CN113050754B - Wrist intelligent wearable device with behavior recognition function - Google Patents
Wrist intelligent wearable device with behavior recognition function Download PDFInfo
- Publication number
- CN113050754B CN113050754B CN202010590014.9A CN202010590014A CN113050754B CN 113050754 B CN113050754 B CN 113050754B CN 202010590014 A CN202010590014 A CN 202010590014A CN 113050754 B CN113050754 B CN 113050754B
- Authority
- CN
- China
- Prior art keywords
- sensor
- wrist strap
- wrist
- data
- behavior recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000000707 wrist Anatomy 0.000 title claims abstract description 58
- 230000006399 behavior Effects 0.000 claims abstract description 33
- 230000008859 change Effects 0.000 claims abstract description 30
- 230000006870 function Effects 0.000 claims abstract description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 230000007246 mechanism Effects 0.000 claims abstract description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013461 design Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009532 heart rate measurement Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 235000019577 caloric intake Nutrition 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/163—Wearable computers, e.g. on a belt
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0346—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Abstract
The invention discloses wrist intelligent wearing equipment with a behavior recognition function, which comprises a placing block, a sensor and a fixing mechanism, wherein the fixing mechanism comprises a spring and a propping block, the sensor can be placed in the placing block, the inner side surface of the placing block is provided with a plurality of springs, the end parts of the springs are fixedly provided with the propping block, the propping block can prop against the sensor, one side of the placing block is provided with a wrist strap I, the rear surface of the wrist strap I is provided with a bulge, the other side of the placing block is provided with a wrist strap II, and the end part of the wrist strap II is provided with a limiting buckle for the wrist strap I to pass through; the beneficial effects of the invention are as follows: the on-line compensation can be carried out on the data change caused by the position change of the wrist sensor; the characteristics are automatically learned by deep learning without manually extracting the characteristics, and the behavior recognition is performed; the recognition rate is basically kept stable before and after the position change of the sensor is realized; through the fixed establishment of design for the sensor installation is firm, has realized the quick installation of sensor.
Description
Technical Field
The invention belongs to the technical field of intelligent wearing, and particularly relates to wrist intelligent wearing equipment with a behavior recognition function.
Background
The wrist wearable product for behavior recognition can conveniently track human motion information and recognize the behavior type of a wearer, and can be used for assisting healthy life, tumble detection, rehabilitation training and the like.
The development of technologies such as sensors, wireless communication, data science, machine learning, etc. has made substantial progress in the intelligent life support system for promoting independent life, guiding active and healthy life of the elderly. The wrist wearable product for behavior recognition can conveniently track movement information and recognize the behavior types of the wearer, and the human body daily behavior recognition auxiliary system can effectively help old people in home or in community to relieve home and social senior citizen pressure.
Most wrist-based wearing sensor behavior recognition systems wear sensors at a certain initially defined position of the wrist, and as shown in fig. 1 (a), the positions of the sensors are required to be fixed as much as possible at the initial position of the wrist in the process of data acquisition, training and recognition, and the wrist sensor behavior recognition systems have been widely applied in the aspects of step counting, exercise amount, calorie consumption, heart rate measurement and the like. However, the recognition of daily activities such as walking, cooking, reading books, lying on television, etc. is much more complex than walking and heart rate measurement, etc. On the other hand, during the daily activities of a person, loose wearing of the sensor and wearing habits of different individuals can cause relative movement between the sensor and the wrist; also, the position at which the sensor is worn by different wearers may be different from the initial position defined by the identification system. When behavior data after sensor position change is recognized directly by a recognition model trained from data from an initially defined wearing position, a relatively large recognition deviation is likely to be caused.
The present inertial sensors can provide attitude angle data of the sensor device in addition to motion data of the individual sensors; the data recorded by the accelerometer sensor is based on the sensor's own coordinate system which changes as the sensor's position or orientation changes, and when the sensor slides or moves from an initially defined position along the wrist to another position shown in fig. 1 (a), the accelerometer's coordinate system is based on the sensor itself and its value changes relative to the ground reference coordinate system shown in fig. 1 (b), so it is difficult to accurately determine the sensor's position change using the accelerometer alone; as shown in fig. 1 (d), the reference coordinate system of the sensor attitude angle is unchanged relative to the ground reference coordinate after the sensor position changes, which is advantageous in that the attitude angle, namely the pitch angle (-90 ° -90 °), the roll angle (-180 ° -180 °) or the yaw angle (0-360 °), is used to judge the new position of the sensor and to conduct a comparison analysis with the initial position, so that the change of sensor data caused by the sensor position change is compensated by using the position difference value, and thus, the change of the behavior recognition rate caused by the sensor position change is compensated.
In order to facilitate the realization of quick installation of the sensor and online compensation of data change caused by wrist sensor position change, a wrist intelligent wearable device with a behavior recognition function is provided.
Disclosure of Invention
The invention aims to provide wrist intelligent wearing equipment with a behavior recognition function, which is convenient for realizing quick installation of a sensor and on-line compensation of data change caused by position change of the wrist sensor.
In order to achieve the above purpose, the present invention provides the following technical solutions: wrist intelligence wearing equipment with action recognition function, including placing piece, sensor and fixed establishment, fixed establishment includes the spring and supports the piece, the sensor can be placed in placing the piece, the medial surface of placing the piece is provided with a plurality of springs, and the tip of this spring is fixed with to support the piece, and supports the piece and can offset with the sensor.
Preferably, a first wrist strap is arranged on one side of the placement block, a bulge is arranged on the rear surface of the first wrist strap, a second wrist strap is arranged on the other side of the placement block, a limiting buckle for the first wrist strap to pass through is arranged at the end part of the second wrist strap, and a fixing opening for the bulge to be inserted into is formed in the surface of the second wrist strap.
Preferably, the limit buckle and the second wrist strap are of an integrated structure, a plurality of evenly distributed fixing openings are formed in the surface of the second wrist strap, and the protrusions are of a cylindrical structure.
Preferably, the wearing device is used as follows:
step one: the wearing equipment is arranged on the wrist, the first wrist strap passes through the inside of the limit buckle, and the bulge on the first wrist strap is buckled on the corresponding fixing port, so that the wearing equipment is firmly worn;
step two: collecting behavior data from wrist-worn sensors, and designing, training and optimizing a deep learning recognition model based on the data;
step three: the trained model carries out behavior recognition on the data after the sensor position is changed;
step four: and detecting the attitude angle of the current sensor position in real time during recognition, comparing the attitude angle with the attitude angle of the initial position, and carrying out statistical compensation on the current sensor data when the position error is higher than a set threshold value, wherein the compensated sensor data is used for behavior recognition.
Preferably, the model may employ convolutional neural network CNN, cyclic neural network LSTM.
Compared with the prior art, the invention has the beneficial effects that:
(1) The on-line compensation can be carried out on the data change caused by the position change of the wrist sensor; the characteristics are automatically learned by deep learning without manually extracting the characteristics, and the behavior recognition is performed; the recognition rate is basically kept stable before and after the position change of the sensor is realized;
(2) Through the fixed establishment of design for the sensor installation is firm, has realized the quick installation of sensor.
Drawings
FIG. 1 is a schematic diagram of the changing structure of an accelerometer and a sensor attitude coordinate system when the position of a wrist sensor is changed;
FIG. 2 is a block diagram of an implementation of behavior recognition for wrist-worn position adaptation in accordance with the present invention;
FIG. 3 is a flow chart of a wearing position adaptive behavior recognition implementation of the present invention;
FIG. 4 is a schematic view of a sensor mounting structure of the present invention;
FIG. 5 is an enlarged schematic view of the structure of the area B in FIG. 4 according to the present invention;
FIG. 6 is a schematic top view of a wristband according to the present invention;
in the figure: 1. placing a block; 2. a first wrist strap; 3. a sensor; 4. a limit button; 5. a fixed port; 6. a second wrist strap; 7. a spring; 8. abutting blocks; 9. a protrusion.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, 2, 3, 4, 5 and 6, the present invention provides a technical solution: wrist intelligence wearing equipment with action recognition function, including placing piece 1, sensor 3 and fixed establishment, fixed establishment includes spring 7 and supports piece 8, sensor 3 can be placed in and place in the piece 1, place the medial surface of piece 1 and be provided with a plurality of springs 7, the end fixing of this spring 7 has to support piece 8, and support piece 8 can offset with sensor 3, when sensor 3 installs, pick up sensor 3, place the sensor 3 in place in the piece 1, press to support piece 8 when sensor 3 installs, compress spring 7 after supporting piece 8 is pressed, spring 7 is pressed and is reset the effect has, drive to support piece 8 and support on sensor 3, make sensor 3 install firmly, the quick installation of sensor 3 has been realized.
In this embodiment, preferably, one side of the placement block 1 is provided with a first wristband 2, a protrusion 9 is disposed on a rear surface of the first wristband 2, a second wristband 6 is disposed on the other side of the placement block 1, a stop button 4 through which the first wristband 2 passes is disposed at an end of the second wristband 6, a fixing opening 5 through which the protrusion 9 is inserted is formed in a surface of the second wristband 6, the stop button 4 and the second wristband 6 are of an integral structure, a plurality of evenly distributed fixing openings 5 are formed in a surface of the second wristband 6, the protrusion 9 is of a cylindrical structure, the first wristband 2 passes through the stop button 4, and the protrusion 9 on the rear surface of the first wristband 2 is inserted into the fixing opening 5 formed in the surface of the second wristband 6, so that wearing is firm.
The present inertial sensor 3 can provide attitude angle data of the sensor 3 device in addition to the motion data of the individual sensors 3; the data recorded by the accelerometer sensor 3 is based on the coordinate system of the sensor 3 itself, which is changed with the change of the position or direction of the sensor 3, and when the sensor 3 slides or moves from the initial defined position along the wrist to another position shown in fig. 1 (a), the coordinate system of the accelerometer is based on the sensor itself, which is changed with respect to the ground reference coordinate system shown in fig. 1 (b), so that it is difficult to precisely judge the change of the position of the sensor by using the accelerometer alone; as shown in fig. 1 (d), the reference coordinate system of the sensor attitude angle is unchanged relative to the ground reference coordinate after the sensor position changes, which is advantageous in that the attitude angle, namely the pitch angle (-90 ° -90 °), the roll angle (-180 ° -180 °) or the yaw angle (0-360 °), is used to judge the new position of the sensor and to conduct a comparison analysis with the initial position, so that the change of sensor data caused by the sensor position change is compensated by using the position difference value, and thus, the change of the behavior recognition rate caused by the sensor position change is compensated.
The working principle and the using flow of the invention are as follows: working principle: the attitude position of the sensor 3 is used as a set value of a behavior recognition system by utilizing a principle that a coordinate system of an attitude angle of the sensor 3 is based on a mechanism of invariance of a geographic coordinate system and feedback is used, and the attitude position change of the sensor is monitored in real time; when the current gesture position of the sensor 3 is different from the set value, the statistical characteristic compensation is carried out on the current behavior data to reduce the gap between the current sensor 3 data and the set position sensor 3 data, then the recognition model trained on the initial set position is utilized to carry out recognition test on the compensated behavior data so as to stabilize the recognition rate, the position feedback recognition system can effectively avoid the recognition rate conversion problem caused by the data change caused by the position change of the sensor 3, and avoid the repeated work that the model training is required to be carried out again on the data after the position change of the sensor 3, and finally, the wrist sensing and 3-position self-adaptive behavior recognition platform combining a feedback principle and deep learning is realized;
the wearing equipment is arranged on the wrist, the first wrist strap 2 passes through the limit buckle 4, and the bulge 9 on the rear surface of the first wrist strap 2 is inserted into the fixing opening 5 formed on the surface of the second wrist strap 6, so that the wearing equipment is stably worn;
step two: collecting behavior data from the wrist-worn sensor 3, and designing, training and optimizing a deep learning recognition model based on the data; the model can adopt a convolutional neural network CNN and a cyclic neural network LSTM, and the deep learning model directly receives the sensor time sequence and automatically learns the data characteristics without manually extracting the data characteristics and selecting the characteristic set;
step three: the trained model carries out behavior recognition on the data of which the position of the sensor 3 is changed;
step four: and detecting the attitude angle of the current sensor 3 in real time during recognition, comparing the attitude angle with the attitude angle of the initial position, and carrying out statistical compensation on the current sensor 3 data when the position error is higher than a set threshold value, wherein the compensated sensor 3 data is used for behavior recognition.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (1)
1. Wrist intelligence wearing equipment with action recognition function, including placing piece (1), sensor (3) and fixed establishment, its characterized in that: the fixing mechanism comprises springs (7) and abutting blocks (8), the sensor (3) can be arranged in the placing block (1), a plurality of springs (7) are arranged on the inner side surface of the placing block (1), the abutting blocks (8) are fixed at the end parts of the springs (7), and the abutting blocks (8) can abut against the sensor (3); one side of the placement block (1) is provided with a first wrist strap (2), the rear surface of the first wrist strap (2) is provided with a bulge (9), the other side of the placement block (1) is provided with a second wrist strap (6), the end part of the second wrist strap (6) is provided with a limit buckle (4) for the first wrist strap (2) to pass through, and the surface of the second wrist strap (6) is provided with a fixing opening (5) for the bulge (9) to insert; the limiting buckle (4) and the wrist strap II (6) are of an integrated structure, a plurality of uniformly distributed fixing openings (5) are formed in the surface of the wrist strap II (6), and the protrusions (9) are of a cylindrical structure; the using method of the wearable device comprises the following steps:
step one: the wearing equipment is arranged on the wrist, the first wrist strap (2) passes through the limit buckle (4) and the bulge (9) on the first wrist strap (2) is buckled on the corresponding fixing port (5), so that the wearing equipment is firmly worn;
step two: collecting behavior data from a wrist wearing sensor (3), and designing, training and optimizing a deep learning identification model based on the data, wherein the deep learning identification model is a convolutional neural network CNN or a cyclic neural network LSTM;
step three: the trained model carries out behavior recognition on the data after the position of the sensor (3) is changed;
step four: detecting the attitude angle of the current sensor (3) in real time during recognition, comparing the attitude angle with the attitude angle of the initial position, and carrying out statistical compensation on the current sensor (3) data when the position error is higher than a set threshold value, wherein the compensated sensor (3) data is used for behavior recognition, and judging the new position of the sensor through a pitch angle (-90 degrees to 90 degrees), a roll angle (-180 degrees to 180 degrees) or a yaw angle (0 to 360 degrees) and carrying out comparison analysis with the initial position, so that the position difference value is utilized to compensate the change of the sensor data caused by the change of the sensor position, and further the change of the behavior recognition rate caused by the change of the sensor position is compensated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590014.9A CN113050754B (en) | 2020-06-24 | 2020-06-24 | Wrist intelligent wearable device with behavior recognition function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010590014.9A CN113050754B (en) | 2020-06-24 | 2020-06-24 | Wrist intelligent wearable device with behavior recognition function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113050754A CN113050754A (en) | 2021-06-29 |
| CN113050754B true CN113050754B (en) | 2024-02-20 |
Family
ID=76507599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010590014.9A Active CN113050754B (en) | 2020-06-24 | 2020-06-24 | Wrist intelligent wearable device with behavior recognition function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113050754B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106679649A (en) * | 2016-12-12 | 2017-05-17 | 浙江大学 | Hand movement tracking system and tracking method |
| CN206964188U (en) * | 2017-07-25 | 2018-02-06 | 刘昕 | Intelligence learning aids in bracelet |
| CN108198383A (en) * | 2017-12-26 | 2018-06-22 | 深圳市宇恒互动科技开发有限公司 | The high-precision Activity recognition method, apparatus and system of a kind of multi sensor combination |
| CN108297101A (en) * | 2018-03-20 | 2018-07-20 | 四川大学 | The position and attitude error detection of multi-joint arm serial manipulator end and dynamic compensation method |
| CN210520244U (en) * | 2019-12-05 | 2020-05-15 | 中科海微(北京)科技有限公司 | Children's myopia prevention intelligence bracelet |
| WO2020122272A1 (en) * | 2018-12-11 | 2020-06-18 | 상명대학교 산학협력단 | Wearable device and gesture recognition method thereof |
-
2020
- 2020-06-24 CN CN202010590014.9A patent/CN113050754B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106679649A (en) * | 2016-12-12 | 2017-05-17 | 浙江大学 | Hand movement tracking system and tracking method |
| CN206964188U (en) * | 2017-07-25 | 2018-02-06 | 刘昕 | Intelligence learning aids in bracelet |
| CN108198383A (en) * | 2017-12-26 | 2018-06-22 | 深圳市宇恒互动科技开发有限公司 | The high-precision Activity recognition method, apparatus and system of a kind of multi sensor combination |
| CN108297101A (en) * | 2018-03-20 | 2018-07-20 | 四川大学 | The position and attitude error detection of multi-joint arm serial manipulator end and dynamic compensation method |
| WO2020122272A1 (en) * | 2018-12-11 | 2020-06-18 | 상명대학교 산학협력단 | Wearable device and gesture recognition method thereof |
| CN210520244U (en) * | 2019-12-05 | 2020-05-15 | 中科海微(北京)科技有限公司 | Children's myopia prevention intelligence bracelet |
Non-Patent Citations (2)
| Title |
|---|
| 基于倾斜补偿提高多位置捷联寻北精度的研究;王志乾;赵继印;谢慕君;高峰端;;系统仿真学报;20090220(02);全文 * |
| 基于可穿戴传感器的家居行为识别算法;岳雨豪;武一;李家兴;;电子测量技术;20200308(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113050754A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104287703B (en) | The use of gyroscope in personal body-building tracks of device | |
| CN103676604B (en) | Watch and running method thereof | |
| CN103654759B (en) | Movable information checkout gear and movable information detection method | |
| CN106618584B (en) | A method of for monitoring user's lower extremity movement | |
| CN105771187B (en) | A kind of motion state detection method and the intelligent shoe based on this method | |
| CN106445101A (en) | Method and system for identifying user | |
| CN103919536A (en) | Portable Biometric Monitoring Devices And Methods Of Operating Same | |
| CN105561567A (en) | Step counting and motion state evaluation device | |
| CN104207761A (en) | Heart rate data collection | |
| CN104218976A (en) | Self-adaptive data transmission using Bluetooth | |
| CN101493865A (en) | Electricity saving device and method for sport wrist-watch | |
| WO2021004510A1 (en) | Sensor-based separately deployed human body behavior recognition health management system | |
| CN105795571A (en) | Data acquisition system and method for exoskeleton pressure shoe | |
| CN207055003U (en) | A kind of intelligent health monitoring bracelet | |
| CN110025316A (en) | A kind of low-power consumption can radio upgrade intelligent shoe embedded system | |
| He et al. | Adaptive pattern recognition of myoelectric signal towards practical multifunctional prosthesis control | |
| US20220365600A1 (en) | Motion data processing method and motion monitoring system | |
| CN110543922A (en) | real-time walking mode identification method based on knee joint exoskeleton | |
| CN113050754B (en) | Wrist intelligent wearable device with behavior recognition function | |
| CN107943271A (en) | Exercise data detection method, apparatus and system | |
| US20220375590A1 (en) | Sleep staging algorithm | |
| Majoe et al. | Stress and sleep quality estimation from a smart wearable sensor | |
| CN114756114B (en) | Energy saving method and equipment for wearable equipment | |
| Cola et al. | Personalized gait detection using a wrist-worn accelerometer | |
| CN115154224A (en) | Neck massager and control method thereof |
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 |