CN113627236A - Sitting posture identification method, device, equipment and storage medium - Google Patents
Sitting posture identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113627236A CN113627236A CN202110706613.7A CN202110706613A CN113627236A CN 113627236 A CN113627236 A CN 113627236A CN 202110706613 A CN202110706613 A CN 202110706613A CN 113627236 A CN113627236 A CN 113627236A
- Authority
- CN
- China
- Prior art keywords
- sitting posture
- data
- clustering algorithm
- training
- sitting
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/26—Auxiliary measures taken, or devices used, in connection with the measurement of force, e.g. for preventing influence of transverse components of force, for preventing overload
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a sitting posture identification method, a sitting posture identification device, equipment and a storage medium, aiming at solving the problem of lower sitting posture identification precision in the prior art, wherein the sitting posture identification method comprises the following steps: collecting a large amount of sitting posture data, and preprocessing the sitting posture data to obtain a training data set; training the training data set by adopting a clustering algorithm to construct a sitting posture identification model; and (3) acquiring current sitting posture data by adopting a pressure sensor, inputting the current sitting posture data into a sitting posture recognition model for finishing training, and outputting to obtain a recognized sitting posture category label. According to the invention, an algorithm model is pre-trained by using a clustering algorithm, and then the trained algorithm model is used for carrying out class judgment on unknown sitting posture data, so that the sitting posture identification precision can be effectively improved, and the calculation resource overhead can be effectively reduced.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a sitting posture identification method, a sitting posture identification device, sitting posture identification equipment and a storage medium.
Background
With the continuous progress of society, the rhythm of life and work is accelerated, most people work and study, leisure and entertainment, social activities and other activities are spent on seats, and the daily time spent on the seats by people is longer and longer. Among them, the incorrect sitting posture causes many health problems, and for students who sit on chairs for a long time every day to study, the incorrect sitting posture may have bad influence on their eyesight and spine. For people who work, the side bending of the spine, musculoskeletal diseases, cervical pain and other diseases can also be caused.
Currently, with the development of computer science and technology, there are many sitting posture detection and correction methods that use vision and image processing technology, for example, a sitting posture detection and correction method proposed by publication No. CN110717392A (published japanese 2020-01-21) obtains an image of a target object by obtaining environmental information of a seat where the target object is currently located and attribute information of the target object as shooting parameters, and performs upper body tracking analysis processing on the obtained image, thereby determining posture information of the current sitting posture of the target object. However, the sitting posture identification method using the image processing technology requires hardware support with high cost, and due to the noise influence of the acquired image, such as clothes, obstacles and the like, the identification result has a problem of low accuracy.
Disclosure of Invention
The invention provides a sitting posture identification method, a sitting posture identification device, equipment and a storage medium, aiming at solving the problem of low sitting posture identification precision in the prior art.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a sitting posture identifying method, comprising the steps of:
s1: collecting a large amount of sitting posture data, and preprocessing the sitting posture data to obtain a training data set;
s2: training the training data set by adopting a clustering algorithm to construct a sitting posture identification model;
s3: and (3) acquiring current sitting posture data by adopting a pressure sensor, inputting the current sitting posture data into a sitting posture recognition model for finishing training, and outputting to obtain a recognized sitting posture category label.
Preferably, the clustering algorithm includes one or more of a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering method, a maximum expected clustering algorithm based on a gaussian mixture model, and a coacervation hierarchical clustering algorithm.
As an optimal scheme, the step of constructing the sitting posture recognition model by performing fitting training on the training data set by adopting a K-means clustering algorithm comprises the following steps:
s21: selecting the first k sitting posture data from the training data set as initial clustering centroids, wherein the initial clustering centroids form clusters respectively; wherein k is a positive integer;
s22: calculating the distance from the rest sitting posture data samples to each cluster centroid, and distributing the distance to the closest cluster;
s23: judging whether the cluster to which the current sitting posture data sample belongs is changed, if so, updating the mass center, and skipping to execute the step S22; and if not, completing the construction of the sitting posture identification model.
Preferably, the step of preprocessing the sitting posture data comprises: cleaning data; and manually labeling sitting posture category labels on the sitting posture data respectively.
Preferably, the sitting posture category labels include forward leaning, backward leaning, left leaning, right leaning and sitting.
The invention also provides a sitting posture identifying device which comprises a cushion, a pressure sensor group and a sitting posture identifying module, wherein the pressure sensor group is arranged on the cushion, and the output end of the pressure sensor group is connected with the input end of the sitting posture identifying module; the sitting posture identification module is used for storing a sitting posture identification model constructed based on a clustering algorithm, sitting posture data collected by the pressure sensor group is input into the sitting posture identification module, and the sitting posture identification module is used for inputting the sitting posture data into the sitting posture identification model which is trained to obtain a sitting posture category label.
In the sitting posture identification module in the technical scheme, a stored sitting posture identification model constructed based on a clustering algorithm is pre-trained by adopting a large amount of sitting posture data collected by a pressure sensor group, and parameters of the sitting posture identification model are stored in the sitting posture identification module after being adjusted.
Preferably, the pressure sensor set comprises an array of resistive thin film sensors.
Preferably, the device further comprises a communication module, an input end of the communication module is connected with an output end of the sitting posture identification module, and the communication module transmits the sitting posture type label output by the sitting posture identification module to an external terminal.
The invention also provides a sitting posture identifying device, which comprises one or more processors; a memory; and one or more applications; wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the operations of the sitting posture identifying method according to any one of the above-mentioned embodiments.
The invention also provides a computer readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to perform the operations of the sitting posture identifying method according to any one of the above technical solutions.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: according to the invention, a large amount of sitting posture information is utilized to pre-train an algorithm model by using a clustering algorithm, and then the trained algorithm model is used to judge the category of unknown sitting posture data, so that the sitting posture identification precision can be effectively improved, and the calculation resource overhead can be effectively reduced.
Drawings
Fig. 1 is a flowchart of a sitting posture identifying method according to embodiment 1.
Fig. 2 is a schematic diagram of a sitting posture identifying apparatus according to embodiment 2.
Fig. 3 is a schematic view of the pressure sensor distribution of the sitting posture identifying apparatus of embodiment 2.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
The present embodiment provides a sitting posture identifying method, as shown in fig. 1, which is a flowchart of the sitting posture identifying method of the present embodiment.
The sitting posture identifying method provided by the embodiment comprises the following steps:
step 1: a large amount of sitting posture data are collected and preprocessed to obtain a training data set.
In this embodiment, a large amount of collected sitting posture data for training the sitting posture recognition model is acquired by using a pressure sensor, or is acquired by using an existing sitting posture data set.
In this step, the step of preprocessing the sitting posture data includes: cleaning data; and manually labeling sitting posture category labels on the sitting posture data respectively.
The sitting posture category labels set in the present embodiment include forward leaning, backward leaning, leftward leaning, rightward leaning, and sitting.
Step 2: and training the training data set by adopting a clustering algorithm to construct a sitting posture identification model.
The clustering algorithm adopted in the step comprises one or more of a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering method, a maximum expectation clustering algorithm based on a Gaussian mixture model and a coacervation hierarchical clustering algorithm.
Clustering techniques are processes that divide a collection of physical or abstract objects into classes that are composed of similar objects. The clusters generated by clustering are a set of data objects, which are similar to objects in the same cluster and different from objects in other clusters, and sitting posture data belonging to the same cluster can be classified into the same sitting posture category in the same way.
In this embodiment, the steps of training the training data set by using a K-means clustering algorithm and constructing a sitting posture recognition model include:
step 21: selecting the first k sitting posture data from the training data set as initial clustering centroids, wherein the initial clustering centroids form clusters respectively; wherein k is a positive integer;
step 22: calculating the distance from the rest sitting posture data samples to each cluster centroid, and distributing the distance to the closest cluster;
step 23: judging whether the cluster to which the current sitting posture data sample belongs is changed, if so, updating the mass center, and skipping to execute the step S22; and if not, completing the construction of the sitting posture identification model.
And step 3: and (3) acquiring current sitting posture data by adopting a pressure sensor, inputting the current sitting posture data into a sitting posture recognition model for finishing training, and outputting to obtain a recognized sitting posture category label.
The sitting posture category labels output in this step include forward leaning, backward leaning, left leaning, right leaning and sitting.
Furthermore, the user can judge whether the current sitting posture is correct according to the recognized sitting posture category label, so that the health problem caused by incorrect sitting postures is further avoided.
Furthermore, the sitting posture identification method provided by the embodiment can be combined with an image identification technology to identify the sitting posture, so that the accuracy of sitting posture identification is further improved.
In the embodiment, a great amount of sitting posture information is utilized to pre-train an algorithm model by using a K-means clustering algorithm, and then the trained algorithm model is used to perform category judgment on unknown sitting posture data, so that the sitting posture identification precision can be effectively improved, and the calculation resource overhead including memory space overhead and operation overhead can be effectively reduced.
Example 2
The present embodiment provides a sitting posture recognition apparatus, and applies the sitting posture recognition method provided in embodiment 1. Fig. 2 is a schematic diagram of the sitting posture identifying apparatus of the present embodiment.
The sitting posture identifying device provided by the embodiment comprises a seat cushion 1, a pressure sensor group 2 and a sitting posture identifying module 3, wherein the pressure sensor group 2 is arranged on the seat cushion 1, and the output end of the pressure sensor group 2 is connected with the input end of the sitting posture identifying module 3; the sitting posture identification module 3 stores a sitting posture identification model constructed based on a clustering algorithm, the sitting posture data collected by the pressure sensor group 2 is input into the sitting posture identification module 3, and the sitting posture identification module 3 inputs the sitting posture data into the sitting posture identification model which is trained to obtain a sitting posture category label.
In this embodiment, the pressure sensor group 2 adopts a resistance-type thin film sensor array, and the resistance-type thin film sensor array is distributed on the seat cushion 1. Fig. 3 is a schematic diagram of the distribution of the pressure sensors in this embodiment. The pressure sensor group 2 in this embodiment adopts 12 resistive thin film sensors, and each of the resistive thin film sensors disposed adjacently is disposed at equal intervals.
Further, the device further comprises a communication module 4, wherein an input end of the communication module 4 is connected with an output end of the sitting posture identification module 3, and the communication module 4 transmits the sitting posture type label output by the sitting posture identification module 3 to an external terminal.
The sitting posture identification module 3 of the present embodiment employs a processor, in which a sitting posture identification model constructed based on a clustering algorithm is stored. In a specific implementation process, a sitting posture recognition model built based on a clustering algorithm and stored in the sitting posture recognition module 3 is pre-trained by adopting a large amount of sitting posture data collected by the pressure sensor group 2, and parameters of the sitting posture recognition model are adjusted and then stored in the sitting posture recognition module 3.
When a user sits on the seat cushion 1 provided with the pressure sensor group 2, the pressure sensor group 2 generates an induction voltage signal in an induction mode and transmits the induction voltage signal to the sitting posture identification module 3, the sitting posture identification module 3 converts the induction voltage signal into a digital signal and judges the digital signal, when the digital signal tends to be stable, namely when the user keeps sitting posture, collected sitting posture data (digital signal) are input into a sitting posture identification model completing training, and a sitting posture category label is output.
Furthermore, the sitting posture identification device in this embodiment further includes a communication module 4, an input end of the communication module 4 is connected with an output end of the sitting posture identification module 3, and the communication module 4 transmits the sitting posture category label output by the sitting posture identification module 3 to an external terminal for a user to check a current sitting posture identification result and further correct the sitting posture.
The embodiment also provides a sitting posture identifying device, which comprises one or more processors; a memory; and one or more applications; wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the operations of the sitting posture identification method of embodiment 1.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to perform the operations of the sitting posture identifying method according to embodiment 1.
The same or similar reference numerals correspond to the same or similar parts;
the terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A sitting posture identification method is characterized by comprising the following steps:
s1: collecting a large amount of sitting posture data, and preprocessing the sitting posture data to obtain a training data set;
s2: training the training data set by adopting a clustering algorithm to construct a sitting posture identification model;
s3: and (3) acquiring current sitting posture data by adopting a pressure sensor, inputting the current sitting posture data into a sitting posture recognition model for finishing training, and outputting to obtain a recognized sitting posture category label.
2. The sitting posture identifying method of claim 1, wherein the clustering algorithm comprises one or more of a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering method, a maximum expectation clustering algorithm based on a gaussian mixture model, and a cohesion hierarchy clustering algorithm.
3. The sitting posture recognition method of claim 2, wherein the step of training the training data set by using a K-means clustering algorithm and constructing a sitting posture recognition model comprises:
s21: selecting the first k sitting posture data from the training data set as initial clustering centroids, wherein the initial clustering centroids form clusters respectively; wherein k is a positive integer;
s22: calculating the distance from the rest sitting posture data samples to each cluster centroid, and distributing the distance to the closest cluster;
s23: judging whether the cluster to which the current sitting posture data sample belongs is changed, if so, updating the mass center, and skipping to execute the step S22; and if not, completing the construction of the sitting posture identification model.
4. The sitting posture identifying method as claimed in claim 1, wherein the step of preprocessing the sitting posture data comprises: cleaning data; and manually labeling sitting posture category labels on the sitting posture data respectively.
5. The sitting posture identification method of claim 1, wherein the sitting posture category labels comprise forward leaning, backward leaning, left leaning, right leaning, and sitting.
6. The sitting posture identifying device is characterized by comprising a cushion, a pressure sensor group and a sitting posture identifying module, wherein the pressure sensor group is arranged on the cushion, and the output end of the pressure sensor group is connected with the input end of the sitting posture identifying module; the sitting posture identification module is used for storing a sitting posture identification model constructed based on a clustering algorithm, sitting posture data collected by the pressure sensor group is input into the sitting posture identification module, and the sitting posture identification module is used for inputting the sitting posture data into the sitting posture identification model which is trained to obtain a sitting posture category label.
7. The seating posture identification device of claim 6, wherein the set of pressure sensors comprises an array of resistive thin film sensors.
8. The sitting posture identifying device as claimed in claim 7, further comprising a communication module, wherein an input end of the communication module is connected with an output end of the sitting posture identifying module, and the communication module transmits the sitting posture category label output by the sitting posture identifying module to an external terminal.
9. A sitting posture identification device comprising one or more processors; a memory; and one or more applications; wherein the one or more applications are stored in the memory and configured to perform the operations of the method of any of claims 1-5 by the processor.
10. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform operations of the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706613.7A CN113627236A (en) | 2021-06-24 | 2021-06-24 | Sitting posture identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110706613.7A CN113627236A (en) | 2021-06-24 | 2021-06-24 | Sitting posture identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627236A true CN113627236A (en) | 2021-11-09 |
Family
ID=78378333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110706613.7A Pending CN113627236A (en) | 2021-06-24 | 2021-06-24 | Sitting posture identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627236A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023104206A1 (en) * | 2021-12-09 | 2023-06-15 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on buttock pressure |
| CN117838107A (en) * | 2024-03-07 | 2024-04-09 | 亿慧云智能科技（深圳）股份有限公司 | Healthy sitting posture monitoring method, device and equipment of intelligent cushion and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130251249A1 (en) * | 2012-03-23 | 2013-09-26 | Microsoft Corporation | Rotation-free recognition of handwritten characters |
| 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 |
| CN107788989A (en) * | 2017-09-04 | 2018-03-13 | 浙江大学 | A kind of writing posture monitoring system and method based on acceleration transducer |
| CN109820373A (en) * | 2019-03-28 | 2019-05-31 | 重庆邮电大学 | Sitting posture self-adapting regulation method based on Intelligent seat |
| CN110946584A (en) * | 2019-10-18 | 2020-04-03 | 沈阳大学 | Method for recognizing human body sitting posture by using piezoresistive film pressure sensor group |
| CN112364712A (en) * | 2020-10-21 | 2021-02-12 | 厦门大学 | Human posture-based sitting posture identification method and system and computer-readable storage medium |
-
2021
- 2021-06-24 CN CN202110706613.7A patent/CN113627236A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130251249A1 (en) * | 2012-03-23 | 2013-09-26 | Microsoft Corporation | Rotation-free recognition of handwritten characters |
| 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 |
| CN107788989A (en) * | 2017-09-04 | 2018-03-13 | 浙江大学 | A kind of writing posture monitoring system and method based on acceleration transducer |
| CN109820373A (en) * | 2019-03-28 | 2019-05-31 | 重庆邮电大学 | Sitting posture self-adapting regulation method based on Intelligent seat |
| CN110946584A (en) * | 2019-10-18 | 2020-04-03 | 沈阳大学 | Method for recognizing human body sitting posture by using piezoresistive film pressure sensor group |
| CN112364712A (en) * | 2020-10-21 | 2021-02-12 | 厦门大学 | Human posture-based sitting posture identification method and system and computer-readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| RINKI GUPTA等: "Detection of Poor Posture using Wearable Sensors and Unsupervised Learning", 《2021 7TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING AND COMMUNICATION SYSTEMS (ICACCS)》 * |
| 冯琳: "基于商用RFID的坐姿识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 施宏: "基于Kinect的哺乳期母猪姿态识别算法的研究", 《南京农业大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023104206A1 (en) * | 2021-12-09 | 2023-06-15 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on buttock pressure |
| CN117838107A (en) * | 2024-03-07 | 2024-04-09 | 亿慧云智能科技（深圳）股份有限公司 | Healthy sitting posture monitoring method, device and equipment of intelligent cushion and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | Transforming sensor data to the image domain for deep learning—An application to footstep detection | |
| CN111161879B (en) | Disease prediction system based on big data | |
| CN113255728B (en) | Depression classification method based on graph embedding and multi-mode brain network | |
| CN113627236A (en) | Sitting posture identification method, device, equipment and storage medium | |
| Rosero-Montalvo et al. | Intelligent system for identification of wheelchair user’s posture using machine learning techniques | |
| Jain et al. | Autism Detection of MRI Brain Images Using Hybrid Deep CNN With DM-Resnet Classifier | |
| CN111401219B (en) | Palm key point detection method and device | |
| CN112183314B (en) | Expression information acquisition device, expression recognition method and system | |
| CN109919903A (en) | A kind of vertebra detection positioning and marking method, system and electronic equipment | |
| Xu et al. | A sensing cushion using simple pressure distribution sensors | |
| CN115688760B (en) | Intelligent diagnosis guiding method, device, equipment and storage medium | |
| CN111563549B (en) | Medical image clustering method based on multitasking evolutionary algorithm | |
| Parsaei et al. | SVM-based validation of motor unit potential trains extracted by EMG signal decomposition | |
| WO2018159558A1 (en) | Data generation method, data generation device, data generation program | |
| CN113925311B (en) | Full-automatic human back fitting intelligent seat interaction method and system | |
| Kapoor et al. | Early diagnosis of Alzheimer's disease using machine learning based methods | |
| CN114155952A (en) | Senile dementia illness auxiliary analysis system for elderly people | |
| Ma et al. | Smart cushion-based activity recognition: Prompting users to maintain a healthy seated posture | |
| CN108664904A (en) | A kind of human body sitting posture Activity recognition method and system based on Kinect | |
| CN112183315B (en) | Action recognition model training method and action recognition method and device | |
| CN105046193B (en) | A kind of human motion recognition method based on fusion rarefaction representation matrix | |
| CN114171194B (en) | Quantitative assessment method, device, electronic device and medium for Parkinson multiple symptoms | |
| Ma et al. | Activity level assessment of wheelchair users using smart cushion | |
| CN113616466A (en) | Massage mode generation method and device, electronic equipment and storage medium | |
| CN106388779B (en) | Method and system for marking sleep state sample data types |
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 |