CN211484541U - Old person who fuses multisensor falls down prediction device - Google Patents
Old person who fuses multisensor falls down prediction device Download PDFInfo
- Publication number
- CN211484541U CN211484541U CN201921159285.8U CN201921159285U CN211484541U CN 211484541 U CN211484541 U CN 211484541U CN 201921159285 U CN201921159285 U CN 201921159285U CN 211484541 U CN211484541 U CN 211484541U
- Authority
- CN
- China
- Prior art keywords
- module
- old
- signals
- body temperature
- signal acquisition
- 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.)
- Expired - Fee Related
Links
- 230000036760 body temperature Effects 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 230000033001 locomotion Effects 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 230000009471 action Effects 0.000 claims abstract description 5
- 230000036772 blood pressure Effects 0.000 claims abstract description 5
- 230000004927 fusion Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 11
- 238000000034 method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000009977 dual effect Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002496 oximetry Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000009023 proprioceptive sensation Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The utility model discloses a multi-sensor fused old people falling prediction device, which comprises a signal acquisition module, a pulse prediction module and a body temperature prediction module, wherein the signal acquisition module is used for acquiring motion state, pulse and body temperature signals; the main control module is provided with a fuzzy neural network control module and is used for processing and calculating the acquired signals and outputting a tumble judging instruction; a Bluetooth module: data transmission is carried out through Bluetooth; the voice alarm module is used for generating an alarm signal when detecting that the action of the old exceeds an alarm threshold value; a physiological detection module: monitoring heart rate, blood pressure and body temperature signals of the old in real time; the signal acquisition module, the communication module, the voice alarm module and the physiological detection module are respectively and electrically connected with the main control module. This practicality adopts three kinds of sensors to gather different human information signals, utilizes fuzzy neural network algorithm to carry out data fusion to the human characteristic parameter and falls down the warning, improves that current intelligent wearing equipment data record deviation is great, the high condition of misstatement rate.
Description
Technical Field
The utility model relates to an old man prevents falling technical field, especially relates to a merge old person of multisensor falls down prediction unit.
Background
Most of the old people with inconvenient actions need to take care of and care of in life, and a large amount of social resources are consumed. With the increase of age, the physiological functions of the elderly are obviously changed, which is reflected in the aging of organs and the decline of functions. Wherein the aging of proprioception, vision etc. leads to the old person to take place to fall easily when using the old-person-assistant accompanying robot, not only makes the old person fear and anxiety, and can make its health cause serious damage after falling, brings very big puzzlement for its life.
The human falling is a complicated changeable process, including the motion of human four limbs and the motion of truck, through sensor acquisition people's hand touch information and the human current motion state of truck angle information description, comes to predict the falling of human body through vision and health state earlier, and the judgement time overlength, and the people only has 2 ~ 6s from the body unbalance to the whole process of falling of lying on the ground at last with the ground striking. Therefore, it is necessary to provide a device for predicting the fall of an old person, which incorporates a plurality of sensors, and which can rapidly predict the fall of the old person and perform alarm processing.
SUMMERY OF THE UTILITY MODEL
The utility model aims to overcome the defects and provide a multi-sensor fused device for predicting the fall of the old people, which comprises a signal acquisition module, a pulse and body temperature signal acquisition module and a control module, wherein the signal acquisition module is used for acquiring the motion state, the pulse and the body temperature signal; the main control module is provided with a fuzzy neural network control module and is used for processing and calculating the acquired signals and outputting a tumble judging instruction; a Bluetooth module: data transmission is carried out through Bluetooth; the voice alarm module is used for generating an alarm signal when detecting that the action of the old exceeds an alarm threshold value; a physiological detection module: monitoring heart rate, blood pressure and body temperature signals of the old in real time; the signal acquisition module, the Bluetooth module, the voice alarm module and the physiological detection module are respectively and electrically connected with the main control module.
Preferably, the signal acquisition module comprises a six-axis sensor, a heart rate monitoring sensor and a temperature sensor; the six-axis sensor is used for collecting motion state signals, the heart rate monitoring sensor is used for collecting pulse signals, and the temperature sensor is used for collecting body temperature signals.
Preferably, the physiological detection module comprises a key and a monitoring screen.
Preferably, the system also comprises a GPS + LBS dual positioning module, and the GPS + LBS dual positioning module is connected with the main control module.
Preferably, the intelligent mobile phone further comprises a conversation module, wherein the conversation module is connected with the main control module, and the conversation module enables the old people to communicate with relatives through the GSM module.
The utility model discloses owing to adopted above technical scheme, have apparent technological effect: this practicality adopts three kinds of sensors to gather different human information signals to motion data, pulse signal and temperature carry out the data fusion to human characteristic parameter when utilizing fuzzy neural network algorithm to 3 kinds of movements and fall down the warning, and it is great to improve current intelligent wearing equipment data record deviation, and the problem of the high condition of false alarm rate has higher efficiency and rate of accuracy to falling down the prediction, can judge by accurate quick to old person's health state.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic flow chart of the fuzzy neural algorithm of the present invention;
description of the main reference numerals: 1. a signal acquisition module; 2. a Bluetooth module; 3. a main control module; 4. a fuzzy neural network module; 5. a voice alarm module; 6. a physiological detection module; 7. a call module; 8. a six-axis sensor; 9. a heart rate monitoring sensor; 10. a temperature sensor; 11. and a double positioning module.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
As shown in fig. 1-2, the utility model provides a device for predicting the fall of old people with multiple sensors, which comprises a signal acquisition module 1 for acquiring motion state, pulse and body temperature signals; the main control module 3 is provided with a fuzzy neural network control module 4, and is used for processing and calculating the acquired signals and outputting a tumble judging instruction; bluetooth module 2: data transmission is carried out through Bluetooth; the voice alarm module 5 generates an alarm signal when detecting that the action of the old man exceeds an alarm threshold value; the physiological detection module 6: monitoring heart rate, blood pressure and body temperature signals of the old in real time; the signal acquisition module 1, the Bluetooth module 2, the voice alarm module 5 and the physiological detection module 6 are respectively and electrically connected with the main control module 2.
The signal acquisition module comprises a six-axis sensor 8, a heart rate monitoring sensor 9 and a temperature sensor 10; the six-axis sensor 8 is used for collecting motion state signals, the heart rate monitoring sensor 9 is used for collecting pulse signals, and the temperature sensor 10 is used for collecting body temperature signals. In the embodiment, a six-axis sensor 8 is adopted to adopt MPU-6050, the six-axis sensor 8 comprises a three-axis gyroscope, a three-axis accelerator, a three-axis digital electronic compass and an embedded complete 9-axis fusion calculation technology, and complex data measured by motion sensing can be processed; the heart rate oximetry sensor 9 employs a heart rate monitoring sensor with an integrated pulse oximeter.
The fuzzy neural network is generally a multi-layer feedforward network, which is divided into a front layer, a middle layer and a back layer. The front layer realizes fuzzification, the middle layer realizes fuzzy reasoning, and then realizes defuzzification. The algorithm process is carried out by firstly constructing a neural network according to input, determining the hierarchy and the number of the neural network, constructing a proper membership function according to input characteristic parameters and setting a corresponding fuzzy judgment rule base; calculating the input and output of each layer of network through a neuron conduction model; conducting weights of all levels of the network, training the constructed model by collected sample data, continuously adjusting and correcting weights of the neural network in the training process, carrying out fuzzy inference judgment on the dangerous or non-dangerous probability output by the network, outputting the probability of dangerous time occurrence, and judging the dangerous probability occurrence by using a threshold value method.
The utility model discloses a fuzzy neural network algorithm is as the input of network with the signal of telecommunication of 3 characteristic parameter conversions of human motion state, pulse, body temperature when dangerous signal appears, and the neural network model that founds not less than 4 layers is input layer, linear transformation layer, fuzzy layer, normalization layer, deblurring layer respectively. C. Y, T respectively represent the output values of the electric signals collected by 3 sensors of the motion state, pulse and body temperature of human body after being preprocessed. S, M, L represent respectively "small", "medium", and "large" in the fuzzy inference. After the dangerous signals are input into the neural network model, dividing the three paths of signals into S, M, L according to 3 different membership functions through connecting weights, then selecting fuzzy rules, carrying out normalization processing to obtain the probability of occurrence of 'normal N', 'fall S', 'fall L' caused by irregular heart rate, and finally outputting a dangerous event judgment result through the network.
Membership function and fuzzy inference rule:
the blurring layer mainly performs blurring processing on the first layer output quantity, and specific input quantities are represented by "S (small)", "M (medium)", and "L (large)" by a membership function. In the fuzzification process, the membership function selection has an important influence on the output of the model. The membership function established by the model adopts an S-shaped function and a Gaussian function.
Due to inputThe layer has 3 parameters, and each parameter has 3 states of "S", "M", "L", i.e. the fuzzy rule should have 33And (3) summarizing 10-15 fuzzy rules according to the rules, wherein the fuzzy rules have no actual judgment significance in consideration of the occurrence condition of actual dangerous signals, and the excessive rules increase the complexity of the model, and determining according to the subsequent training results.
The following effects are achieved:
the judgment result is N, normal signal, no alarm; if the judgment result is S, sending an alarm signal; and if the judgment result is L, sending an alarm signal and calling for help by the SOS.
Calculating each layer of unit of the neural network: and determining the input and output values of each layer of the network according to the determined membership function and the neural network conduction model.
Correcting the weight value: and finding out a proper network weight according to the established neural network model to enable the actual output of the network to be as close to the expected output as possible, determining the connection weight according to the layer number of the neural network when the system is constructed, training the connection weight by adopting an additional momentum term neural network algorithm, and adjusting the weight by utilizing a gradient descent method of error back propagation.
The working principle of the utility model is that the six-axis sensor 8, the heart rate monitoring sensor 9 and the temperature sensor 10 of the signal acquisition module 1 respectively acquire the motion state, the pulse and the body temperature signal of the user, the signal data is transmitted to the main control module 3 through the Bluetooth module 2, the fuzzy neural network control module 4 of the main control module 3 processes the signal data through the fuzzy neural network algorithm, the judgment result is normal N, and the normal signal does not give an alarm; the judgment result is a tumbling S, and an alarm signal is sent through the voice alarm module; and the judgment result is that the irregular heart rate causes the fall L, an alarm signal is sent through the voice alarm module 5, and SOS call for help is carried out. Set up GPS + LBS dual positioning module 11, the instant accurate inquiry of APP operation, the position of real time monitoring old man obtains old man's concrete position the very first time when the old man meets accident. Physiological detection module 6 carries out real time monitoring to old man's rhythm of the heart, blood pressure, body temperature signal including button and supervision screen, can change different threshold values according to different people through setting up the button, and the screen of keeping watch on makes things convenient for the old man to look over detection data. If the body temperature or the heart rate of the old people are changed sharply, an alarm signal is sent to a mobile phone of a guardian through the remote call module 7 at once, and the call module 7 comprises a GSM module and a remote monitoring module, so that the old people can communicate with relatives, the old people can call the old people in real time conveniently, the old people can get a car quickly by one key, and the trip of the old people is realized. The remote monitoring module has a wireless data transmission function, performs information interaction with the terminal through the cloud server, performs remote storage and transmission of information and data, and sends longitude and latitude positioning data information of the old people to the guardian mobile phone.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention should not be limited to the above description, and all the equivalent changes and decorations made according to the claims of the present invention should still fall within the scope covered by the present invention.
Claims (5)
1. The device for predicting the tumbling of the old people integrating the multiple sensors is characterized by comprising a signal acquisition module, a pulse prediction module and a body temperature prediction module, wherein the signal acquisition module is used for acquiring motion state, pulse and body temperature signals; the main control module is provided with a fuzzy neural network control module and is used for processing and calculating the acquired signals and outputting a tumble judging instruction; a Bluetooth module: data transmission is carried out through Bluetooth; the voice alarm module is used for generating an alarm signal when detecting that the action of the old exceeds an alarm threshold value; a physiological detection module: monitoring heart rate, blood pressure and body temperature signals of the old in real time; the signal acquisition module, the Bluetooth module, the voice alarm module and the physiological detection module are respectively and electrically connected with the main control module.
2. The old people fall prediction apparatus fusing multiple sensors according to claim 1, wherein: the signal acquisition module comprises six sensors, a heart rate monitoring sensor and a temperature sensor; the six-axis sensor is used for collecting motion state signals, the heart rate monitoring sensor is used for collecting pulse signals, and the temperature sensor is used for collecting body temperature signals.
3. The old people fall prediction apparatus fusing multiple sensors according to claim 1, wherein: the physiological detection module comprises a key and a monitoring screen.
4. The old people fall prediction apparatus fusing multiple sensors according to claim 1, wherein: the GPS and LBS dual-positioning module is connected with the main control module.
5. The old people fall prediction apparatus fusing multiple sensors according to claim 1, wherein: the intelligent mobile phone is characterized by further comprising a conversation module, wherein the conversation module is connected with the main control module, and the conversation module enables the old people to communicate with relatives through the GSM module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921159285.8U CN211484541U (en) | 2019-07-23 | 2019-07-23 | Old person who fuses multisensor falls down prediction device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201921159285.8U CN211484541U (en) | 2019-07-23 | 2019-07-23 | Old person who fuses multisensor falls down prediction device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN211484541U true CN211484541U (en) | 2020-09-15 |
Family
ID=72394302
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201921159285.8U Expired - Fee Related CN211484541U (en) | 2019-07-23 | 2019-07-23 | Old person who fuses multisensor falls down prediction device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN211484541U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110464315A (en) * | 2019-07-23 | 2019-11-19 | 闽南理工学院 | It is a kind of merge multisensor the elderly fall down prediction technique and device |
CN113706827A (en) * | 2021-09-03 | 2021-11-26 | 浙江远图互联科技股份有限公司 | Wireless acquisition system for vital signs of household old people |
CN114287920A (en) * | 2021-12-15 | 2022-04-08 | 闽南理工学院 | Old man prevents falling auxiliary device with monitoring function |
-
2019
- 2019-07-23 CN CN201921159285.8U patent/CN211484541U/en not_active Expired - Fee Related
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110464315A (en) * | 2019-07-23 | 2019-11-19 | 闽南理工学院 | It is a kind of merge multisensor the elderly fall down prediction technique and device |
CN113706827A (en) * | 2021-09-03 | 2021-11-26 | 浙江远图互联科技股份有限公司 | Wireless acquisition system for vital signs of household old people |
CN114287920A (en) * | 2021-12-15 | 2022-04-08 | 闽南理工学院 | Old man prevents falling auxiliary device with monitoring function |
CN114287920B (en) * | 2021-12-15 | 2024-03-01 | 闽南理工学院 | Old man prevents falling auxiliary device with monitoring function |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN211484541U (en) | Old person who fuses multisensor falls down prediction device | |
CN103810817B (en) | A kind of detection alarm method of the wearable human paralysis device of falling detection alarm | |
CN105342623B (en) | Intelligent tumble monitor device and its processing method | |
US9898915B2 (en) | Tracking and monitoring apparatus and system | |
CN110464315A (en) | It is a kind of merge multisensor the elderly fall down prediction technique and device | |
CN102646319B (en) | Organism-falling detection device and method | |
CN106056849B (en) | Falls Among Old People intelligent measurement and the passive warning system of master and method of positioning | |
CN105726034B (en) | Based on Wristwatch type of the alarm with track and localization function is fallen down, intelligently platform is nursed in endowment | |
CN105913614A (en) | Method and device of monitoring tumbling, intelligent wearable device and tumbling alarm system | |
US20210064141A1 (en) | System for detecting a signal body gesture and method for training the system | |
CN104224182B (en) | Method and device for monitoring human tumbling | |
CN102760341A (en) | Health information monitoring system and method | |
CN109171734A (en) | Human body behavioural analysis cloud management system based on Fusion | |
CN205050303U (en) | Human paralysis of intelligence is monitoring devices | |
CN107669250A (en) | A kind of health degree monitoring method based on big data analysis | |
CN111325946A (en) | Fall detection method and system based on edge calculation | |
CN107330240A (en) | A kind of intelligent remote based on both hands ring sensor provides special care to monitoring system and method | |
CN112603327B (en) | Electrocardiosignal detection method, device, terminal and storage medium | |
CN107633883A (en) | A kind of health degree evaluation method based on big data analysis | |
CN106650300B (en) | Old man monitoring system and method based on extreme learning machine | |
CN106228015A (en) | A kind of healthy and safe monitor system of intelligent medical based on technology of Internet of things | |
CN107019501B (en) | Remote tumble detection method and system based on genetic algorithm and probabilistic neural network | |
CN106456060A (en) | Activity amount measuring device, activity amount measuring method, activity amount measuring program | |
CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
Qu et al. | Convolutional neural network for human behavior recognition based on smart bracelet |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200915 |
|
CF01 | Termination of patent right due to non-payment of annual fee |