CN106714220A - WSN (Wireless Sensor Network) anomaly detection method based on MEA-BP neural network - Google Patents
WSN (Wireless Sensor Network) anomaly detection method based on MEA-BP neural network Download PDFInfo
- Publication number
- CN106714220A CN106714220A CN201710008709.XA CN201710008709A CN106714220A CN 106714220 A CN106714220 A CN 106714220A CN 201710008709 A CN201710008709 A CN 201710008709A CN 106714220 A CN106714220 A CN 106714220A
- Authority
- CN
- China
- Prior art keywords
- sensor node
- data
- node
- cluster
- mea
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a WSN (Wireless Sensor Network) anomaly detection method based on an MEA-BP neural network. The method comprises the following steps: initializing various distributed sensor nodes, and starting to acquire data by various sensor nodes; using a K-means algorithm to perform space clustering on the various sensor nodes to obtain a plurality of cluster structures; using a mind evolutionary algorithm to perform parameter optimization on a BP neural network, optimizing the weight and threshold of the BP neural network through a convergence and dissimilation operation, obtaining optimal weight and threshold, inputting the optimal weight and threshold, and establishing an MEA-BP neural network model; and adopting a distributed algorithm to execute anomaly detection on the sensor nodes in each group of clusters independently, after anomaly detection is finished, transferring a detection result to cluster head nodes of the group of clusters for further verification by the sensor nodes. The WSN anomaly detection method based on the MEA-BP neural network provided by the invention improves the algorithm performance of the BP neural network, accelerates the learning rate of the BP neural network, effectively improves the accuracy of the abnormal data detection and reduces the false positive rate.
Description
Technical field
The invention belongs to wireless sensor network (WSN) data reliability detection technique field, a kind of base is specifically related to
In MEA-BP neutral net WSN method for detecting abnormality.
Background technology
Used as a kind of wireless self-organization network, wireless sensor network has low energy consumption, section to wireless sensor network (WSN)
Put and distinguish flexibly, even without manual maintenance, the features such as being worked long hours in adverse circumstances.By by sensor network
Node is dispersed in Target monitoring area, and the monitoring for carrying out collection and the particular event of environmental data is presently the most universal
One of using.Due to wireless sensor node resource-constrained, and easily by the interference and destruction of extraneous factor, or external rings
The influence of border accident, the data that node is collected probably produce obvious deviation with environmental characteristic under normal circumstances,
This kind of data are referred to as abnormal data.Therefore, it is that wireless sensor network is different in recent years to design a kind of effective method for detecting abnormality
The emphasis of often detection research.
The no theoretical foundation of selection of traditional BP neural network many parameters when study is trained so that actual nerve net
Network application has a limitation, and Shortcomings part is main that pace of learning is slow, fault-tolerant ability is poor, can converge on local minimum
Deng.As a example by environmental monitoring wireless sensor network node, the temperature data that wireless sensor network node is collected without
By the amplitude, the frequency that are fluctuation, or the statistical nature such as average, intermediate value, variance all can be with other in section of same sampling time
Data have obvious difference, discounting for the otherness between different types of data, can undoubtedly influence the performance of detection algorithm,
Want more accurately to judge data exception, except the temporal correlation of data itself is also contemplated that spatial coherence.In addition, being directed to
The abnormality detection problem of wireless sensor network environment data, BP neural network algorithm presence is easily trapped into locally optimal solution, instruction
Practice that the time is long, the low problem of efficiency.
The content of the invention
Goal of the invention:In order to overcome the deficiencies in the prior art, the present invention to provide a kind of based on MEA-BP nerve nets
Network WSN method for detecting abnormality, exists for BP neural network algorithm and is easily trapped into that locally optimal solution, training time be long, efficiency is low
The problems such as, BP neural network is improved using mind evolutionary, BP neural network algorithm performance is improve, accelerate BP
The learning rate of neutral net, effectively increases the accuracy rate of anomaly data detection, reduces rate of false alarm.
Technical scheme:To achieve the above object, it is of the invention based on MEA-BP neutral net WSN method for detecting abnormality, institute
The method of stating is comprised the following steps:
Each distribution sensor node initializing, each sensor node are started gathered data by S1;
If sensor node number is n, each sensor node is Xtj(j=1,2 ..., n), sensor node XtjSlip
Window is Wj, the sliding window size of each sensor node is m, then sensor node XtjIn its sliding window WjOn measurement
Data sequence isSensor node XtjIn tpMoment collection data beThe data include h
Property measurement value, then
S2 carries out space division to each sensor node and obtains some component clusters using K-means algorithms;
If q+1 sensor node constitutes a component cluster, 1 leader cluster node Xt is included per component clustercWith q distribution section
Point (Xt1,Xt2,…,Xtq);
S3 carries out parameter optimization using mind evolutionary to BP neural network, by convergent operation dissimilation to BP nerve nets
The weights and threshold value of network are optimized, and obtain best initial weights and threshold value, are input into best initial weights and threshold value, set up MEA-BP nerve nets
Network model;
S4 uses distributed algorithm, to sensor node (Xt in every component cluster1,Xt2,…,Xtq) independently execute exception
Detection, abnormality detection finishes rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the cluster head section of the component cluster
Point XtcFurther checking.
Further, the step S2 is comprised the following steps:
S21 any K sensor node object of selection first from the distribution sensor node object of Target monitoring area is made
It is K cluster centre;
S22 calculates sensor node object with K respectively then for the sensor node object in addition to cluster centre
Similarity between cluster centre, obtains and the sensor node immediate cluster centre of object similarity;
S23 distributes to sensor node object poly- with the sensor node immediate cluster centre of object similarity
Class, will obtain K cluster after the completion of all the sensors node distribution;
S24 recalculates this K cluster centre of cluster, obtains new cluster centre;
S25 recalculates the similarity of each sensor node and new cluster centre, returns to step S22;
S26 terminates this operation when the cluster centre for recalculating is restrained.
Further, the step S3 is comprised the following steps:Produce training data;Determine BP neural network topological structure;
Parameter setting is carried out by mind evolutionary;Randomly generate initial population, winning sub- population and interim sub- population;To sub- population
Carry out operation similartaxis;Operation dissimilation is carried out to sub- population;Judge whether to meet termination condition, if it is satisfied, then optimal of output
Body, obtains best initial weights and threshold value, otherwise re-starts convergent operation dissimilation.
Further, the step S4 is comprised the following steps:
S41 is by temporal correlation to sensor node (Xt1,Xt2,…,Xtq) abnormality detection is independently executed, using each
Current time passes through sensor node XtjSliding window WjDataTo train neutral net, complete
The forecast of subsequent time data, chooses training dataRear v sample data, by formula (1) count
Calculate the model residual error S of MEA-BP neutral nets:
Wherein, Er(r=1,2 ..., v) be choose sampled data values, F be choose sample data averages,
S42 calculates the confidential interval at sensor node current time, and confidential interval is Wherein SprePrediction for MEA-BP neutral nets to subsequent time data
Value, tα/2,v-1For the t of free degree v-1 is distributed, suitable α values are chosen in t distribution tables, obtain t values;
S43 works as subsequent time data SnewWhen in into sensor node sliding window, subsequent time data S is judgednewIt is
In the no fiducial interval range for falling into current time, if so, then judging data SnewIt is normal data;Otherwise judge the data
SnewIt is abnormal data;
S44 abnormality detections finish rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the component cluster
Leader cluster node XtcIn;
S45 leader cluster nodes XtcVoting mechanism verificating sensor node abnormal data is detected and introduced by spatial coherence
Producing cause, reason includes that event anomalies, node failure are abnormal and judge by accident.
Further, in the step S42, α=0.05 is chosen.
Further, spatial coherence is carried out in the step S45 detect and introduce voting mechanism to comprise the following steps:
S451 is by the abnormal data of sensor node and other node datas with the sensor node in same sub-clustering
It is compared;If q+1 sensor node constitutes a component cluster, 1 leader cluster node Xt is included per component clustercWith q distribution
Node (Xt1,Xt2,…,Xtq);
S452 presets error amount θ, if the abnormal data of sensor node is STIf, with the sensor node same
The data of other nodes in sub-clustering are Si(i=1,2 ..., q-1), if | ST-Si|<θ, then initial value is that 0 counting NN plus 1,
The final NN values of statistics;
If S453Then judge that the detection node abnormal data is due to event anomalies;IfThen judging should
Detection node abnormal data is due to node failure or erroneous judgement;IfThe reference node in the sub-clustering is then chosen, if reference
The data of node are SCCIf, | ST-SCC|≤θ, then judge the sensor node abnormal data be due to event anomalies, if | ST-SCC
|>θ, then judge that the sensor node abnormal data is due to node failure or erroneous judgement;It is in the sub-clustering wherein with reference to node
The nearest node of cluster centre node Euclidean distance;
During S454 is for the step S453, when judge to obtain the sensor node abnormal data be due to node failure or
During erroneous judgement, determine whether that the sensor node abnormal data is, due to node failure or erroneous judgement, to specifically include following steps:
Temporal correlation detection is carried out by sensor node, when abnormal data is produced in sensor node continuous time, is then sentenced
The disconnected sensor node abnormal data is due to node failure;When sensor node only has the moment for abnormal data, other when
Carve and produce data to be normal data, then judge that the sensor node abnormal data is due to erroneous judgement.
Beneficial effect:The present invention compared with the prior art, this have the advantage that:
Traditional BP neural network algorithm has being easily trapped into that locally optimal solution, training time be long, efficiency is low, it is difficult to
Meet detection demand, utilization mind evolutionary proposed by the present invention is improved to improve BP neural network to BP neural network
Algorithm performance, when multidimensional data is processed using between the event correlation between sensor network circuit-switched data stream and different nodes
Spatial coherence, so as to effectively increase the accuracy rate of anomaly data detection;
Compared with conventional BP neural network, context of methods by optimizing weights and threshold value after accelerate BP neural network
Learning rate, improve abnormality detection rate, reduce False Rate.
Brief description of the drawings
Fig. 1 is t distribution table schematic diagrames.
Fig. 2 is k-means clustering algorithm flow charts.
Fig. 3 is MEA Optimized BP Neural Network weight threshold flow charts.
Fig. 4 is MEA-BP neutral net anomaly data detection flow charts.
Specific embodiment
The present invention is further described below in conjunction with the accompanying drawings.
The present invention propose it is a kind of based on MEA-BP neutral net WSN method for detecting abnormality, introduce the inventive method it
Before, some definition are introduced first:
1st, sensor network model, in distributed sensor networks, if sensor node number is n, each sensor section
Point is Xtj(j=1,2 ..., n).
2nd, time series data, is a series of sequence datas produced in chronological order by sensor node, its feature
It is fast, a large amount of and continuous arrival of change.So before detection model is set up, first having to introduce sliding window mechanism, utilize
Sliding window observes the situation of change of data in a nearest time period, and rejecting outliers are carried out inside sliding window.
3rd, sliding window model, sliding window model is for observing the time series number in nearest sampling time section
According to method is the sliding window that a regular length is taken to sensing data, by the new data reduction for adding and just leaving for the treatment of
Time complexity;In distributed sensor networks, if sensor node number is n, each sensor node is Xtj(j=1,
2 ..., n), sensor node XtjSliding window be Wj, the sliding window size of each sensor node is m, then sensor section
Point XtjIn its sliding window WjOn measurement data sequence beSensor node XtjIn tpMoment adopts
The data of collection areThe data include h property measurement value, then
4th, the ratio between verification and measurement ratio refers to the abnormal data sample number that detects of algorithm with the abnormal data total sample number of reality.
5th, rate of false alarm, refer to by algorithm be mistaken for abnormal normal data sample number and total normal data sample number it
Than.
The present invention is divided space nodes based on the temporal correlation of sensor node using K-means algorithms
Cluster, the similar sensor node of data is divided into same cluster, then proposes to be examined extremely based on MEA-BP neutral nets WSN
Survey method, the method is broadly divided into parameter optimization, three steps of the detection of abnormal data and the judgement of data exception, its main spy
Point has:(1) parameter optimization is carried out to BP neural network using mind evolutionary, is operated to BP nerve nets by convergent alienation etc.
Weights, threshold value of network etc. are optimized;(2) data flow mainly collected to sensor node in the detection-phase of abnormal data
In exceptional data point that may be present be identified, the step use distributed algorithm, independently executed in each sensor node,
Then result is delivered to leader cluster node and further verified by each sensor node;(3) propose that each is worked as during anomaly data detection
The preceding moment trains neutral net to complete the forecast of subsequent time by the history data set of sensor node sliding window, leads to
The model residual error of neutral net is crossed, it is determined that the confidential interval for judging subsequent time data exception, when subsequent time data fall
Enter in confidential interval, then data Ei is judged to normally, conversely, the data are further by spatial coherence in leader cluster node
Ground checking, specific the method is comprised the following steps:
By the initialization of each branch's sensor node, each sensor node starts gathered data, if sensor node number is
N, each sensor node is Xtj(j=1,2 ..., n), sensor node XtjSliding window be Wj, the cunning of each sensor node
Dynamic window size is m, then sensor node XtjIn its sliding window WjOn measurement data sequence beSensor node XtjIn tpMoment collection data beThe data include h property measurement value,
Then
Space sub-clustering is carried out to each sensor node using K-means algorithms and obtains some groups of clusters, by the similar biography of data
Sensor node is divided into same cluster, improves cluster interior nodes space similarity, and this is completed before being operated in node failure detection, complete
Cheng Houzai carries out temporal correlation detection and spatial coherence detection to node gathered data, is utilized when spatial coherence is detected
The result that leading space is divided, sensor node first carries out temporal correlation detection, works as the time to the data that current time gathers
When correlation detection shows problematic, then suspicious data is informed leader cluster node by the sensor node, and leader cluster node is to the data
Carry out spatial coherence detection;Reference picture 2, basic thought is:It is any first from sensor node object to select K object work
It is cluster centre, for remaining sensor node, then according to their similarity (Euclideans with the cluster centre for being selected out
Distance), sensor node of system distribution is given the cluster of its most like cluster centre respectively, each new cluster is then calculated again
Cluster centre (averages of all objects in the cluster), constantly repeat this process until cluster centre start convergence untill;
K-means algorithm steps are as follows:
If sensor node number is p, the coordinate of sensor node is { x(1),x(2),…,x(p), each x(i)(i=1,
2,…,p)∈R;
Step 1, randomly selects K sensor node as cluster centre, and the K coordinate of cluster centre is u(j)(j=1,
2 ..., k) ∈ R, K cluster of K cluster centre correspondence;
Step 2, repeats following process until cluster centre is restrained
{
For each sensor node sample i, its cluster that should belong to is calculated, formula is as follows:
c(i):=argminj||x(i)-u(j)||2Formula (2)
For each cluster j, the cluster centre of the cluster is recalculated, formula is as follows:
U in formula (2)(j)One in K cluster centre is represented, (j=1,2 ..., k), make by continuous adjusting parameter j
Obtain the overhead functions c of each point(i)Reach minimum value, c(i)Representative sensor node sample i is with distance in K cluster centre most
Each point, is divided into the cluster of cluster centre nearest apart from its by near cluster;
Denominator represents the sum of sample in each cluster in formula (3), and molecule is sensor node sample i in each cluster
Corresponding coordinate and.
Some groups of clusters are finally given, if q+1 sensor node constitutes a component cluster, 1 cluster head is included per component cluster
Nodes X tcWith q distribution node (Xt1,Xt2,…,Xtq);
Parameter optimization is carried out to BP neural network using mind evolutionary, by convergent operation dissimilation to BP neural network
Weights and threshold value optimize, obtain best initial weights and threshold value, be input into best initial weights and threshold value, set up MEA-BP neutral nets
Model, the flow of Optimized BP Neural Network is as shown in figure 3, substantially step is as follows:
Step 1:Mind-evolution initial population is produced, and N group numbers is randomly generated as initial population in solution space, in every group of number
An individual (i.e. neural network structure) is represented comprising n element, each individual matrix is 1*n, and group matrix is N*n,
Colony includes individuality;
Step 2:According to BP neural network topological structure, solution space is mapped to space encoder, each space encoder correspondence
One solution of problem, i.e. an individual, code length are equal to the element number in each individuality, and code length n is
N=tL+wL+L+w formula (4)
In formula (4), t is neutral net input number of nodes, and w is output node number, and L is node in hidden layer, is selected herein
Take t=19, L=20, w=1;
Step 3:The number of generation number iter, winning sub-group M and interim sub-group T is fallen in definition;Evolutionary process it is each
All groups of individuals in generation turn into a colony, and a colony is divided into M winning sub-group and T interim sub-group, often
Individual winning sub-group and interim sub-group contain SG individuality, and SG is:
SG=N/ (M+T) formula (5)
Generally choose iter=10, M=T=5, N=200, SG=20;
Step 4:The determination of scoring function, neutral net is made up of input layer, hidden layer, output layer, training sample
Input layer is AK=(a1 k,a2 k,…,at k), (K=1,2 ..., P, P are number of training), input matrix is t*p, expectation network
Output layer is YK=(Y1 k,Y2 k,…,Yw k), output matrix is w*p, each sample input one output of correspondence, one in sample
Have p inputoutput pair;Each node input of hidden layer is Z in the middle of networkK=(z1,z2,…,zL), middle each node of hidden layer
It is output as BK=(b1,b2,…,bL);Each node input of network is QK=(q1,q2,…,qw), each node of network output layer is output as
GK=(g1,g2,…,gw).Define input layer and hidden layer weights Wij(i=1,2 ..., t, j=1,2 ..., L), hidden layer with it is defeated
Go out a layer weights Vju(j=1,2 ..., L, u=1,2 ..., w), hidden layer threshold value be { θj(j=1,2 ..., L) }, output layer threshold value
{βu(u=1,2 ..., w) }, matrix is w*w.According to coding rule, WijFor it is single individuality in the 1st to (L*t) individual element,
Matrix is L*t;Vju(L*t+1) is individual to (L*t+w*L) individual element in single individuality, and matrix is w*L;θjFor in single individuality
(L*t+w*L+1) is individual to (L*t+w*L+L) individual element, and matrix is w*L;βu(L*t+w*L+1) is individual in single individuality
To last element.Each node input Z of calculating network hidden layerj, then with { ZjCalculate implicit by S types activation primitive
Each node output { b of layerj, S type function expression formulas are:
bj=f (Zj), j=1,2 ... L formula (7)
∑ Wa is referred to as the activation value of this model in formula (7), is the input summation of model;In formula (7) f () for model swash
Function living.
Then output { the b according to hidden layerj, weights VjuAnd threshold value { βuCalculate each node input Q of output layeru, Ran Houyong
{QuOutput { the G of each node of output layer is calculated by S type functionsu}:
Gu=f (Qu) (u=1,2 ..., w) formula (9)
Formula (8) (9) is ibid;
Select the scoring function as each individual and colony reciprocal of the mean square error of training sampleykThe desired output of k-th training sample is represented, matrix is w*p, GkActual output valve is represented,
I.e. by neural metwork training value out, matrix is also w*p, and p is training sample number;
Step 5:Training weights and threshold value, for each individuality to be uniformly distributed generation n group random numbers between (- 1,1),
Individual volume matrix is 1*n, as initial weight threshold colony, according to network calculations rule, is calculated per each and every one according to scoring function
Body score, the individuality of highest scoring is referred to as winner, and the q best individuality of score is chosen in punching as winner, chooses q=
10;
Step 6:Sub-group operation similartaxis, in sub-group, individuality as victor the process that competes be called it is convergent, one
Sub-group it is convergent during, if not producing new victor, as subgroup body maturation, convergent process terminates, respectively with every
Centered on one winner, Normal Distribution produces individuality, forms M winning sub-group and T interim sub-group, every height
Colony is individual comprising SG, and the normal distribution can be expressed as N (u, ∑), and u is the center vector of normal distribution in formula, and ∑ is this
The covariance matrix of normal distribution, the center of normal distribution is exactly the coordinate of victor, i.e. the weights and threshold value of victor;
Step 7:Sub-group operation dissimilation.Dissimilation is the mistake that each sub-group turns into victor and competes in whole solution space
Journey.By global advertisement plate, it have recorded each sub-group scoring function value and maturity, be carried out between each sub-group complete
Office's competition, if an interim sub-group score is higher than certain ripe winning sub-group score, interim sub-group replaces winning
Sub-group, the individuality in former winning sub-group is abandoned;If a score for the interim sub-group of maturation is excellent less than any one
Win the score of sub-group, then the interim sub-group is abandoned, and individuality therein is released.The number of the interim sub-group being abandoned
Tr is designated as, the number of the winning sub-group being abandoned is designated as Mr, under the guidance of global advertisement plate, is regenerated in solution space
Mr+Tr interim sub-group;
Step 8:Parsing optimum individual.Repeat above-mentioned 6,7 step, when iteration stopping condition is met, mind evolutionary
Terminate optimization process.Now, according to coding rule, the optimum individual to searching out is parsed, so as to obtain corresponding BP god
Through the best initial weights and threshold value of network, best initial weights and threshold value are input into, set up MEA-BP neural network models;
Reference picture 4, using distributed algorithm, to sensor node (Xt in every component cluster1,Xt2,…,Xtq) independently hold
Row abnormality detection, abnormality detection finishes rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the component cluster
Leader cluster node XtcFurther checking, comprises the following steps:
S41 is by temporal correlation to sensor node (Xt1,Xt2,…,Xtq) abnormality detection is independently executed, using each
Current time passes through sensor node XtjSliding window WjDataTo train neutral net, complete
The forecast of subsequent time data, chooses training dataRear v sample data, by formula (1) count
Calculate the model residual error S of MEA-BP neutral nets:
Wherein, Er(r=1,2 ..., v) be choose sampled data values, F be choose sample data averages,
S42 calculates the confidential interval at sensor node current time, and confidential interval is Wherein SprePrediction for MEA-BP neutral nets to subsequent time data
Value, tα/2,v-1For the t of free degree v-1 is distributed, suitable α values are chosen in t distribution tables, obtain t values;T distribution tables such as Fig. 1 institutes
Show, normal distribution also known as Gaussian Profile, if it is that μ, variance are the Gaussian Profile of σ 2 that stochastic variable obeys a mathematic expectaion, be designated as
N (μ, σ 2), our usually said standardized normal distributions are μ=0, the normal distribution of σ=1.From average value be μ, variance be σ 2
Standardized normal distribution totality in extract capacity for v sample, sample obey average value be μ, variance for σ 2/v normal distribution,
Population variance σ 2 is always unknown, so as to can only be replaced with s2.If v is very big, then, s2 is exactly one of σ 2 and preferably estimates
Metering, is still an approximate standardized normal distribution;If v is smaller, s2 and σ's 2 differs greatly, therefore, now sample divides
Cloth is no longer just a standardized normal distribution, but obeys t distributions, and t distributions are the curves become according to the free degree, in coordinate
Axle Y-axis both sides are symmetrical, and average is that 0, t distributions are applied to when population standard deviation is unknown, then uses sample standard deviation generation
For population standard deviation.The free degree in t distributions refers to the number that can freely change in any variable.Sample t-test now
Only estimate a parameter:Population mean, sample size v constitutes v kinds for estimating the information of population mean and its variability, disappears
Consume one degree of freedom to estimate average, remaining v-1 free degree is used to estimate variability, therefore, sample t-test uses the free degree
For the t of v-1 is distributed;When that need not estimate parameter, the free degree is v;Generally choose α=0.05.
S43 works as subsequent time data SnewWhen in into sensor node sliding window, subsequent time data S is judgednewIt is
In the no fiducial interval range for falling into current time, if so, then judging data SnewIt is normal data;Otherwise judge the data
SnewIt is abnormal data;
S44 abnormality detections finish rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the component cluster
Leader cluster node XtcIn;
S45 leader cluster nodes XtcVoting mechanism verificating sensor node abnormal data is detected and introduced by spatial coherence
Producing cause, reason includes that event anomalies, node failure are abnormal and judge by accident, specifically includes following steps:
S451 is by the abnormal data of sensor node and other node datas with the sensor node in same sub-clustering
It is compared;If q+1 sensor node constitutes a component cluster, 1 leader cluster node Xt is included per component clustercWith q distribution
Node (Xt1,Xt2,…,Xtq);
S452 presets error amount θ, if the abnormal data of sensor node is STIf, with the sensor node same
The data of other nodes in sub-clustering are Si(i=1,2 ..., q-1), if | ST-Si|<θ, then initial value is that 0 counting NN plus 1,
The final NN values of statistics;
If S453Then judge that the detection node abnormal data is due to event anomalies;IfThen judging should
Detection node abnormal data is due to node failure or erroneous judgement;IfThe reference node in the sub-clustering is then chosen, if reference
The data of node are SCCIf, | ST-SCC|≤θ, then judge the sensor node abnormal data be due to event anomalies, if | ST-SCC
|>θ, then judge that the sensor node abnormal data is due to node failure or erroneous judgement;It is in the sub-clustering wherein with reference to node
The nearest node of cluster centre node Euclidean distance;With reference to node:Space is carried out to each sensor node using K-means algorithms
Sub-clustering obtains some groups of clusters, and the similar sensor node of data is divided into same cluster, according to final sub-clustering result, choosing
It is with reference to node to take the node nearest apart from the cluster barycenter Euclidean distance;
During S454 is for the step S453, when judge to obtain the sensor node abnormal data be due to node failure or
During erroneous judgement, determine whether that the sensor node abnormal data is, due to node failure or erroneous judgement, to specifically include following steps:
Temporal correlation detection is carried out by sensor node, when abnormal data is produced in sensor node continuous time, is then sentenced
The disconnected sensor node abnormal data is due to node failure;When sensor node only has the moment for abnormal data, other when
Carve and produce data to be normal data, then judge that the sensor node abnormal data is due to erroneous judgement;
For the abnormal data in detection node, each node can be formed and belonged to the section with some cycles gathered data
The data flow of point, in order to ensure the correctness of the regional nodes gathered data sample, each node is all needed before data are uploaded
The exceptional value that utilize the value of neural network prediction to replace in sliding window.
Data sample from Intel's Berkeley laboratory sensor network data, the data sampling frequency be every
Sampling in 31 seconds is once.Choose sensor node 1-5 100 groups of temperature of node, humidity as training data, 20 groups of temperature, humidity
As prediction data.
S1 training=[20.6156,20.6254,20.6450,20.6352,20.6450,20.6156,20.6058,
20.576420.4882,20.4588,20.4392,20.4196,20.3804,20.3510,20.3020,20.2726,
20.2530,20.1942,20.184420.1354,20.0864,20.0668,20.0374,20.0178,19.9982,
19.9786,19.9688,19.8414,19.8022,19.8022,19.7826,19.8022,19.8218,19.8316,
19.8610,19.9002,19.9296,19.9786,19.9884,20.0080,20.0374,20.0472,20.1060,
20.1060,20.1256,20.1354,20.1550,20.2236,20.2432,20.2432,20.3020,20.3216,
20.3608,20.4588,20.4980,20.5176,20.5568,20.5666,20.5960,20.6254,21.4192,
21.4094,21.3996,21.3604,21.3212,21.3016,21.2624,21.2330,21.2232,21.2036,
21.1252,21.1252,21.1056,21.1056,21.0860,21.0860,21.0860,21.0762,21.0664,
21.0664,21.0468,21.0076,20.9880,20.9586,20.9684,20.9096,20.8998,20.8998,
20.8802,20.8704,20.8704,20.8704,20.8704,20.8802,20.8704,20.8802,20.8802,
20.8802,20.8704,20.8704]
[37.5737,37.6079,37.6422,37.6422,37.7107,37.7107,37.7792,37.8477,
38.0529,38.1213,38.189738.1897,38.3263,38.3946,38.4629,38.5311,38.5311,
38.7357,38.8039,38.8720,39.0082,39.0763,39.1443,39.1783,39.2123,39.2803,
39.3143,39.6200,39.755739.7896,39.755739.5521,39.5521,39.5521,39.4162,
39.4502,39.3143,39.2803,39.2123,39.178339.1443,39.110339.0082,39.0082,
38.9401,39.0082,38.9401,38.8379,38.8720,38.8039,38.7357,38.769838.7357,
38.6675,38.4970,38.3946,38.3946,38.3263,38.2580,38.2580,38.2239,
38.155537.9845,38.1897,38.1555,38.0529.37.9845,37.9161,37.8134,
37.813437.8819,37.8819,37.9161,37.9503,37.9503,37.9161,37.9503,37.9161,
37.8477,37.7792,37.7450,37.7450,37.7107,37.7107,37.7107,37.7107,37.6765,
37.6765,37.6422,37.8134,37.7792,37.7107,37.7107,37.6765,37.6765,37.7107,
37.7450,37.7792,37.9161,38.0529]
S1 predictions=[20.7724,20.7332,20.7528,20.7430,20.7332,20.7332,20.7234,
20.7136,20.7234,22.1530,20.7038,20.6940,20.6940,20.7038,20.6940,22.1530,
20.6744,20.6450,20.6352,20.6254][39.6200,39.9929,40.3652,40.9055,41.1414,
41.2761,41.3771,41.4780,41.7805,41.8812,41.9818,41.9483,42.2500,42.3840,
42.3170,52.3170,42.2500,42.2835,42.0824,41.9818]
S2 training=[20.6226,20.6224,20.6350,20.6352,20.6350,20.6256,20.6358,
20.5764,20.4782,20.4388,20.4492,20.4296,20.3604,20.3310,20.3320,20.2326,
20.2330,20.1042,20.1644,20.1354,20.0464,20.0468,20.0274,20.0178,19.9482,
19.9486,19.9588,19.8614,19.8322,19.8222,19.7926,19.8122,19.8518,19.8516,
19.8510,19.9502,19.9296,19.9386,19.9884,20.0080,20.0374,20.0472,20.1060,
20.1060,20.1236,20.1454,20.1350,20.2236,20.2332,20.2432,20.3020,20.3216,
20.3608,20.4588,20.4380,20.5376,20.5568,20.5666,20.5960,20.6354,20.6450,
20.7136,20.7038,20.6744,20.7528,20.8412,20.8506,20.8600,20.8796,20.8802,
20.8402,20.8704,20.8902,20.8704,20.8704,20.8704,20.8802,20.9096,20.9586,
20.9782,20.9380,21.0376,21.0076,21.0174,21.0076,21.0272,21.0468,21.0566,
20.9978,21.0370,21.0468,21.0366,21.0360,21.0368,21.0368,21.0634,21.0732,
21.0938,21.0360,21.1356]
[37.5337,37.6179,37.6222,37.6322,37.7207,37.7307,37.7492,37.8277,
38.0129,38.1113,38.149738.1597,38.3163,38.3546,38.4629,38.5311,38.5311,
38.7357,38.8039,38.8720,39.0082,39.0763,39.1443,39.1783,39.2123,39.2803,
39.3153,39.6200,39.7557,39.7896,39.7357,39.5521,39.5521,39.5521,39.4152,
39.4502,39.3143,39.2803,39.2123,39.1783,39.1443,39.1103,39.0032,39.0082,
38.9431,39.0042,38.8401,38.8479,38.8520,38.8039,38.7357,38.7698,38.7357,
38.6635,38.4970,38.3946,38.3946,38.3263,38.2380,38.2380,38.2339,38.1355,
37.9345,38.1897,38.1555,38.0529,37.9845,37.9161,37.8134,37.8134,37.8819,
37.8819,37.9161,37.9503,37.9503,37.9161,37.9503,37.9161,37.8477,37.7792,
37.7450,37.7450,37.7107,37.7107,37.7107,37.7107,37.6765,37.6765,37.6522,
37.8034,37.7592,37.6907,37.6807,37.6565,37.6865,37.7207,37.7550,37.7732,
37.9261,38.0629]
S2 predictions=(20.5670,20.5376,20.4788,20.4494,20.4984,20.4788,20.4592,
20.4494,20.4788,20.4690,20.4788,20.4592,20.4592,20.4494,20.4396,20.4396,
22.4396,20.4396,20.4396,20.3710)(39.4300,40.7863,40.4722,40.8955,41.3214,
41.4361,41.5671,41.6880,41.8205,41.9036,42.0142,42.0100,42.3200,42.4140,
42.3270,42.3370,52.3500,42.3825,42.1824,41.8918)
S3 training=[20.6156,20.6254,20.6450,20.6352,20.6450,20.6156,20.6058,
20.576420.4882,20.4588,20.4392,20.4196,20.3804,20.3510,20.3020,20.2726,
20.2530,20.1942,20.1844,20.1354,20.0864,20.0668,20.0374,20.0178,19.9982,
19.9786,19.9688,19.8414,19.8022,19.8022,19.7826,19.8022,19.8218,19.8316,
19.8610,19.9002,19.9296,19.9786,19.9884,20.0080,20.0374,20.0472,20.1060,
20.1060,20.1256,20.1354,20.1550,20.2236,20.2432,20.2432,20.3020,20.3216,
20.3608,20.4588,20.4980,20.5176,20.5568,20.5666,20.5960,20.6254,20.6450,
20.7136,20.7038,20.6744,20.7528,20.8312,20.8606,20.8900,20.9096,20.8802,
20.8802,20.8704,20.8802,20.8704,20.8704,20.8704,20.8802,20.9096,20.9586,
20.9782,20.9880,21.0076,21.0076,21.0174,21.0076,21.0272,21.0468,21.0566,
20.9978,21.0370,21.0468,21.0566,21.0860,21.0468,21.0468,21.0664,21.0762,
21.0958,21.0860,21.1056]
[37.5737,37.6079,37.6422,37.6422,37.7107,37.7107,37.7792,37.8477,
38.0529,38.1213,38.189738.1897,38.3263,38.3946,38.4629,38.5311,38.5311,
38.7357,38.8039,38.8720,39.0082,39.0763,39.1443,39.1783,39.2123,39.2803,
39.3143,39.6200,39.7557,39.7896,39.7557,39.5521,39.5521,39.5521,39.4162,
39.4502,39.3143,39.2803,39.2123,39.1783,39.1443,39.1103,39.0082,39.0082,
38.9401,39.0082,38.9401,38.8379,38.8720,38.8039,38.7357,38.7698,38.7357,
38.6675,38.4970,38.3946,38.3946,38.3263,38.2580,38.2580,38.2239,38.1555,
37.9845,38.1897,38.1555,38.0529,37.9845,37.9161,37.8134,37.8134,37.8819,
37.8819,37.9161,37.9503,37.9503,37.9161,37.9503,37.9161,37.8477,37.7792,
37.7450,37.7450,37.7107,37.7107,37.7107,37.7107,37.6765,37.6765,37.6422,
37.8134,37.7792,37.7107,37.7107,37.6765,37.6765,37.7107,37.7450,37.7792,
37.9161,38.0529]
S3 predictions=(20.4396,20.4102,20.4102,20.4004,20.3710,20.3612,20.3612,
20.3612,20.3612,20.3514,20.3710,20.3808,20.3416,20.3220,20.3220,20.3318,
20.3318,22.3220,20.3514,20.3416)(39.4200,40.7963,40.4422,40.8755,41.3614,
41.4161,41.5871,41.6780,41.8405,41.9236,42.0242,42.0200,42.3300,42.4240,
42.3170,42.3270,42.3400,52.3525,42.1624,41.8718)
S4 training=[20.4154,20.4254,20.4450,20.4352,20.4450,20.4154,20.4057,
20.574420.4772,20.4577,20.4392,20.4194,20.3704,20.3510,20.3020,20.2724,
20.2530,20.1942,20.1744,20.1354,20.0744,20.0447,20.0374,20.0277,19.9972,
19.9774,19.9477,19.7414,19.7022,19.7022,19.7724,19.7022,19.7217,19.7314,
19.7410,19.9002,19.9294,19.9774,19.9774,20.0070,20.0374,20.0472,20.1040,
20.1040,20.1254,20.1354,20.1350,20.2234,20.2432,20.2432,20.3020,20.3214,
20.3407,20.4577,20.4970,20.5174,20.5547,20.5444,20.5940,20.4254,20.4450,
20.7134,20.7037,20.4744,20.7527,20.7312,20.7404,20.7900,20.9094,20.7702,
20.7702,20.7704,20.7702,20.7704,20.7704,20.7704,20.7702,20.9094,20.9574,
20.9772,20.9770,21.0074,21.0074,21.0174,21.0074,21.0272,21.0447,21.0544,
20.9977,21.0370,21.0447,21.0544,21.0740,21.0447,21.0447,21.0444,21.0742,
21.0957,21.0840,21.1054]
[37.5737,37.4079,37.4422,37.4422,37.7107,37.7107,37.7792,37.8477,
38.0529,38.1213,38.189738.1897,38.3243,38.3944,38.4429,38.5311,38.5311,
38.7357,38.8039,38.8720,39.0082,39.0743,39.1443,39.1783,39.2123,39.2803,
39.3143,39.4200,39.755739.7894,39.755739.5521,39.5521,39.5521,39.4142,
39.4502,39.3143,39.2803,39.2123,39.178339.1443,39.110339.0082,39.0082,
38.9401,39.0082,38.9401,38.8379,38.8720,38.8039,38.7357,38.749838.7357,
38.4475,38.4970,38.3944,38.3944,38.3243,38.2580,38.2580,38.2239,
38.155537.9845,38.1897,38.1555,38.0529.37.9845,37.9141,37.8134,
37.813437.8819,37.8819,37.9141,37.9503,37.9503,37.9141,37.9503,37.9141,
37.8477,37.7792,37.7450,37.7450,37.7107,37.7107,37.7107,37.7107,37.4745,
37.4745,37.4422,37.8134,37.7792,37.7107,37.7107,37.4745,37.4745,37.7107,
37.7450,37.7792,37.9141,38.0529]
S4 predictions=(20.4394,20.4102,20.4788,20.4494,20.4984,20.4788,20.3412,
20.3412,20.3412,20.3514,20.3710,20.3808,20.3414,20.2240,20.2240,20.2338,
20.2240,20.3318,22.3514,20.3414)(39.4500,40.7343,40.4222,40.8555,41.4214,
41.5341,41.4471,41.4980,41.8805,41.9334,42.0142,42.0120,42.3100,42.4240,
42.3070,42.3470,42.3800,42.3925,52.2024,41.9118)
S5 training=[20.4154,20.4254,20.4450,20.4352,20.4450,20.4154,20.4058,
20.574420.4882,20.4588,20.4392,20.4194,20.3804,20.3510,20.3020,20.2724,
20.2530,20.1942,20.184420.1354,20.0844,20.0448,20.0374,20.0178,19.9982,
19.9784,19.9488,19.8414,19.8022,19.8022,19.7824,19.8022,19.8218,19.8314,
19.8410,19.9002,19.9294,19.9784,19.9884,20.0080,20.0374,20.0472,20.1040,
20.1040,20.1254,20.1354,20.1550,20.2234,20.2432,20.2432,20.3020,20.3214,
20.3408,20.4588,20.4980,20.5174,20.5548,20.5444,20.5940,20.4254,20.4450,
20.7134,20.7038,20.4744,20.7528,20.8312,20.8404,20.8900,20.9094,20.8802,
20.8802,20.8704,20.8802,20.8704,20.8704,20.8704,20.8802,20.9094,20.9584,
20.9782,20.9880,21.0074,21.0074,21.0174,21.0074,21.0272,21.0448,21.0544,
20.9978,21.0370,21.0448,21.0544,21.0840,21.0448,21.0448,21.0444,21.0742,
21.0958,21.0840,21.1054]
[37.5737,37.4079,37.4422,37.4422,37.7107,37.7107,37.7792,37.8477,
38.0529,38.1213,38.189738.1897,38.3243,38.3944,38.4429,38.5311,38.5311,
38.7357,38.8039,38.8720,39.0082,39.0743,39.1443,39.1783,39.2123,39.2803,
39.3143,39.4200,39.755739.7894,39.755739.5521,39.5521,39.5521,39.4142,
39.4502,39.3143,39.2803,39.2123,39.178339.1443,39.110339.0082,39.0082,
38.9401,39.0082,38.9401,38.8379,38.8720,38.8039,38.7357,38.749838.7357,
38.4475,38.4970,38.3944,38.3944,38.3243,38.2580,38.2580,38.2239,
38.155537.9845,38.1897,38.1555,38.0529.37.9845,37.9141,37.8134,
37.813437.8819,37.8819,37.9141,37.9503,37.9503,37.9141,37.9503,37.9141,
37.8477,37.7792,37.7450,37.7450,37.7107,37.7107,37.7107,37.7107,37.4745,
37.4745,37.4422,37.8134,37.7792,37.7107,37.7107,37.4745,37.4745,37.7107,
37.7450,37.7792,37.9141,38.0529]
S5 predictions=(20.4204,205002,20.4200,20.4200,20.3906,20.3612,20.3024,
20.2828,20.3122,20.2828,20.2828,20.2632,20.2436,20.2240,20.2240,20.2338,
20.2240,20.1848,20.1848,22.1848)(39.4050,40.7663,40.4532,40.8865,41.3314,
41.4261,41.5871,41.7080,41.7905,41.9236,42.0242,42.0180,42.3150,42.4040,
42.2970,42.3270,42.3700,42.3535,42.1924,51.9218)
Now the temperature with sensor node collection is as sample.As shown in figure 1, being saved to space by K-means algorithms first
Point is divided, it is assumed that then 1-5 nodes carry out parameter optimization using the data of node as shown in Figure 2 in same cluster,
Set up MEA-BP neural network models.Determine confidential interval using neural network model residual error, this posterior nodal point gathers new data,
It is predicted by sliding window, if the data of collection judge that the data are exceptional value not in confidential interval, while transmission
Verified to cluster head.Otherwise, the data of collection are normal.
The initial weight and threshold value of neutral net are random, and optimum individual is obtained by optimized algorithm, are advised according to coding
Optimum individual is then parsed, the element in individuality is divided into four parts, input layer and hidden layer weights W, hidden layer and output layer
Weights V, hidden layer threshold value θ, output layer threshold value beta.
W=[0.5773, -0.0366, -0.5442,0.6235,1.1156,0.3768,0.3825,0.3136,
0.1267,-0.7622,-0.5179,1.0760,-0.7651,-0.6149,0.3441,0.9941,0.0842,0.9022,-
0.2135,0.0192;
1.0865,0.2526,0.6696,-0.5513,0.2104,0.2332,0.5453,-0.1723,1.3676,
0.3422,-0.3744,0.8603,0.0330,0.3656,-0.2953,0.0479,-0.3960,-0.6000,0.2272,-
0.7731;
-0.5749,0.5627,0.5373,1.0035,-0.9583,1.1374,0.9935,0.5132,0.5842,
0.4948,-0.5388,0.9441,0.3067,-0.5114,0.3832,-0.0877,-0.6106,-0.8577,-0.4521,
0.5040;
-0.1253,-0.9239,0.5082,0.5222,0.0151,0.0033,-0.2452,-0.3727,-0.7296,
1.0824,1.0505,-0.6283,-0.5399,0.4255,0.3935,-0.5921,-0.6411,-0.8547,0.5181,
0.7837;
-0.4296,-0.6532,0.1644,0.4362,1.2707,0.4877,-0.6715,0.9923,1.2893,
0.8293,,0.9933,-0.6541,-0.1126,0.5300,-0.7672,0.0751,0.2299,-0.2186,0.8131,-
0.9794;
-0.9365,-0.2176,1.0960,0.0105,1.3308,-0.3746,-1.0590,-0.5488,-0.8550,
0.2305,0.4455,-0.2741,-0.0727,-0.8329,0.6602,0.6955,1.2929,-0.2030,0.6805,-
0.1515;
0.9026,0.4729,0.4579,0.0247,-0.3627,-0.1774,0.3376,0.2647,-0.2081,-
0.9794,0.8114,0.0375,-0.1698,0.1191,-0.1169,0.3339,0.4083,-0.3918,-0.3013,
0.8716;
-0.1600,0.5712,-0.4983,-0.5316,-0.4528,-0.1343,0.6454,-0.6407,
0.9763,-0.3584,-0.5402,0.1329,0.7943,0.3628,-0.3161,0.5328,0.5403,0.7219,-
0.3242,0.4581;
-0.0458,-0.7775,0.1541,-0.0951,-0.5324,0.1833,-0.6400,-0.1086,-
0.8386,-0.1227,-1.1306,0.3747,-1.2653,-0.4936,-0.1682,0.7071,-0.3657,1.0828,
0.5700,1.1866;
-0.5898,-0.7801,0.5664,0.0111,0.3069,0.1700,0.3791,-0.3305,0.3633,
0.3725,0.0423,-0.0695,0.2999,0.9656,0.6382,0.1977,-0.4587,0.2812,-0.5573,-
0.3800;
0.9481,-0.0495,0.6783,-0.5981,-0.4970,0.8797,-0.9796,-0.3040,0.9687,-
1.1954,0.3528,-0.1131,-0.1752,-0.8480,0.0283,-0.1791,1.1680,0.1180,1.0543,-
0.7890;
0.9876,-0.5693,0.2064,1.0028,-0.7505,-0.0915,0.8364,0.0396,1.3324,
0.6910,0.4675,0.2987,-0.7527,-0.5169,-0.8266,1.0537,0.9445,-0.1559,-0.2290,
0.7849;
0.7757,0.0837,0.6734,-1.0255,0.2378,0.4449,0.5047,0.0004,0.4182,
0.1178,0.5781,-0.2788,0.5544,-0.6854,0.2246,-0.9034,-0.5780,-1.0345,-1.0602,-
0.5880;
-0.9348,-0.4230,-0.7827,-0.9307,-0.1429,-0.1718,0.2480,0.8521,-
0.9502,0.8372,0.5072,-0.5041,0.0417,-0.0333,0.1855,-0.1131,0.7978,1.2911,
0.3152,0.5734;
-0.4313,0.3686,-0.4494,-0.2113,-0.8895,-0.6692,0.8727,0.5028,-
1.2660,-0.1608,-1.1177,0.9249,-0.7744,-0.8300,-0.6689,-0.6472,0.5649,-
0.0527,-0.2023,0.7030;
0.8426,0.8520,0.6722,-0.9511-0.7137,-0.6196,0.1978,0.5044,-0.6855,-
0.3957,-1.1713,0.8359,0.2987,-0.3332,-0.7046,-0.0307,0.7013,-1.0424,-0.2173,-
0.8635;
0.4429,-0.5530,0.2594,-0.0055,-0.2293,-0.1312,0.1046,-1.1803,0.6552,
1.1167,0.2293,0.8949,0.2872,0.0639,-0.7069,-0.6443,-0.5359,-0.7943,0.0749,
0.2322;
0.1580,0.3637,-0.3663,0.3326,0.5618,-0.0908,0.6683,-0.1572,0.0053,-
0.6843,-1.1245,0.6485-0.4312,-0.7010,-0.1113,0.7301,-0.0746,0.0622,0.1535,-
0.0938;
-1.1087,-0.0046,-0.9751,-0.0265,1.1469,-0.7158,0.6888,-0.5601,0.5212,
0.6409,-0.5567,1.1806,-0.1444,0.5397,-0.5531,0.5221,-0.5053,-1.2739,-0.4797,
0.3794]
V=[- 0.8852, -0.4987, -1.0526,0.3578, -0.0436, -0.6403,1.1844, -1.2437, -
0.9961,-0.1289,-0.8779,-0.0577,-0.5220,0.4834,0.3050,0.5123,0.4276,-0.0404,
0.9207,0.0199]
θ=[- 0.3454, -0.0724, -0.9978, -1.0797,1.0350,0.2819,0.8036,0.2719,
0.2332,-0.6689,0.9885,-0.7912,0.1800,-0.6851,-0.7595,0.2428,-0.1237,-0.2353,-
0.0445,0.4698]
β=[- 1.2285]
Then confidential interval is calculated, 1 one predicted values at moment of node are randomly selected, it is 20.8692 to be worth, now choose instruction
Practice rear 40 data of data by the computation model residual error of formula 1, the model residual values S=0.1776 for obtaining obtains t values by Fig. 1
It is 2.02108, interval bound now is calculated as [20.5058,21.2326] by formula 2.
Assuming that node S1 has trained MEA-BP models, new data are added by sliding window, as it appears from the above, working as
When sliding window predicts the 1st data, now temperature prediction value be 20.8692, fiducial interval range for [20.5058,
21.2326], this moment sensing data is 20.7724, it can be seen that 20.7724 this data are obvious within interval range,
Then think that the time data is normal;When sliding window predicts the 10th data, now temperature prediction value is 20.7062,
Fiducial interval range is [20.3428,21.0696], and this moment sensing data is 22.1530, and the data are in interval range
Outside, being then passed to leader cluster node carries out spatiality checking, finds the data at the moment in same cluster by voting mechanism
Interior temperature is abnormal, the then temperature data exception that node 1 is gathered, and node breaks down or reports by mistake, if finding in same cluster
Middle data are similar, then it is assumed that event occur.Humidity temperature data for other nodes can similarly be recognized accurately exception.
The inventive method is divided with K-means algorithms based on the temporal correlation of sensor node to node,
Then MEA-BP neural network models are set up on each node, and following each distribution node of each moment is detected according to the model
Whether the data of interior arrival are abnormal, the result after detection is then delivered to leader cluster node and is verified.At present, abnormality detection exists
The characteristics of being all a problem for further investigation, wireless sensor network uniqueness in every field and strict constraints are caused
The research of the problem is more challenging.Method proposed by the present invention is multiple primarily directed to resource-constrained wireless sensor network
Miscellaneous abnormality detection, greatly reduces the communication consumption between node, and can accurately detect abnormal data, suitable with more environment
Should be able to power.
The above is only the preferred embodiment of the present invention, it should be pointed out that:Come for those skilled in the art
Say, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (6)
- It is 1. a kind of to be based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The described method comprises the following steps:Each distribution sensor node initializing, each sensor node are started gathered data by S1;If sensor node number is n, each sensor node is Xtj(j=1,2 ..., n), sensor node XtjSliding window It is Wj, the sliding window size of each sensor node is m, then sensor node XtjIn its sliding window WjOn measurement data Sequence isSensor node XtjIn tpMoment collection data beThe data include that h attribute is surveyed Value, thenS2 carries out space sub-clustering to each sensor node and obtains some groups of clusters using K-means algorithms;If q+1 sensor node constitutes one group of cluster, every group of cluster includes 1 leader cluster node XtcWith q distribution node (Xt1, Xt2,…,Xtq);S3 carries out parameter optimization using mind evolutionary to BP neural network, by convergent operation dissimilation to BP neural network Weights and threshold value are optimized, and obtain best initial weights and threshold value, are input into best initial weights and threshold value, set up MEA-BP neutral net moulds Type;S4 uses distributed algorithm, to sensor node (Xt in every component cluster1,Xt2,…,Xtq) abnormality detection is independently executed, Abnormality detection finishes rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the leader cluster node Xt of the component clusterc Further checking.
- 2. according to claim 1 based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The step Rapid S2 is comprised the following steps:S21 arbitrarily selects K sensor node object as K cluster centre first from distribution sensor node object;S22 calculates sensor node object with K cluster respectively then for the sensor node object in addition to cluster centre Similarity between center, obtains and the sensor node immediate cluster centre of object similarity;S23 is distributed to the cluster with the sensor node immediate cluster centre of object similarity by sensor node object, K cluster will be obtained after the completion of all the sensors node distribution;S24 recalculates this K cluster centre of cluster, obtains new cluster centre;S25 recalculates the similarity of each sensor node and new cluster centre, returns to step S22;S26 terminates this operation when the cluster centre for recalculating is restrained.
- 3. according to claim 1 based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The step Rapid S3 is comprised the following steps:Produce training data;Determine BP neural network topological structure;Line parameter is entered by mind evolutionary Set;Randomly generate initial population, winning sub- population and interim sub- population;Operation similartaxis are carried out to sub- population;Sub- population is entered Row operation dissimilation;Judge whether to meet termination condition, if it is satisfied, then output optimum individual, obtains best initial weights and threshold value, it is no Then re-start convergent operation dissimilation.
- 4. according to claim 1 based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The step Rapid S4 is comprised the following steps:S41 is by temporal correlation to sensor node (Xt1,Xt2,…,Xtq) abnormality detection is independently executed, it is current using each Moment passes through sensor node XtjSliding window WjDataTo train neutral net, complete next The forecast of time data, chooses training dataRear v sample data, by formula (1) calculate The model residual error S of MEA-BP neutral nets:Wherein, Er(r=1,2 ..., v) be choose sampled data values, F be choose sample data averages,S42 calculates the confidential interval at sensor node current time, and confidential interval is Wherein SprePrediction for MEA-BP neutral nets to subsequent time data Value, tα/2,v-1For the t of free degree v-1 is distributed, suitable α values are chosen in t distribution tables, obtain t values;S43 works as subsequent time data SnewWhen in into sensor node sliding window, subsequent time data S is judgednewWhether fall Enter in the fiducial interval range at current time, if so, then judging data SnewIt is normal data;Otherwise judge data SnewFor Abnormal data;S44 abnormality detections finish rear sensor node (Xt1,Xt2,…,Xtq) testing result is delivered to the cluster head of the component cluster Nodes X tcIn;S45 leader cluster nodes XtcVoting mechanism verificating sensor node abnormal data is detected and introduced by spatial coherence produces original Cause, reason includes that event anomalies, node failure are abnormal and judge by accident.
- 5. according to claim 4 based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The step In rapid S42, α=0.05 is chosen.
- 6. according to claim 4 based on MEA-BP neutral net WSN method for detecting abnormality, it is characterised in that:The step Spatial coherence is carried out in rapid S45 and detects and introduce voting mechanism to comprise the following steps:S451 carries out the abnormal data of sensor node and other node datas with the sensor node in same sub-clustering Compare;If q+1 sensor node constitutes a component cluster, 1 leader cluster node Xt is included per component clustercWith q distribution node (Xt1,Xt2,…,Xtq);S452 presets error amount θ, if the abnormal data of sensor node is STIf, with the sensor node in same sub-clustering In other nodes data be Si(i=1,2 ..., q-1), if | ST-Si|<θ, then initial value is that 0 counting NN plus 1, is counted Final NN values;If S453Then judge that the detection node abnormal data is due to event anomalies;IfThen judge the detection Node abnormal data is due to node failure or erroneous judgement;IfThe reference node in the sub-clustering is then chosen, if with reference to node Data be SCCIf, | ST-SCC|≤θ, then judge the sensor node abnormal data be due to event anomalies, if | ST-SCC|>θ, Then judge that the sensor node abnormal data is due to node failure or erroneous judgement;It is to be clustered in the sub-clustering wherein with reference to node The nearest node of Centroid Euclidean distance;It is due to node failure or erroneous judgement when judgement obtains the sensor node abnormal data during S454 is for the step S453 When, determine whether that the sensor node abnormal data is, due to node failure or erroneous judgement, to specifically include following steps:Pass through Temporal correlation detection is carried out to sensor node, when abnormal data is produced in sensor node continuous time, then judging should Sensor node abnormal data is due to node failure;When sensor node only has the moment for abnormal data, other moment produce Raw data are normal data, then judge that the sensor node abnormal data is due to erroneous judgement.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710008709.XA CN106714220B (en) | 2017-01-06 | 2017-01-06 | One kind being based on MEA-BP neural network WSN method for detecting abnormality |
PCT/CN2017/119421 WO2018126984A2 (en) | 2017-01-06 | 2017-12-28 | Mea-bp neural network-based wsn abnormality detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710008709.XA CN106714220B (en) | 2017-01-06 | 2017-01-06 | One kind being based on MEA-BP neural network WSN method for detecting abnormality |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106714220A true CN106714220A (en) | 2017-05-24 |
CN106714220B CN106714220B (en) | 2019-05-17 |
Family
ID=58907069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710008709.XA Expired - Fee Related CN106714220B (en) | 2017-01-06 | 2017-01-06 | One kind being based on MEA-BP neural network WSN method for detecting abnormality |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106714220B (en) |
WO (1) | WO2018126984A2 (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107249000A (en) * | 2017-07-06 | 2017-10-13 | 河南科技大学 | A kind of mobile subscriber's anomaly detection method |
CN107272660A (en) * | 2017-07-26 | 2017-10-20 | 江南大学 | A kind of random fault detection method of the network control system with packet loss |
CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
CN107613540A (en) * | 2017-11-07 | 2018-01-19 | 合肥工业大学 | A kind of wireless chargeable sensor network cluster cluster routing method |
WO2018126984A3 (en) * | 2017-01-06 | 2018-09-13 | 江南大学 | Mea-bp neural network-based wsn abnormality detection method |
CN108763346A (en) * | 2018-05-15 | 2018-11-06 | 中南大学 | A kind of abnormal point processing method of sliding window box figure medium filtering |
CN109714311A (en) * | 2018-11-15 | 2019-05-03 | 北京天地和兴科技有限公司 | A method of the unusual checking based on clustering algorithm |
CN110542659A (en) * | 2019-09-06 | 2019-12-06 | 四川大学 | pearl luster detection method based on visible light spectrum |
CN111542010A (en) * | 2020-04-22 | 2020-08-14 | 青岛黄海学院 | WSN data fusion method based on classification adaptive estimation weighting fusion algorithm |
CN111950505A (en) * | 2020-08-24 | 2020-11-17 | 湖南科技大学 | State evaluation method for wind driven generator sensor of SSA-AANN |
CN112418281A (en) * | 2020-11-11 | 2021-02-26 | 国网福建省电力有限公司电力科学研究院 | Fire detection sensor data anomaly detection method and system |
CN113128626A (en) * | 2021-05-28 | 2021-07-16 | 安徽师范大学 | Multimedia stream fine classification method based on one-dimensional convolutional neural network model |
CN113640308A (en) * | 2021-08-31 | 2021-11-12 | 郑州铁路职业技术学院 | Track abnormity monitoring system based on machine vision |
CN114484732A (en) * | 2022-01-14 | 2022-05-13 | 南京信息工程大学 | Air conditioning unit sensor fault diagnosis method based on novel voting network |
Families Citing this family (48)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109856299A (en) * | 2018-11-26 | 2019-06-07 | 国家电网有限公司 | A kind of transformer online monitoring differentiation threshold value dynamic setting method, system |
CN110427593B (en) * | 2018-12-19 | 2022-12-02 | 西安电子科技大学 | SMT printing parameter optimization method based on industrial big data |
CN110147829B (en) * | 2019-04-29 | 2022-10-11 | 郑州工程技术学院 | Aircraft data processing method and device based on cloud computing |
CN111899040B (en) * | 2019-05-05 | 2023-09-01 | 腾讯科技(深圳)有限公司 | Method, device, equipment and storage medium for detecting target object abnormal propagation |
CN110084326B (en) * | 2019-05-13 | 2022-12-06 | 东北大学 | Industrial equipment anomaly detection method based on fuzzy set |
CN109963317A (en) * | 2019-05-14 | 2019-07-02 | 中国联合网络通信集团有限公司 | A kind of election of cluster head method, apparatus |
CN110362608B (en) * | 2019-06-11 | 2023-04-28 | 广东工业大学 | Rain flow counting method and local anomaly factor-based energy consumption anomaly detection method |
CN110457550B (en) * | 2019-07-05 | 2022-11-18 | 中国地质大学(武汉) | Method for correcting abnormal operation data in sintering process |
CN110750641B (en) * | 2019-09-24 | 2022-02-11 | 武汉大学 | Classification error correction method based on sequence connection model and binary tree model |
CN111127184B (en) * | 2019-11-01 | 2023-05-30 | 复旦大学 | Distributed combined credit evaluation method |
CN110849404B (en) * | 2019-11-18 | 2022-03-22 | 中国华能集团清洁能源技术研究院有限公司 | Continuous discrimination method for sensor data abnormity |
CN111126437B (en) * | 2019-11-22 | 2023-05-02 | 中国人民解放军战略支援部队信息工程大学 | Abnormal group detection method based on weighted dynamic network representation learning |
CN110969198A (en) * | 2019-11-24 | 2020-04-07 | 广东浪潮大数据研究有限公司 | Distributed training method, device, equipment and storage medium for deep learning model |
CN110912272B (en) * | 2019-12-03 | 2023-02-21 | 合肥工业大学 | Urban power grid fault detection method and system based on regional abnormal pattern recognition |
CN111654831B (en) * | 2020-04-14 | 2023-01-31 | 南京信息工程大学 | Grinding machine load detection method based on wireless sensor network |
CN111654874B (en) * | 2020-06-03 | 2023-02-24 | 枣庄学院 | Wireless sensor network anomaly detection method |
CN111683137B (en) * | 2020-06-05 | 2021-08-13 | 震兑工业智能科技有限公司 | 5G and block chain intelligent management system |
CN111814826B (en) * | 2020-06-08 | 2022-06-03 | 武汉理工大学 | Rapid detection and rating method for residual energy of retired power battery |
CN112001638B (en) * | 2020-08-25 | 2024-01-23 | 瑞洲建设集团有限公司 | Building site management system based on internet of things |
CN112165485B (en) * | 2020-09-25 | 2022-08-09 | 昆明市网络建设运营有限公司 | Intelligent prediction method for large-scale network security situation |
CN112437440B (en) * | 2020-09-30 | 2024-02-02 | 北京工业大学 | Malicious collusion attack resistance method based on correlation theory in wireless sensor network |
CN112565183B (en) * | 2020-10-29 | 2022-12-09 | 中国船舶重工集团公司第七0九研究所 | Network flow abnormity detection method and device based on flow dynamic time warping algorithm |
CN112329351A (en) * | 2020-11-19 | 2021-02-05 | 上海嗨酷强供应链信息技术有限公司 | Flow analysis system and method based on data tracking |
CN112437085B (en) * | 2020-11-23 | 2023-03-24 | 中国联合网络通信集团有限公司 | Network attack identification method and device |
CN112506990B (en) * | 2020-12-03 | 2022-10-04 | 河海大学 | Hydrological data anomaly detection method based on spatiotemporal information |
CN112702408A (en) * | 2020-12-20 | 2021-04-23 | 国网山东省电力公司临沂供电公司 | Internet of things system and method based on multi-sensing function |
CN112770282B (en) * | 2020-12-23 | 2022-08-05 | 龙海建设集团有限公司 | Data processing system based on intelligent building Internet of things |
CN112820120B (en) * | 2020-12-30 | 2022-03-01 | 杭州趣链科技有限公司 | Multi-party traffic flow space-time cross validation method based on alliance chain |
CN112783938B (en) * | 2020-12-30 | 2022-10-04 | 河海大学 | Hydrological telemetering real-time data anomaly detection method |
CN112804255B (en) * | 2021-02-09 | 2022-10-18 | 中国人民解放军国防科技大学 | Network abnormal node detection method based on node multidimensional characteristics |
CN112861436A (en) * | 2021-02-18 | 2021-05-28 | 天津大学 | Real-time prediction method for engine emission |
CN113378990B (en) * | 2021-07-07 | 2023-05-05 | 西安电子科技大学 | Flow data anomaly detection method based on deep learning |
CN113556770A (en) * | 2021-07-27 | 2021-10-26 | 广东电网有限责任公司 | Data verification method, device, terminal and readable storage medium |
CN114051218B (en) * | 2021-11-09 | 2024-05-14 | 华中师范大学 | Environment-aware network optimization method and system |
CN114021297B (en) * | 2021-11-18 | 2023-12-01 | 吉林建筑科技学院 | Complex pipe network leakage positioning method based on echo state network |
CN114401516B (en) * | 2022-01-11 | 2024-05-10 | 国家计算机网络与信息安全管理中心 | 5G slice network anomaly detection method based on virtual network traffic analysis |
CN114422554B (en) * | 2022-01-27 | 2024-03-01 | 曹颂群 | Service area intelligent equipment management method and device based on distributed Internet of things |
CN114861776B (en) * | 2022-04-21 | 2024-04-09 | 武汉大学 | Dynamic self-adaptive network anomaly detection method based on artificial immunity technology |
CN114997276B (en) * | 2022-05-07 | 2024-05-28 | 北京航空航天大学 | Heterogeneous multi-source time sequence data anomaly identification method for compression molding equipment |
CN115002824A (en) * | 2022-05-25 | 2022-09-02 | 厦门大学 | Real-time fault detection and recovery method for underwater acoustic network data based on LSTM |
CN115022049B (en) * | 2022-06-06 | 2024-05-14 | 哈尔滨工业大学 | Distributed external network flow data detection method based on calculated mahalanobis distance, electronic equipment and storage medium |
CN115608793B (en) * | 2022-12-20 | 2023-04-07 | 太原科技大学 | Finish rolling temperature regulation and control method for mechanism fusion data |
CN116109176B (en) * | 2022-12-21 | 2024-01-05 | 成都安讯智服科技有限公司 | Alarm abnormity prediction method and system based on collaborative clustering |
CN116257892B (en) * | 2023-05-09 | 2023-08-29 | 广东电网有限责任公司佛山供电局 | Data privacy security verification method for digital archives |
CN116405368B (en) * | 2023-06-02 | 2023-08-22 | 南京信息工程大学 | Network fault diagnosis method and system under high-dimensional unbalanced data condition |
CN117093947B (en) * | 2023-10-20 | 2024-02-02 | 深圳特力自动化工程有限公司 | Power generation diesel engine operation abnormity monitoring method and system |
CN117349779B (en) * | 2023-12-04 | 2024-02-09 | 水利部交通运输部国家能源局南京水利科学研究院 | Method and system for judging potential sliding surface of deep-excavation expansive soil channel side slope |
CN117892095B (en) * | 2024-03-14 | 2024-05-28 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103916896A (en) * | 2014-03-26 | 2014-07-09 | 浙江农林大学 | Anomaly detection method based on multi-dimensional Epanechnikov kernel density estimation |
CN105791051A (en) * | 2016-03-25 | 2016-07-20 | 中国地质大学(武汉) | WSN (Wireless Sensor Network) abnormity detection method and system based on artificial immunization and k-means clustering |
CN106447092A (en) * | 2016-09-12 | 2017-02-22 | 浙江工业大学 | Marine reverse osmosis desalination system performance prediction method based on MEA-BP neural network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103747537B (en) * | 2014-01-15 | 2017-05-03 | 广东交通职业技术学院 | Wireless sensor network outlier data self-adaption detecting method based on entropy measurement |
CN105764162B (en) * | 2016-05-10 | 2019-05-17 | 江苏大学 | A kind of wireless sensor network accident detection method based on more Attribute Associations |
CN106714220B (en) * | 2017-01-06 | 2019-05-17 | 江南大学 | One kind being based on MEA-BP neural network WSN method for detecting abnormality |
-
2017
- 2017-01-06 CN CN201710008709.XA patent/CN106714220B/en not_active Expired - Fee Related
- 2017-12-28 WO PCT/CN2017/119421 patent/WO2018126984A2/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103916896A (en) * | 2014-03-26 | 2014-07-09 | 浙江农林大学 | Anomaly detection method based on multi-dimensional Epanechnikov kernel density estimation |
CN105791051A (en) * | 2016-03-25 | 2016-07-20 | 中国地质大学(武汉) | WSN (Wireless Sensor Network) abnormity detection method and system based on artificial immunization and k-means clustering |
CN106447092A (en) * | 2016-09-12 | 2017-02-22 | 浙江工业大学 | Marine reverse osmosis desalination system performance prediction method based on MEA-BP neural network |
Non-Patent Citations (1)
Title |
---|
胡石 等: "基于神经网络的无线传感器网络异常数据检测方法", 《计算机科学》 * |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018126984A3 (en) * | 2017-01-06 | 2018-09-13 | 江南大学 | Mea-bp neural network-based wsn abnormality detection method |
CN107358021A (en) * | 2017-06-01 | 2017-11-17 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
CN107358021B (en) * | 2017-06-01 | 2020-07-28 | 华南理工大学 | DO prediction model establishment method based on BP neural network optimization |
CN107249000B (en) * | 2017-07-06 | 2020-02-25 | 河南科技大学 | Method for detecting abnormal behaviors of mobile user |
CN107249000A (en) * | 2017-07-06 | 2017-10-13 | 河南科技大学 | A kind of mobile subscriber's anomaly detection method |
CN107272660A (en) * | 2017-07-26 | 2017-10-20 | 江南大学 | A kind of random fault detection method of the network control system with packet loss |
CN107272660B (en) * | 2017-07-26 | 2019-05-17 | 江南大学 | A kind of random fault detection method of the network control system with packet loss |
CN107613540A (en) * | 2017-11-07 | 2018-01-19 | 合肥工业大学 | A kind of wireless chargeable sensor network cluster cluster routing method |
CN107613540B (en) * | 2017-11-07 | 2019-08-30 | 合肥工业大学 | A kind of wireless chargeable sensor network cluster cluster routing method |
CN108763346A (en) * | 2018-05-15 | 2018-11-06 | 中南大学 | A kind of abnormal point processing method of sliding window box figure medium filtering |
CN109714311A (en) * | 2018-11-15 | 2019-05-03 | 北京天地和兴科技有限公司 | A method of the unusual checking based on clustering algorithm |
CN109714311B (en) * | 2018-11-15 | 2021-12-31 | 北京天地和兴科技有限公司 | Abnormal behavior detection method based on clustering algorithm |
CN110542659A (en) * | 2019-09-06 | 2019-12-06 | 四川大学 | pearl luster detection method based on visible light spectrum |
CN110542659B (en) * | 2019-09-06 | 2020-04-07 | 四川大学 | Pearl luster detection method based on visible light spectrum |
CN111542010A (en) * | 2020-04-22 | 2020-08-14 | 青岛黄海学院 | WSN data fusion method based on classification adaptive estimation weighting fusion algorithm |
CN111950505A (en) * | 2020-08-24 | 2020-11-17 | 湖南科技大学 | State evaluation method for wind driven generator sensor of SSA-AANN |
CN111950505B (en) * | 2020-08-24 | 2023-08-29 | 湖南科技大学 | SSA-AANN wind driven generator sensor state evaluation method |
CN112418281A (en) * | 2020-11-11 | 2021-02-26 | 国网福建省电力有限公司电力科学研究院 | Fire detection sensor data anomaly detection method and system |
CN113128626A (en) * | 2021-05-28 | 2021-07-16 | 安徽师范大学 | Multimedia stream fine classification method based on one-dimensional convolutional neural network model |
CN113640308A (en) * | 2021-08-31 | 2021-11-12 | 郑州铁路职业技术学院 | Track abnormity monitoring system based on machine vision |
CN113640308B (en) * | 2021-08-31 | 2024-03-29 | 夏冰心 | Rail anomaly monitoring system based on machine vision |
CN114484732A (en) * | 2022-01-14 | 2022-05-13 | 南京信息工程大学 | Air conditioning unit sensor fault diagnosis method based on novel voting network |
Also Published As
Publication number | Publication date |
---|---|
WO2018126984A3 (en) | 2018-09-13 |
WO2018126984A2 (en) | 2018-07-12 |
CN106714220B (en) | 2019-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106714220A (en) | WSN (Wireless Sensor Network) anomaly detection method based on MEA-BP neural network | |
CN110547792B (en) | Atrial fibrillation detection method and device, computer equipment and storage medium | |
CN102302370B (en) | Method and device for detecting tumbling | |
CN110309886B (en) | Wireless sensor high-dimensional data real-time anomaly detection method based on deep learning | |
CN106510619B (en) | ECG Signal Analysis method based on complex network and in the application being intelligently worn by | |
CN105843919A (en) | Moving object track clustering method based on multi-feature fusion and clustering ensemble | |
CN109902564A (en) | A kind of accident detection method based on the sparse autoencoder network of structural similarity | |
CN117407827B (en) | Abnormal operation data detection method for purification engineering waste gas purification equipment | |
CN106407998A (en) | Probability time-varying seawater hydraulic pump fault prediction method | |
CN108211268B (en) | exercise load monitoring and exercise fatigue early warning method and system based on exercise training data | |
CN111191559A (en) | Overhead line early warning system obstacle identification method based on time convolution neural network | |
CN113569756B (en) | Abnormal behavior detection and positioning method, system, terminal equipment and readable storage medium | |
CN107368858A (en) | A kind of parametrization measurement multi-model intelligent method for fusing of intelligent environment carrying robot identification floor | |
CN108717548B (en) | Behavior recognition model updating method and system for dynamic increase of sensors | |
CN106407699A (en) | Coronary heart disease prediction method and prediction system based on incremental neural network model | |
CN103136540A (en) | Behavior recognition method based on concealed structure reasoning | |
CN116311497A (en) | Tunnel worker abnormal behavior detection method and system based on machine vision | |
CN113780432B (en) | Intelligent detection method for operation and maintenance abnormity of network information system based on reinforcement learning | |
CN104280253B (en) | A kind of fault diagnosis method and system based on immune detectors | |
Lee et al. | Mobile embedded health-care system working on wireless sensor network | |
WO2024041053A1 (en) | Indoor passive human behavior recognition method and apparatus | |
CN116839228A (en) | Intelligent control system of modular general water heater | |
CN115099275B (en) | Training method of arrhythmia diagnosis model based on artificial neural network | |
CN112022149B (en) | Atrial fibrillation detection method based on electrocardiosignals | |
CN114652319A (en) | Arrhythmia detection method based on graph neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190517 Termination date: 20220106 |