CN112885035A - Old man falling detection method and system in real environment based on big data - Google Patents
Old man falling detection method and system in real environment based on big data Download PDFInfo
- Publication number
- CN112885035A CN112885035A CN202110043711.7A CN202110043711A CN112885035A CN 112885035 A CN112885035 A CN 112885035A CN 202110043711 A CN202110043711 A CN 202110043711A CN 112885035 A CN112885035 A CN 112885035A
- Authority
- CN
- China
- Prior art keywords
- data
- falling
- module
- field
- fall
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0446—Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0453—Sensor means for detecting worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
Landscapes
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Biophysics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physical Education & Sports Medicine (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a big data-based old man falling detection system in a real environment, wherein a wearable unit comprises a sensor module, a field processing single chip microcomputer and a field storage module, wherein the sensor module is arranged on the old man, and the sensor module and the field storage module are correspondingly and electrically connected with the field processing single chip microcomputer; the remote service unit comprises a falling condition database, a support vector machine, a falling data processing module and a remote service control chip, wherein the remote service control chip is correspondingly and electrically connected with the falling condition database, the support vector machine and the falling data processing module; the field processing single chip microcomputer is correspondingly and electrically connected with the communication unit, the communication unit is correspondingly and electrically connected with the remote service unit and the falling alarm unit, and the communication unit is correspondingly and electrically connected with the remote service control chip. The invention can use big data to carry out self-learning, accurately and intelligently judge whether the old falls down, and solves the problem of pain point with higher misjudgment rate in the prior art.
Description
Technical Field
The invention relates to the field of old people falling detection, in particular to a method and a system for detecting the falling of old people in a real environment based on big data.
Background
With the gradual progress of China into aging society, the safety precaution of the old in daily life becomes a hot point of social attention increasingly. According to the report in the Shanghai, 1983 people died only by falls in 2010, 87.1% of which are elderly people over 65 years old, the mortality rate reaches 77.9/10 ten thousand, which is equivalent to 4.7 elderly people died by falls each day. In addition, more than half of the cases of old people who see a doctor due to injury are tumble cases; of the hospitalized cases due to injury, more than 80% are cases of falls.
According to investigation and research make internal disorder or usurp, the old people can reduce the injury to the minimum degree in rescue within 20 minutes after falling down, and the rescue is the gold time for rescue. Therefore, an accurate fall detection technology can certainly exert huge social and economic benefits in the aging society of China; however, fall detection is an extremely challenging technology, and the main difficulties are as follows:
1. real old people falling data are difficult to obtain and serve as basic data for designing and verifying a falling detection method; 2. the existing sensor acquires data, and an intersection exists between falling and non-falling actions, so that the existing sensor is difficult to distinguish, and misjudgment and missed judgment are easily caused; 3. data samples for fall algorithm verification do not exist all over the world, so that the difficulty of algorithm verification is invisibly increased, and the method is pioneering work; 4. differences in individual characteristics of each person, such as gender, height, weight, etc., can cause some data differences in the fall monitoring process, thereby increasing the difficulty in the development and verification of the fall algorithm.
Therefore, there is a need to design a method and a system for detecting the falling of the old people in the real environment based on big data.
Disclosure of Invention
In order to overcome the defects in the prior art, a method and a system for detecting the falling of the old people in the real environment based on big data are provided.
The invention is realized by the following scheme:
a system for detecting the falling of old people in a real environment based on big data comprises a wearable unit, a communication unit, a remote service unit and a falling alarm unit;
the wearable unit comprises a sensor module, a field processing single chip microcomputer and a field storage module, wherein the sensor module is arranged on the body of the old, and the sensor module and the field storage module are correspondingly and electrically connected with the field processing single chip microcomputer;
the remote service unit comprises a falling condition database, a support vector machine, a falling data processing module and a remote service control chip, wherein the remote service control chip is correspondingly and electrically connected with the falling condition database, the support vector machine and the falling data processing module;
the field processing single chip microcomputer is correspondingly and electrically connected with the communication unit, the communication unit is correspondingly and electrically connected with the remote service unit and the falling alarm unit, and the communication unit is correspondingly and electrically connected with the remote service control chip.
The sensor module comprises a plurality of acceleration sensors and angular velocity sensors.
The wearable unit further comprises a field condition confirmation module, and the field condition confirmation module is correspondingly and electrically connected with the field processing single chip microcomputer.
The wearable unit further comprises a heart rate acquisition module, and the heart rate acquisition module is electrically connected with the field processing single chip microcomputer correspondingly.
A method for detecting falling of old people in a real environment based on big data comprises the following steps:
firstly, an acceleration sensor and an angular velocity sensor collect three-axis angular velocity and three-axis angular velocity data of an old person, and a heart rate collecting module collects heart rate data of the old person and transmits the heart rate data to a field processing single chip microcomputer;
secondly, the on-site processing single chip microcomputer processes the triaxial angular velocity data, the triaxial angular velocity data and the heart rate data, if the data exceed a falling threshold value, the data are packaged and marked as alarm data, then the alarm data are subjected to alarm processing through the communication unit and the falling alarm unit in sequence, meanwhile, the alarm data are stored in a local on-site storage module and are sent to the communication unit, and then the old or other operators confirm whether the on-site actually falls down in an on-site condition confirmation module;
if the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data do not exceed the threshold value after being processed by the single chip microcomputer in the field, but the old man actually falls down in the field, the data are packaged and marked as fall-down misinformation data, meanwhile, the data storage is carried out on the fall-down misinformation data in a local field storage module, the packaged fall-down misinformation data are sent to a communication unit, the old man or other operators confirm whether the field actually falls down in a field condition confirmation module, and at the moment, the fall-down alarm unit directly carries out automatic alarm processing;
thirdly, the communication unit transmits the received alarm data and the received fall false alarm data to a fall data processing module of the remote service unit, the fall data processing module processes the alarm data and the fall false alarm data, characteristic values in the alarm data and the fall false alarm data are extracted, and the characteristic values and the attached actual fall condition are sent to a support vector machine;
fourthly, classifying and learning the characteristic values and the accompanying actual falling condition by a support vector machine, realizing classification and modeling by using LIBSVM, and testing by using DAG-SVM; the progressive learning can solve the problem of relevance between the actual falling condition and the characteristic value, and the learning result is stored in a falling condition database;
the feature values of the old people and the attached actual falling conditions are stored in the falling condition database separately, the feature value matching level is continuously improved after correction learning for many times, the on-site processing single chip microcomputer receives the latest learning results, and after the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data of the old people appear, the on-site processing single chip microcomputer pushes the falling conditions of the old people according to the latest learning results, so that the purpose of intelligent correction is achieved.
The invention has the beneficial effects that:
the old people falling detection method and system based on big data in the real environment can use the big data to carry out self-learning, accurately and intelligently judge whether the old people fall or not, and solve the problem of pain points with high misjudgment rate in the prior art.
Drawings
Fig. 1 is a block diagram of a fall detection system for old people in a real environment based on big data according to the present invention;
Detailed Description
The preferred embodiment of the present invention is further illustrated below in conjunction with FIG. 1:
a system for detecting the falling of old people in a real environment based on big data comprises a wearable unit, a communication unit, a remote service unit and a falling alarm unit;
the wearable unit comprises a sensor module, a field processing single chip microcomputer and a field storage module, wherein the sensor module is arranged on the body of the old, and the sensor module and the field storage module are correspondingly and electrically connected with the field processing single chip microcomputer;
the remote service unit comprises a falling condition database, a support vector machine, a falling data processing module and a remote service control chip, wherein the remote service control chip is correspondingly and electrically connected with the falling condition database, the support vector machine and the falling data processing module;
the field processing single chip microcomputer is correspondingly and electrically connected with the communication unit, the communication unit is correspondingly and electrically connected with the remote service unit and the falling alarm unit, and the communication unit is correspondingly and electrically connected with the remote service control chip.
The sensor module comprises a plurality of acceleration sensors and angular velocity sensors. The angular velocity sensor applies the Coriolis force principle, a special ceramic device is arranged in the angular velocity sensor, the equipment structure and the circuit device are greatly simplified, and therefore the angular velocity sensor has excellent operation characteristics. Angular velocity sensors, also known as gyroscopes, are devices for detecting angular motion about one or two axes orthogonal to the axis of rotation relative to the inertial space using a moment-of-momentum sensitive housing of a high-speed solid of revolution. An acceleration sensor is a sensor capable of measuring acceleration. The damper is generally composed of a mass block, a damper, an elastic element, a sensitive element, an adjusting circuit and the like. In the acceleration process, the sensor obtains an acceleration value by measuring the inertial force borne by the mass block and utilizing Newton's second law. Common acceleration sensors include capacitive, inductive, strain, piezoresistive, piezoelectric, etc. depending on the sensor sensing element. The acceleration sensor can detect alternating current signals and vibration of objects, the person can generate certain regular vibration when walking, and the acceleration sensor can detect zero crossing points of the vibration, so that the walking steps or the running steps of the person can be calculated, and the moving displacement of the person can be calculated. And calorie consumption can be calculated using a certain formula.
The wearable unit further comprises a field condition confirmation module, and the field condition confirmation module is correspondingly and electrically connected with the field processing single chip microcomputer.
The wearable unit further comprises a heart rate acquisition module, and the heart rate acquisition module is electrically connected with the field processing single chip microcomputer correspondingly. Techniques for heart rate acquisition module "photoplethysmography" (PPG). The method utilizes the absorption of the blood to green light, reflects the change of blood flow by measuring the change of reflected light intensity, namely the contraction (high blood flow and weak reflected light) and the relaxation (opposite to the contraction condition) of the heart, and obtains corresponding heart rate data.
A method for detecting falling of old people in a real environment based on big data comprises the following steps:
firstly, an acceleration sensor and an angular velocity sensor collect three-axis angular velocity and three-axis angular velocity data of an old person, and a heart rate collecting module collects heart rate data of the old person and transmits the heart rate data to a field processing single chip microcomputer;
secondly, the on-site processing single chip microcomputer processes the triaxial angular velocity data, the triaxial angular velocity data and the heart rate data, if the data exceed a falling threshold value, the data are packaged and marked as alarm data, then the alarm data are subjected to alarm processing through the communication unit and the falling alarm unit in sequence, meanwhile, the alarm data are stored in a local on-site storage module and are sent to the communication unit, and then the old or other operators confirm whether the on-site actually falls down in an on-site condition confirmation module;
if the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data do not exceed the threshold value after being processed by the single chip microcomputer in the field, but the old man actually falls down in the field, the data are packaged and marked as fall-down misinformation data, meanwhile, the data storage is carried out on the fall-down misinformation data in a local field storage module, the packaged fall-down misinformation data are sent to a communication unit, the old man or other operators confirm whether the field actually falls down in a field condition confirmation module, and at the moment, the fall-down alarm unit directly carries out automatic alarm processing;
thirdly, the communication unit transmits the received alarm data and the received fall false alarm data to a fall data processing module of the remote service unit, the fall data processing module processes the alarm data and the fall false alarm data, characteristic values in the alarm data and the fall false alarm data are extracted, and the characteristic values and the attached actual fall condition are sent to a support vector machine;
fourthly, classifying and learning the characteristic values and the accompanying actual falling condition by a support vector machine, realizing classification and modeling by using LIBSVM, and testing by using DAG-SVM; the progressive learning can solve the problem of relevance between the actual falling condition and the characteristic value, and the learning result is stored in a falling condition database;
the feature values of the old people and the attached actual falling conditions are stored in the falling condition database separately, the feature value matching level is continuously improved after correction learning for many times, the on-site processing single chip microcomputer receives the latest learning results, and after the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data of the old people appear, the on-site processing single chip microcomputer pushes the falling conditions of the old people according to the latest learning results, so that the purpose of intelligent correction is achieved. The method is insensitive to abnormal values, can help people to grasp the data of key samples, and has good robustness by removing a large number of redundant samples "
The specific process of classifying and learning the characteristic values and the attached actual falling situations by the support vector machine is as follows:
(1) the SVM classification, wherein the SVM is originally designed for binary classification, when a plurality of classifications are used, the classifications can be made by different combinations of the binary classifications. Generally to address the problem of sample identification. The SVM transforms the input data into a high-dimensional feature space, finds the most difficult data points, and forms an optimal hyperplane by using the most difficult data points, so that the two groups of data are farthest away.
(2) In the progressive learning, in a learning mechanism of the SVM, original feature data D is used, and a model is trained by using the feature data D. A new feature D2 is obtained from the new acoustic signal and is associated with the support vector SV1, and the original model is updated after the new feature and support vector are associated. Thus, the step of progressive learning can be considered as a segmented training.
The process of progressive learning is to add new feature data into the support vector and retrain once by using SVM, and the detailed steps are as follows:
training: the algorithm uses the original data D. For training SVM and obtaining a set of support vectors SV1
Obtaining new characteristics: the new audio signal is processed through I, II to obtain new feature data D1.
Finding the total number of features: to reduce the number of calculations, the total number of SVs 1 and D2 is found, and the number of iterations is less than the total number.
Retraining: and (3) performing union on the obtained feature data to obtain D2 ═ { SV1 ═ D1}, and re-executing the step (1) to obtain a new group of training models, namely progressive learning models.
Aiming at the actual situation that the old people fall down to form a limited sample, the optimal solution under the existing information can be obtained by adopting the classification and learning process of the method, and not only the optimal solution when the number of samples tends to be infinite.
Although the invention has been described and illustrated in some detail, it should be understood that various modifications may be made to the described embodiments or equivalents may be substituted, as will be apparent to those skilled in the art, without departing from the spirit of the invention.
Claims (5)
1. The utility model provides an old man detection system that tumbles under real environment based on big data which characterized in that: the system comprises a wearable unit, a communication unit, a remote service unit and a falling alarm unit;
the wearable unit comprises a sensor module, a field processing single chip microcomputer and a field storage module, wherein the sensor module is arranged on the body of the old, and the sensor module and the field storage module are correspondingly and electrically connected with the field processing single chip microcomputer;
the remote service unit comprises a falling condition database, a support vector machine, a falling data processing module and a remote service control chip, wherein the remote service control chip is correspondingly and electrically connected with the falling condition database, the support vector machine and the falling data processing module;
the field processing single chip microcomputer is correspondingly and electrically connected with the communication unit, the communication unit is correspondingly and electrically connected with the remote service unit and the falling alarm unit, and the communication unit is correspondingly and electrically connected with the remote service control chip.
2. The old man fall detection system based on big data in real environment according to claim 1, characterized in that: the sensor module comprises a plurality of acceleration sensors and angular velocity sensors.
3. The old man fall detection system based on big data in real environment according to claim 1, characterized in that: the wearable unit further comprises a field condition confirmation module, and the field condition confirmation module is correspondingly and electrically connected with the field processing single chip microcomputer.
4. The old man fall detection system based on big data in real environment according to claim 1, characterized in that: the wearable unit further comprises a heart rate acquisition module, and the heart rate acquisition module is electrically connected with the field processing single chip microcomputer correspondingly.
5. A method for detecting falling of old people in real environment based on big data is characterized by comprising the following steps:
firstly, an acceleration sensor and an angular velocity sensor collect three-axis angular velocity and three-axis angular velocity data of an old person, and a heart rate collecting module collects heart rate data of the old person and transmits the heart rate data to a field processing single chip microcomputer;
secondly, the on-site processing single chip microcomputer processes the triaxial angular velocity data, the triaxial angular velocity data and the heart rate data, if the data exceed a falling threshold value, the data are packaged and marked as alarm data, then the alarm data are subjected to alarm processing through the communication unit and the falling alarm unit in sequence, meanwhile, the alarm data are stored in a local on-site storage module and are sent to the communication unit, and then the old or other operators confirm whether the on-site actually falls down in an on-site condition confirmation module;
if the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data do not exceed the threshold value after being processed by the single chip microcomputer in the field, but the old man actually falls down in the field, the data are packaged and marked as fall-down misinformation data, meanwhile, the data storage is carried out on the fall-down misinformation data in a local field storage module, the packaged fall-down misinformation data are sent to a communication unit, the old man or other operators confirm whether the field actually falls down in a field condition confirmation module, and at the moment, the fall-down alarm unit directly carries out automatic alarm processing;
thirdly, the communication unit transmits the received alarm data and the received fall false alarm data to a fall data processing module of the remote service unit, the fall data processing module processes the alarm data and the fall false alarm data, characteristic values in the alarm data and the fall false alarm data are extracted, and the characteristic values and the attached actual fall condition are sent to a support vector machine;
fourthly, classifying and learning the characteristic values and the accompanying actual falling condition by a support vector machine, realizing classification and modeling by using LIBSVM, and testing by using DAG-SVM; the progressive learning can solve the problem of relevance between the actual falling condition and the characteristic value, and the learning result is stored in a falling condition database;
the feature values of the old people and the attached actual falling conditions are stored in the falling condition database separately, the feature value matching level is continuously improved after correction learning for many times, the on-site processing single chip microcomputer receives the latest learning results, and after the three-axis angular velocity data, the three-axis angular velocity data and the heart rate data of the old people appear, the on-site processing single chip microcomputer pushes the falling conditions of the old people according to the latest learning results, so that the purpose of intelligent correction is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110043711.7A CN112885035A (en) | 2021-01-13 | 2021-01-13 | Old man falling detection method and system in real environment based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110043711.7A CN112885035A (en) | 2021-01-13 | 2021-01-13 | Old man falling detection method and system in real environment based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112885035A true CN112885035A (en) | 2021-06-01 |
Family
ID=76045607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110043711.7A Pending CN112885035A (en) | 2021-01-13 | 2021-01-13 | Old man falling detection method and system in real environment based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112885035A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926959A (en) * | 2022-06-16 | 2022-08-19 | 王思杨 | Self-power-generation old man falling alarm device and falling judgment method thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007260389A (en) * | 2006-03-01 | 2007-10-11 | Shinshu Univ | Fall inferring device and fall protecting device |
| CN103393412A (en) * | 2013-08-15 | 2013-11-20 | 重庆邮电大学 | Intelligent home based old person caring device |
| CN204028698U (en) * | 2014-05-30 | 2014-12-17 | 宣东 | A kind ofly guard the intelligent robot of serving the elderly |
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN105590409A (en) * | 2016-02-26 | 2016-05-18 | 江苏大学 | Human body tumble detection method and human body tumble detection system based on big data |
| CN105769205A (en) * | 2016-02-23 | 2016-07-20 | 中国科学院深圳先进技术研究院 | Body information detection device and fall detection system |
| CN110728833A (en) * | 2019-08-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Alarm confirmation method, device, equipment and computer readable medium |
-
2021
- 2021-01-13 CN CN202110043711.7A patent/CN112885035A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007260389A (en) * | 2006-03-01 | 2007-10-11 | Shinshu Univ | Fall inferring device and fall protecting device |
| CN103393412A (en) * | 2013-08-15 | 2013-11-20 | 重庆邮电大学 | Intelligent home based old person caring device |
| CN204028698U (en) * | 2014-05-30 | 2014-12-17 | 宣东 | A kind ofly guard the intelligent robot of serving the elderly |
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN105769205A (en) * | 2016-02-23 | 2016-07-20 | 中国科学院深圳先进技术研究院 | Body information detection device and fall detection system |
| CN105590409A (en) * | 2016-02-26 | 2016-05-18 | 江苏大学 | Human body tumble detection method and human body tumble detection system based on big data |
| CN110728833A (en) * | 2019-08-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Alarm confirmation method, device, equipment and computer readable medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114926959A (en) * | 2022-06-16 | 2022-08-19 | 王思杨 | Self-power-generation old man falling alarm device and falling judgment method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Saleh et al. | FallAllD: An open dataset of human falls and activities of daily living for classical and deep learning applications | |
| Bennett et al. | Inertial measurement unit-based wearable computers for assisted living applications: A signal processing perspective | |
| Wang et al. | Human activity recognition with user-free accelerometers in the sensor networks | |
| CN104888444B (en) | Wisdom gloves, the method and system of a kind of calorie of consumption and hand positions identification | |
| TW202036245A (en) | System for recognizing user gestures according to mechanomyogram detected from user’s wrist and method thereof | |
| CN108831527A (en) | A kind of user movement condition detection method, device and wearable device | |
| CN104586398A (en) | Old man falling detecting method and system based on multi-sensor fusion | |
| CN105139029B (en) | A kind of Activity recognition method and device of prison prisoner | |
| US10588517B2 (en) | Method for generating a personalized classifier for human motion activities of a mobile or wearable device user with unsupervised learning | |
| CN104637242A (en) | Elder falling detection method and system based on multiple classifier integration | |
| CN108596074A (en) | A kind of human body lower limbs action identification method based on inertial sensor | |
| CN106388831A (en) | Method for detecting falling actions based on sample weighting algorithm | |
| CN107293092A (en) | Emergency system for robot of supporting parents | |
| CN109603142A (en) | A kind of the identification method of counting and its device of dumbbell exercise | |
| CN107105092A (en) | A kind of human body tumble recognition methods based on dynamic time warping | |
| CN112885035A (en) | Old man falling detection method and system in real environment based on big data | |
| CN107019501B (en) | Remote tumble detection method and system based on genetic algorithm and probabilistic neural network | |
| Chen et al. | Detection of falls with smartphone using machine learning technique | |
| CN110807471A (en) | Behavior recognition system and recognition method of multi-mode sensor | |
| AU2020102094A4 (en) | GROUP ACTIVITY RECOGNITION BY INTEGRATION AND FUSION OF INDIVIDUAL MULTISENSORY IoT DATA | |
| Chunsheng et al. | Human gait feature data analysis and person identification based on IMU | |
| Peng et al. | Experimental analysis of artificial neural networks performance for accessing physical activity recognition in daily life | |
| Ma et al. | Research on human motion recognition system based on MEMS sensor network | |
| CN108648417A (en) | Raspberry Pi old man based on deep learning falls down detecting system | |
| Liu et al. | Preimpact fall detection for elderly based on fractional domain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |