CN108703444B - The Intelligent bracelet and method of occupant and driver for identification - Google Patents
The Intelligent bracelet and method of occupant and driver for identification Download PDFInfo
- Publication number
- CN108703444B CN108703444B CN201810616652.6A CN201810616652A CN108703444B CN 108703444 B CN108703444 B CN 108703444B CN 201810616652 A CN201810616652 A CN 201810616652A CN 108703444 B CN108703444 B CN 108703444B
- Authority
- CN
- China
- Prior art keywords
- user
- module
- bracelet
- value
- neural network
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A44—HABERDASHERY; JEWELLERY
- A44C—PERSONAL ADORNMENTS, e.g. JEWELLERY; COINS
- A44C5/00—Bracelets; Wrist-watch straps; Fastenings for bracelets or wrist-watch straps
- A44C5/0007—Bracelets specially adapted for other functions or with means for attaching other articles
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The Intelligent bracelet and method of occupant and driver for identification, belong to intelligent wearable device field, the Intelligent bracelet includes bracelet band, bracelet shell and control circuit board, bracelet band is provided on bracelet shell, bracelet enclosure interior is embedded with control circuit board, power module is laid in control circuit board, sensor module, position tracking module, show touch-control module, wireless communication module, shock module, memory module and microprocessor, the present invention judges whether user rides on carrier by bracelet position tracking module, judge whether user has the movement of doubtful steering wheel rotation by sensor.And to mobile terminal push message several times, inquiry user whether correct judgment.After data collection several times, self study is carried out with BP neural network, realization accurately identifies user's driving states, to identify that fatigue state provides theory support with bracelet later.
Description
Technical field
The invention belongs to intelligent wearable device fields, are related to the Intelligent bracelet of a kind of occupant and driver for identification, and
A method of occupant and driver are identified based on Intelligent bracelet
Background technique
Current automobile active safety technology, is all the control theory centered on taking vehicle, and not fine consideration is driven
Sail human factor.But driver is to have absolute leading position in driving procedure in fact, the habit of driving of driver, life
Reason, psychological condition etc. all can cause tremendous influence to traffic safety.Therefore more and more scientists start to carry out to driving
The physiological research of the popular feeling.
With the development of intelligent wearable device technology, by these equipment, people can preferably perceive it is external with itself
Information, can under computer, network even other people auxiliary highly efficient rate processing information, can be realized more seamless
Exchange.More and more intelligent wearable devices be used to study fatigue detecting now.All such as amazfit and Ticwatch bracelet
There is the similar function that fatigue strength detection is carried out to user.
But the difficult point currently encountered is exactly, none accurate and high method of robustness, to judge that bracelet is
It is worn over driver or with occupant.Thus most products are detected for public daily state, without special
For the intelligent wearable device product of driver or the personnel that operate.
Summary of the invention
The technical problems to be solved by the present invention are: whether being unable to automatic identification user for existing intelligent wearable device
The problem of for driver, the present invention provides the Intelligent bracelet and method of occupant for identification and driver, combined use person's
Behavior state judges that user is or to be state by bus in driving condition, accurately to identify tired shape with bracelet later
State provides theory support.
The present invention is achieved by the following technical scheme: the Intelligent bracelet of occupant and driver for identification, feature
It is, which includes bracelet band, bracelet shell and control circuit board, and bracelet band, bracelet shell are provided on bracelet shell
Internal portion is embedded with control circuit board, and power module is laid in control circuit board, sensor module, position tracking module, is shown
Show touch-control module, wireless communication module, shock module, memory module and microprocessor, and power module, sensor module, position
It sets tracking module, display touch-control module, wireless communication module, shock module and memory module while being connect with microprocessor, institute
Stating sensor module includes position sensor and six axis gyro sensors.
Six axis gyroscopes are substituted using 3-axis acceleration sensor cooperation three-axis gyroscope in the sensor module to pass
Sensor.
The sensor module further includes heart rate sensor and blood pressure sensor.
Wherein, the power module uses position tracking module using power module BQ24050, position tracking module
AT6558, display touch-control module use wireless communication module using display touch-control module SWC208, wireless communication module
DA14580, microprocessor use six axis gyro sensors using microprocessor MSP430F169 and six axis gyro sensors
1428-1050-6-ND。
Method based on Intelligent bracelet identification occupant and driver, which is characterized in that this method is using described for knowing
The Intelligent bracelet of other occupant and driver, specifically comprise the following steps:
Step 1: starting the worn bracelet of user, bracelet and mobile terminal establish wireless communication connection；
Step 2: detecting the status information of user by the sensor module inside bracelet and sending it in bracelet
The microprocessor in portion, the microprocessor receive user status information simultaneously handle, judge user be ride state or
Driving condition, and judging result is pushed to mobile terminal, inquiry message is sent to user by mobile terminal, inquires that this is sentenced
Whether disconnected result is correct；
Alternatively,
The status information of user is detected by the sensor module inside bracelet and sends it to mobile terminal, it is mobile
The status information that terminal receives user is simultaneously handled, and judges that user is state or driving condition, while mobile end by bus
It holds to user and sends inquiry message, inquire whether the judging result is correct；
Wherein, the status information of the user include relative to the relative velocity v on ground and the behavioural information of user,
The behavioural information of user includes the roll value of user, pitch value, yaw value, X-direction acceleration, Y direction acceleration
And Z-direction acceleration, wherein roll value is the data that tilt, and pitch value is to tilt forward and back data, and yaw value is that left and right is shaken
Swing data；
Step 3: obtaining training sample, training sample is trained using BP neural network, identification user is by bus
State or driving condition, detailed process is as follows:
1. presetting training sample amount is m, m >=10 acquire m group training sample, and the training sample is by tilting
Big ups and downs number, tilt forward and back big ups and downs number, the big ups and downs number that is swung left and right, X-axis acceleration big ups and downs number,
Y-axis acceleration big ups and downs number and Z axis acceleration big ups and downs number composition；
2. establishing BP neural network, BP mind in the application program of mobile terminal according to preset training sample amount
It is made of through network architecture input layer, hidden layer and output layer, hidden layer is located between input layer and output layer, BP nerve
Network have 6 input nodes and 1 output node, the big ups and downs number that will tilt, tilt forward and back big ups and downs number,
Be swung left and right big ups and downs number, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and Z axis acceleration is acute
Input of the training sample that strong fluctuation number is constituted as BP neural network, user are that state or driving condition are corresponding by bus
Output of the parameter as BP neural network；
3. initializing BP neural network, activation primitive is selected, wherein the activation primitive of hidden layer uses tanh function, output
The activation primitive of layer uses Sigmoid function；
4. training sample is inputted BP neural network, it is trained using error backpropagation algorithm, BP neural network
When all reality outputs and consistent its target output, training terminates；Otherwise, by correcting weight, make the target of BP neural network
Output is consistent with reality output, and identification user is ride state or driving condition.
Judge that user is as follows for state by bus or the process of driving condition in the step 2:
When relative velocity v > 25km/h and v < 130km/h relative to ground, judgement operation is executed, is analyzed t seconds continuous
The roll value of user, pitch value, yaw value, X-direction acceleration, Y direction acceleration and Z-direction add in detection time
Continuous t seconds detection time is divided into N number of detection cycle by speed, and each detection cycle is user in r seconds, u-th r seconds
The standard deviation of roll value is greater than 13.5, and when standard deviation of pitch value and yaw value is respectively less than 6.5 is denoted as go to action, otherwise remembers
For non-go to action, go to action and non-go to action constitute steering wheel rotation groups of operands a [u], and a [u] is for sentencing section use
Person's hand motion whether the rotary motion of plane where relative direction disk；The X-direction for obtaining user in u-th of r seconds accelerates
Degree, the maximum value of Y direction acceleration and Z-direction acceleration, respectively x, y, z, z > (5x+5y) Shi Jiwei translation motion,
Otherwise it is denoted as non-translation motion, translation motion and non-translation motion constitute steering wheel translation array b [u], and b [u] is for sentencing
Section user hand motion whether relative direction disk translational motion in the plane；Rotary motion in continuous t seconds detection times
Matching degree threshold value with translational motion is M, otherwise it is the state of riding that 0.8 < M < 1.2, which determines that user is in driving condition, wherein
The matching degree threshold value of rotary motion and translational motion is that M meets relational expression and is in continuous t seconds detection times
The r value is 3 seconds.
Relative velocity v continuous 10 minutes relative to ground both less than 25km/h, are judged as and exit driving condition, and to shifting
Dynamic terminal PUSH message, inquires whether the result of judgement is correct.
Through the above design, the present invention can be brought the following benefits compared with prior art: the present invention passes through
Bracelet position tracking module judges whether user rides on carrier, judges whether user has doubtful rotation by sensor
The movement of steering wheel.And to mobile terminal push message several times, inquiry user whether correct judgment.Passing through several numbers
After collection, self study is carried out with BP neural network, realization accurately identifies user's driving states, to use bracelet later
Identify that fatigue state provides theory support.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description explanation does not constitute improper restriction of the invention for understanding the present invention, in the accompanying drawings:
Fig. 1 is the structural block diagram of the Intelligent bracelet of occupant and driver for identification in the embodiment of the present invention.
Specific embodiment
In order to avoid obscuring essence of the invention, there is no detailed for well known method, process, process, element and circuit
Narration.
The invention proposes the Intelligent bracelets of a kind of occupant and driver for identification, as shown in Figure 1, the Intelligent bracelet packet
Bracelet band, bracelet shell and control circuit board are included, bracelet band is provided on bracelet shell, bracelet enclosure interior is embedded with control electricity
Road plate is laid with power module, sensor module, position tracking module, display touch-control module, wireless communication in control circuit board
Module, shock module, memory module and microprocessor, and power module, sensor module, position tracking module, display touch-control
Module, wireless communication module, shock module and memory module are connect with microprocessor simultaneously, and the sensor module includes position
Sensor and six axis gyro sensors.
Six axis gyroscopes are substituted using 3-axis acceleration sensor cooperation three-axis gyroscope in the sensor module to pass
Sensor.
The sensor module further includes heart rate sensor and blood pressure sensor, respectively the heart rate of real-time monitoring user,
Blood pressure parameter, and these parameters are transmitted to microprocessor MSP430F169.
The power module uses position tracking modules A T6558 using power module BQ24050, position tracking module, shows
Show touch-control module using display touch-control module SWC208, wireless communication module using wireless communication module DA14580, microprocessor
Six axis gyro sensor 1428-1050-6-ND are used using microprocessor MSP430F169 and six axis gyro sensors.
The invention also provides a kind of methods based on Intelligent bracelet identification occupant and driver, and this method is using described
The Intelligent bracelet of occupant and driver for identification, specifically comprises the following steps:
Step 1: starting the worn bracelet of user, bracelet and mobile terminal establish wireless communication connection；
Step 2: detecting the status information of user by the sensor module inside bracelet and sending it in bracelet
The microprocessor in portion, the microprocessor receive user status information simultaneously handle, judge user be ride state or
Driving condition, and judging result is pushed to mobile terminal, inquiry message is sent to user by mobile terminal, inquires that this is sentenced
Whether disconnected result is correct；
Alternatively,
The status information of user is detected by the sensor module inside bracelet and sends it to mobile terminal, it is mobile
The status information that terminal receives user is simultaneously handled, and judges that user is state or driving condition, while mobile end by bus
It holds to user and sends inquiry message, inquire whether the judging result is correct；
Wherein, the status information of the user include relative to the relative velocity v on ground and the behavioural information of user,
The behavioural information of user includes the roll value of user, pitch value, yaw value, X-direction acceleration, Y direction acceleration
And Z-direction acceleration, wherein roll value is the data that tilt, and pitch value is to tilt forward and back data, and yaw value is that left and right is shaken
Swing data；
Step 3: acquisition training sample, is trained training sample using BP neural network, identification user is by bus
State or driving condition, detailed process is as follows:
1. presetting training sample amount is m, m >=10 acquire m group training sample, and the training sample is by tilting
Big ups and downs number, tilt forward and back big ups and downs number, the big ups and downs number that is swung left and right, X-axis acceleration big ups and downs number,
Y-axis acceleration big ups and downs number and Z axis acceleration big ups and downs number composition；
2. establishing BP neural network, BP mind in the application program of mobile terminal according to preset training sample amount
It is made of through network architecture input layer, hidden layer and output layer, hidden layer is located between input layer and output layer, BP nerve
Network have 6 input nodes and 1 output node, the big ups and downs number that will tilt, tilt forward and back big ups and downs number,
Be swung left and right big ups and downs number, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and Z axis acceleration is acute
Input of the training sample that strong fluctuation number is constituted as BP neural network, user are that state or driving condition are corresponding by bus
Output of the parameter as BP neural network；
3. initializing BP neural network, activation primitive is selected, wherein the activation primitive of hidden layer uses tanh function, output
The activation primitive of layer uses Sigmoid function；
4. training sample input BP neural network is trained using error backpropagation algorithm, the institute of BP neural network
When having reality output and consistent its target output, training terminates；Otherwise, by correcting weight, keep the target of BP neural network defeated
Consistent with reality output out, identification user is ride state or driving condition.
The present invention is described in further detail below, to enable those skilled in the art can be real accordingly referring to text
It applies.
After user wears bracelet, start the worn bracelet of user, bracelet is started to work, and user starts to drive
It sails.Module DA14580 is contacted with mobile terminal foundation by wireless communication after bracelet work, by being embedded in bracelet of the present invention
Position sensor AT6558, collect relative velocity v of the bracelet relative to ground；
(or accelerated using three axis by the six axis gyro sensor 1428-1050-6-ND that are embedded in bracelet of the present invention
Degree sensing KS91BHAAM-313B cooperation three-axis gyroscope substitutes six axis gyro sensors), the behavioral data of user is collected,
The roll value of user can be collected, pitch value, yaw value, X-direction acceleration, Y direction acceleration or Z-direction add
The comprehensive multidate information that speed is constituted, roll value are the data that tilt, and pitch value is to tilt forward and back data, and yaw value is a left side
Wave data in the right side；
By the memory module and microprocessor MSP430F169 inside bracelet, storage and analyte sensors module are collected
Data, and processing result is exported；
As v > 25km/h and v < 130km/h, into link is judged roughly, six axis in continuous t seconds detection time are analyzed
The roll value for the user that gyro sensor 1428-1050-6-ND is detected, pitch value, yaw value, X-direction acceleration,
Continuous t seconds detection time is divided into N number of detection cycle, each detection cycle by Y direction acceleration and Z-direction acceleration
It is 3 seconds, is judging link roughly, according to standard deviation s calculation formula:
Wherein xu is u-th of sample,For sample mean, w is sample size, the roll value for being assigned a value of user of xu,
Pitch value or yaw value, the standard deviation of the roll value of user is greater than 13.5, and the mark of pitch value and yaw value in u-th 3 seconds
Quasi- difference is denoted as go to action when being respectively less than 6.5, is otherwise denoted as non-go to action, and go to action and non-go to action constitute steering wheel
Rotate groups of operands a [u], a [u] be used to sentence section user's hand motion whether the rotary motion of plane where relative direction disk,
Steering wheel rotation groups of operands a [u] is set to 1 when go to action, otherwise sets 0；Obtain the X-direction of user in u-th 3 seconds
Acceleration, the maximum value of Y direction acceleration and Z-direction acceleration, respectively x, y, z, it is dynamic that when z > (5x+5y), is denoted as translation
Make, be otherwise denoted as non-translation motion, translation motion and non-translation motion constitute steering wheel translation array b [u], and b [u] is used for
Sentence section user's hand motion whether relative direction disk translational motion in the plane, translation motion is by steering wheel translation
Array b [u] is set to 1, otherwise sets 0；The matching degree threshold value of rotary motion and translational motion is M in continuous t second detection times, 0.8 <
M < 1.2 determines that user is in driving condition, is otherwise the state of riding, i.e., without driving behavior, wherein in continuous t seconds detection time
The matching degree threshold value of rotary motion and translational motion is that M meets relational expression are as follows:
At v continuous 10 minutes, both less than 25km/h, was judged as and exits driving condition, then to mobile terminal PUSH message, ask
Ask whether the result of user's judgement is correct.But the push times of default in total are set m times, m >=10 can be in mobile terminal
The interior value for changing m.More than no longer carrying out self study behavior after m value.
It is described in further detail below to by establishing BP neural network progress self study behavior step principle:
BP neural network architecture is made of input layer, hidden layer and output layer, and hidden layer is located at input layer and output
Between layer, totally interconnected connection, the neuron in each level are formed in used BP neural network between the neuron of each level
Between do not connect, the output of input layer is identical as input.The operating characteristic of the neuron of hidden layer and output layer are as follows:
opj=fj(netpj)；
Wherein p indicates current input sample number, and input sample is above-mentioned six axis gyro sensor 1428-1050-
6 variables that 6-ND is measured；ωjiFor from neuron i to the connection weight of neuron j, opiFor the current input of neuron j,
netpjFor the input of neuron j, opjFor the output of neuron j, fjFor activation primitive, it is generally taken as Sigmoid type function, i.e.,
The effect of aforesaid operations is that 6 variables for measuring six axis gyro sensor 1428-1050-6-ND pass through connection
Weight and activation primitive are mapped to judging result, i.e., when output layer parameter is 0, user is in state by bus at this time；Work as output
When layer parameter is 1, user is in driving condition at this time.
In the present invention, 6 parameters of input layer are respectively indicated are as follows: the big ups and downs number that tilts tilts forward and back violent wave
Dynamic number, the big ups and downs number that is swung left and right, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and Z axis
Acceleration big ups and downs number.
The preparation method of input layer parameter measures for sensor module, then gives after being handled by microprocessor MSP430F169
Out.
When output layer parameter is 0, user is in state by bus at this time；When exporting layer parameter is 1, at this time at user
In driving condition.
After establishing BP neural network, BP neural network is trained.Each subnet is using individually trained method；Training
When, it first has to provide one group of training sample, each of these sample, to forming, is inputted new by input sample and target output
Sample or a new periodic samples, until BP neural network restrains, in training in each period sample input sequence will again with
Machine sequence shows that training terminates when all reality outputs of BP neural network and consistent its target output；Otherwise, by repairing
Positive weight exports the target of BP neural network consistent with reality output.
In system design, system model is one merely through the BP neural network being initialized, and weight needs basis to exist
The training sample obtained in use process carries out study adjustment, devises the self-learning function of system thus.Specifying study
In the case where sample and quantity, system can carry out self study, to constantly improve BP neural network performance.
When practical operation, training set after m training sample is collected, is being established, training sample amount is m.It uses again
Standard deviation calculates the big ups and downs number that tilts in continuous t seconds detection time, tilts forward and back big ups and downs number, is swung left and right
Big ups and downs number, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and the big ups and downs time of Z axis acceleration
Number.By establish three layers of BP neural network come by the big ups and downs number that tilts, tilt forward and back big ups and downs number, left and right
Wave big ups and downs number, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and the violent wave of Z axis acceleration
Dynamic corresponding 6 variables of number are as input layer, and by the vectorization in order of above-mentioned variable, form is x={ x1,x2,x3,x4,x5,
x6, wherein x1Corresponding is the big ups and downs number that tilts, x2Corresponding is to tilt forward and back big ups and downs number, x3It is corresponding
It is the big ups and downs number that is swung left and right, x4Corresponding is X-axis acceleration big ups and downs number, x5Corresponding is that Y-axis acceleration is violent
Fluctuate number, x6Corresponding is Z axis acceleration big ups and downs number；Again with collected true value substitute into above-mentioned BP neural network come
Accurate study wearer above-mentioned 6 variables corresponding user's state when driving.
By the input layer DUAL PROBLEMS OF VECTOR MAPPING to hidden layer, the activation primitive of hidden layer uses tanh function, and output layer swashs
Function living uses Sigmoid function, obtains output layer neuron vector Corresponding user is state of riding or drives
Sail state, the output layer neuronValue isWhenWhen being 0, user is in state by bus at this time；When
When being 1, user is in driving condition at this time.
Below with reference to specific embodiment further to it is provided by the invention it is a kind of based on Intelligent bracelet identification occupant with
The method of driver is illustrated.
It has selected specific user 10 times driving or data judges and its result by bus.
Input layer data
Driving condition judgement conclusion
By test, with the increasing set to m value, judging nicety rate can also be risen with it.It is optimized, when m takes default
When 10, predictablity rate is up to 80% or more, and as m > 20, predictablity rate is up to 90% or more.
Claims (2)
1. the Intelligent bracelet includes bracelet band, bracelet shell and control based on the method for Intelligent bracelet identification occupant and driver
Circuit board, bracelet band is provided on bracelet shell, and bracelet enclosure interior is embedded with control circuit board, is laid in control circuit board
Power module, sensor module, position tracking module, display touch-control module, wireless communication module, shock module, memory module
And microprocessor, and power module, sensor module, position tracking module, display touch-control module, wireless communication module, vibration
Module and memory module are connect with microprocessor simultaneously, and the sensor module includes position sensor and six axis gyro sensors
Device；
The sensor module further includes heart rate sensor and blood pressure sensor；
The power module is using power module BQ24050, position tracking module using position tracking modules A T6558, display touching
It controls module and is used using display touch-control module SWC208, wireless communication module using wireless communication module DA14580, microprocessor
Microprocessor MSP430F169 and six axis gyro sensors use six axis gyro sensor 1428-1050-6-ND；
It is characterized by: specifically comprise the following steps,
Step 1: starting the worn bracelet of user, bracelet and mobile terminal establish wireless communication connection；
Step 2: detecting the status information of user by the sensor module inside bracelet and sending it to inside bracelet
Microprocessor, the microprocessor receive the status information of user and handle, and judge user for state or driving by bus
State, and judging result is pushed to mobile terminal, inquiry message is sent to user by mobile terminal, inquires the judgement knot
Whether fruit is correct；
Alternatively,
The status information of user is detected by the sensor module inside bracelet and sends it to mobile terminal, mobile terminal
Receive user status information simultaneously handle, judge user be ride state or driving condition, while mobile terminal to
User sends inquiry message, inquires whether the judging result is correct；
Wherein, the status information of the user includes using relative to the relative velocity v on ground and the behavioural information of user
The behavioural information of person includes the roll value of user, pitch value, yaw value, X-direction acceleration, Y direction acceleration and Z axis
Directional acceleration, wherein roll value is the data that tilt, and pitch value is to tilt forward and back data, and yaw value is the number that is swung left and right
According to；
Step 3: obtaining training sample, training sample is trained using BP neural network, identification user is state of riding
Or driving condition, detailed process is as follows,
1. presetting training sample amount is m, m >=10 acquire m group training sample, and the training sample is by tilting acutely
Fluctuation number tilts forward and back big ups and downs number, the big ups and downs number that is swung left and right, X-axis acceleration big ups and downs number, Y-axis
Acceleration big ups and downs number and Z axis acceleration big ups and downs number composition；
2. establishing BP neural network, BP nerve net in the application program of mobile terminal according to preset training sample amount
Network architecture is made of input layer, hidden layer and output layer, and hidden layer is located between input layer and output layer, BP neural network
With 6 input nodes and 1 output node, the big ups and downs number that will tilt tilts forward and back big ups and downs number, left and right
Wave big ups and downs number, X-axis acceleration big ups and downs number, Y-axis acceleration big ups and downs number and the violent wave of Z axis acceleration
Input of the training sample that dynamic number is constituted as BP neural network, user are ride state or the corresponding parameter of driving condition
Output as BP neural network；
3. initializing BP neural network, activation primitive is selected, wherein the activation primitive of hidden layer uses tanh function, output layer
Activation primitive uses Sigmoid function；
4. training sample is inputted BP neural network, it is trained using error backpropagation algorithm, BP neural network owns
When reality output and consistent its target output, training terminates；Otherwise, by correcting weight, export the target of BP neural network
Consistent with reality output, identification user is ride state or driving condition；
Judge that user is as follows for state by bus or the process of driving condition in the step 2,
When relative velocity v > 25km/h and v < 130km/h relative to ground, judgement operation is executed, continuous t second is analyzed and detects
The roll value of user in time, pitch value, yaw value, X-direction acceleration, Y direction acceleration and Z-direction accelerate
Continuous t seconds detection time is divided into N number of detection cycle by degree, and each detection cycle is user in r seconds, u-th r seconds
The standard deviation of roll value is greater than 13.5, and when standard deviation of pitch value and yaw value is respectively less than 6.5 is denoted as go to action, otherwise remembers
For non-go to action, go to action and non-go to action constitute steering wheel rotation groups of operands a [u], and a [u] is for sentencing section use
Person's hand motion whether the rotary motion of plane where relative direction disk；The X-direction for obtaining user in u-th of r seconds accelerates
Degree, the maximum value of Y direction acceleration and Z-direction acceleration, respectively x, y, z, z > (5x+5y) Shi Jiwei translation motion,
Otherwise it is denoted as non-translation motion, translation motion and non-translation motion constitute steering wheel translation array b [u], and b [u] is for sentencing
Section user hand motion whether relative direction disk translational motion in the plane；Rotary motion in continuous t seconds detection times
Matching degree threshold value with translational motion is M, otherwise it is the state of riding that 0.8 < M < 1.2, which determines that user is in driving condition, wherein
The matching degree threshold value of rotary motion and translational motion is that M meets relational expression and is in continuous t seconds detection times
The r value is 3 seconds.
2. the method according to claim 1 based on Intelligent bracelet identification occupant and driver, it is characterised in that: described
Six axis gyro sensors are substituted using 3-axis acceleration sensor cooperation three-axis gyroscope in sensor module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810616652.6A CN108703444B (en) | 2018-06-15 | 2018-06-15 | The Intelligent bracelet and method of occupant and driver for identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810616652.6A CN108703444B (en) | 2018-06-15 | 2018-06-15 | The Intelligent bracelet and method of occupant and driver for identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108703444A CN108703444A (en) | 2018-10-26 |
| CN108703444B true CN108703444B (en) | 2019-10-18 |
Family
ID=63872734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810616652.6A Expired - Fee Related CN108703444B (en) | 2018-06-15 | 2018-06-15 | The Intelligent bracelet and method of occupant and driver for identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108703444B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740477B (en) * | 2018-12-26 | 2022-12-06 | 联创汽车电子有限公司 | Driver fatigue detection system and fatigue detection method thereof |
| JP7026076B2 (en) * | 2019-03-29 | 2022-02-25 | 日立建機株式会社 | Site management system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001251876A (en) * | 2000-03-01 | 2001-09-14 | Teranishi Denki Seisakusho:Kk | Motor control unit |
| CN106372673A (en) * | 2016-09-06 | 2017-02-01 | 深圳市民展科技开发有限公司 | Apparatus motion identification method |
| CN106444450B (en) * | 2016-10-12 | 2020-01-07 | 广东乐源数字技术有限公司 | Method for stopping events of bracelet |
| CN206534629U (en) * | 2016-11-30 | 2017-10-03 | 中南民族大学 | Health monitoring bracelet and system |
-
2018
- 2018-06-15 CN CN201810616652.6A patent/CN108703444B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN108703444A (en) | 2018-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156524B (en) | A kind of online gait planning method of Intelligent lower limb power assisting device | |
| CN109512643A (en) | Device of walking aid and the method for controlling the device | |
| CN108703444B (en) | The Intelligent bracelet and method of occupant and driver for identification | |
| CN114366556B (en) | Multimode training control system and method for lower limb rehabilitation | |
| CN108720841A (en) | Wearable lower extremity movement correction system based on cloud detection | |
| CN104540557A (en) | Training device | |
| CN106887115A (en) | Old people falling monitoring device and falling risk assessment method | |
| CN106468951A (en) | A kind of intelligent remote control systems based on the fusion of both hands ring sensor and its method | |
| CN105233485A (en) | A bodybuilding-assisting motion mode correction system and method | |
| CN110977961A (en) | Motion information acquisition system of self-adaptive power-assisted exoskeleton robot | |
| CN112336590A (en) | Power-assisted exoskeleton movement intention and gait planning method based on multi-sensing information | |
| CN107616898A (en) | The wearable healing robot of upper limbs and Rehabilitation Assessment method based on everyday actions | |
| CN111506189B (en) | Motion mode prediction and switching control method for complex motion of human body | |
| Wu et al. | Gait phase prediction for lower limb exoskeleton robots | |
| JP7007244B2 (en) | Creation device, component control device, creation method, component control method, computer program and learning model | |
| CN108563891A (en) | A method of traffic accident is intelligently prevented based on Inertial Measurement Unit | |
| Gong et al. | BPNN-based real-time recognition of locomotion modes for an active pelvis orthosis with different assistive strategies | |
| Anand et al. | A deep reinforcement learning based approach towards generating human walking behavior with a neuromuscular model | |
| CN108320456A (en) | It is a kind of fusion multisensor the elderly fall down prediction technique and system | |
| CN114224326A (en) | Wearable gait phase and action recognition device and method | |
| CN108937926A (en) | The analysis method and device of the surface electromyogram signal of big data | |
| CN109011419A (en) | A kind of athletic performance training method based on MEMS sensor | |
| Gupta et al. | Campus safety and the internet of wearable things: Assessing student safety conditions on campus while riding a smart scooter | |
| KR102553359B1 (en) | Wearable Robot Area Network and Intelligent Wearable Robot Communication System and Method in WRAN | |
| Santamaria et al. | Smart wearable device for health monitoring in the internet of things (IoT) domain |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191018 Termination date: 20200615 |