CN108492869A - Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system - Google Patents
Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system Download PDFInfo
- Publication number
- CN108492869A CN108492869A CN201810252085.0A CN201810252085A CN108492869A CN 108492869 A CN108492869 A CN 108492869A CN 201810252085 A CN201810252085 A CN 201810252085A CN 108492869 A CN108492869 A CN 108492869A
- Authority
- CN
- China
- Prior art keywords
- data
- ecg
- electrocardiogram
- knn
- skyline
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The monitoring of smart cloud intelligent ECG and data processing system that the invention discloses a kind of based on Internet of Things, belong to field of wisdom medical treatment, including electrocardio vest hardware, intelligent mobile terminal, cloud server, electrocardio vest is for measuring electrocardiogram (ECG) data and electrocardiogram (ECG) data being sent to intelligent mobile terminal, intelligent mobile terminal is used to receive the electrocardiogram (ECG) data of electrocardio vest transmission, electrocardiogram (ECG) data is through local cache, if meeting preset time window and storage size threshold condition and network-in-dialing state allows, work station gateway is by wireless communication interface to electrocardiogram (ECG) data unloading, cloud server synchronizes overall macro-data, big data technology can be utilized to improve heart disease and the treatment timeliness and success rate of cardiovascular patient.
Description
Technical field
Patent of the present invention belongs to field of wisdom medical treatment, is a kind of combination cloud computing technology, technology of Internet of things and big data
The technologies such as analysis design the smart cloud cardiac monitoring system based on Internet of Things using intelligent mobile medical network system as platform
System.
Background technology
With the increasingly improvement of the development and living standard of society, health problem also increasingly obtains the concern of people.The heart
Popular name for and angiocardiopathy have obtained medicine academia and industrial quarters as one of the principal disease for threatening human life's safety
Extensive concern, but the automatic monitoring of heart disease and angiocardiopathy is not solved effectively yet with the problems such as prevention.
As human health chief threat disease, heart disease and various cardiovascular and cerebrovascular disease incidences show year by year
The trend of growth and increasingly rejuvenation.Big city, large hospital, medical institutions are directed to cardio-cerebralvascular diseases at present, usually adopt
Using the means or mode accurately treated under clinical setting after being admitted to hospital with patient, but the universal cost of this mode is higher, and lacks
It is few it is daily it is necessary effectively monitor with the measures such as diagnosis and treatment at any time, this allows for heart disease and various cardiovascular and cerebrovascular diseases obtain not
To effective prevention and treatment.With the method for information technology, intelligent medical treatment technology is just by traditional medical monitoring product transition
To the stage for carrying out medical assistance using Internet of Things, in the medical terminal based on Sensor Network, a large amount of data are produced, I
These data are monitored except, it is also necessary to carry out effective, intelligent high in the clouds data analysis, could targetedly into
Row auxiliary treatment is simultaneously monitored routine health and feeds back.
But the common electrocardio long distance monitoring of tradition is the application of remote monitoring system, traditional cardiac monitoring platform at present
Website, end fitting used include electrocardio Holter and heart beeper, the former can only record electrocardiosignal and but cannot remotely pass
It is defeated, acquisition electrocardiosignal can not be analyzed in real time, after patient's use, need to be sent to hospital by hospital's special equipment to this
Electrocardiosignal reads, plays back and analyzes, so now with the FLASH card replacement electrocardio Holter with store function.And it is right
It is although able to record the electrocardiogram (ECG) data signal of several minutes of patients in present electrocardio beeper, but it does not ensure that patient can send out
A series of rescue operation is completed when sick in time.
At the same time, since big data needs are allocated the work of a large amount of computers, it must reach such as Map-
Frame the same Reduce could realize this function, and in order to solve these problems, we are by cloud computing and use the portable heart
Electric signal monitoring vest has devised new system.
Invention content
According to defect present in above-mentioned background technology and deficiency, to achieve the goals above, skill of the present invention
Art scheme is：A kind of monitoring of smart cloud intelligent ECG and data processing system based on Internet of Things, including electrocardio vest hardware, intelligence
Energy mobile terminal, cloud server, electrocardio vest is for measuring electrocardiogram (ECG) data and electrocardiogram (ECG) data being sent to intelligent mobile end
End, intelligent mobile terminal are used to receive the electrocardiogram (ECG) data of electrocardio vest transmission, and electrocardiogram (ECG) data is through local cache, if meeting preset
Time window and storage size threshold condition and network-in-dialing state allow, and work station gateway passes through wireless communication interface
To electrocardiogram (ECG) data unloading, cloud server synchronizes overall macro-data, the high in the clouds data processing system of the cloud server
Multifactor mistake is carried out to synchronous electrocardiogram (ECG) data using distributed multifactor Skyline filter algorithms, KNN exceptions matching algorithm
Filter and abnormal matching treatment, and feed back match information.
Further, the distributed multifactor Skyline filter algorithms are as follows：
Data partition：To the abnormal electrocardiogram data that cloud server uploads, alert data is formed, according to inquiry alert data
Point position, to be automatically positioned the medical area where it；
Local beta pruning：Using the search algorithm Skyline SkyGrid based on Spark, by rational partial-block, first
A part of data task is decomposed monitoring station and carries out subtask calculating, then the task after summarizing is carried out multifactor mistake beyond the clouds
It filters and merges pretreatment, call the row's of falling region index of the budget in the region to carry out part Skyline and inquire, and utilize frequency
Skyline lattice technology carries out Fast Labeling to part by beta pruning region；
The overall situation summarizes：Beta pruning is directly carried out using the grid mark of local Skyline, and obtains final Skyline knots
Fruit collects, and is the data set for meeting anomalous ecg monitoring and inquiry condition.
Further, distributed KNN exceptions matching algorithm is as follows：
Assuming that the abnormal electrocardiogram data point set obtained after distributed multifactor Skyline filter algorithm filters is S,
Existing anomalous ecg data point set is R in one database, if if finding most similar one group of data in R and S data
Point set, as doubtful abnormal data, lookup method are as follows：
The file of the partition value comprising R and S is placed according to inverted index；
File is carried out distributed caching by host, while monitor workstation reads R from distributed cachingi∈ R and Si∈S
The partition value of each subregion, and generate key-value pair；
A pair of of R that global KNN is receivediAnd SiBetween all the points, gradually read, in VCm(PartitionID) phase
With one group of key-value pair to upper execution IVkNN algorithms, KNN inquiries are then carried out：Assuming that obtaining electrocardio after skyline is filtered
Data point set S, existing anomalous ecg data point set R in medical expert library, if finding most similar one in R and S data
Group data point set, i.e., doubtful abnormal data are carrying out subregion to point set R and S based on inverted index, are being distributed task according to subregion
Monitor workstation decomposition operation is given, then carries out summarizing joint account beyond the clouds and goes out global kNN values, is checking SiAll subregions
Afterwards, global KNN will export KNN (r, s), and R is read from distributed cachingi∈ R and SiThe partition value of each subregion of ∈ S generates
Key-value pair, object and its possible k arest neighbors in R all enter local calculation as a result, to obtain the knot of KNN inquiries
Fruit shows the heartbeat data for having abnormal, system is then the data feedback to patient and doctor if KNN query results are not sky.
Advantageous effect：Patent of the present invention is set by portable electrocardiosignal of the design with monitoring system and acquisition system
It is standby, counted in detail in conjunction with the intelligent mobile terminal of cloud server and work station gateway and by monitoring data processing system and high in the clouds
According to three big core technology of analysis system, to capture in time and transmit abnormal electrocardiogram signal, and can utilize big
Data technique improves heart disease and the treatment timeliness and success rate of cardiovascular patient.
Description of the drawings
Fig. 1 hierarchical relationship figures of the present invention；
Fig. 2 electrocardio cloud monitoring system figures；
Fig. 3 cloud servers and work station gateway figure；
Fig. 4 big data processing mode figures；
The multifactor filter algorithm flow charts of Fig. 5 distributions Skyline；
Fig. 6 distribution KNN exception matching algorithm flow charts；
Fig. 7 SkyGrid algorithmic code figures；
Fig. 8 IVKNN algorithmic code figures；
Fig. 9 electrocardio vest structural schematic diagrams
Specific implementation mode
Such as Fig. 1, a kind of monitoring of smart cloud intelligent ECG and Data Processing System Design based on Internet of Things, mainly by the heart
Electric vest hardware, intelligent mobile terminal and high in the clouds data processing system three parts composition.Wherein electrocardio vest product uses
In conjunction with the portable electrocardiosignal vest of monitoring system and acquisition system, intelligent mobile terminal is then technological core to electron cloud
Cloud server and work station gateway, and for high in the clouds data processing by monitoring data handle and high in the clouds detail data analysis system
System is constituted, and is matched extremely using the multifactor filter algorithms of distribution Skyline and distribution KNN in monitoring data processing system
Algorithm.
A kind of monitoring of smart cloud intelligent ECG and Data Processing System Design based on Internet of Things, specific implementation includes as follows
Step：
S1. it measures electrocardiogram (ECG) data and abnormal electrocardiogram data is sent to mobile terminal.The stage is mainly by portable electrocardio
Signal guards the monitoring system of vest and acquisition system is completed.Such as Fig. 2, wherein monitoring system is mainly by Internet of Things collecting device
Layer, bearer network network layers, cloud processing system and data service system and five part of application layer software platform form, we are designed
Portable cardiac signal guard vest, the 3G/4G wireless communication techniques utilized and divide monitor center (such as family data center
With Community Watch center) data communication is carried out, and data can be regularly dumped to using cloud simultaneous techniques in medical cloud data
The heart carries out cloud storage and historical data analysis.
In the process, it is as follows：
S1.1. Internet of Things collecting device carries out precise acquisition to data；
S1.2. the mobile communication module in bearer network network layers will be in the data transmission of acquisition to point monitoring using transmission technology
The heart, while to information amplification, the first server terminal host for handling and being transmitted to point monitor center；
Can be buffered in local by the data of wireless base station, and periodically automatic synchronization to cloud service network, these data
It can be on corresponding cloud server.
S1.3. the intelligent cardiac data analysis system in cloud server mainly refers to according to electrocardio situation data and electrocardio
Mark carries out monitoring and big data analysis automatically according to existing expert database and user's history case record data.If there is problem meeting
Automatic early-warning；And the electrocardio medical health service system in cloud server is mainly used for electrocardio medical consultations expert, prison
Bed doctor or medical expert can carry out with reference to decision according to the data of data analysis system and be supplied to patient's remote diagnosis.
S1.4. on the one hand electrocardiogram (ECG) data visualization is converted into high in the clouds chart data by application layer software platform, on the other hand
Carry out big data result of calculation feedback operation.
The collecting device in portable electrocardiosignal monitoring vest is that the keyes electrocardios increased income are utilized to survey in the process
Measure modules A D8232.AD8232 is a integrated front end, and the heart is carried out suitable for carrying out signal condition to heart biology electric signal
Rate is guarded.This is a low-power consumption released for the application of all kinds of vital signs, single lead, before heart rate monitor simulation
End.For system using the Arduino exploitations increased income, essence is a set of optics heart for being integrated with amplifying circuit and noise canceller circuit
Rate sensor, we place it in the lead module of electrocardio vest.
In order to ensure the validity of detection, we believe in the intensity for having carried out transformation electrocardiosignal to the hardware than interference
Number intensity it is much smaller, and the electrocardiosignal of cardiac electrical transmission signal and input is interfered to be in common-mode state, it is desirable that have
Good common-mode rejection ratio.So our preamplifier has selected U.S. Analog Devices.Simultaneously by using leakage
The metalfilmresistor of electric very little can limit amplifier operation point drift, dual power supply to ensure that secondary half-cycle signal is not done
It disturbs, by improving above, Q values are adjustable and active double T.
S2. the abnormal electrocardiogram data that electrocardio vest is sent are received.The stage is mainly by cloud server and work station gateway
It constitutes, such as Fig. 3, the abnormal data of electrocardio vest acquisition is after local cache, if meeting preset time window and memory space
Size threshold value condition and network-in-dialing state allow, and work station gateway will carry out unloading by wireless communication interface to data,
Calculating and storage capacity in view of monitoring station is limited, and cloud server can carry out overall macro-data together using cloud simultaneous techniques
Step.On the one hand cloud system periodically summarizes data, automatically form Visual Report Forms (including electrocardiogram (ECG) data and image etc.) and feed back to
User, still further aspect utilize Spark real-time data analysis systems, using distributed Skyline algorithms, first a part of data
Task-decomposing carries out subtask calculating to monitoring station, then the task after summarizing is carried out multifactor filtering beyond the clouds and merges pre- place
Reason, it is close that we are also carried out using the anomalous ecg data in distributed search algorithm KNN and medical expert library same principle simultaneously
Like inquiry.If there is abnormal conditions, will be fed back in real time by mobile terminal software or mobile calls service system
Patient and responsibility doctor carry out the prompting that gives warning in advance.At this moment it obtained electrocardio images for user and doctor while can use,
And decide whether further to see a doctor.
S3. data utilize Skyline, the collaboration of KNN algorithms to carry out Intelligent treatment and alarm feedback.The stage is mainly by supervising
It controls data processing system and high in the clouds data analysis system is constituted.
Wherein two kinds of algorithms of monitoring data analysis system progress include：The distributed multifactor filter algorithms of Skyline and point
The multifactor filter algorithms of cloth Skyline.
The distributed multifactor filter algorithms of Skyline include three processes, such as Fig. 4：Data partition, local beta pruning, the overall situation
Summarize.In the data partition stage, according to the position where query point, we position the medical area where it, and then calling should
The row's of falling region index that the precomputation in region is good carries out part Skyline inquiries, in local Skyline inquiries, Wo Menli
Fast Labeling is carried out by beta pruning region to part with frequency Skyline lattice technology.In global aggregation stages, no longer calculate global
Skyline directly carries out beta pruning using the grid mark of local Skyline and obtains final Skyline result sets.Specific algorithm
Referring to Fig. 7.
The distributed multifactor filter algorithm algorithm specific steps of Skyline：
S1. the file of the partition value comprising R and S is placed according to inverted index；
S2. then file is carried out distributed caching by host.
S3. monitor workstation reads R from distributed cachingi∈ R and SiThe partition value of each subregions of ∈ S generates key assignments
It is right.In this way, the object in R and its may be that k arest neighbors all enters local calculation result.
S4. a pair of of R that overall situation KNN is receivediAnd SiBetween all the points, can gradually read, in VCmIdentical key-value pair
One group to upper execution particular task, then carry out KNN inquiries.
S5. last, after all subregions for checking Si, global KNN will export KNN (r, s) (the 14th row).The algorithm exports
Key-value pair ＜ r, KNN (r, s) ＞ are to obtain the result of KNN inquiries.Referring specifically to Fig. 8
Wherein detail data analysis system in high in the clouds is using cloud computing as core.The basic principle of cloud computing is with local or remote
Journey data center services internet, to reach the optimization distribution of resource.Its process flow：
S1. data acquire；
S2. the pretreatment of data；
S3. data store；
S4. data analysis and excavation；
S5. result presentation.
See Fig. 5 in detail.
In another embodiment：It is a kind of based on Internet of Things smart cloud intelligent ECG monitoring set with data processing system
Meter, is mainly made of electrocardio vest hardware, intelligent mobile terminal and high in the clouds data processing system three parts.
The major function of electrocardio vest hardware in the invention is to measure electrocardiogram (ECG) data and send abnormal electrocardiogram data
To mobile terminal.Its core is ECG Acquisition System and prison on wireless transmission and data synchronization technology based on mobile terminal
Protecting system.
Further, the acquisition in electrocardio vest and monitor system are characterized in that, composition department includes：
S1. Internet of Things collecting device layer；
S2. bearer network network layers；
S3. cloud processing system；
S4. data service system；
S5. application layer software platform.
Further, step S1. Internet of Things collecting device includes active electrode, heart rate sensor, other minisize components
(power supply voltage stabilizing chip, level translator etc.), environmental monitoring chip, alignment sensor, warning system etc., wherein heart rate sensor
Heart for monitoring user in real time, for environmental monitoring chip for monitoring surrounding enviroment variation in real time, alignment sensor is fixed
Position where the user of position, warning system are filtered processing to the data of heart rate sensor detection in time.
Further, there are two types of ranks for the data exception of heart rate sensor detection：
1. heart rate is in 50-60bpm or 100-120bpm, at this time terminal active alarm, call user's attention.
2. being more than or equal to 1.5s when heart rate is either higher than 120bpm or adjacent cardiac interval occur less than 40bpm
When.
Further, step S2. occurs further, and step S3. and S4. cloud server are mainly by intelligent cardiac data
Analysis system and electrocardio medical health service system composition.
Further, on the one hand electrocardiogram (ECG) data visualization is converted into high in the clouds chart numbers by step S5. application layer softwares platform
According to big data result of calculation feedback operation on the one hand can be carried out.
Further, the acquisition system of electrocardio vest hardware is characterized in that：Its essence is a set of using the Arduino to increase income
Develop and be integrated with the optics heart rate sensor of the elimination circuit of amplifying circuit and noise.The apparatus main feature includes：
Preposition amplifier, metalfilmresistor, dual power supply using U.S. Analog Devices editions.
The major function of intelligent mobile terminal in the invention is to receive electrocardio vest to pass through the wireless biography based on mobile terminal
The alarm abnormal electrocardiogram data sent on defeated and data synchronization technology, core is cloud server and work station gateway.
Further, the anomalous ecg data that client acquires electrocardio vest are after local cache, if meeting preset
Time window and storage size threshold condition and network-in-dialing state allow, and work station gateway will be connect by wireless telecommunications
Mouth carries out unloading to data, and the calculating and storage capacity in view of monitoring station are limited, and cloud server can utilize cloud simultaneous techniques handle
Overall macro-data synchronizes.
High in the clouds data processing system in the invention is responsible for utilizing Skyline to data, KNN algorithms carry out Intelligent treatment with
And alarm feedback.Its core includes：
S1. monitoring data high in the clouds processing system；
Further, the step S1. monitor system main tasks are by big data technology, cloud computing technology and intelligent cardiac
System is combined.Big abnormal electrocardiogram data calculating task is decomposed first, is handled using large number of monitoring data
System carries out subtask calculating, then carries out by high in the clouds summarizing local result of calculation, obtains final global calculation result.It is worth
It is to be noted that our flow chart of data processing are the first progress multifactor filterings of Skyline, then kNN match queries are carried out, but actually
The calculating of Task-decomposing merger can be carried out at the same time in a distributed fashion.
Wherein above-mentioned algorithm includes：
The multifactor filter algorithms of S1.1 distributions Skyline；
S1.2 distribution KNN exception matching algorithms.
Further, the multifactor filter algorithms of step S1.1 distributions Skyline are as follows：
S1.1.1 data partitions：To the abnormal electrocardiogram data that cloud server uploads, according to these alert data points of inquiry
The position at place, to be automatically positioned the medical area where it；
The beta pruning of the parts S1.1.2：The row's of falling region index of the budget in the region is called to carry out part Skyline inquiries, and
Fast Labeling is carried out by beta pruning region to part using frequency Skyline lattice technology；
S1.1.3. the overall situation summarizes：Using the grid mark of local Skyline directly carry out beta pruning obtain it is final
Skyline result sets.
Further, after Skyline is inquired, we will obtain one and meet anomalous ecg monitoring and inquiry condition
Data set is looked into followed by distributed search algorithm kNN is approximate with the existing anomalous ecg data progress in medical expert library
It askes.There is similar query point if there is with anomalous ecg data, this means that being likely to occur heartbeat illness, needs timely medical treatment
Service intervention, in order to use Spark to carry out kNN inquiries, it is assumed that we obtain abnormal electrocardiogram data point after skyline is filtered
Collect S, existing anomalous ecg data point set R in medical expert library, then according to the definition that kNN is inquired, if in R and S data
In if finding most similar one group of data point set, as doubtful abnormal data.The result set of the multifactor filter algorithms of Skyline
As the input set of search algorithm kNN, multifactor interference can be effectively excluded, improves the accurate of big data analysis result
Degree because skyline and kNN be all big data is filtered into relatively small data algorithm (input data amount be more than output number
According to amount), so the execution of the algorithm of the two collaboration, while also improving Distributed Calculation speed
Distributed search algorithm's kNN process is discussed in detail in we below.
Step S1.2 distribution KNN exception matching algorithms are as follows：
S1.2.1 places the file of the partition value comprising R and S according to inverted index；
File is carried out distributed caching by S1.2.1 hosts, while monitor workstation reads R from distributed cachingi∈R
And SiThe partition value of each subregions of ∈ S, and generate key-value pair；
A pair of of R that S1.2.3 overall situations KNN is receivediAnd SiBetween all the points, can gradually read, in VCmIdentical key assignments
To one group to upper execution particular task, then carry out KNN inquiries；
S1.2.4 is checking SiAll subregions after, global KNN will export KNN (r, s) (the 14th row).The algorithm run-out key
Value is to ＜ r, and KNN (r, s) ＞ is to obtain the result of KNN inquiries.
Further, if kNN query results are not sky, this means that have abnormal heartbeat data, our system handle
The data feed back to patient and doctor in a manner of visual by mobile terminal cell phone software or portable medical calling system.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope of present disclosure, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (3)
1. a kind of monitoring of smart cloud intelligent ECG and data processing system based on Internet of Things, which is characterized in that including electrocardio horse
First hardware, intelligent mobile terminal, cloud server, electrocardio vest is for measuring electrocardiogram (ECG) data and electrocardiogram (ECG) data being sent to intelligence
Energy mobile terminal, intelligent mobile terminal are used to receive the electrocardiogram (ECG) data of electrocardio vest transmission, and electrocardiogram (ECG) data is through local cache, if full
The preset time window of foot and storage size threshold condition and network-in-dialing state allow, and work station gateway passes through wireless
Communication interface synchronizes overall macro-data electrocardiogram (ECG) data unloading, cloud server, the high in the clouds data of the cloud server
Processing system carries out synchronous electrocardiogram (ECG) data using distributed multifactor Skyline filter algorithms, KNN exceptions matching algorithm
Multifactor filtering and abnormal matching treatment, and feed back match information.
2. the smart cloud intelligent ECG monitoring based on Internet of Things and data processing system, feature exist as described in claim 1
In the distributed multifactor Skyline filter algorithms are as follows：
Data partition：To the abnormal electrocardiogram data that cloud server uploads, alert data is formed, according to the point of inquiry alert data
Position, to be automatically positioned the medical area where it；
Local beta pruning：Using the search algorithm Skyline SkyGrid based on Spark, by rational partial-block, first one
Partial data Task-decomposing carries out subtask calculating to monitoring station, then the task after summarizing carried out beyond the clouds multifactor filtering with
Merge pretreatment, calls the row's of falling region index of the budget in the region to carry out part Skyline inquiries, and utilize frequency
Skyline lattice technology carries out Fast Labeling to part by beta pruning region；
The overall situation summarizes：Beta pruning is directly carried out using the grid mark of local Skyline, and obtains final Skyline result sets,
It is the data set for meeting anomalous ecg monitoring and inquiry condition.
3. the smart cloud intelligent ECG monitoring based on Internet of Things and data processing system, feature exist as described in claim 1
In distributed KNN exceptions matching algorithm is as follows：
Assuming that the abnormal electrocardiogram data point set obtained after distributed multifactor Skyline filter algorithm filters is S, a number
It is R according to existing anomalous ecg data point set in library, if if finding most similar one group of data point set in R and S data,
As doubtful abnormal data, lookup method are as follows：
The file of the partition value comprising R and S is placed according to inverted index；
File is carried out distributed caching by host, while monitor workstation reads R from distributed cachingi∈ R and Si∈ S are each
The partition value of subregion, and generate key-value pair；
A pair of of R that global KNN is receivediAnd SiBetween all the points, gradually read, in VCmOne group of identical key-value pair to upper
IVkNN algorithms are executed, KNN inquiries are then carried out：Assuming that obtaining electrocardiogram (ECG) data point set S, medical expert after skyline is filtered
Existing anomalous ecg data point set R in library, it is if finding most similar one group of data point set in R and S data, i.e., doubtful different
Regular data is carrying out subregion based on inverted index to point set R and S, and assigning the task to monitor workstation according to subregion decomposes fortune
It calculates, then carries out summarizing joint account beyond the clouds and go out global kNN values, checking SiAll subregions after, global KNN will be exported
KNN (r, s), reads R from distributed cachingi∈ R and SiThe partition value of each subregion of ∈ S generates key-value pair, the object in R
And its possible k arest neighbors all enter local calculation as a result, to obtain KNN inquiry as a result, if KNN query results
It is not sky, shows the heartbeat data for having abnormal, system is then the data feedback to patient and doctor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252085.0A CN108492869A (en) | 2018-03-26 | 2018-03-26 | Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252085.0A CN108492869A (en) | 2018-03-26 | 2018-03-26 | Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108492869A true CN108492869A (en) | 2018-09-04 |
Family
ID=63337769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810252085.0A Pending CN108492869A (en) | 2018-03-26 | 2018-03-26 | Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492869A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108962395A (en) * | 2018-09-06 | 2018-12-07 | 南京龙渊微电子科技有限公司 | One kind is acquired in real time based on parallel score rank physiological signal and analysis method |
| CN111145895A (en) * | 2019-12-24 | 2020-05-12 | 中国科学院深圳先进技术研究院 | Abnormal data detection method and terminal equipment |
| CN113691634A (en) * | 2021-08-30 | 2021-11-23 | 杭州诺为医疗技术有限公司 | Automatic data transmission method and system for implantable medical equipment |
-
2018
- 2018-03-26 CN CN201810252085.0A patent/CN108492869A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| CHANGQING JI,FEI LIU,ZUMIN WANG,YUANTUAN LI,CHUNQIAO QI,ZEYU LI: "Mobile Cloud ECG Intelligent Monitoring and Data Processing System", 《2017 IEEE 19TH INTERNATIONAL CONFERENCE ON E-HEALTH NETWORKING,APPLICATION AND SERVICES(HEALTHCOM)》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108962395A (en) * | 2018-09-06 | 2018-12-07 | 南京龙渊微电子科技有限公司 | One kind is acquired in real time based on parallel score rank physiological signal and analysis method |
| CN108962395B (en) * | 2018-09-06 | 2022-06-07 | 南京龙渊微电子科技有限公司 | Parallel fractional order-based physiological signal real-time acquisition and analysis method |
| CN111145895A (en) * | 2019-12-24 | 2020-05-12 | 中国科学院深圳先进技术研究院 | Abnormal data detection method and terminal equipment |
| CN111145895B (en) * | 2019-12-24 | 2023-10-20 | 中国科学院深圳先进技术研究院 | Abnormal data detection method and terminal equipment |
| CN113691634A (en) * | 2021-08-30 | 2021-11-23 | 杭州诺为医疗技术有限公司 | Automatic data transmission method and system for implantable medical equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108417246A (en) | Use the monitoring method of Internet of Things smart cloud intelligent ECG monitoring and data processing system | |
| Curtis et al. | Physiological signal monitoring in the waiting areas of an emergency room | |
| CN108899084A (en) | A kind of wisdom endowment health monitoring system | |
| CN108492869A (en) | Smart cloud intelligent ECG monitoring based on Internet of Things and data processing system | |
| CN106983500A (en) | Mobile telemedicine monitor system based on Internet of Things | |
| CN201993766U (en) | Portable remote life multi-parameter monitoring terminal and constructed remote monitoring system | |
| CN102117384A (en) | Portable remote life multi-parameter monitoring terminal and constructed remote monitoring system | |
| CN100559382C (en) | Emergent medical rescuing wireless mobile information systems and method for interchanging data | |
| CN107247945A (en) | A kind of ward sufferer monitor system and monitoring method based on Kinect device | |
| CN108606781A (en) | A kind of epilepsy localization system based on the brain electricity higher-order of oscillation rhythm and pace of moving things | |
| CN110926655A (en) | Epidemic situation monitoring method and system based on wearable body temperature sensor | |
| CN108573747A (en) | A kind of wisdom Internet of Things big data cloud platform for health monitoring | |
| CN107092799A (en) | A kind of vital sign data management system and method based on cloud computing | |
| CN107887010A (en) | A kind of angiocardiopathy data acquisition examines platform with dividing | |
| CN107506573A (en) | It is easy to the Telemedicine System of long-term Continuous Observation guardianship | |
| Muneeswaran et al. | IoT based multiple vital health parameter detection and analyzer system | |
| CN204293143U (en) | The long-range multi-parameter monitoring system of a kind of medical Bidirectional intelligent based on cloud computing | |
| CN104933318A (en) | Individual-oriented mobile medical system based on cloud | |
| Paganelli et al. | Iot-based covid-19 health monitoring system: Context, early warning and self-adaptation | |
| CN104933319A (en) | Mobile medical system using mobile terminal and based on cloud | |
| Huang et al. | Development of a wearable biomedical health-care system | |
| CN107948310A (en) | Sign monitoring platform based on technology of Internet of things | |
| CN111789579A (en) | Healthy robot of thing networking | |
| CN113288089A (en) | Isolated person physical condition monitoring system design method based on NBIOT technology | |
| Walke et al. | On-line real time feature extraction of ECG signal: Recent advances & survey |
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: 20180904 |