CN112216065A - Intelligent nursing system for behavior of old people and identification method - Google Patents
Intelligent nursing system for behavior of old people and identification method Download PDFInfo
- Publication number
- CN112216065A CN112216065A CN202011104225.3A CN202011104225A CN112216065A CN 112216065 A CN112216065 A CN 112216065A CN 202011104225 A CN202011104225 A CN 202011104225A CN 112216065 A CN112216065 A CN 112216065A
- Authority
- CN
- China
- Prior art keywords
- information
- network model
- neural network
- audio
- application server
- 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
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
-
- 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
- G06F18/24—Classification techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G08B21/0492—Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
Abstract
The invention relates to an intelligent nursing system and an identification method for behavior of old people, which are based on a network camera, an audio collector and a physiological information collector, carry out abnormal information detection and multi-mode information fusion capability analysis on collected audio, image and physiological information multi-mode information through a convolutional neural network model of a client concentrator, further identify behavior and health condition of the old people, transmit the behavior and health condition to a central application server through a network transmission system, and send abnormal information to an information terminal. The invention can more accurately identify, analyze and predict the home health condition of the old, reduce casualties caused by accidents of the old due to sudden diseases, home environment and the like, realize comprehensive intelligent monitoring on the dangerous condition of the home old, and carry out all-weather intelligent monitoring on the health condition of the home old.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent behavior nursing system for old people and an identification method.
Background
With the coming of the aging society of China, the proportion of the old people, particularly the elderly people living alone, in the society is increased year by year. Monitoring of physical and psychological health conditions of the elderly who are alone at home is becoming more and more of a concern. The method has great social significance and market value for timely discovering and even early warning the physical and psychological dangerous conditions of the old at home. Although the traditional simple monitoring system based on the network camera can enable children or nursing staff to remotely observe at any time, the monitoring of full-time coverage cannot be realized.
In order to solve the above problems, a common solution is an intelligent video monitoring system based on traditional image processing or deep learning, which can have a certain active analysis and observation capability in a range of visual coverage, but when the elderly are in a blind area for monitoring, or there is a potential risk in physical conditions, such as heart disease, hypertension, and poor breathing, which cannot be obviously observed, and cannot be obtained by visual analysis, the monitoring coverage cannot be realized by the intelligent monitoring system based on visual sense only.
The existing old people care system based on the Internet of things cannot fully and intelligently utilize useful information related to the Internet of things. For example, chinese patent CN201320852485.8, "an internet of things-based care system for the elderly", can only transmit information that can be obtained in the internet of things to a server, but cannot intelligently provide analysis and alarm.
In summary, the existing intelligent video monitoring system and the internet of things elderly care system cannot realize comprehensive intelligent monitoring of dangerous conditions of the home elderly, and an all-weather intelligent monitoring technology capable of analyzing health conditions and giving an alarm is still a technical gap in the world.
Disclosure of Invention
The invention mainly provides an intelligent behavior nursing system and an identification method for old people.
An intelligent nursing system for behavior of old people comprises a client concentrator, a central application server, a storage database and an information terminal, wherein the client concentrator is connected with an information acquisition system, the central application server, the storage database and the information terminal, and comprises a multi-mode information acquisition system, a network transmission system and a deep learning network model.
Furthermore, the multi-mode information acquisition system comprises a video acquisition system, an audio acquisition system and a physiological information acquisition system, wherein the video acquisition system is based on a network camera, acquires video data and transmits the video data to the client concentrator; the audio acquisition system is based on an audio acquisition device, acquires audio information and transmits the audio information to the client concentrator; the physiological information acquisition system is based on a physiological information acquisition device, acquires physiological information data in real time and transmits the physiological information data to the client concentrator.
Further, the deep learning network model of the client concentrator comprises a convolutional neural network model and a convolutional neural network training program; the convolutional neural network model comprises a convolutional layer, a pooling layer and a regular layer, the convolutional neural network model can realize normal and abnormal classified behavior analysis through a classifier, and the convolutional neural network model adopts an audio, image and physiological information three-way network to perform abnormal information detection and multi-mode information fusion capability analysis on collected audio, image and physiological information multi-mode information; the convolutional neural network model training program comprises a sample acquisition module, an input data organization module, an information fusion and classification model training module and a deep learning neural network model deployment module.
Further, the client concentrator detects abnormal classification information and analyzes the multi-modal information fusion capability of the collected multi-modal information, and then transmits the abnormal classification data to the central application server through the network transmission system.
Furthermore, the central application server can be erected on a cloud platform and can also be erected on a management center as computer server equipment, the central application server detects and analyzes the convolutional neural network model, and abnormal classification data are stored in a storage database.
Further, the central application server can perform further processing according to the result of the behavior analysis sent by the client concentrator, including:
when the analysis result of the convolutional neural network model is abnormal, the central application server can further refine and analyze, and further analyze and identify the multi-mode information based on the deep learning network model and other algorithms;
when the multi-mode information sent by the client concentrator detects abnormality, recording and storing the abnormality information, and sending the abnormality information to the information terminal through the network;
and the central application server judges the abnormal danger level, and when the danger level is higher than a certain degree, the information terminal is notified through a network or automatic voice.
Further, the information terminal comprises a user mobile phone terminal and a hospital emergency terminal.
The identification method of the intelligent nursing system for the behavior of the old people is characterized in that the intelligent nursing system based on the behavior of the old people comprises the following steps:
step 1: the video acquisition system is based on a network camera and acquires video data; the audio acquisition system acquires audio information based on the audio acquisition device; the physiological information acquisition system is based on a physiological information data acquisition device, acquires physiological information data in real time and transmits the physiological information data to the client concentrator;
step 2: the client concentrator performs abnormal classification information detection and multi-mode information fusion capability analysis on the collected video data, audio information and physiological information data through a convolutional neural network model, and optimizes the convolutional neural network model through a convolutional neural network model training program;
and step 3: the central application server receives the data transmission of the client concentrator after detection and analysis through a network transmission system;
and 4, step 4: when the multi-mode information sent by the client concentrator detects abnormality, the central application server records and stores the abnormality information and sends the abnormality information to the user mobile phone terminal and the hospital emergency terminal through the network;
and 5: and (3) when the multi-modal information sent by the client concentrator is not detected to be abnormal, the central application server records and stores the information and returns to the step 3.
In conclusion, the beneficial effects of the invention are as follows: based on the network camera, the audio collector and the physiological information collector, abnormal information detection and multi-mode information fusion capability analysis are carried out on collected audio, image and physiological information multi-mode information through a convolutional neural network model of the client concentrator, so that the behavior and health condition of the old people are identified, the behavior and health condition are transmitted to a central application server through a network transmission system, and the abnormal information is sent to an information terminal. The invention can more accurately identify, analyze and predict the home health condition of the old, reduce casualties caused by accidents of the old due to sudden diseases, home environment and the like, realize comprehensive intelligent monitoring on the dangerous condition of the home old, and carry out all-weather intelligent monitoring on the health condition of the home old.
Drawings
FIG. 1 is a schematic view of an intelligent nursing system for the behavior of the elderly, according to the present invention;
fig. 2 is a schematic diagram of a three-channel network of audio, image and physiological information according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the following figures and detailed description:
referring to the attached drawing 1, the intelligent nursing system for the behavior of the old people comprises a client concentrator, a central application server, a storage database and an information terminal, wherein the client concentrator is connected with the information acquisition system, the central application server, the storage database and the information terminal, the client concentrator comprises a multi-mode information acquisition system, a network transmission system and a deep learning network model, the client concentrator is realized based on a Raspberry Pi 3B +, and the concentrator is provided with a dual-mode Bluetooth module and a Wifi module. The system adopts Raspbian 9. the development of the client program is based on Python, and OpenCV and Pytrch modules are mainly carried. The multi-mode information acquisition system comprises a video acquisition system, an audio acquisition system and a physiological information acquisition system, wherein the video acquisition system is based on a network camera, and the network camera adopts a high-definition raspberry group camera module (1080P, OV 5647) to acquire video data with pixels not less than 64 x 64 and transmit the video data to a client concentrator; the audio acquisition system is based on an audio acquisition device, such as a microphone and an audio card, acquires audio information and transmits the audio information to the client concentrator; the physiological information acquisition system is based on a physiological information acquisition device, such as an ECG (electrocardiogram), pulse wave, respiration, blood oxygen, body temperature and other physiological information data acquisition devices, physiological information data are acquired in real time and transmitted to a client concentrator, the audio acquisition system and the physiological information acquisition system are based on an ESP32 module, an INMP441 module is used for audio acquisition, physiological information mainly acquires the ECG information, heart rate acquisition is performed based on an ADS8232 ECG sensor, the ESP32 module is integrated with wifi and Bluetooth, the physiological information acquisition system can be directly worn on a user, and acquired voice and physiological information are transmitted to a raspberry pie through the Bluetooth or the wifi.
Further, referring to fig. 1 and 2, the deep learning network model of the client concentrator includes a convolutional neural network model and a convolutional neural network training program; the convolutional neural network model comprises a convolutional layer, a pooling layer and a regular layer, can convolve image information or video information into one-dimensional characteristic information through two-dimensional or three-dimensional convolution and dimensionality reduction, can convolve one-dimensional audio information and one-dimensional physiological characteristic information into one-dimensional characteristic information through a one-dimensional or two-dimensional convolutional neural network layer, and can classify and detect abnormal conditions of voice and physiological characteristic information respectively. The convolutional neural network model adopts an audio, image and physiological information three-channel network to carry out abnormal information detection and multi-mode information fusion capability analysis on collected audio, image and physiological information multi-mode information, an input image (64 x 3) is flattened into a one-dimensional characteristic vector (128 x 1) through three layers of two-dimensional convolutional networks, audio and physiological information signals are flattened into 32 characteristic signals respectively through three layers of one-dimensional convolutional networks, and finally, the audio and physiological information signals are fused in a full convolutional layer, the dimension is reduced into 1 vector, and a sigmoid is adopted as an activation function. The model is based on tensioflow.lite, training and packaging are js, the js is stored in firmware of the ESP, regularly acquired data including 20s of videos, 20s of audios and 20s of electrocardiosignals are called through an application program, and the convolutional neural network model can realize normal and abnormal classified behavior analysis through a classifier, and the classifier can also be realized through an SVM or other classifiers; the convolutional neural network model training program comprises a sample acquisition module, an input data organization module, an information fusion and classification model training module and a deep learning neural network model deployment module, wherein the sample acquisition module is used for acquiring an original training sample, and the original training sample comprises various modal information and labeling information; the input data organization module is used for determining normal information or abnormal information in the information according to the labeled information and cleaning available information from the labeled data, and the training module of the information fusion and classification model is used for training by using the original training sample until a preset termination condition is reached so as to finish the training of the convolutional neural network model; the deep learning neural network model deployment module can deploy and embed the network model into the algorithm flow of the whole system after network training is finished, and can upgrade and replace corresponding models in the client concentrator and the server on line as required; the convolutional neural network training program can adjust the network structure, and the network structure and the output are continuously optimized according to the acquired data.
Further, referring to fig. 1, after the client concentrator performs abnormal information detection and multimodal information fusion capability analysis on the collected multimodal information, the collected multimodal information is transmitted to the central application server through the network transmission system, and the network transmission system transmits Wifi transmission or 5G transmission.
Further, referring to fig. 1, the central application server may be deployed in a cloud, such as the airy cloud and the hua shi cloud, or may be erected in a management center as a computer server device, such as a community or a nursing home, which is responsible for receiving and responding to information uploaded by each terminal. And the central application server acquires the data packets acquired from each terminal through monitoring the network port based on the uwsgi protocol and the Django module. After unpacking, the central application server detects and analyzes the convolutional neural network model, and stores the abnormal classification data into a storage database.
Further, referring to fig. 1, the central application server can perform further processing according to the result of the behavior analysis sent by the client concentrator, including:
when the analysis result of the convolutional neural network model is abnormal, the central application server can further refine and analyze, and further analyze and identify the multi-mode information based on the deep learning network model and other algorithms;
when the multi-mode information sent by the client concentrator detects abnormality, recording and storing the abnormality information, and sending the abnormality information to the information terminal through the network;
and the central application server judges the abnormal danger level, and when the danger level is higher than a certain degree, the information terminal is notified through a network or automatic voice.
Further, referring to fig. 1, the information terminal includes a user mobile phone terminal and a hospital emergency terminal.
The identification method of the intelligent nursing system for the behavior of the old people is characterized in that the intelligent nursing system based on the behavior of the old people comprises the following steps:
step 1: the video acquisition system is based on a network camera and acquires video data; the audio acquisition system acquires audio information based on the audio acquisition device; the physiological information acquisition system is based on a physiological information data acquisition device, acquires physiological information data in real time and transmits the physiological information data to the client concentrator;
step 2: the client concentrator performs abnormal classification information detection and multi-mode information fusion capability analysis on the collected video data, audio information and physiological information data through a convolutional neural network model, and optimizes the convolutional neural network model through a convolutional neural network model training program;
and step 3: the central application server receives the data transmission of the client concentrator after detection and analysis through a network transmission system;
and 4, step 4: when the multi-mode information sent by the client concentrator detects abnormality, the central application server records and stores the abnormality information and sends the abnormality information to the user mobile phone terminal and the hospital emergency terminal through the network;
and 5: and (3) when the multi-modal information sent by the client concentrator is not detected to be abnormal, the central application server records and stores the information and returns to the step 3.
In summary, the preferred embodiments of the present invention are described above, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the scope of the present invention, and equivalents and modifications of the technical solutions and concepts of the present invention should be included in the scope of the present invention.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (8)
1. The intelligent nursing system for the behavior of the old people is characterized by comprising a client concentrator, a central application server, a storage database and an information terminal, wherein the client concentrator is connected with the information acquisition system, the central application server, the storage database and the information terminal, and comprises a multi-mode information acquisition system, a network transmission system and a deep learning network model.
2. The system as claimed in claim 1, wherein the multi-modal information collection system comprises a video collection system, an audio collection system, and a physiological information collection system, wherein the video collection system is based on a web camera, collects video data, and transmits the video data to the client concentrator; the audio acquisition system is based on an audio acquisition device, acquires audio information and transmits the audio information to the client concentrator; the physiological information acquisition system is based on a physiological information acquisition device, acquires physiological information data in real time and transmits the physiological information data to the client concentrator.
3. The system as claimed in claim 2, wherein the deep learning network model of the client concentrator includes a convolutional neural network model and a convolutional neural network training program; the convolutional neural network model comprises a convolutional layer, a pooling layer and a regular layer, the convolutional neural network model can realize normal and abnormal classified behavior analysis through a classifier, and the convolutional neural network model adopts an audio, image and physiological information three-way network to perform abnormal information detection and multi-mode information fusion capability analysis on collected audio, image and physiological information multi-mode information; the convolutional neural network model training program comprises a sample acquisition module, an input data organization module, an information fusion and classification model training module and a deep learning neural network model deployment module.
4. The system as claimed in claim 3, wherein the client concentrator detects abnormal classification information and analyzes multi-modal information fusion ability of the collected multi-modal information, and then transmits the abnormal classification data to the central application server through the network transmission system.
5. The system as claimed in claim 4, wherein the central application server can be erected on a cloud platform and can be erected on a management center as computer server equipment, the central application server detects and analyzes the convolutional neural network model, and abnormal classification data is stored in the storage database.
6. The system as claimed in claim 5, wherein the central application server can perform further processing according to the results of the behavior analysis sent from the client concentrator, and comprises:
when the analysis result of the convolutional neural network model is abnormal, the central application server can further refine and analyze, and further analyze and identify the multi-mode information based on the deep learning network model and other algorithms;
when the multi-mode information sent by the client concentrator detects abnormality, recording and storing the abnormality information, and sending the abnormality information to the information terminal through the network;
and the central application server judges the abnormal danger level, and when the danger level is higher than a certain degree, the information terminal is notified through a network or automatic voice.
7. The system as claimed in claim 6, wherein the information terminal includes a user mobile phone terminal and a hospital emergency terminal.
8. The identification method of the intelligent nursing system for the behavior of the old people is characterized in that the intelligent nursing system based on the behavior of the old people comprises the following steps:
step 1: the video acquisition system is based on a network camera and acquires video data; the audio acquisition system acquires audio information based on the audio acquisition device; the physiological information acquisition system is based on a physiological information data acquisition device, acquires physiological information data in real time and transmits the physiological information data to the client concentrator;
step 2: the client concentrator performs abnormal classification information detection and multi-mode information fusion capability analysis on the collected video data, audio information and physiological information data through a convolutional neural network model, and optimizes the convolutional neural network model through a convolutional neural network model training program;
and step 3: the central application server receives the data transmission of the client concentrator after detection and analysis through a network transmission system;
and 4, step 4: when the multi-mode information sent by the client concentrator detects abnormality, the central application server records and stores the abnormality information and sends the abnormality information to the user mobile phone terminal and the hospital emergency terminal through the network;
and 5: and (3) when the multi-modal information sent by the client concentrator is not detected to be abnormal, the central application server records and stores the information and returns to the step 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104225.3A CN112216065A (en) | 2020-10-15 | 2020-10-15 | Intelligent nursing system for behavior of old people and identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011104225.3A CN112216065A (en) | 2020-10-15 | 2020-10-15 | Intelligent nursing system for behavior of old people and identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112216065A true CN112216065A (en) | 2021-01-12 |
Family
ID=74054604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011104225.3A Pending CN112216065A (en) | 2020-10-15 | 2020-10-15 | Intelligent nursing system for behavior of old people and identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112216065A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820071A (en) * | 2021-02-25 | 2021-05-18 | 泰康保险集团股份有限公司 | Behavior identification method and device |
| CN113114977A (en) * | 2021-02-20 | 2021-07-13 | 广州颐寿科技有限公司 | Intelligent nursing system and intelligent nursing method |
| CN113160518A (en) * | 2021-04-02 | 2021-07-23 | Tcl通讯（宁波）有限公司 | Early warning system and early warning method based on edge calculation |
| CN113488200A (en) * | 2021-07-26 | 2021-10-08 | 平安科技（深圳）有限公司 | Intelligent inquiry method, device, computer equipment and storage medium |
| CN113509156A (en) * | 2021-05-28 | 2021-10-19 | 郑州轻工业大学 | Adaptive information processing method, system and storage medium based on behavior characteristics of old user |
| CN113892928A (en) * | 2021-10-14 | 2022-01-07 | 首都体育学院 | Body-building behavior monitoring system based on Beidou positioning and narrowband Internet of things |
| CN115054209A (en) * | 2022-04-14 | 2022-09-16 | 杭州华视诺维医疗科技有限公司 | Multi-parameter physiological information detection system and method based on intelligent mobile device |
| CN116913519A (en) * | 2023-07-24 | 2023-10-20 | 东莞莱姆森科技建材有限公司 | Health monitoring method, device, equipment and storage medium based on intelligent mirror |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203630821U (en) * | 2013-12-23 | 2014-06-04 | 中国人民解放军国防科学技术大学 | Old man caring system based on Internet-of-things |
| CN107153871A (en) * | 2017-05-09 | 2017-09-12 | 浙江农林大学 | Fall detection method based on convolutional neural networks and mobile phone sensor data |
| CN110473534A (en) * | 2019-07-12 | 2019-11-19 | 南京邮电大学 | A kind of nursing old people conversational system based on deep neural network |
| CN110464315A (en) * | 2019-07-23 | 2019-11-19 | 闽南理工学院 | It is a kind of merge multisensor the elderly fall down prediction technique and device |
| CN110916672A (en) * | 2019-11-15 | 2020-03-27 | 中南民族大学 | Old people daily activity monitoring method based on one-dimensional convolutional neural network |
| EP3678093A1 (en) * | 2019-01-02 | 2020-07-08 | Oxehealth Limited | Monitoring movement and vital signs of a human or animal subject in a room using video imaging |
-
2020
- 2020-10-15 CN CN202011104225.3A patent/CN112216065A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203630821U (en) * | 2013-12-23 | 2014-06-04 | 中国人民解放军国防科学技术大学 | Old man caring system based on Internet-of-things |
| CN107153871A (en) * | 2017-05-09 | 2017-09-12 | 浙江农林大学 | Fall detection method based on convolutional neural networks and mobile phone sensor data |
| EP3678093A1 (en) * | 2019-01-02 | 2020-07-08 | Oxehealth Limited | Monitoring movement and vital signs of a human or animal subject in a room using video imaging |
| CN110473534A (en) * | 2019-07-12 | 2019-11-19 | 南京邮电大学 | A kind of nursing old people conversational system based on deep neural network |
| CN110464315A (en) * | 2019-07-23 | 2019-11-19 | 闽南理工学院 | It is a kind of merge multisensor the elderly fall down prediction technique and device |
| CN110916672A (en) * | 2019-11-15 | 2020-03-27 | 中南民族大学 | Old people daily activity monitoring method based on one-dimensional convolutional neural network |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113114977A (en) * | 2021-02-20 | 2021-07-13 | 广州颐寿科技有限公司 | Intelligent nursing system and intelligent nursing method |
| CN112820071A (en) * | 2021-02-25 | 2021-05-18 | 泰康保险集团股份有限公司 | Behavior identification method and device |
| CN113160518A (en) * | 2021-04-02 | 2021-07-23 | Tcl通讯（宁波）有限公司 | Early warning system and early warning method based on edge calculation |
| CN113509156A (en) * | 2021-05-28 | 2021-10-19 | 郑州轻工业大学 | Adaptive information processing method, system and storage medium based on behavior characteristics of old user |
| CN113509156B (en) * | 2021-05-28 | 2023-12-15 | 郑州轻工业大学 | Self-adaptive information processing method, system and storage medium based on behavioral characteristics of old users |
| CN113488200A (en) * | 2021-07-26 | 2021-10-08 | 平安科技（深圳）有限公司 | Intelligent inquiry method, device, computer equipment and storage medium |
| CN113488200B (en) * | 2021-07-26 | 2023-07-25 | 平安科技（深圳）有限公司 | Intelligent inquiry method, intelligent inquiry device, computer equipment and storage medium |
| CN113892928A (en) * | 2021-10-14 | 2022-01-07 | 首都体育学院 | Body-building behavior monitoring system based on Beidou positioning and narrowband Internet of things |
| CN115054209A (en) * | 2022-04-14 | 2022-09-16 | 杭州华视诺维医疗科技有限公司 | Multi-parameter physiological information detection system and method based on intelligent mobile device |
| CN115054209B (en) * | 2022-04-14 | 2023-09-26 | 杭州华视诺维医疗科技有限公司 | Multi-parameter physiological information detection system and method based on intelligent mobile equipment |
| CN116913519A (en) * | 2023-07-24 | 2023-10-20 | 东莞莱姆森科技建材有限公司 | Health monitoring method, device, equipment and storage medium based on intelligent mirror |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112216065A (en) | Intelligent nursing system for behavior of old people and identification method | |
| El-Bendary et al. | Fall detection and prevention for the elderly: A review of trends and challenges | |
| CN104036147B (en) | Family endowment information on services is reported, processing method and client, processing system | |
| CN101690657A (en) | Patient monitoring system and patient monitoring method | |
| CN113257440A (en) | ICU intelligent nursing system based on patient video identification | |
| CN109891516A (en) | Equipment, system and method for patient-monitoring to predict and prevent bed from falling | |
| Deepika et al. | Iot based elderly monitoring system | |
| CN107506573A (en) | It is easy to the Telemedicine System of long-term Continuous Observation guardianship | |
| CN110897277A (en) | Intelligent bracelet and cloud platform management system | |
| CN113143223A (en) | Edge artificial intelligence infant monitoring method | |
| CN113393936B (en) | Disabled elderly health monitoring system based on end-edge-cloud architecture | |
| Karunanithi et al. | An innovative technology to support independent living: the smarter safer homes platform | |
| Doukas et al. | Advanced classification and rules-based evaluation of motion, visual and biosignal data for patient fall incident detection | |
| CN113593693A (en) | Remote health management platform | |
| Sannino et al. | An evolved ehealth monitoring system for a nuclear medicine department | |
| CN116978510A (en) | Nursing grading evaluation system for home cerebral apoplexy patient | |
| CN116825337A (en) | Patient safety nursing early warning system | |
| CN115662631A (en) | AI intelligence discrimination-based nursing home management system | |
| Podugu et al. | Remote medical assistance for marine fishermen through oceannet | |
| CN113869179A (en) | Multi-mode feature attention fused home-based and aged-care intelligent monitoring method and system | |
| CN113658703A (en) | Wisdom medical treatment endowment system | |
| CN110148110B (en) | Spontaneous intelligent diagnosis system for eye shake | |
| Khawandi et al. | Integrated monitoring system for fall detection in elderly | |
| CN206481329U (en) | A kind of network remote sleep info collection monitoring system under Internet of Things medical environment | |
| CN105595973A (en) | Sleeping abnormity warning device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210112 |