CN106570320A - Prediction system for old people behavior health - Google Patents
Prediction system for old people behavior health Download PDFInfo
- Publication number
- CN106570320A CN106570320A CN201610938048.6A CN201610938048A CN106570320A CN 106570320 A CN106570320 A CN 106570320A CN 201610938048 A CN201610938048 A CN 201610938048A CN 106570320 A CN106570320 A CN 106570320A
- Authority
- CN
- China
- Prior art keywords
- data
- old people
- clouds
- module
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
The invention discloses a service system for old people behavior health, and belongs to the field of the computer science and technology. On the basis of a situation that the daily behavior data of old people who live in a nursing home is collected by the technology of Internet of things, calculus, statistics, an artificial intelligence algorithm, a deep learning technology and the like are used for analyzing and researching the behavior data of the old people. The similarities and differences of the individual behavior data and the group behavior data of the old people are analyzed to find the general activity rule of the old people, a health model is established, the behavior data is combined with the health model to judge the health condition of the old people, the old people who suffer from mental disorder and physical illness are screened, the behavior data of the old people who suffer from the mental disorder and the physical illness is compared with the behavior data of normal old people to find the characteristics of abnormal individuals, and certain assistance and advices based on big data are provided for social old-age care and the recovery and treatment work of chronic diseases. The technology is high in maneuverability, and is especially suitable to use in the pension work of the nursing home and the research work of the chronic diseases of specialized hospitals.
Description
Technical field:
The invention belongs to computer science and technology field, and in particular to RFID signal process, principal component analysiss algorithm, heredity
Algorithm, deep neural network build.
Background technology:
The end of the year 2014, more than 60 years old aging population of China reach 2.12 hundred million, account for the 15.5% of total population, it is contemplated that to 2020
Year, aging population are up to 2.4 hundred million people, account for the 17.17% of total population, and the quantity of old solitary people increases sharply in recent years.
Afterwards the physical function of 30% old man will be remarkably decreased in 1 year within 65 years old, also, 75 years old afterwards, this ratio
It is up to 42%.This shows that China has stepped into aging society, due to the decline of body function and going out for psychological problems
Existing, old people is badly in need of being concerned about, in the middle of our society, age-care becomes a more and more important problem.
The traditional old-age provision model of China is home nursing mode.But, from at this stage, because children leave old man's work, life
Phenomenon it is more and more universal, also, one kind is referred to as the allusion quotation of 4-2-1 (being that a couple has a child and four old men)
The home mode of type progressively increases, and in general, old man and children live apart, and a couple is extremely difficult in family
In look after 4 old men.Therefore, traditional old-age provision model cannot adapt to the development of society, move in nursing house and be increasingly becoming
A kind of trend.
With the development of network technology and wireless sensor devices, technology of Internet of things is played in daily life
More and more important effect.RFID (Radio Frequency Identification, RF identification) technology is high-precision by its
The advantages of degree, short time-delay, low cost, noncontact, non line of sight and big transmission range, in China second-generation identity card, mass transit card, campus
The fields such as card define extensive practical application.
The arriving in big data epoch so that data can provide more contents and useful information, substantial amounts of data are led to
Pretreatment is crossed, the larger factor of disturbance degree is extracted, by analyzing these factors valuable information can be excavated.For example,
Apple Watch can record heart beating, coordinate GPS (the Global Positioning System global positioning systems of IPhone
System) record position, measurement heat consumption, exercise time and move distance etc., the data of various aspects can be analyzed:Motion,
Nutrition, sleep quality etc..
Current health forecast technology lacks large-scale data-handling capacity, and the data set dimension that can be excavated all compares
It is low, so when in the face of high-dimensional mass data, effective information may be omitted because of the problem of operational capability.
The content of the invention:
In order to solve above-mentioned problem, the invention provides a kind of old people's behavior health forecast system, the present invention
Premise based on big data is developed, and behavioral data of the old people for collecting in nursing house is carried out into data using intelligent algorithm
Pretreatment, is then analyzed, is studied using the algorithm of deep learning, and the old people in nest egg institute provides accurately personal strong
Health is assessed and predicted, reaches the purpose of " preventive treatment of disease ".
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, including:RFID is marked
Sign, RFID reader, RFID active antennas, high in the clouds data processing module, high in the clouds data memory module.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
RFID reader needs to be connected with router, and the label data of reading is uploaded to into high in the clouds data processing module.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
Living in the old people in nursing house needs to carry with RFID tag.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
The RFID tag just can work to after the pumping signal of RFID active antennas.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
The RFID tag inside has unique number.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
High in the clouds data processing module is divided into data normalization module and data prediction module.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
The RFID tag carried using old people and RFID reader identification behavioral data of the old people in nursing house region, and by number
According to being uploaded to high in the clouds data processing module.Data are stored in after the data normalization module of high in the clouds data processing module is processed
High in the clouds data memory module.Pretreatment is carried out to the data set stored in the data memory module of high in the clouds using intelligent algorithm,
Then the data after process are combined into deep neural network, sets up senior health and fitness's model, so as to can be with reference to newly collecting
Old people's behavioral data is predicted and assesses to the health status of old people.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
High in the clouds data processing module receives the data of RFID reader upload, and data are entered by the data normalization module in the module
Row standardization, then sends data to high in the clouds data memory module
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
Data normalization module in the high in the clouds data processing module by the data standard of collection turn to three-number set TagID,
Place, Time } form, wherein, TagID is the RFID tag number, and Place is to detect old people place nursing house
In certain region numbering, Time is to detect old people's residence time in this region.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
High in the clouds data processing module turns to data standard after three-number set, sends data to high in the clouds data memory module and is deposited
Storage.
Old people's behavior health forecast system, including following implementation steps:
S1, big data collection:Behavioral data of the old people in nursing house is collected using RFID technique, and is uploaded to high in the clouds.
S2, big data pretreatment:The old people's behavioral data collected is entered using principal component analysiss algorithm and genetic algorithm
Row pretreatment, to facilitate the data analysiss work in future.
S3, data analysiss, prediction:Data after pretreatment are modeled with reference to deep neural network, then tie on model
The data that conjunction is newly collected, so as to play the effect of prediction, realize based on the health forecast demand of big data.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
The data set that will be stored in high in the clouds memory module combines senior health and fitness's model that deep neural network is generated, by the model
It is arranged into the data prediction module of high in the clouds data processing module.The old people's behavioral data newly collected is through high in the clouds data processing
After resume module, the health condition of old people can be estimated.
To achieve these goals, the invention provides a kind of old people's behavior health forecast system, its technical scheme is:
Beyond the clouds, as a result the old people's behavioral data newly collected is shown after the process of high in the clouds data processing module by terminal.
The terminal includes personal computer, panel computer or smart mobile phone.
The invention has the beneficial effects as follows:Valuable information can be excavated in mass data, it is old in nest egg institute
People provided accurate personal health assessment and predicted year, realized preventing trouble before it happens.
Description of the drawings:
The feature of the present invention can clearly be understood by reference to accompanying drawing, accompanying drawing is schematic and should not be construed as
Any restriction is carried out to the present invention, in the accompanying drawings:
Fig. 1 is the signal processing flow figure of the present invention;
Fig. 2 is the modeling work flow chart of the present invention;
Fig. 3 is the form that data in cloud database are stored in the present invention;
Fig. 4 is the system block diagram of the present invention;
Fig. 5 is the flow chart of the present invention.
Specific embodiment:
Technical solution of the present invention is described in detail below, but protection scope of the present invention is not limited to the enforcement
Example.
As shown in figure 1, the working range of the RFID active antennas used in the present invention is 2-7m (adjustable according to voltage),
The working range of RFID reader is 30m, and data collection function is broadly divided into following three step:
First, sensor sample:When old people is in nursing house in a certain region, the RFID tag entrained by old people
It is activated that signal will be sent after the excitation of antenna, after the signal is received by RFID reader, high in the clouds number can be sent to
Processed according to processing module.
2nd, signal processing:High in the clouds data processing module upon receipt of the signals, is carried out data by data normalization module
Standardization.
3rd, data storage:High in the clouds data processing module enters the data transfer after standardization to high in the clouds data memory module
Row storage.
As shown in figure 3, store in the present invention data form in data memory module beyond the clouds be three-number set TagID,
Place, Time } form, wherein, TagID is the RFID tag number, and Place is to detect old people place nursing house
In certain region numbering, Time is to detect old people's residence time in this region.
As shown in figure 4, a kind of old people's behavior health forecast system, including:RFID tag, RFID reader, RFID swashs
Encourage antenna, high in the clouds data processing module, high in the clouds data memory module and terminal.Wherein high in the clouds data processing module includes data
Standardized module and data prediction module, terminal includes personal computer, panel computer, smart mobile phone.
As shown in figure 5, the health forecast of the present invention is completed by following three step:
First, the collection of big data:The collecting work of big data be using RFID device coordinate high in the clouds data processing module with
And high in the clouds data memory module is completed.In the gatherer process of data, its main feature and challenge are that number of concurrent is high, because
In nursing house, it is possible to which a big region of Area comparison can simultaneously accommodate tens old peoples, therefore arrange beyond the clouds
Signal handler needs to use multi-thread concurrent mechanism.
2nd, the pretreatment of big data:Because the signals collecting mechanism set by us is 24 hours uninterrupted samplings, and adopt
Collection frequency is 1 minute.Therefore, the old man data volume of a day is 1440, and we will effectively be divided mass data
Analysis, just must carry out pretreatment to it.After we merge this 1440 data, calculated using Principal Component Analysis Algorithm, heredity
Method carries out dimension-reduction treatment to it, extracts the larger composition of disturbance degree as the initial data of data processor.
3rd, the excavation of big data:Classified using deep neural network on data set mainly after pre-processing
With the calculating of cluster, so as to set up senior health and fitness's forecast model, realize according to the new old people's behavioral data collected and build
Vertical health forecast model, the purpose for the health condition of old people being estimated and being predicted.
The staff of nursing house and the family members of old man can be by strong with old people's behavior installed in terminal unit
The supporting application software of health prognoses system check related old people health evaluating report and health forecast report, in order to and
The abnormal conditions of Shi Faxian old people, and corresponding care is given to old people.
Old people's behavior health forecast system of the present invention is applicable not only to nursing house, while being also applied for sanatorium, doctor
Treat mechanism to use.
As described above, although the present invention has been represented and described with reference to specific embodiment, it shall not be construed as right
The restriction of itself of the invention.On the premise of the spirit and scope of the present invention defined without departing from claims, can be to it
In the form and details various changes can be made.
Claims (15)
1. a kind of old people's behavior health forecast system, it is characterised in that:Premise based on big data is developed, old by what is collected
The behavioral data of year people in nursing house carries out data prediction using intelligent algorithm, is then carried out using the algorithm of deep learning
Analysis, research, the old people in nest egg institute provides accurate personal health assessment and predicts, reaches the purpose of " preventive treatment of disease ".
2. a kind of old people's behavior health forecast system as claimed in claim 1, including:RFID tag, RFID reader,
RFID active antennas, high in the clouds data processing module, high in the clouds data memory module.
3. a kind of old people's behavior health forecast system as claimed in claim 2, it is characterised in that:RFID reader need with
Router connects, and the label data of reading is uploaded to into high in the clouds data processing module.
4. a kind of old people's behavior health forecast system as claimed in claim 3, it is characterised in that:In living in nursing house
Old people needs to carry with RFID tag.
5. a kind of old people's behavior health forecast system as claimed in claim 4, it is characterised in that:The RFID tag
Just can work to after the pumping signal of RFID active antennas.
6. a kind of old people's behavior health forecast system as claimed in claim 5, it is characterised in that:Inside the RFID tag
With unique number.
7. a kind of old people's behavior health forecast system as claimed in claim 6, it is characterised in that:High in the clouds data processing module
It is divided into data normalization module and data prediction module.
8. a kind of old people's behavior health forecast system as claimed in claim 7, it is characterised in that:Carried using old people
The behavioral data of RFID tag and RFID reader identification old people in nursing house region, and data are uploaded to into high in the clouds data
Processing module.Data store data storage mould beyond the clouds after the data normalization module of high in the clouds data processing module is processed
Block.Pretreatment is carried out to the data set stored in the data memory module of high in the clouds using intelligent algorithm, after then processing
Data combine deep neural network, senior health and fitness's model is set up, so as to can be with reference to the old people's behavioral data newly collected
The health status of old people are predicted and are assessed.
9. a kind of old people's behavior health forecast system as claimed in claim 8, it is characterised in that:High in the clouds data processing module
The data of RFID reader upload are received, data is standardized by the data normalization module in the module, so
After send data to high in the clouds data memory module.
10. a kind of old people's behavior health forecast system as claimed in claim 9, it is characterised in that:At the high in the clouds data
The data standard of collection is turned to data normalization module in reason module the form of three-number set { TagID, Place, Time },
Wherein, TagID is the RFID tag number, and Place is the numbering for detecting certain region in the nursing house of old people place,
Time is to detect old people's residence time in this region.
A kind of 11. old people's behavior health forecast systems as claimed in claim 10, it is characterised in that:High in the clouds data processing mould
Block turns to data standard after three-number set, sends data to high in the clouds data memory module and is stored.
12. a kind of old people's behavior health forecast systems as claimed in claim 11, it is characterised in that implement step including following
Suddenly:
S1, big data collection:Behavioral data of the old people in nursing house is collected using RFID technique, and is uploaded to high in the clouds.
S2, big data pretreatment:The old people's behavioral data collected is entered using principal component analysiss algorithm and genetic algorithm
Row pretreatment, to facilitate the data analysiss work in future.
S3, data analysiss, prediction:Data after pretreatment are modeled with reference to deep neural network, then tie on model
The data that conjunction is newly collected, so as to play the effect of prediction, realize based on the health forecast demand of big data.
13. a kind of old people's behavior health forecast systems as claimed in claim 12, it is characterised in that will be stored in high in the clouds and deposit
The data set of storage module combines senior health and fitness's model that deep neural network is generated, and the model is arranged into into high in the clouds data processing
The data prediction module of module.The old people's behavioral data newly collected, can be right after the process of high in the clouds data processing module
The health condition of old people is estimated.
14. a kind of old people's behavior health forecast systems as claimed in claim 13, it is characterised in that beyond the clouds are new to collect
As a result the old people's behavioral data for arriving is shown after the process of high in the clouds data processing module by terminal.The terminal includes
Personal computer, panel computer or smart mobile phone.
15. a kind of old people's behavior health forecast systems as claimed in claim 14, it is characterised in that step S3 is used
Enter the mining analysis of line data set based on Tensorflow framing tools.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610938048.6A CN106570320A (en) | 2016-10-25 | 2016-10-25 | Prediction system for old people behavior health |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610938048.6A CN106570320A (en) | 2016-10-25 | 2016-10-25 | Prediction system for old people behavior health |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106570320A true CN106570320A (en) | 2017-04-19 |
Family
ID=58534762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610938048.6A Pending CN106570320A (en) | 2016-10-25 | 2016-10-25 | Prediction system for old people behavior health |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106570320A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108962379A (en) * | 2017-05-26 | 2018-12-07 | 中国科学院软件研究所 | A kind of mobile phone assisted detection system of cerebral nervous system disease |
CN114723597A (en) * | 2022-04-08 | 2022-07-08 | 江苏中科西北星信息科技有限公司 | Smart home old-age care method and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102178511A (en) * | 2011-04-11 | 2011-09-14 | Tcl集团股份有限公司 | Disease prevention warning system and implementation method |
CN103501330A (en) * | 2013-09-29 | 2014-01-08 | 武汉五心养老科技服务有限公司 | Intelligent identification processing method for personal monitoring |
KR20140120468A (en) * | 2013-04-03 | 2014-10-14 | (주)에스디시스템 | System For Providing Remote Filial Duty Agency Service |
CN104866949A (en) * | 2015-04-23 | 2015-08-26 | 东南大学 | RFID and GPS based nursing home intelligent management system |
CN105243285A (en) * | 2015-11-10 | 2016-01-13 | 广州西麦科技股份有限公司 | Big data health forecast system |
CN105528754A (en) * | 2015-12-28 | 2016-04-27 | 湖南师范大学 | Old people information service system based on dual neural network behavior recognition model |
CN105678104A (en) * | 2016-04-06 | 2016-06-15 | 电子科技大学成都研究院 | Method for analyzing health data of old people on basis of Cox regression model |
CN105725992A (en) * | 2016-01-28 | 2016-07-06 | 无锡南理工科技发展有限公司 | Home-based aged care monitoring system and method |
-
2016
- 2016-10-25 CN CN201610938048.6A patent/CN106570320A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102178511A (en) * | 2011-04-11 | 2011-09-14 | Tcl集团股份有限公司 | Disease prevention warning system and implementation method |
KR20140120468A (en) * | 2013-04-03 | 2014-10-14 | (주)에스디시스템 | System For Providing Remote Filial Duty Agency Service |
CN103501330A (en) * | 2013-09-29 | 2014-01-08 | 武汉五心养老科技服务有限公司 | Intelligent identification processing method for personal monitoring |
CN104866949A (en) * | 2015-04-23 | 2015-08-26 | 东南大学 | RFID and GPS based nursing home intelligent management system |
CN105243285A (en) * | 2015-11-10 | 2016-01-13 | 广州西麦科技股份有限公司 | Big data health forecast system |
CN105528754A (en) * | 2015-12-28 | 2016-04-27 | 湖南师范大学 | Old people information service system based on dual neural network behavior recognition model |
CN105725992A (en) * | 2016-01-28 | 2016-07-06 | 无锡南理工科技发展有限公司 | Home-based aged care monitoring system and method |
CN105678104A (en) * | 2016-04-06 | 2016-06-15 | 电子科技大学成都研究院 | Method for analyzing health data of old people on basis of Cox regression model |
Non-Patent Citations (2)
Title |
---|
中国上市公司业绩评价课题组: "《2016中国上市公司业绩评价报告》", 30 June 2016 * |
刘祎洋: "面向健康评估的疾病风险自动预警技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108962379A (en) * | 2017-05-26 | 2018-12-07 | 中国科学院软件研究所 | A kind of mobile phone assisted detection system of cerebral nervous system disease |
CN108962379B (en) * | 2017-05-26 | 2022-04-22 | 中国科学院软件研究所 | Mobile phone auxiliary detection system for cranial nerve system diseases |
CN114723597A (en) * | 2022-04-08 | 2022-07-08 | 江苏中科西北星信息科技有限公司 | Smart home old-age care method and system |
CN114723597B (en) * | 2022-04-08 | 2023-09-15 | 江苏中科西北星信息科技有限公司 | Intelligent home-based care method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gu et al. | An unsupervised approach to activity recognition and segmentation based on object-use fingerprints | |
Erdogan et al. | A data mining approach for fall detection by using k-nearest neighbour algorithm on wireless sensor network data | |
CN103517042B (en) | A kind of nursing house old man's hazardous act monitoring method | |
CN111613291B (en) | Medicine management, classification and medical staff and patient association system | |
El-Attar et al. | Discrete wavelet transform-based freezing of gait detection in Parkinson’s disease | |
CN106570320A (en) | Prediction system for old people behavior health | |
Anderson et al. | Similarity measure for anomaly detection and comparing human behaviors | |
CN113377845B (en) | Intelligent old-age care data processing method and system based on big data | |
CN109949924A (en) | A kind of size intelligent healthcare system | |
Arablouei et al. | Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data | |
CN108122005B (en) | Method for classifying clinical medicine levels | |
Sim et al. | Improving the accuracy of erroneous-plan recognition system for Activities of Daily Living | |
CN114241270A (en) | Intelligent monitoring method, system and device for home care | |
CN106250712A (en) | A kind of ureteral calculus Forecasting Methodology based on increment type neural network model and prognoses system | |
CN112883999A (en) | Pedometer system and method for detecting abnormal movement of dairy cow | |
Hu et al. | Challenges in studying falls of community-dwelling older adults in the real world | |
Xu et al. | Comparative studies on activity recognition of elderly people living alone | |
CN212990135U (en) | Plant disease and insect pest image recognition device based on MobileNet neural network model | |
Zhang et al. | Sleep-pose recognition based on pyroelectric infrared sensing technology | |
Zhang et al. | Early lameness detection in dairy cattle based on wearable gait analysis using semi-supervised LSTM-Autoencoder | |
CN106407694A (en) | Neurasthenia prediction method and prediction system based on incremental neural network model | |
CN106202986A (en) | A kind of tonsillitis Forecasting Methodology based on increment type neural network model and prognoses system | |
CN109887605A (en) | A kind of mechanism long-term care hospital stays pattern analysis method based on model | |
Hou et al. | Study on individual behavior of dairy cows based on activity data and clustering | |
CN109817318A (en) | A kind of personal health monitoring system based on big data |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170419 |
|
WD01 | Invention patent application deemed withdrawn after publication |