CN106302487B - Agriculture internet of things data throat floater real-time detection processing method and processing device - Google Patents
Agriculture internet of things data throat floater real-time detection processing method and processing device Download PDFInfo
- Publication number
- CN106302487B CN106302487B CN201610702928.3A CN201610702928A CN106302487B CN 106302487 B CN106302487 B CN 106302487B CN 201610702928 A CN201610702928 A CN 201610702928A CN 106302487 B CN106302487 B CN 106302487B
- Authority
- CN
- China
- Prior art keywords
- data
- acquisition
- moment
- sliding window
- current time
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/12—Applying verification of the received information
- H04L63/123—Applying verification of the received information received data contents, e.g. message integrity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
A kind of agriculture internet of things data throat floater real-time detection processing method and processing device provided by the invention, in the method, the size for determining sliding window according to the time interval of the eigenperiod of acquisition data and acquisition first, further according to the measured value and forecast interval of the history acquisition data prediction current time sensor acquisition in sliding window；Then by the actual measured value of current time actual acquisition compared with forecast interval, if not falling in forecast interval, illustrate that the data of current time actual acquisition are abnormal data, to realize the detection to abnormal data.Furthermore, method provided by the invention is after determining current time data for abnormal data, abnormal data is substituted using obtained predicted value, so as to realize the processing to abnormal data, the accuracy of the data flow of acquisition is effectively improved, strong data are provided and are supported for the automatic control of equipment and the analysis of effective data.
Description
Technical field
The invention belongs to field of computer technology, in particular to a kind of agriculture internet of things data throat floater real-time detection processing
Method and device.
Background technique
Internet of Things is widely used in the agricultural productions such as livestock and poultry cultivation, facilities horticulture, aquaculture, becomes acquisition data
One of the important means of.In agriculture Internet of Things, awareness apparatus periodic measurement equipment state and environmental parameter, the time of acquisition
Sequence data has many characteristics, such as infinite property, dynamic, temporal correlation, and data processing system is transmitted in the form of data flow
System.But the environment of agriculture internet of things deployment is more severe, for example livestock and poultry cultivation place dust is more, aquaculture Internet of Things host
It is deployed in seawater or freshwater aquiculture pond, humid environment, the network equipment is easily damaged；Simultaneously as agricultural production is wide
Property, Internet of Things network coverage area is wide, equipment is dispersed, therefore needs to transmit number by wireless network in this environment
According to.
However since the performance of the sensor device in wireless network is not sufficiently stable, data transmission network event can occur for duration
Barrier, so that leading to a phenomenon for abnormal data happens occasionally, causes the quality of data to decline, not can guarantee the automatic control of equipment
It is analyzed with effective data.Therefore, how quickly and efficiently to internet of things data stream carry out anomaly data detection be one urgently
It solves the problems, such as.
In the prior art, generally for the method for the anomaly data detection of internet of things data stream to pay attention to according to data flow more
A certain feature handled emphatically.However such method can not combine internet of things data stream real-time and detection is accurate
The features such as property, so that the accuracy and integrality of the data flow received are not promoted effectively still.
Summary of the invention
It is an advantage of the invention to provide a kind of agriculture internet of things data throat floater real-time detection processing method and dresses
It sets, the defect for overcoming the data accuracy for using existing abnormal deviation data examination method to obtain, real-time inadequate.
In a first aspect, the present invention provides a kind of agriculture internet of things data throat floater real-time detection processing methods, comprising:
According to the eigenperiod and the adjacent time interval acquired twice for acquiring data in agriculture internet of things data stream, obtain
Take the size q of sliding window；Wherein, the size q of the sliding window, for limiting the acquisition for including in the sliding window
The number of historical data；
When collected data forward slip is to subsequent time in internet of things data stream, according in the sliding window
Historical data obtains the predicted value and forecast interval of the acquisition of current time sensor；
When the actual measured value that judgement knows that current time sensor acquires is not fallen in the forecast interval, then will work as
Preceding moment actual measured value is classified as abnormal data, and the data that the predicted value is acquired as current time sensor；
Update the sliding window；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNWhen the moment, according to described
The step of history acquisition data for including in sliding window, the predicted value and forecast interval of acquisition current time sensor acquisition
It include: according to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, is based on preset prediction mould
Type obtains tNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, the step of updating the sliding window includes: by the tNThe data of moment sensor acquisition are added to
In sliding window, the t in sliding window is deletedN-qThe acquisition data at moment.
Optionally, described adjacent to acquire according to the eigenperiod for acquiring data in agriculture internet of things data stream and twice
Time interval, the step of obtaining the size q of sliding window include:
According to the T and adjacent time interval Δ acquired twice eigenperiod for acquiring data in agriculture internet of things data stream
T obtains the size q of sliding window based on following formula:
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors
Acquire the time interval of data.
Optionally, described according to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, is based on
Preset prediction model obtains tNThe predicted value of moment sensor acquisition and the step of forecast interval include:
According to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear support
Vector regression model obtains tNThe predicted value and forecast interval of moment sensor acquisition.
Optionally, the method also includes:
When the actual measured value missing of current time acquisition is known in judgement, sensed the predicted value as current time
The acquisition data of device.
Optionally, the method also includes:
When judgement knows that the actual measured value of current time sensor falls into the forecast interval, by the actual measurement
It is worth the acquisition data as current time sensor.
Second aspect, the present invention provides a kind of agriculture internet of things data throat floater real-time detection processing units, comprising:
Sliding window acquiring size module, for acquiring eigenperiod and the phase of data according to agriculture internet of things data stream
The time interval that neighbour acquires twice, obtains the size q of sliding window；Wherein, the size q of the sliding window, for limiting
State the historical data number for including in sliding window；
Data prediction module is acquired, is used in one time interval of sliding window forward slip, according to the sliding
Historical data in window obtains the predicted value and forecast interval of the acquisition of current time sensor；
Data classification and processing module are acquired, for knowing that it is described pre- that the actual measured value of this moment sensor is not fallen within
When surveying in section, which is classified as abnormal data, and using the predicted value as current time sensor
Acquisition data；
Window update module, for updating the sliding window；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNMoment is constantly, described to adopt
Collect data prediction module, is further used for: according to the t for including in sliding windowN-qMoment is to tN-1Q history number of moment acquisition
According to based on preset prediction model, acquisition tNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, the window update module, is further used for: by the tNThe data of moment sensor acquisition are added to
In sliding window, the t in sliding window is deletedN-qThe acquisition data at moment.
Optionally, the sliding window acquiring size module, is further used for:
The eigenperiod of acquisition data and the adjacent time interval Δ t acquired twice, base in agriculture internet of things data stream
The size q of sliding window is obtained in following formula:
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors
Acquire the time interval of data.
Optionally, the acquisition data prediction module, is further used for:
According to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear support
Vector regression model obtains tNThe predicted value and forecast interval of moment sensor acquisition
Optionally, the acquisition data classification and processing module, are further used for:
When the actual measured value missing of current time acquisition is known in judgement, sensed the predicted value as current time
The acquisition data of device.
Optionally, the acquisition data classification and processing module, are further used for:
When judgement knows that the actual measured value of current time sensor falls into the forecast interval, by the actual measurement
It is worth the acquisition data as current time sensor.
In agricultural internet of things data throat floater real-time detection processing method provided in an embodiment of the present invention, first according to acquisition
Period and interval obtain sliding window size, further according in sliding window history acquisition data prediction current time acquisition
Predicted value and forecast interval；Then by the actual measured value of current time actual acquisition compared with forecast interval, if not falling
Enter in forecast interval, then illustrates that the data of current time actual acquisition are abnormal data, to realize the detection to abnormal data.
In addition, method provided by the invention is substituted different after determining current time data for abnormal data using obtained predicted value
Regular data effectively improves the accuracy of the data flow of acquisition so as to realize the processing to abnormal data, is the automatic of equipment
Control and the analysis of effective data provide strong data and support.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, embodiment will be described below
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Example for those of ordinary skill in the art without creative efforts, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is agriculture internet of things data throat floater real-time detection processing method embodiment flow chart provided by the invention；
Fig. 2 is agriculture internet of things data throat floater real-time detection processing device embodiment structural representation provided by the invention
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, ordinary skill people every other reality obtained without creative efforts
Example is applied, shall fall within the protection scope of the present invention.
In a first aspect, the embodiment of the invention provides a kind of agriculture internet of things data throat floater real-time detection processing method,
As shown in Figure 1, comprising:
S1, according in agriculture internet of things data stream acquire data eigenperiod and the adjacent time acquired twice between
Every obtaining the size q of sliding window；Wherein, the size q of the sliding window includes for limiting in the sliding window
The number of the historical data of acquisition；
S2, when collected data forward slip is to subsequent time in internet of things data stream, according to the sliding window
Interior historical data obtains the predicted value and forecast interval of the acquisition of current time sensor；
S3, judgement know current time sensor acquisition actual measured value do not fall in the forecast interval when, then
Current time actual measured value is classified as abnormal data, and the number that the predicted value is acquired as current time sensor
According to；
S4, sliding window is updated；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNWhen the moment:
Step S2 may include: according to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition,
Based on preset prediction model, t is obtainedNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, step S4 may include: by the tNThe data of moment sensor acquisition are added in sliding window, are deleted
Except the t in sliding windowN-qThe acquisition data at moment.
In agricultural internet of things data throat floater real-time detection processing method provided in an embodiment of the present invention, first according to acquisition
Period and interval obtain sliding window size, further according in sliding window history acquisition data prediction current time acquisition
Predicted value and forecast interval；Then by the actual measured value of current time actual acquisition compared with forecast interval, if not falling
Enter in forecast interval, then illustrates that the data of current time actual acquisition are abnormal data, to realize the detection to abnormal data.
In addition, method provided by the invention is substituted different after determining current time data for abnormal data using obtained predicted value
Regular data effectively improves the accuracy of the data flow of acquisition so as to realize the processing to abnormal data, is the automatic of equipment
Control and the analysis of effective data provide strong data and support.
In the specific implementation, it is to be understood that the method in step S1 can be accomplished in several ways, below to step
A kind of optional embodiment of rapid S1 is illustrated.
The size q of sliding window is determined first.Here the size q of sliding window includes for limiting in sliding window
History acquisition data number.Have the characteristics that timing, periodic, cunning due to acquiring data flow in agriculture Internet of Things
The size of dynamic window q depends on eigenperiod and the adjacent time acquired twice that data are acquired in agriculture internet of things data stream
Interval, can specifically be acquired by formula (1):
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors
The time interval of data is acquired, t is the current acquisition moment.
After obtaining the size of sliding window by step S1, a kind of optional embodiment of step S2 be can wrap
It includes: when data collected in internet of things data stream are by tN-1Moment forward slip is to tNWhen the moment, include according in sliding window
TN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear support vector regression model, obtains tNMoment sensing
The predicted value and forecast interval of device acquisition.
Specifically, the case where being acquired using internet of things sensors n-th of the support vector regression model to t moment is carried out
Calculating is estimated, the predicted value of n-th acquisition can be calculated by formula (2):
Wherein,Indicate the predicted value of t moment；M(Dt) indicate non-linear support vector regression model；R indicates experience wind
Danger, is described with the insensitive function of loss function-e.
It for non-linear support vector regression algorithm, needs to introduce kernel function, the data of luv space is mapping through φ
It is mapped in higher dimensional space, shown in mapping relations such as formula (3):
Ф: x → φ (x) (3)
Approximately linear recurrence is done in high-dimensional feature space, shown in training set such as formula (4):
Θ={ (φ (x1),y1), (φ (x2),y2) ... (φ (xq),yq)} (4)
Regression problem can be described as: according to given training set Θ, find RnOn certain real-valued function y=f (x), with
This infers y value corresponding to either mode φ (x).Specific function may be expressed as:
F (x)=wT·φ(x)+b (5)
Wherein, w is normal vector；B is intercept.
The largest interval model classified using approximately linear, obtains following objective functions:
S.t., yi(wTφ(xi)+b) >=1, i=1 ..., n (6)
Convex quadratic programming problem is converted by the objective function, i.e., target is optimal under certain condition, loss reduction.To convex
Quadratic programming problem transforms to the optimization problem of dual variable using Lagrange duality, is obtained by solving its dual problem
The optimal solution of primal problem, Lagrangian are as follows:
In the case where requiring constraint condition to obtain satisfaction, objective function is as follows:
Here p is used*It indicates the optimal value of this problem, and is of equal value with initial problem.To be converted into the antithesis
The solution namely p of problem*For the predicted value of t moment acquisition.
It acquires predicted value and then is utilizing model residual error, calculating using predicted value as sample average, confidence level p
Forecast interval PI.
Specifically, it is assumed that in the probability that the actual measured value of t moment acquisition falls into forecast interval PI be that (p can be p
95% or 99%), and model residual error meets the Gaussian Profile that mean value is zero, therefore, forecast interval PI bound can be such as formula (9)
It is shown:
Wherein,Indicate the predicted value of t moment, tα/2,n-1The percentile freedom degree for indicating p is n-1
Meet student's-t distribution probability distribution function, s is the standard deviation of n sample, thus according to formula (9) acquisition forecast interval
PI。
After step S2 obtains predicted value and forecast interval, step S3 can be according to forecast interval to current time
The actual measured value of acquisition is detected, and judges whether it is abnormal data.
Specifically, when the actual measured value that judgement knows that t moment acquires is not fallen in forecast interval PI, then it is assumed that t
The actual measured value of moment acquisition is abnormal data, which is replaced with to the t moment obtained by step S2 at this time
The data that the predicted value of sensor acquisition is acquired as current time sensor.
In the detection to actual measured value, other than the case where above-mentioned abnormal data is detected, it is also possible to go out
Existing two kinds of situations:
When the actual measured value missing of t moment acquisition is known in judgement, then it is assumed that current time acquisition failure, at this time by t
The acquisition data that the predicted value of moment sensor acquisition is acquired as n-th.
When the actual measured value that judgement knows that t moment acquires falls into the forecast interval, then it is assumed that current time adopts
The data of collection do not detect exception, therefore the acquisition data that the actual measured value is acquired as t moment.
Understandable to be, three kinds of situations described above cover the actual measured value detection of current time acquisition substantially
Several situations that may occur, can carry out abnormality detection the data of actual acquisition each time according to the above method, detect
When to exception or when detecting acquisition failure, using predicted value as current time acquisition data, adopted so as to effectively improve
The accuracy and integrality of the data flow of collection provide strong data branch for the automatic control of equipment and the analysis of effective data
It holds.
After the judgement by step S3, step S4 also needs to be updated sliding window.
Specifically, the data flow that sensor acquires in agriculture Internet of Things is exactly according to the unlimited of certain time order composition
Set, can use ..., xt-1,xt,xt+1... } and it indicates；Sliding window refers to the window for choosing fixed data quantity as data processing,
Use Dt{xt-q,xt-q+1,…xt-1Indicate；After carrying out anomaly classification to current time actual measured value, window forward slip increases
xt, delete xt-q；Sliding window size is kept to fix, terminal is the current last moment for acquiring the corresponding moment forever, consequently facilitating
Acquisition judgement next time.
Second aspect, the embodiment of the present invention also provide a kind of agriculture internet of things data stream abnormal real-time detection processing dress in real time
It sets, as shown in Figure 2, comprising:
Sliding window acquiring size module, for acquiring eigenperiod and the phase of data according to agriculture internet of things data stream
The time interval that neighbour acquires twice, obtains the size q of sliding window；Wherein, the size q of the sliding window, for limiting
State the historical data number for including in sliding window；
Data prediction module is acquired, is used in one time interval of sliding window forward slip, according to the sliding
Historical data in window obtains the predicted value and forecast interval of the acquisition of current time sensor；
Data classification and processing module are acquired, for knowing that it is described pre- that the actual measured value of this moment sensor is not fallen within
When surveying in section, which is classified as abnormal data, and using the predicted value as current time sensor
Acquisition data；
Window update module, for updating the sliding window；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNMoment is constantly, described to adopt
Collect data prediction module, is further used for: according to the t for including in sliding windowN-qMoment is to tN-1Q history number of moment acquisition
According to based on preset prediction model, acquisition tNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, the window update module, is further used for: by the tNThe data of moment sensor acquisition are added to
In sliding window, the t in sliding window is deletedN-qThe acquisition data at moment.
In the specific implementation, the sliding window acquiring size module, is further used for:
The eigenperiod of acquisition data and the adjacent time interval Δ t acquired twice, base in agriculture internet of things data stream
The size q of sliding window is obtained in following formula:
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors
Acquire the time interval of data.
In the specific implementation, the acquisition data prediction module, is further used for:
According to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear support
Vector regression model obtains tNThe predicted value and forecast interval of moment sensor acquisition
In the specific implementation, the acquisition data classification and processing module, are further used for:
When the actual measured value missing of current time acquisition is known in judgement, sensed the predicted value as current time
The acquisition data of device.
In the specific implementation, the acquisition data classification and processing module, are further used for:
When judgement knows that the actual measured value of current time sensor falls into the forecast interval, by the actual measurement
It is worth the acquisition data as current time sensor.
Since the agriculture internet of things data throat floater real-time detection processing unit that the present embodiment is introduced is that can execute sheet
The device of agriculture internet of things data throat floater real-time detection processing method in inventive embodiments, so it is based on the embodiment of the present invention
Described in the detection of agriculture internet of things data throat floater method, those skilled in the art can understand the present embodiment
The specific embodiment and its various change form of agriculture internet of things data throat floater real-time detection processing unit, so herein
How agriculture Internet of Things in the embodiment of the present invention is realized for the agricultural internet of things data throat floater real-time detection processing unit
Data flow anomaly real-time detection processing method is no longer discussed in detail.As long as those skilled in the art implement the embodiment of the present invention
Device used by middle agricultural internet of things data throat floater real-time detection processing method, belongs to the model to be protected of the application
It encloses.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments
Including certain features rather than other feature, but the combination of the feature of different embodiment means in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment claimed it is any it
One can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize gateway according to an embodiment of the present invention, proxy server, in system
Some or all components some or all functions.The present invention is also implemented as executing side as described herein
Some or all device or device programs (for example, computer program and computer program product) of method.It is such
It realizes that program of the invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from an internet website to obtain, and perhaps be provided on the carrier signal or with any other shape
Formula provides.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (8)
1. a kind of agricultural internet of things data throat floater real-time detection processing method characterized by comprising
According to the eigenperiod and the adjacent time interval acquired twice for acquiring data in agriculture internet of things data stream, obtains and slide
The size q of dynamic window；Wherein, the size q of the sliding window, for limiting the history for the acquisition for including in the sliding window
The number of data；
When collected data forward slip is to subsequent time in internet of things data stream, according to the history in the sliding window
Data obtain the predicted value and forecast interval of the acquisition of current time sensor；
When judgement knows that the actual measured value of current time sensor acquisition is not fallen in the forecast interval, then when will be current
It carves actual measured value and is classified as abnormal data, and the data that the predicted value is acquired as current time sensor；
Update the sliding window；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNWhen the moment, according to the sliding
The step of history acquisition data for including in window, the predicted value and forecast interval of acquisition current time sensor acquisition, wraps
It includes: according to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, is based on preset prediction model,
Obtain tNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, the step of updating the sliding window includes: by the tNThe data of moment sensor acquisition are added to sliding window
In mouthful, the t in sliding window is deletedN-qThe acquisition data at moment；
It is described according in agriculture internet of things data stream acquire data eigenperiod and the adjacent time interval acquired twice, obtain
The step of taking the size q of sliding window include:
According to the eigenperiod T and the adjacent time interval Δ t acquired twice for acquiring data in agriculture internet of things data stream, base
The size q of sliding window is obtained in following formula:
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors acquisition
The time interval of data；
Wherein, the forecast interval PI is obtained by following formula:
Wherein, Indicate the predicted value of t moment, tα/2,n-1The percentile freedom degree for indicating p is the symbol of n-1
The probability-distribution function of conjunction-t distribution, s are the standard deviation of n sample, and p is described in the actual measured value of t moment acquisition is fallen into
The probability of forecast interval.
2. the method according to claim 1, wherein described according to the t for including in sliding windowN-qMoment is to tN-1
Q historical data of moment acquisition, is based on preset prediction model, obtains tNThe predicted value and prediction of moment sensor acquisition
The step of section includes:
According to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear supporting vector
Regression model obtains tNThe predicted value and forecast interval of moment sensor acquisition.
3. the method according to claim 1, wherein the method also includes:
When the actual measured value missing of current time acquisition is known in judgement, using the predicted value as current time sensor
Acquire data.
4. the method according to claim 1, wherein the method also includes:
When judgement knows that the actual measured value of current time sensor falls into the forecast interval, the actual measured value is made
For the acquisition data of this moment sensor.
5. a kind of agricultural internet of things data throat floater real-time detection processing unit characterized by comprising
Sliding window acquiring size module, for acquiring the eigenperiod and adjacent two of data according to agriculture internet of things data stream
The time interval of secondary acquisition obtains the size q of sliding window；Wherein, the size q of the sliding window, for limiting the cunning
The historical data number for including in dynamic window；
Data prediction module is acquired, is used in one time interval of sliding window forward slip, according to the sliding window
Interior historical data obtains the predicted value and forecast interval of the acquisition of current time sensor；
Data classification and processing module are acquired, for knowing that the actual measured value of this moment sensor do not fall within the Target area
When interior, which is classified as abnormal data, and adopting using the predicted value as current time sensor
Collect data；
Window update module, for updating the sliding window；
Wherein, when data collected in internet of things data stream are by tN-1Moment forward slip is to tNMoment constantly, the acquisition number
It is predicted that module, is further used for: according to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition,
Based on preset prediction model, t is obtainedNThe predicted value and forecast interval of moment sensor acquisition；
Correspondingly, the window update module, is further used for: by the tNThe data of moment sensor acquisition are added to sliding
In window, the t in sliding window is deletedN-qThe acquisition data at moment；
The sliding window acquiring size module, is further used for:
The eigenperiod of acquisition data and the adjacent time interval Δ t acquired twice, are based on down in agriculture internet of things data stream
The size q of formula acquisition sliding window:
Wherein, T indicates the eigenperiod for acquiring data in agriculture Internet of Things in data flow, and Δ t indicates internet of things sensors acquisition
The time interval of data；
It acquires data prediction module and obtains the forecast interval PI especially by following formula:
Wherein, Indicate the predicted value of t moment, tα/2,n-1The percentile freedom degree for indicating p is the symbol of n-1
The probability-distribution function of conjunction-t distribution, s are the standard deviation of n sample, and p is described in the actual measured value of t moment acquisition is fallen into
The probability of forecast interval.
6. device according to claim 5, which is characterized in that the acquisition data prediction module is further used for:
According to the t for including in sliding windowN-qMoment is to tN-1Q historical data of moment acquisition, constructs non-linear supporting vector
Regression model obtains tNThe predicted value and forecast interval of moment sensor acquisition.
7. device according to claim 5, which is characterized in that the acquisition data classification and processing module are further used
In:
When the actual measured value missing of current time acquisition is known in judgement, using the predicted value as current time sensor
Acquire data.
8. device according to claim 6, which is characterized in that the acquisition data classification and processing module are further used
In:
When judgement knows that the actual measured value of current time sensor falls into the forecast interval, the actual measured value is made
For the acquisition data of current time sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610702928.3A CN106302487B (en) | 2016-08-22 | 2016-08-22 | Agriculture internet of things data throat floater real-time detection processing method and processing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610702928.3A CN106302487B (en) | 2016-08-22 | 2016-08-22 | Agriculture internet of things data throat floater real-time detection processing method and processing device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106302487A CN106302487A (en) | 2017-01-04 |
| CN106302487B true CN106302487B (en) | 2019-08-09 |
Family
ID=57662165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610702928.3A Active CN106302487B (en) | 2016-08-22 | 2016-08-22 | Agriculture internet of things data throat floater real-time detection processing method and processing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106302487B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346301B (en) * | 2016-12-02 | 2020-09-04 | 西交利物浦大学 | Water quality monitoring noise data real-time detection method based on double-time-window verification |
| CN108304315A (en) * | 2017-12-14 | 2018-07-20 | 国家计算机网络与信息安全管理中心 | A kind of sorting technique and system of software aging abnormal behaviour |
| US10841020B2 (en) * | 2018-01-31 | 2020-11-17 | Sap Se | Online self-correction on multiple data streams in sensor networks |
| CN110311879B (en) * | 2018-03-20 | 2022-02-22 | 重庆邮电大学 | Data flow abnormity identification method based on random projection angle distribution |
| CN109617765A (en) * | 2019-01-02 | 2019-04-12 | 中国联合网络通信集团有限公司 | A kind of prediction technique and device of Internet of Things quality of connection |
| CN109890002B (en) * | 2019-01-04 | 2022-08-16 | 中国电子科技集团公司电子科学研究院 | Method and device for predicting environmental risk based on knowledge reasoning |
| JP6700509B1 (en) * | 2019-04-02 | 2020-05-27 | 澪標アナリティクス株式会社 | Estimating apparatus, estimating method, and program |
| CN110839032A (en) * | 2019-11-18 | 2020-02-25 | 河南牧业经济学院 | Internet of things abnormal data identification method and system |
| CN110971488A (en) * | 2019-11-27 | 2020-04-07 | 软通动力信息技术有限公司 | Data processing method, device, server and storage medium |
| CN111414586A (en) * | 2020-03-31 | 2020-07-14 | 北京派得伟业科技发展有限公司 | Environment monitoring method and system |
| CN111599174B (en) * | 2020-05-13 | 2021-11-16 | 北京百度网讯科技有限公司 | Traffic index abnormity detection method and electronic equipment |
| CN115388931B (en) * | 2022-10-27 | 2023-02-03 | 河北省科学院应用数学研究所 | Credible monitoring method, monitoring terminal and storage medium for sensor abnormal data |
| CN115859209B (en) * | 2023-02-08 | 2023-05-16 | 烟台市福山区动物疫病预防控制中心 | Livestock industry poultry breeding abnormality identification method based on feed consumption data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102014031A (en) * | 2010-12-31 | 2011-04-13 | 湖南神州祥网科技有限公司 | Method and system for network flow anomaly detection |
| CN103336906A (en) * | 2013-07-15 | 2013-10-02 | 哈尔滨工业大学 | Sampling GPR method of continuous anomaly detection in collecting data flow of environment sensor |
| CN103974311A (en) * | 2014-05-21 | 2014-08-06 | 哈尔滨工业大学 | Condition monitoring data stream anomaly detection method based on improved gaussian process regression model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9320445B2 (en) * | 2011-05-17 | 2016-04-26 | Siemens Medical Solutions Usa, Inc. | System for cardiac condition detection responsive to blood pressure analysis |
-
2016
- 2016-08-22 CN CN201610702928.3A patent/CN106302487B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102014031A (en) * | 2010-12-31 | 2011-04-13 | 湖南神州祥网科技有限公司 | Method and system for network flow anomaly detection |
| CN103336906A (en) * | 2013-07-15 | 2013-10-02 | 哈尔滨工业大学 | Sampling GPR method of continuous anomaly detection in collecting data flow of environment sensor |
| CN103974311A (en) * | 2014-05-21 | 2014-08-06 | 哈尔滨工业大学 | Condition monitoring data stream anomaly detection method based on improved gaussian process regression model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106302487A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106302487B (en) | Agriculture internet of things data throat floater real-time detection processing method and processing device | |
| Palm et al. | Mapping migratory flyways in Asia using dynamic Brownian bridge movement models | |
| US9390331B2 (en) | System and method for assessing riparian habitats | |
| Wittemyer et al. | Disentangling the effects of forage, social rank, and risk on movement autocorrelation of elephants using Fourier and wavelet analyses | |
| CN111512178A (en) | Machine learning motion detection based on wireless signal attributes | |
| EP4005186B1 (en) | Provision of a mixed reality service | |
| US20210255116A1 (en) | Image Processing Techniques for Multi-Sensor Inspection of Pipe Interiors | |
| JP6260824B2 (en) | Cultivation support method, cultivation support apparatus, and computer program | |
| CN109843034B (en) | Yield prediction for grain fields | |
| EP2914099A1 (en) | A system and a method for real time detection of the position and behaviour of a plurality of animals | |
| JP2018143160A5 (en) | ||
| JP6184344B2 (en) | Observation value processing equipment | |
| JP6159594B2 (en) | Observation value processing apparatus, observation value processing method, and observation value processing program | |
| Villacrés et al. | Foliar moisture content from the spectral signature for wildfire risk assessments in Valparaíso-Chile | |
| Schreier et al. | Recurrent patterning in the daily foraging routes of hamadryas baboons (Papio hamadryas): spatial memory in large‐scale versus small‐scale space | |
| Fleishman et al. | Patterns of spatial autocorrelation of assemblages of birds, floristics, physiognomy, and primary productivity in the central Great Basin, USA | |
| Won et al. | Ecological drought condition index to monitor vegetation response to meteorological drought in Korean Peninsula | |
| US9654997B2 (en) | Method and system for evaluation of sensor observations | |
| Thomson et al. | Comparison of predictor sets for species richness and the number of rare species of butterflies and birds | |
| KR102233454B1 (en) | Method and system for forecasting tree disease based on water data | |
| JP2013092929A5 (en) | ||
| FR3026510B1 (en) | DEVICE AND METHOD FOR MONITORING THE OPERATION OF AN HVAC SYSTEM, ASSEMBLY COMPRISING AN HVAC SYSTEM AND SUCH A MONITORING DEVICE, AND ASSOCIATED COMPUTER PROGRAM PRODUCT | |
| KR101384133B1 (en) | Method for Identifying failure data in sensor network and sensor network system using the same | |
| KR101636410B1 (en) | Method, server, terminal, system, and recording medium for diagnosing thermal insulation property of building | |
| WO2021019457A2 (en) | Weight estimation of broilers using 3d computer vision and artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |