on compression depth and frequency, the system expands the dimension of sensing chest compression quality information by introducing machine learning on a software method on the premise of not introducing hardware complexity, such as increasing the monitoring of the compliance of the posture on the arm and elbow of a rescuer.
4. The auxiliary system introduces voice interaction aiming at the chest compression scene, a rescuer controls the workflow of auxiliary equipment through voice instructions, and the auxiliary equipment feeds back the real-time detected multidimensional index to the rescuer through voice information. The voice interaction algorithm is realized at the end side of the wearable device, and network connection is not needed.
5. When the chest compression assisting system is used for chest compression assisting, training is performed on a cardiopulmonary resuscitation dummy model based on a learning mode, so that the machine learning algorithm of the system can learn compression habits of different rescuers, and learning is performed based on personalized features such as palm thickness, palm heel bending capability and the like of the rescuers, so that the method of the system can be more generalized.
Drawings
FIG. 1 is a schematic diagram of the hardware components of the wristband type auxiliary system;
FIG. 2 is a schematic diagram of the overall structure of the wristband type auxiliary system;
FIG. 3 is a schematic view of a usage scenario;
FIG. 4 is a task and algorithm framework block diagram;
FIG. 5 is a graph of continuous output of corresponding pitch angles for both normal and non-normal arm and elbow presses;
FIG. 6 is an evaluation of consistency between compression depth reference criteria and depth solutions proposed by this patent;
FIG. 7 is a flow chart of the auxiliary system operation.
Accessory description
1-1, A central control processing module; 1-2, an inertial measurement module; 1-3, a voice interaction module; 1-4, a touch display module; 1-5, a power module; 1-6, a communication module; 1-7, a data storage module; 1-8, a shell and a rubber bandage; 2-1, an interactive touch screen; 2-2, a shell; 2-3, an integrated circuit board; 2-4, rubber bandage; 3-1, patient or dummy model; 3-2, a rescuer; 3-3, auxiliary equipment.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and detailed description:
In the present application, the rescuer wears the device on his wrist to apply chest compressions to the patient in need of cardiopulmonary resuscitation. Although there is the possibility of the patient lying on a slope, in most situations where chest compressions are required, the patient is lying on a horizontal hard floor or bed with a hard backboard. Thus, in embodiments of the present application, the direction in which the patient's sternum is deformed by compression may be considered to be perpendicular to the horizontal plane. When the rescuer presses outside the chest, the hand movement of the rescuer and the inertia information of the forced movement of the sternum of the patient are identical.
As described above, most of the existing chest compression aids are placed directly on the chest of the patient, or a cell phone end application is designed and the cell phone is sandwiched between the left and right hands of the rescuer. The first one is that a hard shell is introduced to interfere the touch sense of a rescuer, and discomfort is introduced to influence the judgment of the rescuer on the integrity and accurate force application position of the rib sternum; in the latter case, the smart phone is clamped between the hands, and false touch is also easy to occur, so that the pressure applying mode of the rescuer is disturbed.
In order to solve the problems in the prior chest compression auxiliary equipment, in the application, a compliance detection system for chest compression is provided.
Referring to fig. 1, the system is composed of a central control processing module 1-1, an inertial measurement module 1-2, a voice interaction module 1-3, a touch display module 1-4, a power module 1-5, a communication module 1-6, a data storage module 1-7, a shell and a rubber bandage 1-8. The central control processing module adopts a low-power consumption embedded microprocessor which can be single-core or multi-core, is responsible for logic control, data operation and algorithm deployment of the whole system, and performs data communication with other modules such as a touch display module, a voice interaction module and the like. The inertial measurement module is an integrated unit composed of an accelerometer, a gyroscope and a magnetometer, can measure triaxial inertial data of a system attachment body, comprises acceleration, angular velocity and attitude quaternion, has a data preprocessing function, and transmits inertial data acquired in real time to the central control processing module through a data transmission bus. The voice interaction module consists of a voice interaction controller, a microphone and a micro-speaker, wherein the voice interaction controller can deploy a voice interaction instruction and a voice model under a required cardiopulmonary resuscitation scene, and the voice interaction module senses the voice instruction sent by a rescuer in the environment through the microphone and gives the rescuer guidance opinion and real-time feedback correction through the micro-speaker. The touch display module is composed of a miniature touch screen, a touch driving circuit and a display driving circuit, before chest compression begins, the auxiliary system can be configured through the touch display module, after chest compression is completed, the touch display module can check compression index detection statistical information, and preferably, the touch display module can be matched with the voice interaction module to carry out audio-visual feedback when chest compression is applied. The ground power module consists of a power conversion module, a battery and a charging module and is responsible for supplying and discharging of the whole system. The communication module comprises wired communication and wireless communication and is used for transmitting data of the nodes to network equipment or PC equipment; the data storage module is used for storing the acquired IMU data, chest compression process state data and other necessary information, and can select external storage equipment such as TF memory cards and the like; the shell is formed by 3D printing, injection molding or die processing, a necessary man-machine interaction interface and an interface are reserved for the outside of the shell, and the modules are installed in the shell in a sealing mode. Rubber straps are used to connect the housing to the wrist of the rescuer.
Referring to fig. 2, a schematic diagram of the overall structure of the wristband type auxiliary system of the present application is described, the system as a whole is composed of an interactive touch screen 2-1, a housing 2-2, an integrated circuit board 2-3, and a rubber band 2-4. Referring to fig. 3, a use scenario of the present embodiment is described, in which a patient or dummy model 3-1 lies on a horizontal ground, and a rescuer 3-2 wears an auxiliary device 3-3 proposed by the present application on the wrist, and performs chest compressions in a clinical or training scenario, without tactile or visual disturbance to the rescuer, without the rescuer changing the original chest compression habit or general operation procedure.
The embodiment of the application also provides a method for detecting the compliance of the multi-dimensional index for chest compressions. Referring to fig. 4, a task driven algorithm (method) framework is depicted, which is run in the aforementioned auxiliary system after being converted to a program by a programming language. Because the algorithm needs to run in real time in dual-core micro control to solve the target for the data acquired in real time, the program needs to maintain a dynamically updated data window and calculate according to the following algorithm steps:
s1: the wrist strap IMU receives and divides the data, and the microcontroller collects the data output by the IMU through the UART communication interface, divides the data and adds the data into the data window.
S2: carrying out coordinate transformation on the acceleration under the obtained carrier system by using the attitude quaternion;
S3: the acceleration in the vertical direction after coordinate transformation is selected, trapezoidal value integral calculation is carried out, and then the calculation result is input into a 0.3Hz Bart Wo Sigao pass filter to remove trend items, so that the speed in the vertical direction is obtained;
s4: dividing the speed in the vertical direction into a speed curve section of a pressing stage and a rebound stage;
s5: performing trapezoidal numerical integration on the segmented curve in the pressing and rebound stage to obtain the depth of the pressing and rebound stage;
s6: according to the fixed sampling rate and the number of data points of the speed curve obtained by segmentation in the step S4, the time consumed by pressing and rebound can be solved;
s7: a linear displacement sensor is arranged in the chest of the dummy model, and the sternum depression distance actually generated when the sternum of the dummy is pressed is acquired;
S8: obtaining a continuous pressing displacement curve, and carrying out curve characteristic identification based on peak detection and frequency domain analysis;
s9: obtaining reference depth, frequency and time spent in the pressing and rebound processes;
S10: comparing the solution values of S9, S6 and S5 with a reference value, performing error correction by using a machine learning method,
So as to obtain more accurate information such as pressing depth, frequency and the like;
s11: and inputting the pitch angle serving as a characteristic vector into an LSTM network, performing sequence identification, and detecting arm compliance.
The algorithm described below is analyzed in terms of the necessary details and theoretical methods:
In this embodiment, considering that the device is worn on the arm of the rescuer, the posture of the arm is changed during the chest compression, as one of the embodiments, the condition that the arm of the rescuer does not meet the standard vertical compression needs to be considered, and the posture of the device has uncertainty during wearing, therefore, the three-axis acceleration of the coordinate transformation under the geographic coordinate system needs to be solved for the acceleration of implementing the acquisition based on the posture quaternion, and the following algorithm is based:
pbody＝[0,abx,aby,abz]T
pworld＝q·pbody·q-1＝q·pbody·q*/||q||2
Wherein a bx,aby,abz is the triaxial acceleration under the IMU carrier coordinate system, and p body is a virtual quaternion describing the acceleration under the carrier system. q is an attitude quaternion under a world coordinate system obtained by IMU measurement, p world is an acceleration quaternion under the world coordinate system, and as the acceleration quaternion is also a virtual quaternion, the imaginary part of the acceleration quaternion can be taken to obtain three-axis acceleration under the world coordinate system, and three axes are northeast days respectively.
In terms of compression depth solution, the following formula is based:
Where a' is the offset after subtracting the gravitational acceleration (from low cost IMU calibration imperfections and low accuracy), a noise is the wide band measurement noise, a (t), V (t) and D (t) are the ideal motion induced accelerations, velocities and displacements.
Firstly, a 4-order 0.3Hz Bart Wo Sigao pass filter is introduced to restrain a drift trend term for a speed signal obtained after one trapezoidal integration of Z-axis acceleration after coordinate transformation, and most of the speed signal still remains in a speed solving value v after integration of broadband noise in the acceleration and errors introduced by measurement accuracy. When integrating again, the error will also accumulate continuously over the length of the acceleration sequence. After one integration and filtering, the numerical sign of the velocity changes as the direction of motion changes during the compression to rebound. Thus, we split the obtained velocity profile into compression and rebound phases, the resulting velocity sequence is also non-equal length. And carrying out trapezoidal numerical integration again in the small section interval, and solving to obtain the motion displacement in the pressing and rebound process in each period. The sampling rate and the length of the speed sequence obtained by the segmentation are known, so that the time and speed of the pressing and rebound process can be obtained by solving. Because of the error between the solving value and the true value, in the existing method, a 1Hz high-pass filter is used for correcting the solved pressing displacement error, and the low-frequency noise component in the displacement signal is restrained to a certain extent; in the foregoing analysis, we indicate that the solution error includes noise over a wide frequency band and errors introduced by low cost IMU accuracy, which results in some error between the solution value and the true value obtained by the linear displacement sensor resolution, but positive correlation.
To this end, we introduced a machine learning regression algorithm to correct the error. As an alternative embodiment, a linear regression model may be applied to correct the error between the compression depth solution and the reference value. Consider a set of datasets { (x i,yi), i=1, 2, …, n }, where x i is the reference depth and y i is the solution depth, the linear regression model is based on the following form:
y＝xTβ+ε
Where ε N (0, σ 2), the error variable σ 2 and the parameter vector β need to be based on existing datasets, their parameters are determined by training and iteration.
In this embodiment, to achieve normalized recognition of the hand, elbow and body gestures of the pressing arm, we focus the input features of the algorithm on the data of the wristband IMU, as previously described, when the rescuer applies chest compressions, we consider that the chest of the rescuer and the rescuee have the same inertial data, on the other hand, when the rescuer presses outside the chest, some non-normalized chest compression behavior occurs, such as elbow bending compressions, arm tilting compressions, kneeling long-distance longitudinal pitching compressions, etc. These non-canonical compression poses and movements are due to the fact that they will ultimately all act on the patient's sternum via the wrist connection and via the palm base. Therefore, the information of different modes such as angular velocity, acceleration, attitude angle and the like obtained by the IMU sensor at the wrist part can be used as effective observation input for evaluating arm normalization of a rescuer.
Referring to fig. 5, when the IMU node is worn on the wrist of the rescuer, continuous observation of the pitch angle is performed, and in fig. 4, the pitch angle curve is divided into three parts: segment1, segment2, segment3.segment1 describe that the arm is pressed vertically 30 times in a relatively normal posture, segment2 describes that the arm is pressed obliquely 30 times, segment3 describes that the elbow is pressed bent 30 times; from the pitch angle feature of fig. 4, the human eye can easily discern the differences between these curves.
Therefore, in the method of the present embodiment, an effective algorithm needs to be designed to be able to identify the normal and non-normal categories represented in the pitch angle continuous curve in real time.
As an alternative to identifying the normalization described above, a neural network is used to classify the classes of sequences, and LSTM may be used to handle time series classification, regression and prediction tasks. The LSTM network is a recurrent neural network that can learn the long-term dependence of time steps of sequence data. In this embodiment, the class to which the pitch angle sampling sequence of the fixed-length sampling belongs needs to be classified, and because the mapping between the time value and the value or between the value and the class constructed by the common neural network cannot satisfy the classification of the sampling sequence analogy in the application, the LSTM can use the point set in a certain moment of the current sampling point history as input, and mine the class of the characteristics of the sequence formed by the continuous point sets. In the model training process, the residual error performance of the verification set is observed by adjusting the quantity of neurons, so that the identification effect is optimal.
As one of the methods for identifying the normative of the pressing arm and the posture of the rescuer in the embodiment, it is preferable that the inertial information of other modes such as acceleration and angular velocity of the horizontal orthogonal axis is used as the input of the identification algorithm in addition to the pitch angle as the input of the algorithm, so as to enhance the robustness of the algorithm.
As described above, the method is forwarded as program code through a programming language, compiled and downloaded into a wristband device. All the calculation, reasoning, storage and communication tasks are independently completed in the wearable node, and no external computer is required to provide additional calculation force support.
Referring to fig. 6, the error distribution between the solved value after error correction and the reference value of the compression depth is described, experiments are designed, 30 participants are invited to collect 4000 times of compression experiments, after the compression depth and the reference depth are solved through the algorithm steps, an error correction model is trained through 5-fold cross validation by using a gaussian process regression model, the compression depth after error correction is predicted, the consistency between the extremum and the true value is shown in a Bland-Altman graph mode, and the upper and lower boundaries of the 95% consistency in fig. 6 are 2.9449mm and 2.9439mm respectively.
Referring to fig. 7, a flow chart of the auxiliary system operation of the present application when applied in a training or clinical setting is depicted:
S1: the rescuer configures the equipment in advance to enable the equipment to be in a standby state; the rescuer can set the feedback mode, feedback frequency, monitoring index, learning mode or training mode and other related parameter indexes of the system through the touch interaction module;
S2: the rescuer wakes up the device through the voice command, the waken command word can be customized through the habit of the rescuer, and preferably, the rescuer can wake up through one or more of various modes, such as touch, key and other modes.
S3: the device guides the rescuer to press at a standard pressing speed through the breathing effect of the audio frequency and the screen brightness and the vibration information;
s4-1 to S4-4: after the rescuer finishes starting through voice, the chest compression is started, the auxiliary system starts working, the compression times are counted, and the compression depth and frequency are solved; solving the pressing and rebound depth and time consumption of each period, and evaluating whether impact pressing exists or not, and whether the pressing and rebound consumed time is balanced or not; solving the normalization of the gesture of the arm and the elbow when pressing;
S5: the voice and image feedback and guidance correction, and the auxiliary system feeds back necessary guidance information through the voice interaction module and the touch display screen when executing the steps S4-1 to S4-4;
S6: in executing steps S4-1 to S4-4, the auxiliary system will count the number of compressions, and the compressions and ventilations are performed in a 30:2 ratio according to the AHA guidelines, so when the system counts the number of compressions 30 times, the system directs the subsequent steps of ventilation and defibrillation, etc., through voice or graphical interfaces.
S7: when the rescuer passes through the voice command, the trigger system starts a new round of auxiliary pressing monitoring, otherwise, the current real-time auxiliary system is exited.
S8: historical data is recorded, and comprehensive multidimensional evaluation in the chest compression emergency process is fed back.
S9: when the rescuer presses, a voice command is sent to trigger, namely, the patient recovers the autonomous circulation, the system can exit from the real-time auxiliary monitoring, and the system goes to S8.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the present invention in any other way, but is intended to cover any modifications or equivalent variations according to the technical spirit of the present invention, which fall within the scope of the present invention as defined by the appended claims.
Claims (7)
1. The utility model provides a cardiopulmonary resuscitation chest presses compliance detecting system, comprises central control processing module (1-1), inertial measurement module (1-2), voice interaction module (1-3), touch-control display module (1-4), power module (1-5), communication module (1-6) and data storage module (1-7), its characterized in that:
the central control processing module (1-1) adopts a low-power consumption embedded microprocessor, is responsible for logic control, data operation and algorithm deployment of the whole system, and performs data communication with the inertia measuring module (1-2), the voice interaction module (1-3), the touch display module (1-4), the power module (1-5), the communication module (1-6) and the data storage module (1-7);
The inertial measurement module (1-2) is an integrated unit composed of an accelerometer, a gyroscope and a magnetometer, and can measure triaxial inertial data of a system attachment body, wherein the triaxial inertial data comprises acceleration, angular velocity and attitude quaternion, the inertial measurement module (1-2) has a data preprocessing function and transmits inertial data acquired in real time to the central control processing module (1-1) through a data transmission bus, and the voice interaction module (1-3) is composed of a voice interaction controller, a microphone and a micro loudspeaker;
the voice interaction controller deploys a voice interaction instruction and a voice model in a required cardiopulmonary resuscitation scene, and the voice interaction module perceives the voice instruction sent by a rescuer in the environment through a microphone and gives the rescuer guidance comments and real-time feedback correction through a micro-speaker;
The touch display module (1-4) is composed of a miniature touch screen and a touch driving and display driving circuit, an auxiliary system is configured through the touch display module (1-4) before chest compression begins, and after chest compression is completed, compression index detection statistical information is checked through the touch display module (1-4);
The power supply module (1-5) consists of a power supply conversion module, a battery and a charging module and is responsible for supplying and discharging of the whole system;
The communication module (1-6) comprises wired communication and wireless communication and is used for transmitting data of the nodes to network equipment or PC equipment; the data storage module is used for storing the IMU data for implementing acquisition and the related information of the chest compression process state data; the method for detecting the cardiopulmonary resuscitation chest compression compliance detection system comprises the following specific steps of:
S1: the data acquisition and segmentation of the wrist strap IMU node are carried out, and the microcontroller acquires the data output by the IMU through the UART communication interface, segments the data and adds the segmented data into a data window;
S2: carrying out coordinate transformation on the acceleration under the obtained carrier system by using the attitude quaternion;
S3: selecting acceleration in the vertical direction after coordinate transformation, performing trapezoidal value integral calculation, and then inputting a calculation result into a 0.3Hz Baud Wo Sigao pass filter to remove trend items, so as to obtain speed in the vertical direction;
s4: dividing the speed in the vertical direction into a speed curve section of a pressing stage and a rebound stage;
S5: detecting the pressing depth, and performing trapezoidal value integration on the segmented curve in the pressing and rebound stage to obtain the depth of the pressing and rebound stage;
s6: according to the fixed sampling rate and the number of data points of the speed curve obtained by segmentation in the step S4, the time consumed by pressing and rebound can be solved;
s7: a linear displacement sensor is arranged in the chest of the dummy model, and the sternum depression distance actually generated when the sternum of the dummy is pressed is acquired;
S8: obtaining a continuous pressing displacement curve, and carrying out curve characteristic identification based on peak detection and frequency domain analysis;
s9: according to the curve characteristics, solving the reference depth, frequency and time spent in the pressing and rebound processes;
S10: comparing the solution values of S9, S6 and S5 with a reference value, and performing error correction by using a machine learning method to obtain more accurate pressing depth and frequency information;
s11: inputting a longitudinal rocking angle as a characteristic vector into a long-short-term memory artificial neural network LSTM, performing sequence identification, and detecting arm compliance through an arm pressing verticality detection method and an elbow bending detection method;
The arm pressing perpendicularity detection method and the elbow bending detection method of the step S11 are as follows:
In order to identify the compliance of arms and elbows of a rescuer when the rescuer applies pressure, wearing an IMU node on the wrist of the rescuer, continuously observing a pitching angle, and recording standard pressing data for a certain period of time, wherein the included angle between the arms and the horizontal plane is a threshold value for judging whether the arms and the horizontal plane are in compliance or not; arm inclination pressing data, namely an included angle between the arm and the horizontal plane is between lambda 1 and lambda 2, and lambda 1 and lambda 2 are thresholds for judging whether compliance exists or not; elbow bending press data, i.e. the elbow remains unlocked during the press, elbow angle bending changes and the elbow applies force, the data set obtained above will be used as feature observation and model training data;
Classifying the categories of the model training data sequence by using LSTM, wherein the LSTM can take a point set in a certain moment of the current sampling point history as input, and mine the categories of the characteristics of the sequence formed by the continuous point sets;
The LSTM neural network structure consists of a sequence input layer, a LSTM layer, a full connection layer, a softmax layer and a classification layer; the input layer receives an input sequence as a feature vector, when the pitch angle is used as the feature vector, the number of the input layer is set to be 1, the lstm layer is set to be the number of hidden layer neurons, the output mode is set to be sequence output, and a section of class to which the sequence belongs is output through the full connection layer, the softmax layer and the classification layer;
Training was performed using adam algorithm, calculating an exponential moving average of gradient m l, an exponential moving average of gradient square v l:
where β 1、β2 is the gradient descent factor and the mean square gradient descent factor, m l-1 is the exponential moving average of the gradient over the last time step, v l-1 is the exponential moving average of the gradient square over the last time step, Is the gradient of the current time step;
Next, using m l and v l solved by the above equation, adam updates the network parameters using a moving average:
θ l is the parameter of the current time step, α is the learning rate, ε is a constant;
Before the model training process, the number of neurons and corresponding solver parameters in the algorithm formula are adjusted, the numerical value of an MSE of a verification set and an MSE graph in an iterative process are observed, when the MSE is not converged any more, the identification effect is optimal, and the MSE measures the same descriptive statistics between a predicted value and a true value label:
Wherein n is the number of feature vectors, y i and Respectively a predicted value and a true value.
2. The cardiopulmonary resuscitation chest compression compliance detection system of claim 1, wherein: the auxiliary system is matched with the shell and the rubber binding belt, the shell is formed by 3D printing, injection molding or die processing, a necessary man-machine interaction interface and an interface are reserved for the shell, the modules are installed in the shell in a sealing mode, and the rubber binding belt is used for connecting the shell and the wrist of a rescuer.
3. The cardiopulmonary resuscitation chest compression compliance detection system of claim 1, wherein: the low-power consumption embedded microprocessor is a single-core or multi-core processor.
4. The cardiopulmonary resuscitation chest compression compliance detection system of claim 1, wherein: the touch display module (1-4) is matched with the voice interaction module to perform audio-visual feedback when chest compression is applied.
5. The cardiopulmonary resuscitation chest compression compliance detection system of claim 1, wherein: the data storage module selects the TF memory card as external storage equipment.
6. The cardiopulmonary resuscitation chest compression compliance detection system of claim 1, wherein:
the method for transforming the coordinates of the acceleration under the obtained carrier system by using the attitude quaternion in the step S2 is as follows:
For the acceleration for implementing acquisition, based on the gesture quaternion, the triaxial acceleration of coordinate transformation to a geographic coordinate system is solved, and the method is based on the following algorithm:
pbody＝[0,abx,aby,abz]T
pworld＝q·pbody·q–1＝q·pbody·q*/||q||2
Wherein a bx,aby,abz is the triaxial acceleration under the IMU carrier coordinate system, p body is a virtual quaternion, the acceleration under the carrier system is described, q is the attitude quaternion under the world coordinate system obtained by IMU measurement, p world is the acceleration quaternion under the world coordinate system, and because the acceleration quaternion is also a virtual quaternion, the triaxial acceleration under the world coordinate system can be obtained by taking the imaginary part of the acceleration quaternion, and the triaxial acceleration is northeast day.
7. The method of cardiopulmonary resuscitation chest compression compliance detection system according to claim 1, wherein:
The method for detecting the pressing depth in the pressing stage in the step S5 is as follows: based on the following formula:
Wherein a represents the acceleration of the IMU in the vertical direction under the geographic coordinate system, V represents the speed generated by a, a' is the offset after subtracting the gravitational acceleration, a noise is the wide-band measurement noise, the acceleration, the speed and the displacement of the arm motion are respectively represented by A (t), V (t) and D (t), V noise,dnoise represents the noise components in the speed and displacement analysis, C d is a displacement constant term, and C v is a speed constant term; and (3) carrying out trapezoidal numerical integration again in the small section of the speed curve section of the pressing stage and the rebound stage, and solving to obtain a motion displacement Distance of the pressing and rebound process in each period, wherein the sampling rate Sample and the speed sequence Length obtained by the segmentation are known, so that the time t and the speed v of the pressing and rebound process and the average frequency f of each minute are obtained by solving:
t＝Length/Sample
v＝Distance/t
Where N is the cumulative number of compressions, t 1 is the time spent in the compression process, t 2 is the time spent in the rebound process, and a machine learning regression algorithm is introduced to correct the compression depth error, a linear regression model is applied to correct the error between the compression depth solution and the reference value, considering a set of datasets { (x i,yi), i=1, 2, …, N }, where x i is the reference depth, y i is the solution depth, the linear regression model is based on the following form:
y＝xTβ+ε
Where ε N (0, σ 2), the error variable σ 2 and the parameter vector β need to be based on existing datasets, their parameters are determined by training and iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211729849.3A CN116019443B (en) | 2022-12-30 | 2022-12-30 | Cardiopulmonary resuscitation chest compression compliance detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211729849.3A CN116019443B (en) | 2022-12-30 | 2022-12-30 | Cardiopulmonary resuscitation chest compression compliance detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116019443A CN116019443A (en) | 2023-04-28 |
| CN116019443B true CN116019443B (en) | 2024-07-19 |
Family
ID=86071836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211729849.3A Active CN116019443B (en) | 2022-12-30 | 2022-12-30 | Cardiopulmonary resuscitation chest compression compliance detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116019443B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116994746B (en) * | 2023-09-27 | 2024-01-30 | 普美康(江苏)医疗科技有限公司 | Intelligent AED first aid auxiliary method, system, device and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114886758A (en) * | 2022-04-28 | 2022-08-12 | 东南大学 | Wearable doctor motion acquisition device for cardio-pulmonary resuscitation and use method |
| CN115227234A (en) * | 2022-07-07 | 2022-10-25 | 电子科技大学 | Cardiopulmonary resuscitation pressing action evaluation method and system based on camera |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11219575B2 (en) * | 2016-03-23 | 2022-01-11 | Zoll Medical Corporation | Real-time kinematic analysis during cardio-pulmonary resuscitation |
| US11213454B1 (en) * | 2021-06-05 | 2022-01-04 | Altrix Medical, Inc. | Method to provide real-time feedback and coaching to augment cardiac rescue |
-
2022
- 2022-12-30 CN CN202211729849.3A patent/CN116019443B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114886758A (en) * | 2022-04-28 | 2022-08-12 | 东南大学 | Wearable doctor motion acquisition device for cardio-pulmonary resuscitation and use method |
| CN115227234A (en) * | 2022-07-07 | 2022-10-25 | 电子科技大学 | Cardiopulmonary resuscitation pressing action evaluation method and system based on camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116019443A (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102915111B (en) | A kind of wrist gesture control system and method | |
| WO2018120964A1 (en) | Posture correction method based on depth information and skeleton information | |
| US20200275895A1 (en) | Methods and apparatus for unsupervised one-shot machine learning for classification of human gestures and estimation of applied forces | |
| CN112739254A (en) | Neuromuscular control of augmented reality systems | |
| JP2021535465A (en) | Camera-guided interpretation of neuromuscular signals | |
| WO2022193851A1 (en) | Method and system for recognizing user actions | |
| CN106527738A (en) | Multi-information somatosensory interaction glove system and method for virtual reality system | |
| CN111318009A (en) | Somatosensory health entertainment system based on wearable inertial sensing and working method thereof | |
| JP7520123B2 (en) | Systems and methods for automated anomaly detection in mixed human-robot manufacturing processes | |
| CN107194193A (en) | A kind of ankle pump motion monitoring method and device | |
| CN111708433B (en) | Gesture data acquisition glove and sign language gesture recognition method based on gesture data acquisition glove | |
| CN107389052A (en) | A kind of ankle pump motion monitoring system and terminal device | |
| KR102453304B1 (en) | A system that provides virtual reality content for dementia prevention and self-diagnosis | |
| CN111539245B (en) | CPR (CPR) technology training evaluation method based on virtual environment | |
| CN116019443B (en) | Cardiopulmonary resuscitation chest compression compliance detection system and method | |
| CN115105819B (en) | Motion monitoring method and system | |
| CN113341564A (en) | Computer input device | |
| CN113663312A (en) | Micro-inertia-based non-apparatus body-building action quality evaluation method | |
| CN114224325A (en) | Gait analysis system and method for calculating joint moment and angle by using inertial sensor | |
| Tu et al. | A Review of Human Motion Monitoring Methods using Wearable Sensors. | |
| KR102425481B1 (en) | Virtual reality communication system for rehabilitation treatment | |
| Miao et al. | A novel approach for upper limb functionality assessment based on deep learning and multimodal sensing data | |
| Viana et al. | GymApp: A real time physical activity trainner on wearable devices | |
| CN110694252A (en) | Running posture detection method based on six-axis sensor | |
| KR102429627B1 (en) | The System that Generates Avatars in Virtual Reality and Provides Multiple Contents |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |