CN113706827A - Wireless acquisition system for vital signs of household old people - Google Patents

Wireless acquisition system for vital signs of household old people Download PDF

Info

Publication number
CN113706827A
CN113706827A CN202111029610.0A CN202111029610A CN113706827A CN 113706827 A CN113706827 A CN 113706827A CN 202111029610 A CN202111029610 A CN 202111029610A CN 113706827 A CN113706827 A CN 113706827A
Authority
CN
China
Prior art keywords
data
unit
signal
module
user
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.)
Pending
Application number
CN202111029610.0A
Other languages
Chinese (zh)
Inventor
吴俊宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Yuantu Interconnection Technology Co ltd
Original Assignee
Zhejiang Yuantu Interconnection Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Yuantu Interconnection Technology Co ltd filed Critical Zhejiang Yuantu Interconnection Technology Co ltd
Priority to CN202111029610.0A priority Critical patent/CN113706827A/en
Publication of CN113706827A publication Critical patent/CN113706827A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438Sensor means for detecting
    • G08B21/0453Sensor means for detecting worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0407Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
    • G08B21/043Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438Sensor means for detecting
    • G08B21/0446Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines

Abstract

The invention discloses a wireless acquisition system for vital signs of a family elder in the technical field; the system comprises a data acquisition module, a remote server module and a user module; s1: the data acquisition module includes: collecting human body node data, blood sugar data and pulse data; s2: the remote server module includes: the system comprises a communication unit, a section unit, a database unit and a data processing unit; s3: the user module includes: a display unit and an ANDROID application; the human body phase data acquisition comprises a signal processing unit, a signal filtering unit and a signal input unit, the blood sugar data acquisition comprises a signal processing unit and a signal acquisition unit, and the pulse data acquisition comprises a signal processing unit, a signal filtering unit and a signal acquisition unit. The invention has the beneficial effects that: convenient operation can not reveal the old man privacy, really provides the guarantee to the safety and health of solitary old man, and the rate of accuracy is high, can guarantee to a certain extent to take timely effectual rescue measure to falling down the old man.

Description

Wireless acquisition system for vital signs of household old people
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a wireless acquisition system for vital signs of the elderly at home.
Background
The aging of population becomes a problem to be solved urgently in China, but the existing endowment service organizations and facilities cannot fundamentally meet the endowment requirements of 2.12 million old people in China. Under the existing national conditions, the old people mostly stay on duty or live with children, and according to statistics, falling down becomes the most easily occurring safety incident in the old people group, so that the accurate and timely nursing and monitoring of the old people can effectively avoid the serious consequence that the old people cannot be timely treated due to falling down. Therefore, those skilled in the art provide a wireless collecting system for vital signs of the elderly at home to solve the above problems in the background art.
Disclosure of Invention
The invention aims to provide a wireless acquisition system for vital signs of the elderly at home to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a wireless acquisition system for vital signs of the household old people comprises a data acquisition module, a remote server module and a user module;
s1: the data acquisition module includes: collecting human body node data, blood sugar data and pulse data;
s2: the remote server module includes: the system comprises a communication unit, a section unit, a database unit and a data processing unit;
s3: the user module includes: a display unit and an ANDROID application;
human phase data acquisition includes signal processing unit, signal filtering unit and signal input unit, blood sugar data acquisition includes signal processing unit and signal acquisition unit, pulse data acquisition includes signal processing unit, signal filtering unit and signal acquisition unit, the ANDROID application program includes data receiving unit and alarm initiating unit.
Preferably: the data acquisition module is provided with four sole pressure sensors and five six-axis screw instrument acceleration sensors, the pressure sensors are mainly positioned on the soles and used for acquiring pressure values of four points of each sole, the six-axis acceleration sensors are internally provided with three-axis angular velocity sensors and three-axis acceleration sensors and are mainly applied to measuring the isoangular velocities and accelerations of the tail ends of the chest, the left hand and the right leg so as to acquire various data of human body nodes, a signal input unit in the human body phase data acquisition is mainly composed of a ZCH304 pressure sensor, a BMI160 six-axis screw instrument acceleration sensor internally provided with three-axis angular velocity sensors and three-axis acceleration sensors, a signal filtering unit is used for acquiring signals generated by the signal input unit and processing the signals by an adaptive filter to attenuate noise, and a signal processing unit is used for acquiring signals amplified by the signal amplifying unit, the signal is converted from analog quantity to digital quantity, so that the analysis of a remote service module is facilitated; a signal acquisition unit in blood sugar data acquisition, which consists of GA-3 type blood sugar test paper and an MC9S08LL16CLH chip and acquires a circuit signal in a blood sugar measurement circuit, wherein the signal processing unit adopts an MCP6002 operational amplifier as a circuit and converts the circuit signal acquired from the data acquisition unit into a digital quantity through an A/D module; the signal acquisition unit in the pulse data acquisition adopts HK1205 piezoelectric type pulse sensor to detect pulse signals, and the signal filtering unit is used for obtaining the signals generated by the signal input unit and passing the signals through the signal amplification conditioning circuit, and the signal processing unit is used for obtaining the signals amplified by the signal amplification unit and converting the signals from analog quantity to digital quantity, thereby facilitating the analysis of the remote service module.
Preferably: the remote server module is used for storing and analyzing data such as user pulse, blood sugar and human body node data collected by the data collection module; the communication unit in the remote service module is a network communication interface unit with the server side based on the GPRS232-7S3 module, and a user can monitor query data in real time and monitor the health condition of the user based on real-time monitoring software of a Web front end; the database unit is used for storing data such as pulse, blood sugar, plantar pressure, three-axis angular velocity, three-axis acceleration and the like; the data processing unit, because data such as sole pressure, triaxial angular velocity and triaxial acceleration are the chronogenesis data, data processing unit will judge whether the user falls down based on DSGU algorithm, wherein DSGU algorithm includes: the method comprises the steps of collecting vital sign data of a user in various living states, constructing a data set, preprocessing the data, dividing the data into a training set, a testing set and a verification set according to the ratio of 6: 3: 1, constructing a DSGU neural network for detecting whether falling occurs, training the neural network by using the testing set and the verification set to enable the neural network to reach the highest precision, collecting wearable system data in real time, inputting the data into the DSGU network, and judging whether falling occurs.
Preferably: the user module is used for displaying user data information, the user module is an ANDROID application program and is used for receiving data of the remote service module and sending an alarm, and meanwhile, the user can check body health data through the terminal.
The DSGU network used in the method is a cyclic structure used for learning time sequence data relationship, and by optimizing the cyclic network structures such as RNN, LSTM, GRU and the like, the number of parameters required by training in a time classification task is reduced, and the training speed is accelerated. LSTM uses mainly three gate functions to control the flow of information across time steps to determine if previous information needs to be retained or forgotten. However, DSGU only sets reset and update gates, which makes DSGU simpler and faster in terms of computation time compared to LSTM. The input sequence of DSGU is { xt|x1,x2,...,xnThe intermediate state of the hidden layer sequence is
Figure BSA0000251598760000031
The final state is { ht|h1,h2,...,hn}。
DSRU network reset gate r of the present inventiontUpdate gate ztOutput sequence ytAs shown in fig. 5, as follows:
xg=Wgxt+bg
rt=σr(Wr[ht-1,xg])
Figure BSA0000251598760000032
zt=σz(Wz[ht-1,xt])
Figure BSA0000251598760000033
in the formula, xtTo input a sequence, rtTo reset the gate, ztTo update the gate, 'o' is the Hadamard product,
Figure BSA0000251598760000034
intermediate states of the hidden layer at time t, htFor the final state of the hidden layer at time t, ht-1The final state of the hidden layer at time t-1, bg,boRepresents a bias term, Wg,Wr,Wz,WoRepresenting a weight parameter, σr,σh,σzRepresenting sigmoid activation functions
Figure BSA0000251598760000035
Reset gate r in DSGUtFirst, for the input sequence xtLinear transformation to xg,xgPassing through sigmoid sigmarProcessing the gate function to obtain rtTo a certain extent, rtDetermines h of the previous timet-1To pair
Figure BSA0000251598760000036
The influence of (c). Update gate z in DSGUtIs an internal memory unit of DSGU, and is composed of input sequence xtAnd a hidden layer h of the previous momentt-1Obtained by weight processing and sigmoid function, ztDetermining the hidden layer h at the current momenttIncluding the last time information and the degree of bias of the time information.
The wearable sensor is characterized in that the acquisition frequency is set to be j Hz, data such as sole pressure, three-dimensional angular velocity and three-dimensional acceleration acquired within L seconds are used as original data, a total jL acquisition points form three original data sets, the sizes of the three original data sets are 1 xjL, 3 xjL and 3 xjL respectively, and labels are added to the original data according to two categories such as falling and non-falling according to different behaviors such as user walking, jogging and falling.
Step 402, the original data is preprocessed, in order to improve the accuracy of the model, all the original data of the invention takes the difference between the adjacent sampled data and is normalized, the formula is as follows,
ti=ai+1-ai
Figure BSA0000251598760000041
in the formula { ai|a1,a2,...,anIs the raw input data, tiIs a sequence { ai|a1,a2,...,anThe difference between the front and rear, E [ t ]i]Is a sequence ti|t1,t2,...,tnExpected value of D (t)i) Is a sequence ti|t1,t2,...,tnThe variance of.
The present example was sampled 4521, wherein the fall category was 2242 and the non-fall category was 2279, and the samples were divided into training set, test set, and verification set at a ratio of 6: 3: 1.
Step 403, as shown in fig. 4, in the forward propagation process of the neural network constructed based on the DSGU, three tensor data of the obtained plantar pressure difference, the three-axis angular velocity difference and the three-axis acceleration difference are respectively transmitted into the input layer, the full connection layer and the two layers of DSGU networks, and after the three types of data are combined and laminated, a classification result is finally obtained through the two layers of the full connection layer, the activation layer and the output layer. The invention adopts the formula that the active layer is RELU and the output layer is SoftMax, and the formulas are respectively as follows,
Figure BSA0000251598760000042
Figure BSA0000251598760000043
in the formula, q is output data of the full connection layer 2, z is a sequence obtained after q is processed by the activation layer, and finally { z ist|z1,z2,...,znGet the prediction sequence of the two-classification problem after the output layer processing
Figure BSA0000251598760000044
In the back propagation process, in steps 404 and 405, due to the two-classification problem, the loss function loss adopts binary _ cross, the loss function is optimized through regularization by L2, the square of the weight coefficient is used as the cost of the loss function, so that overfitting is favorably reduced, the optimizer selects an rmsprop optimizer, and the formula is as follows
Figure BSA0000251598760000051
In the formula
Figure BSA0000251598760000052
Predict sequence for model, { y | y1,y2The original label is used as the label.
Compared with the prior art, the invention has the beneficial effects that: firstly, the safety alarm wearable device based on the plantar pressure sensor and the six-axis acceleration sensor can detect the body condition of the old people in real time, is convenient to operate and does not leak the privacy of the old people; secondly, the blood sugar and pulse vital sign information acquisition module configured by the system can also facilitate the old people to master the health state of the old people in real time, and really provides guarantee for the safety and health of the old people living alone. Thirdly, the invention provides a DSGU deep learning network which is combined with multi-aspect data to judge whether the falling occurs, the accuracy rate is high, and timely and effective rescue measures can be guaranteed to be taken for the falling old people to a certain extent.
Drawings
FIG. 1 is a schematic diagram of a system flow structure according to the present invention;
FIG. 2 is a schematic structural diagram of an internal module structure according to the present invention;
FIG. 3 is a schematic view of the work flow structure of the alarm system of the present invention;
FIG. 4 is a diagram of the neural network structure of the DSGU algorithm of the present invention;
FIG. 5 is a diagram of the internal structure of the DSGU of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 5, in an embodiment of the present invention, a wireless acquisition system for vital signs of a household elderly person includes a data acquisition module, a remote server module and a user module;
s1: the data acquisition module includes: collecting human body node data, blood sugar data and pulse data;
s2: the remote server module includes: the system comprises a communication unit, a section unit, a database unit and a data processing unit;
s3: the user module includes: a display unit and an ANDROID application;
the human body phase data acquisition comprises a signal processing unit, a signal filtering unit and a signal input unit, the blood sugar data acquisition comprises a signal processing unit and a signal acquisition unit, the pulse data acquisition comprises a signal processing unit, a signal filtering unit and a signal acquisition unit, and the ANDROID application program comprises a data receiving unit and an alarm initiating unit.
Wherein, the data acquisition module is provided with four sole pressure sensors and five six-axis screw instrument acceleration sensors, the pressure sensors are mainly positioned on the soles and are used for acquiring pressure values of four points of each sole, the six-axis acceleration sensors are internally provided with three-axis angular velocity sensors and three-axis acceleration sensors and are mainly applied to measuring the isoangular velocities and accelerations of the tail ends of the chest, the left hand and the right hand and the left leg and further acquiring various data of human body nodes, a signal input unit in the human body stage data acquisition is mainly composed of a ZCH304 pressure sensor, a BMI160 six-axis screw instrument acceleration sensor internally provided with three-axis angular velocity sensors and three-axis acceleration sensors, a signal filtering unit is used for acquiring signals generated by the signal input unit and processing the signals by an adaptive filter to attenuate noise, a signal processing unit is used for acquiring the signals amplified by the signal amplifying unit, the signal is converted from analog quantity to digital quantity, so that the analysis of a remote service module is facilitated; a signal acquisition unit in blood sugar data acquisition, which consists of GA-3 type blood sugar test paper and an MC9S08LL16CLH chip and acquires a circuit signal in a blood sugar measurement circuit, wherein the signal processing unit adopts an MCP6002 operational amplifier as a circuit and converts the circuit signal acquired from the data acquisition unit into a digital quantity through an A/D module; the signal acquisition unit in the pulse data acquisition adopts HK1205 piezoelectric type pulse sensor to detect pulse signals, and the signal filtering unit is used for obtaining the signals generated by the signal input unit and passing the signals through the signal amplification conditioning circuit, and the signal processing unit is used for obtaining the signals amplified by the signal amplification unit and converting the signals from analog quantity to digital quantity, thereby facilitating the analysis of the remote service module.
The remote server module is used for storing and analyzing data such as user pulse, blood sugar and human body node data collected by the data collection module; the communication unit in the remote service module is a network communication interface unit with the server side based on the GPRS232-7S3 module, and a user can monitor query data in real time and monitor the health condition of the user based on real-time monitoring software of a Web front end; the database unit is used for storing data such as pulse, blood sugar, plantar pressure, three-axis angular velocity, three-axis acceleration and the like; the data processing unit, because data such as sole pressure, triaxial angular velocity and triaxial acceleration are the chronogenesis data, data processing unit will judge whether the user falls down based on DSGU algorithm, wherein DSGU algorithm includes: collecting vital sign data of a user in various living states, constructing a data set, preprocessing the data, dividing the data into a training set, a testing set and a verification set according to the ratio of 6: 3: 1, constructing a DSGU neural network for detecting whether falling occurs, training the neural network by using the testing set and the verification set to enable the neural network to reach the highest precision, collecting wearable system data in real time, inputting the data into the DSGU network, and judging whether falling occurs; the user module is used for displaying user data information, the user module is an ANDROID application program and is used for receiving data of the remote service module and sending an alarm, and meanwhile, the user can check body health data through the terminal.
In the training process, the epoch is selected to be 50, experiments show that when the epoch is 22, the model generalization effect is the best, the precision reaches 90.12%, and the trained parameters are used to judge whether the following embodiment falls down, wherein the embodiment collects vital sign data of the same user in three states of walking, jogging, falling down and the like, and the details are as follows:
example 1
The first patient wears the wireless vital sign acquisition equipment of wearing formula and walks, and the average heart rate that equipment measured patient 10 minutes is 96bmp, and average blood pressure is 115/87mmHg, and average blood glucose is 5.6mmol/L, and plantar pressure sensor 11 during walking, 12, 13, 14 peak data are 210N in proper order, 267N, 201N, 260N, and the three-dimensional acceleration sensor 21 peak data absolute value of wearing is 0.6m/s2, 0.8m/s2, 1.2m/s2, and the three-dimensional angular velocity sensor 21 peak data absolute value is about 26, 10, 59, and old man safety alarm system based on DSGU judges that the old man state is not tumbleing.
Example 2
The first patient wears the wearable wireless vital sign acquisition equipment to jogge, the average heart rate of the first patient measured by the equipment in 10 minutes is 109bmp, the average blood pressure is 135/99mmHg, the average blood sugar is 4.3mmol/L, peak data of the pressure sensors 11, 12, 13 and 14 during jogging are 298N, 189N, 301N and 178N in sequence, the absolute value of the peak data of the worn three-dimensional acceleration sensor 21 is 0.9m/s2, 1.1m/s2 and 0.4m/s2, the absolute value of the peak data of the three-dimensional angular velocity sensor 21 is about 15 degrees, 88 degrees and 10 degrees, and the old people safety alarm system based on DSGU judges that the old people state is not fallen.
Example 3
The first patient wears the wireless vital sign acquisition equipment of wearing and falls down, the average heart rate that the equipment measured the patient in 10 minutes is 98bmp, average blood pressure is 126/85mHg, average blood glucose is 6.3mmol/L, plantar pressure sensor 11 when falling down, 12, 13, 14 peak data are 498N, 103N, 378N, 57N, the three-dimensional acceleration sensor 21 who wears peak absolute value data are 2.1m/s2, 1.8m/s2, 1.9m/s2, three-dimensional angular velocity 21 sensor peak absolute value is about 79, 88, 29, old man's safety alarm system based on DSGU judges that old man's state is the fall down.
The working principle of the invention is as follows: wearable wireless vital sign acquisition equipment, and set up and be in this internal data acquisition processing module of wearable will pass sole pressure sensor, the data that six-axis spirometer acceleration sensor measured carry out filtering amplification in signal processing module, and use analog-to-digital converter to turn into digital signal with analog signal, data acquisition processing module passes through GPRS232-7S3 module in the communication unit in the teleservice module and calls socket () function, adopt transmission control protocol TCP with data transmission to data processing unit, DSGU neural network in the data processing unit will be according to sole pressure data that afferent, three-dimensional acceleration data and triaxial angular velocity data judgement old person whether tumble. If a falling event occurs; the remote server module sends the judgment result to the user module through the data communication unit in the body, and the user side sends out an alarm to inform children or hospitals to rescue in time. In addition, the data processing unit can upload measured pulse, blood sugar and other data to the database unit through the Web front-end technology and update the vital signs of the user on the interface unit in real time, so that the user can conveniently check the data in real time and know the physical health condition of the user.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (4)

1. The utility model provides a wireless collection system of old man's vital sign at home, includes data acquisition module, remote server module and user module, its characterized in that:
s1: the data acquisition module includes: collecting human body node data, blood sugar data and pulse data;
s2: the remote server module includes: the system comprises a communication unit, a section unit, a database unit and a data processing unit;
s3: the user module includes: a display unit and an ANDROID application;
human phase data acquisition includes signal processing unit, signal filtering unit and signal input unit, blood sugar data acquisition includes signal processing unit and signal acquisition unit, pulse data acquisition includes signal processing unit, signal filtering unit and signal acquisition unit, the ANDROID application program includes data receiving unit and alarm initiating unit.
2. The wireless collection system of the vital signs of the elderly at home according to claim 1, wherein: the data acquisition module is provided with four sole pressure sensors and five six-axis screw instrument acceleration sensors, the pressure sensors are mainly positioned on the soles and used for acquiring pressure values of four points of each sole, the six-axis acceleration sensors are internally provided with three-axis angular velocity sensors and three-axis acceleration sensors and are mainly applied to measuring the isoangular velocities and accelerations of the tail ends of the chest, the left hand and the right leg so as to acquire various data of human body nodes, a signal input unit in the human body phase data acquisition is mainly composed of a ZCH304 pressure sensor, a BMI160 six-axis screw instrument acceleration sensor internally provided with three-axis angular velocity sensors and three-axis acceleration sensors, a signal filtering unit is used for acquiring signals generated by the signal input unit and processing the signals by an adaptive filter to attenuate noise, and a signal processing unit is used for acquiring signals amplified by the signal amplifying unit, the signal is converted from analog quantity to digital quantity, so that the analysis of a remote service module is facilitated; a signal acquisition unit in blood sugar data acquisition, which consists of GA-3 type blood sugar test paper and an MC9S08LL16CLH chip and acquires a circuit signal in a blood sugar measurement circuit, wherein the signal processing unit adopts an MCP6002 operational amplifier as a circuit and converts the circuit signal acquired from the data acquisition unit into a digital quantity through an A/D module; the signal acquisition unit in the pulse data acquisition adopts HK1205 piezoelectric type pulse sensor to detect pulse signals, and the signal filtering unit is used for obtaining the signals generated by the signal input unit and passing the signals through the signal amplification conditioning circuit, and the signal processing unit is used for obtaining the signals amplified by the signal amplification unit and converting the signals from analog quantity to digital quantity, thereby facilitating the analysis of the remote service module.
3. The wireless collection system of the vital signs of the elderly at home according to claim 1, wherein: the remote server module is used for storing and analyzing data such as user pulse, blood sugar and human body node data collected by the data collection module; the communication unit in the remote service module is a network communication interface unit with the server side based on the GPRS232-7S3 module, and a user can monitor query data in real time and monitor the health condition of the user based on real-time monitoring software of a Web front end; the database unit is used for storing data such as pulse, blood sugar, plantar pressure, three-axis angular velocity, three-axis acceleration and the like; the data processing unit, because data such as sole pressure, triaxial angular velocity and triaxial acceleration are the chronogenesis data, data processing unit will judge whether the user falls down based on DSGU algorithm, wherein DSGU algorithm includes: the method comprises the steps of collecting vital sign data of a user in various living states, constructing a data set, preprocessing the data, dividing the data into a training set, a testing set and a verification set according to the ratio of 6: 3: 1, constructing a DSGU neural network for detecting whether falling occurs, training the neural network by using the testing set and the verification set to enable the neural network to reach the highest precision, collecting wearable system data in real time, inputting the data into the DSGU network, and judging whether falling occurs.
4. The wireless collection system of the vital signs of the elderly at home according to claim 1, wherein: the user module is used for displaying user data information, the user module is an ANDROID application program and is used for receiving data of the remote service module and sending an alarm, and meanwhile, the user can check body health data through the terminal.
CN202111029610.0A 2021-09-03 2021-09-03 Wireless acquisition system for vital signs of household old people Pending CN113706827A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111029610.0A CN113706827A (en) 2021-09-03 2021-09-03 Wireless acquisition system for vital signs of household old people

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111029610.0A CN113706827A (en) 2021-09-03 2021-09-03 Wireless acquisition system for vital signs of household old people

Publications (1)

Publication Number Publication Date
CN113706827A true CN113706827A (en) 2021-11-26

Family

ID=78657763

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111029610.0A Pending CN113706827A (en) 2021-09-03 2021-09-03 Wireless acquisition system for vital signs of household old people

Country Status (1)

Country Link
CN (1) CN113706827A (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090161915A1 (en) * 2007-12-24 2009-06-25 National Chiao Tung University Of Taiwan Multi-person pose recognition system using a zigbee wireless sensor network
CN103021129A (en) * 2012-12-04 2013-04-03 东南大学 System and method for monitoring falling down of old people
CN103393412A (en) * 2013-08-15 2013-11-20 重庆邮电大学 Intelligent home based old person caring device
CN106056849A (en) * 2016-07-15 2016-10-26 西安电子科技大学 Elder fall-down intelligent detection and positioning active and passive alarm system and method
CN106652346A (en) * 2016-12-23 2017-05-10 平顶山学院 Home-based care monitoring system for old people
CN106846729A (en) * 2017-01-12 2017-06-13 山东大学 A kind of fall detection method and system based on convolutional neural networks
CN108621159A (en) * 2018-04-28 2018-10-09 首都师范大学 A kind of Dynamic Modeling in Robotics method based on deep learning
CN109171734A (en) * 2018-10-18 2019-01-11 中国科学院重庆绿色智能技术研究院 Human body behavioural analysis cloud management system based on Fusion
CN110047247A (en) * 2019-05-21 2019-07-23 武汉理工大学 A kind of smart home device accurately identifying Falls in Old People
CN209299299U (en) * 2019-01-02 2019-08-23 常州机电职业技术学院 A kind of family endowment monitor system based on ZigBee
CN110737732A (en) * 2019-10-25 2020-01-31 广西交通科学研究院有限公司 electromechanical equipment fault early warning method
CN110766070A (en) * 2019-10-22 2020-02-07 北京威信通信息技术股份有限公司 Sparse signal identification method and device based on cyclic self-encoder
CN211484541U (en) * 2019-07-23 2020-09-15 闽南理工学院 Old person who fuses multisensor falls down prediction device

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090161915A1 (en) * 2007-12-24 2009-06-25 National Chiao Tung University Of Taiwan Multi-person pose recognition system using a zigbee wireless sensor network
CN103021129A (en) * 2012-12-04 2013-04-03 东南大学 System and method for monitoring falling down of old people
CN103393412A (en) * 2013-08-15 2013-11-20 重庆邮电大学 Intelligent home based old person caring device
CN106056849A (en) * 2016-07-15 2016-10-26 西安电子科技大学 Elder fall-down intelligent detection and positioning active and passive alarm system and method
CN106652346A (en) * 2016-12-23 2017-05-10 平顶山学院 Home-based care monitoring system for old people
CN106846729A (en) * 2017-01-12 2017-06-13 山东大学 A kind of fall detection method and system based on convolutional neural networks
CN108621159A (en) * 2018-04-28 2018-10-09 首都师范大学 A kind of Dynamic Modeling in Robotics method based on deep learning
CN109171734A (en) * 2018-10-18 2019-01-11 中国科学院重庆绿色智能技术研究院 Human body behavioural analysis cloud management system based on Fusion
CN209299299U (en) * 2019-01-02 2019-08-23 常州机电职业技术学院 A kind of family endowment monitor system based on ZigBee
CN110047247A (en) * 2019-05-21 2019-07-23 武汉理工大学 A kind of smart home device accurately identifying Falls in Old People
CN211484541U (en) * 2019-07-23 2020-09-15 闽南理工学院 Old person who fuses multisensor falls down prediction device
CN110766070A (en) * 2019-10-22 2020-02-07 北京威信通信息技术股份有限公司 Sparse signal identification method and device based on cyclic self-encoder
CN110737732A (en) * 2019-10-25 2020-01-31 广西交通科学研究院有限公司 electromechanical equipment fault early warning method

Similar Documents

Publication Publication Date Title
CN106971059B (en) Wearable equipment based on neural network self-adaptation health monitoring
CN110420019B (en) Deep regression heart rate estimation method for ballistocardiogram signals
US20160038061A1 (en) Method for detecting falls and a fall detector
Kangas et al. Sensitivity and false alarm rate of a fall sensor in long-term fall detection in the elderly
CN111248879B (en) Hypertension old people activity analysis method based on multi-mode attention fusion
CN107137071A (en) It is a kind of to analyze the method that heart impact signal is used for calculating short-term heart beat value
CN111973151B (en) Infectious disease monitoring system and method based on wearable intelligent bandage
CN106937808A (en) A kind of data collecting system of intelligent mattress
CN106901705A (en) A kind of unaware human Body Physiology Multi-parameter harvester and acquisition method and application
Czech et al. GaitPy: an open-source python package for gait analysis using an accelerometer on the lower back
CN106456024A (en) Resting heart rate monitor system
CN111325946A (en) Fall detection method and system based on edge calculation
CN110448281A (en) A kind of wearable work fatigue detection system based on multisensor
CN111631698A (en) Wearable blood pressure monitoring and correcting method based on motion mode cascade constraint
US20230298760A1 (en) Systems, devices, and methods for determining movement variability, illness and injury prediction and recovery readiness
CN112016619A (en) Fall detection method based on insoles
CN108882866A (en) The method and apparatus of urination for monitoring object
CN113040738B (en) Blood pressure detecting device
Poorani et al. Sensor based decision making inference system for remote health monitoring
Annese et al. Wearable platform for automatic recognition of Parkinson Disease by muscular implication monitoring
CN113706827A (en) Wireless acquisition system for vital signs of household old people
Ahmed et al. Classification of sleep-wake state in ballistocardiogram system based on deep learning
CN113869179A (en) Multi-mode feature attention fused home-based and aged-care intelligent monitoring method and system
Dong et al. Home-based detection of epileptic seizures using a bracelet with motor sensors
US11375896B2 (en) Edge-intelligent iot-based wearable device for detection of cravings in individuals

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20211126

RJ01 Rejection of invention patent application after publication