CN108549834A - A kind of human body sitting posture recognition methods and its system based on flexible sensor - Google Patents
A kind of human body sitting posture recognition methods and its system based on flexible sensor Download PDFInfo
- Publication number
- CN108549834A CN108549834A CN201810188887.XA CN201810188887A CN108549834A CN 108549834 A CN108549834 A CN 108549834A CN 201810188887 A CN201810188887 A CN 201810188887A CN 108549834 A CN108549834 A CN 108549834A
- Authority
- CN
- China
- Prior art keywords
- flexible sensor
- sitting posture
- bending data
- human body
- unit
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The human body sitting posture recognition methods based on flexible sensor that the invention discloses a kind of, the first bending data at acquisition user back, and pretreatment and feature extraction are carried out to bending data, feature vector is identified followed by the artificial neural network of trained error back propagation and can be obtained recognition result, then recognition result can be transferred to the intelligent terminal of user；A kind of human body sitting posture identifying system based on flexible sensor of the present invention, the bending data at user back is detected using flexible sensor, using the Classification and Identification unit of the artificial neural network provided with error back propagation, to treated, bending data is identified can be obtained final recognition result, and recognition result is transferred to the intelligent terminal of user by unit by radio communication, due to being detected using flexible sensor, it is simple in structure, it is easy to detect.
Description
Technical field
The present invention relates to sensor technology application field, especially a kind of human body sitting posture identification side based on flexible sensor
Method and its system.
Background technology
Sitting posture state is student group, the most time state in which of office crowd, and incorrect sitting-pose can be to people
Health cause prodigious influence, teenager tends not to pay attention to keeping correct body well in studying and living
Appearance, and parent and teacher cannot remind at one's side all the time, just form myopia and hunchback for a long time；Working clan is come
It says, as rhythm of life quickening and operating pressure increasingly increase, more and more adults need to face computer for a long time, by
It is true in abnormal sitting posture, it can usually cause the symptoms such as occupational musculoskeletal disorder and back pain, incorrect sitting-pose is caused by health
Negative effect, can not only seriously affect the physical and mental health and ability to work of patient, also be brought for health care serious economical negative
Therefore load has very important meaning for the research of human body sitting posture identification to the health of people.
Traditional method is mainly based upon the technologies such as computer vision, is believed by image and acquiring video information human body sitting posture
Breath, such recognition methods generally requires equipped with hardware devices such as camera, camera, video cameras, this note identification apparatus often valence
Lattice are expensive, are easily illuminated by the light, the factors such as the precision of human dressing, imaging device influence, and the data of user's sitting posture are acquired and are existed
Certain error causes final sitting posture recognition result less accurate.
Invention content
To solve the above problems, the purpose of the present invention is to provide a kind of human body sitting posture identification side based on flexible sensor
Method and its system detect the bending data of human body back by flexible sensor, are recognized to sitting posture in conjunction with neural network,
Identification is more accurate, while user can receive the sitting posture data of itself by intelligent terminal.
Technical solution is used by the present invention solves the problems, such as it：A kind of human body sitting posture identification side based on flexible sensor
Method includes the following steps：
A, the bending data at flexible sensor acquisition user back；
B, the bending data at user back is pre-processed；
C, to treated, bending data carries out feature extraction and composition characteristic vector；
D, feature vector is divided into training set and test set, builds the artificial nerve network model of error back propagation, profit
The artificial neural network of error back propagation is trained with training set and test set；
E, using the artificial neural network of trained error back propagation to the bending data at user back to be identified
Feature vector be identified, and obtain recognition result；
F, recognition result is transferred to intelligent terminal.
Further, the bending data at user back is pre-processed in the step B, using arithmetic mean method to user
The bending data at back is filtered processing.
Further, feature extraction and composition characteristic vector carried out to treated bending data in the step C, at extraction
The temporal signatures of bending data after reason, and by temporal signatures composition characteristic vector, wherein temporal signatures include mean value, standard
Value, maximum value and minimum value.
Further, feature vector is divided into training set and test set in the step D, wherein by feature vector with 4：1
Ratio is divided into training set and test set.
Further, the artificial nerve network model of error back propagation, wherein error back propagation are built in the step D
Artificial neural network include three layers, first layer is the input layer with 4 neurons, and the second layer is with 4 neurons
Hidden layer, third layer are the output layer with 3 neurons.
A kind of human body sitting posture identifying system based on flexible sensor, includes the bending data for acquiring user back
Measuring unit and the recognition unit for being handled bending data and being identified, the measuring unit include for acquiring user's back of the body
The flexible sensor of the bending data in portion, the microcontroller that the bending data that flexible sensor acquires is converted into voltage apportioning cost
And recognition result is sent to the wireless communication unit of user's intelligent terminal, the recognition unit includes being carried out to bending data
Pretreated pretreatment unit carries out treated data the feature extraction unit of feature extraction and to be provided with error reversed
The Classification and Identification unit of the artificial nerve network model of propagation, the flexible sensor, microcontroller, pretreatment unit and spy
Sign extraction unit is sequentially connected, and the feature vector that the Classification and Identification unit exports feature extraction unit is identified, and will
Recognition result is transferred in the microcontroller, and unit sends recognition result to the microcontroller by radio communication.
Further, the sport plaster cloth for being fixed in user back, the flexible biography are provided on the flexible sensor
Sensor includes the foil gauge and divider resistance being made of silicone-nickel nanocomposite, the foil gauge and divider resistance point
Microcontroller is not connected to it.
Further, the measuring unit further includes portable sandwich type element, and the microcontroller is set in portable sandwich type element, institute
State the clip or safety pin being provided on portable sandwich type element for being fixed on user's clothes or waistband.
Further, the wireless communication unit is bluetooth communication.
The beneficial effects of the invention are as follows：A kind of human body sitting posture recognition methods based on flexible sensor that the present invention uses,
It is acquired by the bending data to user back, and the bending data of acquisition is subjected to pretreatment and feature extraction, then
The artificial neural network of error back propagation is trained using the feature vector extracted, the error that training is completed reversely passes
The bending data at user back to be identified can be identified in the artificial neural network broadcast, and recognition result is sent to use
On the intelligent terminal at family, user is made to be recognized that oneself current sitting posture situation；
A kind of human body sitting posture identifying system based on flexible sensor of the present invention, using flexible sensor to user back
Bending data be acquired, simple in structure, identification is accurate, can be exported according to the different angle of user's flexes different
It is worth in microcontroller, finally bending data is being identified by recognition unit to obtain recognition result, then by wireless
Recognition result is sent to user's intelligent terminal by communication unit, and user is allow to recognize the sitting posture situation of itself at any time, is used
Detection device of the flexible sensor as sitting posture, for traditional detection pressure value by pressure sensor, structure is more
Add simple.
Description of the drawings
The invention will be further described with example below in conjunction with the accompanying drawings.
Fig. 1 is a kind of flow diagram of the human body sitting posture recognition methods based on flexible sensor of the present invention；
Fig. 2 is a kind of functional block diagram of the human body sitting posture identifying system based on flexible sensor of the present invention；
Fig. 3 is the network architecture figure of the artificial neural network of error back propagation.
Specific implementation mode
Referring to Fig.1, a kind of human body sitting posture recognition methods based on flexible sensor of the invention, includes the following steps：A、
Flexible sensor 11 acquires the bending data at user back；B, the bending data at user back is pre-processed；C, to processing
Bending data afterwards carries out feature extraction and composition characteristic vector；D, feature vector is divided into training set and test set, structure misses
The artificial nerve network model of poor backpropagation, using training set and test set to the artificial neural network of error back propagation
It is trained；E, using the artificial neural network of trained error back propagation to the bending data at user back to be identified
Feature vector be identified, and obtain recognition result；F, recognition result is transferred to intelligent terminal.
The present invention acquire user sitting posture data when and traditional pressure that each test point is detected by pressure detector
Force value is different, but the bending data for acquiring user back is used as sitting posture data, due to the weight of each user, stature difference,
So traditional there is certain error using pressure detector detection, and detection that cannot be accurate and comprehensive, the number of detection
It also is difficult to be mapped according to sitting posture data, and the present invention is relatively reasonable using the bending data at user back as sitting posture data
, flexes can be converted different sitting posture data in various degree, in carrying out subsequent calculating and identification also more
It is convenient.
Specifically, in the bending data to back pre-processes, using be arithmetic mean method carry out filtering at
Reason, since human body sitting posture signal floats up and down in a certain particular range, and the signal interference randomness being subject to is stronger, so
Sitting posture signal is filtered using arithmetic mean method, sample frequency of the invention is set as 50Hz, each sitting posture maintains 60 seconds,
So in sampling each time, each sitting posture has 3000 sampled points, for any one sampled point, to its continuous 100
A sampled point carries out arithmetic average operation, and the sampled value of the point is replaced with the value being calculated.
Specifically, temporal signatures of the bending data after extraction process, and by temporal signatures composition characteristics vector, wherein when
Characteristic of field includes mean value, standard value, maximum value and minimum value.
Specifically, before the artificial nerve network model to error back propagation is trained, first by feature vector point
For training set and test set, wherein by feature vector with 4：1 ratio is divided into training set and test set, and training set is used for error
The artificial nerve network model of backpropagation is trained, and test set is used for the artificial neuron to trained error back propagation
Network model is tested.
The artificial neural network of error back propagation of the present invention, including three layers, first layer is with 4 nerves
The input layer of member, the second layer are the hidden layer with 4 neurons, and third layer is the output layer with 3 neurons, such as Fig. 3
Shown, wherein 201 being input layer, 202 being hidden layer, 203 being output layer, the course of work of whole network is divided into two parts：
First part's forward-propagating process input information successively calculates the output valve of each neuron from input layer through hidden layer；Second part
Back-propagation process output error successively calculates forward the error of each neuron of hidden layer, is constantly updated with this error
The other parameters of network so that neural network can improve the accurate of identification with adjust automatically parameter, constantly improve self structure
Degree.
With reference to Fig. 2, a kind of human body sitting posture identifying system based on flexible sensor of the invention, including measuring unit 1 with
And recognition unit 2, measuring unit 1 are used to acquire the bending data at user back, bending data are then transferred to recognition unit
2, recognition result is transmitted back in measuring unit 1 by recognition unit 2 after being identified, and is passed to recognition result by measuring unit 1
It is defeated.
Specifically, measuring unit 1 includes flexible sensor 11, microcontroller 12 and wireless communication unit 13, and flexibility passes
Sensor 11 is made of foil gauge 111 and sensor circuit, and foil gauge 111 can be deformed upon due to the bending at user back, so
The voltage distributed on foil gauge 111 will change, then microcontroller 12 can be obtained between 0 in its simulation input port~
The analogue value between 1023 represents the bending data at user back with it in the present invention, to obtain the sitting posture data of user,
And wireless communication unit 13 is used to final recognition result being transferred to the intelligent terminal of user, for user to the sitting posture of itself
Progress is online to be checked, so that user understands the sitting posture of oneself and is adjusted.
Specifically, sensor circuit is a divider resistance 112, divider resistance 112 and the flexible biography in series of foil gauge 111
Sensor 11, and the resistance value of the resistance value of divider resistance 112 and foil gauge 111 at steady state is equal.
It is provided with sport plaster cloth on flexible sensor 11, flexible sensor 11 can be fixed on to the clothes at user back
On, user will not be impacted and sense of discomfort, foil gauge 111 of the invention is mainly by silicone-nickel nanocomposite structure
At the deformation range that the foil gauge 111 of this material senses is larger, while unique back-pressure can be kept resistive, and cost
Relatively low, foil gauge 111 selects copolyesters silicone material as substrate, and adds NiNs nickel nano chain and NCCF nickel-plated carbons wherein
Fiber, the deformation suffered by foil gauge 111 is bigger, and resistance value is smaller.
Specifically, measuring unit 1 further includes a portable sandwich type element, by divider resistance 112, microcontroller 12, channel radio
Believe that unit 13 and power module are arranged in portable sandwich type element, then in the outside of portable sandwich type element setting clip or not
Needle avoids causing discomfort to user so that portable sandwich type element can be fixed on the clothes or waistband of user.
Specifically, microcontroller 12 of the invention is realized by Arduino Uno, microcontroller 12Arduino Uno
Each simulation input port A0~A5 resolution ratio be 10 i.e. read the analogues value between 0~1023.
And wireless communication unit 13 is bluetooth communication, and wireless data transmission is carried out by bluetooth, by final sitting posture
The recognition result of data is transferred to the intelligent terminal of user, bluetooth communication of the invention using HC-06 bluetooth equipments,
Compact, transmission range can reach 10 meters, increase the reliability of the present invention.
Recognition unit 2 includes pretreatment unit 21, feature extraction unit 22 and Classification and Identification unit 23, pretreatment unit
The bending data of 21 pairs of microcontrollers 12 transmission is filtered processing, reduces interference, is then extracted by feature extraction unit 22
The temporal signatures for bending data that treated, and composition characteristic vector, it is finally artificial provided with error back propagation in utilization
Feature vector is identified the recognition result that can be obtained sitting posture data in the Classification and Identification unit 23 of neural network model, then
Recognition result is transferred in microcontroller 12, recognition result is transferred to user to microcontroller 12 by unit 13 by radio communication
Intelligent terminal.
The artificial nerve network model of error back propagation in the present invention can be transplanted in the intelligent terminal of user, and
By develop APP provide related service to the user, can according to classification results, in advance in APP set the other threshold value of sitting posture and
Duration, once the sitting posture data of user are less than threshold value, and when the duration reaches the preset duration of threshold value, APP will be by shaking
Dynamic or the tinkle of bells form notifies user to correct the sitting posture of mistake, and in addition to this, intelligent terminal can also show real-time seat
Appearance situation, and by the relevant technologies of big data and cloud computing, suggestion more personalized in more detail is on the one hand provided for user,
On the other hand it can share with good friend and compare, establish an incentive mechanism, to contribute to user in daily life into connection of racking
Good sitting posture is consciously kept in work.
The above, only presently preferred embodiments of the present invention, the invention is not limited in the above embodiments, as long as
It reaches the technique effect of the present invention with identical means, should all belong to the scope of protection of the present invention.
Claims (9)
1. a kind of human body sitting posture recognition methods based on flexible sensor, it is characterised in that：Include the following steps：
A, the bending data at flexible sensor (11) acquisition user back；
B, the bending data at user back is pre-processed；
C, to treated, bending data carries out feature extraction and composition characteristic vector；
D, feature vector is divided into training set and test set, builds the artificial nerve network model of error back propagation, utilizes instruction
Practice collection and test set is trained the artificial neural network of error back propagation；
E, using the artificial neural network of trained error back propagation to the spy of the bending data at user back to be identified
Sign vector is identified, and obtains recognition result；
F, recognition result is transferred to intelligent terminal.
2. a kind of human body sitting posture recognition methods based on flexible sensor according to claim 1, it is characterised in that：It is described
The bending data at user back is pre-processed in step B, the bending data at user back is carried out using arithmetic mean method
Filtration treatment.
3. a kind of human body sitting posture recognition methods based on flexible sensor according to claim 1, it is characterised in that：It is described
Feature extraction and composition characteristic vector are carried out to treated bending data in step C, the bending data after extraction process when
Characteristic of field, and by temporal signatures composition characteristic vector, wherein temporal signatures include mean value, standard value, maximum value and minimum value.
4. a kind of human body sitting posture recognition methods based on flexible sensor according to claim 1, it is characterised in that：It is described
Feature vector is divided into training set and test set in step D, wherein by feature vector with 4：1 ratio is divided into training set and test
Collection.
5. a kind of human body sitting posture recognition methods based on flexible sensor according to claim 1, it is characterised in that：It is described
The artificial nerve network model of error back propagation is built in step D, the artificial neural network of wherein error back propagation includes
Three layers, first layer be the input layer with 4 neurons, the second layer be the hidden layer with 4 neurons, third layer be with
The output layer of 3 neurons.
6. a kind of system using any human body sitting posture recognition methods based on flexible sensor of claim 1-5, special
Sign is：Include the measuring unit (1) of the bending data for acquiring user back and bending data is handled and is known
Other recognition unit (2), the measuring unit (1) include the flexible sensor of the bending data for acquiring user back
(11), the bending data that flexible sensor (11) acquires is converted into the microcontroller (12) of voltage apportioning cost and ties identification
Fruit is sent to the wireless communication unit (13) of user's intelligent terminal, and the recognition unit (2) includes being located in advance to bending data
The pretreatment unit (21) of reason carries out treated data the feature extraction unit (22) of feature extraction and is provided with error
The Classification and Identification unit (23) of the artificial nerve network model of backpropagation, the flexible sensor (11), microcontroller (12),
Pretreatment unit (21) and feature extraction unit (22) are sequentially connected, and the Classification and Identification unit (23) is to feature extraction unit
(22) feature vector exported is identified, and recognition result is transferred in the microcontroller (12), the microcontroller
(12) unit (13) sends recognition result by radio communication.
7. a kind of human body sitting posture identifying system based on flexible sensor according to claim 6, it is characterised in that：It is described
The sport plaster cloth for being fixed in user back is provided on flexible sensor (11), the flexible sensor (11) includes by silicon
The foil gauge (111) and divider resistance (112), the foil gauge (111) and divider resistance that ketone-nickel nanocomposite is constituted
(112) it is connected respectively to microcontroller (12).
8. a kind of human body sitting posture identifying system based on flexible sensor according to claim 6, it is characterised in that：It is described
Measuring unit (1) further includes portable sandwich type element, and the microcontroller (12) is set in portable sandwich type element, the portable sandwich type element
On be provided with clip or safety pin for being fixed on user's clothes or waistband.
9. a kind of human body sitting posture identifying system based on flexible sensor according to claim 6, it is characterised in that：It is described
Wireless communication unit (13) is bluetooth communication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810188887.XA CN108549834A (en) | 2018-03-08 | 2018-03-08 | A kind of human body sitting posture recognition methods and its system based on flexible sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810188887.XA CN108549834A (en) | 2018-03-08 | 2018-03-08 | A kind of human body sitting posture recognition methods and its system based on flexible sensor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108549834A true CN108549834A (en) | 2018-09-18 |
Family
ID=63515859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810188887.XA Pending CN108549834A (en) | 2018-03-08 | 2018-03-08 | A kind of human body sitting posture recognition methods and its system based on flexible sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549834A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063697A (en) * | 2018-10-11 | 2018-12-21 | 浙江工业大学 | A kind of human body sitting posture detection method based on channel state information |
| CN109820373A (en) * | 2019-03-28 | 2019-05-31 | 重庆邮电大学 | Sitting posture self-adapting regulation method based on Intelligent seat |
| CN110135447A (en) * | 2018-10-30 | 2019-08-16 | 初速度（苏州）科技有限公司 | The system for adjusting personnel's sitting posture in vehicle according to the personal information of identification |
| CN112190258A (en) * | 2020-09-30 | 2021-01-08 | 珠海格力电器股份有限公司 | Seat angle adjusting method and device, storage medium and electronic equipment |
| CN113855004A (en) * | 2021-09-30 | 2021-12-31 | 山东科技大学 | Preparation method and application of flexible pressure sensor |
| CN114323368A (en) * | 2021-12-09 | 2022-04-12 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on hip pressure |
| CN115127704A (en) * | 2022-06-24 | 2022-09-30 | 永艺家具股份有限公司 | Sitting posture identification method based on flexible film pressure sensor |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011250915A (en) * | 2010-06-01 | 2011-12-15 | Sharp Corp | Posture recognition device |
| CN104720821A (en) * | 2015-04-01 | 2015-06-24 | 深圳柔微传感科技有限公司 | Method and smart clothing for achieving real-time posture monitoring |
| CN105761454A (en) * | 2016-03-22 | 2016-07-13 | 宁波元鼎电子科技有限公司 | Intelligent sitting posture corrector |
| CN106530640A (en) * | 2016-12-16 | 2017-03-22 | 深圳柔微传感科技有限公司 | Intelligent children garment, gesture data processing method and intelligent children wearable device |
| CN107038404A (en) * | 2016-10-19 | 2017-08-11 | 中国地质大学（武汉） | A kind of sitting posture detecting method and system based on BP neural network |
| CN107296427A (en) * | 2017-08-24 | 2017-10-27 | 云康新智能科技（深圳）有限公司 | A kind of cushion and sitting posture analysis method |
-
2018
- 2018-03-08 CN CN201810188887.XA patent/CN108549834A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011250915A (en) * | 2010-06-01 | 2011-12-15 | Sharp Corp | Posture recognition device |
| CN104720821A (en) * | 2015-04-01 | 2015-06-24 | 深圳柔微传感科技有限公司 | Method and smart clothing for achieving real-time posture monitoring |
| CN105761454A (en) * | 2016-03-22 | 2016-07-13 | 宁波元鼎电子科技有限公司 | Intelligent sitting posture corrector |
| CN107038404A (en) * | 2016-10-19 | 2017-08-11 | 中国地质大学（武汉） | A kind of sitting posture detecting method and system based on BP neural network |
| CN106530640A (en) * | 2016-12-16 | 2017-03-22 | 深圳柔微传感科技有限公司 | Intelligent children garment, gesture data processing method and intelligent children wearable device |
| CN107296427A (en) * | 2017-08-24 | 2017-10-27 | 云康新智能科技（深圳）有限公司 | A kind of cushion and sitting posture analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 何园: "基于神经网络的坐姿传感技术", 《中国优秀硕士学位论文全文数据库 信息科技辑（月刊）自动化技术》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063697A (en) * | 2018-10-11 | 2018-12-21 | 浙江工业大学 | A kind of human body sitting posture detection method based on channel state information |
| CN110135447A (en) * | 2018-10-30 | 2019-08-16 | 初速度（苏州）科技有限公司 | The system for adjusting personnel's sitting posture in vehicle according to the personal information of identification |
| CN110135447B (en) * | 2018-10-30 | 2021-08-24 | 初速度（苏州）科技有限公司 | System for adjusting sitting posture of personnel in vehicle according to identified personnel information |
| CN109820373A (en) * | 2019-03-28 | 2019-05-31 | 重庆邮电大学 | Sitting posture self-adapting regulation method based on Intelligent seat |
| CN112190258A (en) * | 2020-09-30 | 2021-01-08 | 珠海格力电器股份有限公司 | Seat angle adjusting method and device, storage medium and electronic equipment |
| CN112190258B (en) * | 2020-09-30 | 2021-07-20 | 珠海格力电器股份有限公司 | Seat angle adjusting method and device, storage medium and electronic equipment |
| CN113855004A (en) * | 2021-09-30 | 2021-12-31 | 山东科技大学 | Preparation method and application of flexible pressure sensor |
| CN114323368A (en) * | 2021-12-09 | 2022-04-12 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on hip pressure |
| CN115127704A (en) * | 2022-06-24 | 2022-09-30 | 永艺家具股份有限公司 | Sitting posture identification method based on flexible film pressure sensor |
| CN115127704B (en) * | 2022-06-24 | 2023-07-28 | 永艺家具股份有限公司 | Sitting posture identification method based on flexible film pressure sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108549834A (en) | A kind of human body sitting posture recognition methods and its system based on flexible sensor | |
| CN102138860B (en) | Intelligentized rehabilitation training equipment for hand functions of patients suffering from cerebral injury | |
| WO2020119245A1 (en) | Wearable bracelet-based emotion recognition system and method | |
| CN109480858B (en) | Wearable intelligent system and method for quantitatively detecting motor retardation symptoms of Parkinson patients | |
| US10993651B2 (en) | Exercise guidance method and exercise guidance device | |
| Roy et al. | A combined sEMG and accelerometer system for monitoring functional activity in stroke | |
| RU2626672C2 (en) | Device (versions) and method for eating habits automated monitoring | |
| Sadarangani et al. | Force myography for monitoring grasping in individuals with stroke with mild to moderate upper-extremity impairments: A preliminary investigation in a controlled environment | |
| WO2020253558A1 (en) | Health parameter testing method, apparatus and system based on massage chair | |
| CN104274191B (en) | A kind of Psychological Evaluation method and system thereof | |
| CN106037738A (en) | Wearable physical training evaluation system and device | |
| CN106999065A (en) | Use the wearable pain monitor of accelerometry | |
| Ma et al. | sEMG-based trunk compensation detection in rehabilitation training | |
| CN104571504B (en) | A kind of online brain-machine interface method based on Imaginary Movement | |
| CN105595977A (en) | Mental health monitoring system based on cloud data platform | |
| Lin et al. | A comparative study of smart insole on real-world step count | |
| CN109765996A (en) | Insensitive gesture detection system and method are deviated to wearing position based on FMG armband | |
| Pires et al. | Limitations of energy expenditure calculation based on a mobile phone accelerometer | |
| TW201424803A (en) | Intelligent physical fitness training system | |
| CN204336935U (en) | A kind of multi-path physiology psychological tester based on pulse, breathing and skin resistance | |
| Bustamante et al. | A low-cost platform for testing activities in parkinson and ALS patients | |
| CN207590681U (en) | A kind of portable muscular fatigue degree detection device based on electronics epidermis | |
| Grandez et al. | Sensor device for testing activities in Parkinson and ALS patients | |
| CN108464831A (en) | A kind of device and method of wearable muscular fatigue detection | |
| CN111603151B (en) | Noninvasive blood component detection method and system based on time-frequency combined analysis |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180918 |