CN109670541A - A kind of mosquito matchmaker's infectious disease fever crowd's range flags method based on spatial clustering - Google Patents

A kind of mosquito matchmaker's infectious disease fever crowd's range flags method based on spatial clustering Download PDF

Info

Publication number
CN109670541A
CN109670541A CN201811490660.7A CN201811490660A CN109670541A CN 109670541 A CN109670541 A CN 109670541A CN 201811490660 A CN201811490660 A CN 201811490660A CN 109670541 A CN109670541 A CN 109670541A
Authority
CN
China
Prior art keywords
class
sample
fever
circle
points
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
Application number
CN201811490660.7A
Other languages
Chinese (zh)
Other versions
CN109670541B (en
Inventor
王鑫
唐烨榕
张凤军
周红宁
杜龙飞
梁赓
丁海元
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yunnan Institute Of Parasitic Diseases
Institute of Software of CAS
Original Assignee
Yunnan Institute Of Parasitic Diseases
Institute of Software of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yunnan Institute Of Parasitic Diseases, Institute of Software of CAS filed Critical Yunnan Institute Of Parasitic Diseases
Priority to CN201811490660.7A priority Critical patent/CN109670541B/en
Publication of CN109670541A publication Critical patent/CN109670541A/en
Application granted granted Critical
Publication of CN109670541B publication Critical patent/CN109670541B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Image Analysis (AREA)

Abstract

Mosquito matchmaker's infectious disease fever crowd's range flags method based on spatial clustering that the invention discloses a kind of: extensive collecting zone fever demographic data, and data are pre-processed；Unsupervised clustering is carried out according to individual coordinate, the closer individual of space length is polymerized to one kind；In every one kind, the area minimum circle-cover comprising all the points in class is found using minimum circle-cover algorithm, finally result is visualized.The method of non parameter modeling is applied to mosquito matchmaker's infectious disease fever crowd's range flags field by the present invention, the section of fever crowd can accurately be delimited, mosquito matchmaker fever patientss space diffusion tendency is described, it assists disease control officer to carry out the epidemic situation investigation and dissipation work of relevant range, corresponding measure control infectious disease is taken to break out on a large scale in time.

Description

A kind of mosquito matchmaker's infectious disease fever crowd's range flags method based on spatial clustering
Technical field
Mosquito matchmaker's infectious disease fever crowd's range flags method based on spatial clustering that the present invention relates to a kind of, belongs to computer Application field.
Background technique
With the warming of global climate, the quickening of urbanization process, countries in the world trade contacts it is frequent and international The continuous deterioration of the quick convenience, ecological environment of vehicles transport, global mosquito matchmaker infectious disease incidence is in rising trend, original mosquito The epidemic regions of matchmaker's infectious disease constantly extend, the popular frequency of disease constantly enhances.So that originally be confined to a certain region or Disease in country breaks through the boundary in border, causes wide-scale distribution worldwide and popular, once or popular Mosquito matchmaker's infectious disease brings significant damage to the people of the world.Therefore, to the research of mosquito matchmaker's infectious disease there is an urgent need to.
Mosquito matchmaker's infectious disease is people-mosquito-people communication mode, has complicated Spatial-Temporal Variability, by multiple dimensioned, random The multifactor impacts such as property, process feature renaturation have strong nonlinearity correlation between causality, while insect-borne infectious disease is broken out Period is short, spread speed is fast, and the big area of flow of personnel amount more exacerbates the risk of epidemic outbreak, and conventional method is difficult to send out in time Now with capture disease occur and developing state.In recent years, most of research is devoted to directly utilize the case of mosquito matchmaker infectious disease The trend of infectious disease is described, such as the epidemic place inverse analysis method based on geographical sidelights on, the case interpolation based on space length be in Existing technology etc..But these methods only consider the distribution situation of confirmed cases, and ignore potential case and possible infection population, And the analysis method for being mostly based on space can not directly describe disease situation, cannot support epidemic disease when outbreak of disease well Feelings disposing task.
A part of researcher by mass data point mark in the way of mark crowd, such as summarize and hang up one's hat in a certain spy Everyone is considered as a point label by longitude and latitude and is analyzed and processed on map by the crowd's information for determining region.On the one hand, The workload that this scheme acquires data is excessive, and area biggish for flow of personnel, and data update frequently, is easy The problem of existing dirty data, influences to hold the entirety of Yunnan province.On the other hand, the presentation mode based on massive point is unfavorable for seeing It surveys, directly can not therefrom obtain the development trend of epidemic situation, and be difficult therefrom to find simply by virtue of expertise potential easily touching Group and epidemic place is broken out, virtually increases burden to epidemic situation disposition and mosquito matchmaker's dissipation work in later period.
Summary of the invention
The technology of the present invention solves the problems, such as: overcoming the deficiencies in the prior art, provides a kind of mosquito based on spatial clustering Matchmaker's infectious disease fever crowd's range flags method, has the advantages that science is feasible, is easy to observe, go out from the angle of fever crowd Hair carries out spatial clustering to the geographical location information of heating paresthesia crowd, marks the territorial scope of possible epidemic outbreaks, fitting area Domain space description carries out visualization presentation, realizes early stage observation and early warning to insect-borne infectious disease situation, dramatically assists Epidemic situation disposition and mosquito dissipation work.
The technical solution adopted by the present invention to solve the technical problems is: a kind of mosquito matchmaker's infectious disease hair based on spatial clustering Thermal man's group's range flags method, comprising the following steps:
The first step is collected the particulars of mosquito matchmaker infectious disease fever crowd and is pre-processed to the coordinate data of individual；
Second step, to treated, data use unsupervised clustering, obtain the individual coordinate data inside every one kind, Delete lonely class；
Third step is successively handled the individual coordinate data inside described every one kind using minimum circle-cover algorithm, Obtain several minimum circle-covers；
4th step visualizes the minimum circle-cover of fever crowd spatial clustering.
In the step 1, the particulars of the fever crowd include number, name, nationality, gender, the age, address, Enrollment time, body temperature, residence abscissa, residence ordinate remove residence abscissa or residence ordinate as sky Data, while removing repeated data.
In the step 2, unsupervised clustering is specific as follows:
(1) it regard each fever individual as a sample, the residence abscissa and residence ordinate for choosing individual are made For sample information x, N is initializedcA class, is denoted asCorresponding to cluster centre is respectivelySjCluster in Heart zjMeetWherein NumjIndicate SjThe sample number for including, threshold value is arranged: K is pre- Phase cluster centre number, θNIt is the number of samples lower limit of every one kind, θSIt is the standard deviation upper limit of sample in class, θcIt is between cluster centre Minimum range, L is the maximum times of union operation in iteration；
(2) for each sample, calculating the sample to the Euclidean distance of each cluster centre, the nearest class of distance sample is found, Assuming that x to SjDistance meet Dx=min | | x-zj| |, j=1,2 ... Nc, wherein | | x-zj| | indicate x and zjEuclidean away from From then x ∈ Sj；
(3) if SjIn sample number Numj<θN, then such is deleted, NcSubtract 1；
(4) each cluster centre is updated,
(5) average distance of sample and cluster centre in each class is calculated
(6) the overall average distance of whole samples is calculatedIf merging at this time secondary Number enables θ more than Lc=0, (10) are gone to, if(7) are gone to, if the number of iterations is even number or Nc> 2K goes to (10), Otherwise (7) are gone to；
(7) standard deviation of the sample on each component in each class, σ are calculatedxjIndicate the abscissa standard deviation of jth class, σyjTable Show the ordinate standard deviation of jth class, remembers σj=(σxj, σyj)T, j=1,2 ... Nc；
(8) the largest component σ in each standard deviation is recordedjmax=max { σj, j=1,2 ... Nc}；
(9) in any largest component set, if meeting simultaneously:
σjmax>θS,Nj>2(θN+1)
Two samples in such are then randomly selected as cluster centre, such is decomposed into two classes, NcAdd 1, goes to (2), (10) are otherwise gone to；
(10) distance of whole cluster centres, D are calculatedij=| | zi-zj| |, i=1,2 ... Nc- 1, j=1,2 ... Nc, i ≠ j.By DijBy apart from incremental arrangement；
It (11) will be apart from for DijAnd Dij<θcCluster centre ziAnd zjMerge, obtain new cluster centre, is labeled as i-th Class, NcSubtract 1, while updating sample classification,
(12) if last time iteration, (13) are gone to, otherwise go to (2)；
(13) sample information that every one kind is included is obtained, all classes comprising a point are deleted, these points are not done Subsequent processing.
In the step 3, minimum circle-cover algorithm is specific as follows:
(1) assume to share N number of point, number consecutively P1,P2…Pi,…PN, 1≤i≤N, with P1And P2Justify for diameter work, if For Cx；
(2) all the points are successively scanned in order, if all the points are in CxIt is interior, return to CxFor final result, and exit the program, Otherwise it finds not in CxIt is interior, it is set as Pi, enter step (3)；
(3) it executes so far, illustrates CxNot comprising Pi, with P1And PiJustify for diameter work, is set as Cy, CyIt not necessarily include P1~Pi All the points, all the points are successively scanned in order, if all the points are in CyIt is interior, enable Cx=CyIt returns to (2) to execute, otherwise finds one Point is not in CyIt is interior, it is set as Pj, centainly have j < i at this time, enter step (4)；
(4) with P1And PjJustify for diameter work, is set as Cz, CzIt not necessarily include P1~PjAll the points, successively scan in order All the points, if all the points are in CzIt is interior, then more new circle Cx=CzIt returns to (2) to execute, otherwise finds a point PkNot in this circle, this When Pi, Pj, PkOne is scheduled on the boundary for updating circle, crosses Pi, Pj, Pk3 points of work circles simultaneously update Cx, return to (2) and execute.
In the step 4, the result that visualizes includes the scatterplot and minimum vertex-covering in plane right-angle coordinate Circle.
Compared with prior art, the beneficial effects of the present invention are:
(1) present invention passes through the details for collecting fever crowd, the inhabitation position of Susceptible population during extraction epidemic situation Information realizes the spatial description to potential case；
(2) present invention devises a kind of spatial clustering adaptive algorithm based on fever crowd's geographical location information, enhancing To the descriptive power of mass data point, disease control range is reduced, symptom crowd's Regional Distribution of Registered is more accurately described；
(3) the present invention is based on minimum circle-cover algorithms, and spatial clustering is presented as a result, being easy to observe the diffusion state of fever crowd Gesture and potential epidemic situation development trend are promoted to arthropod-borne disease early prevention and later period epidemic situation disposing capacity.
Detailed description of the invention
Fig. 1 is the method for the present invention flow diagram；
Fig. 2 is system layout schematic diagram；
Fig. 3 is that schematic diagram is presented in visualization result.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing and example, to this Invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, and does not have to It is of the invention in limiting.In addition, as long as technical characteristic involved in the various embodiments of the present invention described below is each other Between do not constitute conflict and can be combined with each other.
Basic ideas of the invention are, comprehensive collection insect-borne infectious disease generates heat the information of crowd, according to fever crowd's Spatial positional information carries out non parameter modeling to individual, realizes the region mark of fever crowd based on minimum circle-cover algorithm in class It is fixed, visualization presentation is carried out to result in conjunction with coordinate system.
In order to realize method of the invention, using four core Ali's Cloud Servers, CPU frequency is 3.2GHz, and memory is 8G, behaviour Making system is Windows Server 2008；Local device CPU frequency is 3.4GHz, and memory is 8G, and operating system is Microsoft Windows 10.System layout is as shown in Fig. 2, the survey data of commune hospital and hospital is passed through this by disease control officer Ground equipment uploads to Cloud Server, and local server obtains required data from Cloud Server, while pre-processing to data, it Spatial clustering is carried out to fever crowd using non parameter modeling method afterwards, minimum circle-cover is used to each class in polymerization result Algorithm tab area range, user are checked by local device as a result, describing fever crowd spatial distribution, precisely for epidemic situation disposition Strong foundation is provided with mosquito dissipation decision.
Flow diagram of the present invention is as shown in Figure 1, this method shown in specific step is as follows:
The first step collects data and pretreatment.
The particulars of mosquito matchmaker infectious disease fever crowd are collected, including number, name, nationality, gender, the age, address, are stepped on Between clocking, body temperature, residence abscissa, residence ordinate, it is empty for removing residence abscissa or residence ordinate Data, while removing repeated data.
Second step, unsupervised clustering.
(1) it regard each fever individual as a sample, the residence abscissa and residence ordinate for choosing individual are made For sample information x, N is initializedcA class, is denoted asCorresponding to cluster centre is respectivelySjCluster in Heart zjMeetWherein NumjIndicate SjThe sample number for including, threshold value is arranged: K is pre- Phase cluster centre number, θNIt is the number of samples lower limit of every one kind, θSIt is the standard deviation upper limit of sample in class, θcIt is between cluster centre Minimum range, L is the maximum times of union operation in iteration；
(2) for each sample, calculating the sample to the Euclidean distance of each cluster centre, the nearest class of distance sample is found, Assuming that x to SjDistance meet Dx=min | | x-zj| |, j=1,2 ... Nc, wherein | | x-zj| | indicate x and zjEuclidean away from From then x ∈ Sj；
(3) if SjIn sample number Numj<θN, then such is deleted, NcSubtract 1；
(4) each cluster centre is updated,
(5) average distance of sample and cluster centre in each class is calculated
(6) the overall average distance of whole samples is calculatedIf merging at this time secondary Number enables θ more than Lc=0, (10) are gone to, if(7) are gone to, if the number of iterations is even number or Nc> 2K goes to (10), Otherwise (7) are gone to；
(7) standard deviation of the sample on each component in each class, σ are calculatedxjIndicate the abscissa standard deviation of jth class, σyjTable Show the ordinate standard deviation of jth class, remembers σj=(σxj, σyj)T, j=1,2 ... Nc；
(8) the largest component σ in each standard deviation is recordedjmax=max { σj, j=1,2 ... Nc}；
(9) in any largest component set, if meeting simultaneously:
σjmax>θS,Nj>2(θN+1)
Two samples in such are then randomly selected as cluster centre, such is decomposed into two classes, NcAdd 1, goes to (2), (10) are otherwise gone to；
(10) distance of whole cluster centres, D are calculatedij=| | zi-zj| |, i=1,2 ... Nc- 1, j=1,2 ... Nc, i ≠ j.By DijBy apart from incremental arrangement；
It (11) will be apart from for DijAnd Dij<θcCluster centre ziAnd zjMerge, obtain new cluster centre, is labeled as i-th Class, NcSubtract 1, while updating sample classification,
(12) if last time iteration, (13) are gone to, otherwise go to (2)；
(13) sample information that every one kind is included is obtained, all classes comprising a point are deleted, these points are not done Subsequent processing.
Third step, class is interior to run minimum circle-cover algorithm.
If the minimum circle-cover algorithm based on increment can find the area for covering and doing most in linear time complexity Small circle finds out central coordinate of circle and radius.
(1) assume to share N number of point, number consecutively P1,P2…Pi,…PN, 1≤i≤N, with P1And P2Justify for diameter work, if For Cx；
(2) all the points are successively scanned in order, if all the points are in CxIt is interior, return to CxFor final result, and exit the program, Otherwise it finds not in CxIt is interior, it is set as Pi, enter step (3)；
(3) it executes so far, illustrates CxNot comprising Pi, with P1And PiJustify for diameter work, is set as Cy, CyIt not necessarily include P1~Pi All the points, all the points are successively scanned in order, if all the points are in CyIt is interior, enable Cx=CyIt returns to (2) to execute, otherwise finds one Point is not in CyIt is interior, it is set as Pj, centainly have j < i at this time, enter step (4)；
(4) with P1And PjJustify for diameter work, is set as Cz, CzIt not necessarily include P1~PjAll the points, successively scan in order All the points, if all the points are in CzIt is interior, then more new circle Cx=CzIt returns to (2) to execute, otherwise finds a point PkNot in this circle, this When Pi, Pj, PkOne is scheduled on the boundary for updating circle, crosses Pi, Pj, Pk3 points of work circles simultaneously update Cx, return to (2) and execute.
A. the method for two o'clock distance is sought:
If the coordinate of two o'clock A and B are respectively (X in plane1, Y1) and (X2, Y2), the distance definition of A and B are
B. the method that two o'clock makees circle is crossed:
If the coordinate of two o'clock A and B are respectively (X in plane1, Y1) and (X2, Y2), using A, B line as the center of circle of the circle of diameter Coordinate is ((X1+X2)/2,(Y1+Y2)/2), radius is
C. the method for two o'clock perpendicular bisector is sought:
If the coordinate of two o'clock A and B are respectively (X in plane1, Y1) and (X2, Y2), the perpendicular bisector equation of AB two o'clock is (X1- X2)X+(Y1-Y2) Y=((X1 2-X2 2)+(Y1 2-Y2 2))/2。
D. the method for two straight-line intersections is sought:
If two straight lines are A1x+B1Y=C1And A2x+B2Y=C2, intersecting point coordinate:
X=(B2*C1-B1*C2)/(A1*B2-A2*B1)
Y=(A1*C2-A2*C1)/(A1*B2-A2*B1)
E. 3 points of methods for making circle are crossed:
If the coordinate of three point A, B and C is respectively (X in plane1, Y1)、(X2, Y2) and (X3, Y3):
If (X2-X1)(Y3-Y1)=(X3-X1)(Y2-X1), i.e. three point on a straight line calculates the distance of A, B two o'clock using a method, It is set as LAB, the maximum two o'clock of distance in 3 points is taken, L=max (L is metAB, LAC, LBC), this two o'clock work circle is crossed using b method and is returned Return result；
If (X2-X1)(Y3-Y1)≠(X3-X1)(Y2-X1), i.e., 3 points are not conllinear, and the method point of two o'clock perpendicular bisector is sought using c The perpendicular bisector equation for not obtaining AB two o'clock is denoted as A1X+B1Y=C1, the perpendicular bisector equation of BC two o'clock is denoted as A2X+B2Y=C2, utilize Asking the method d of two straight-line intersections to obtain the intersection point of two perpendicular bisectors is the center of circle, and the distance of the center of circle to A point is radius.
4th step, result visualization are presented.
Fever individual is plotted in plane right-angle coordinate in dots, while drawing minimum circle-cover, it is specific to open up Show as shown in Figure 3.The aggregation zone that round position and size reflection fever crowd are covered in Fig. 3, can be considered potential epidemic outbreak Area, user more accurately analyze epidemic situation diffusion tendency by the change procedure of viewing area, so that it is early to assist disease control officer to carry out The disposition of phase epidemic situation and early warning.
The above, the only specific embodiment in the present invention, but scope of protection of the present invention is not limited thereto, appoints What is familiar with the people of the technology within the technical scope disclosed by the invention, it will be appreciated that expects transforms or replaces, and should all cover Within scope of the invention, therefore, the scope of protection of the invention shall be subject to the scope of protection specified in the patent claim.

Claims (8)

  1. A kind of crowd's range flags method 1. mosquito matchmaker's infectious disease based on spatial clustering is generated heat, which is characterized in that including following step It is rapid:
    The first step is collected the particulars of mosquito matchmaker infectious disease fever crowd and is pre-processed to the coordinate data of individual；
    Second step, to treated, data use unsupervised clustering, obtain the individual coordinate data inside every one kind, delete Lonely class；
    Third step successively handles the individual coordinate data inside described every one kind using minimum circle-cover algorithm, obtains Several minimum circle-covers；
    4th step visualizes the minimum circle-cover of fever crowd spatial clustering.
  2. 2. according to the method described in claim 1, it is characterized by: in the step 1, the particulars of the fever crowd Including number, name, nationality, gender, age, address, enrollment time, body temperature, residence abscissa, residence ordinate.
  3. 3. according to the method described in claim 1, it is characterized by: in the step 1, the coordinate data of the individual includes The residence abscissa and residence ordinate of fever crowd.
  4. 4. including as follows according to the method described in claim 1, it is characterized by: pre-processed to the coordinate data of individual Process: removing residence abscissa or residence ordinate is empty data, removes repeated data.
  5. 5. according to the method described in claim 1, it is characterized by: unsupervised clustering is specific as follows in the step 2:
    (1) it regard each fever individual as a sample, the residence abscissa and residence ordinate for choosing individual are as sample This information x initializes NcA class, is denoted asCorresponding to cluster centre is respectivelySjCluster centre zj MeetWherein NumjIndicate SjThe sample number for including, threshold value is arranged: K is expected poly- Calculation in class, θNIt is the number of samples lower limit of every one kind, θSIt is the standard deviation upper limit of sample in class, θcBe between cluster centre most Small distance, L are the maximum times of union operation in iteration；
    (2) for each sample, calculating the sample to the Euclidean distance of each cluster centre, the nearest class of distance sample is found, it is assumed that x To SjDistance meet Dx=min | | x-zj| |, j=1,2 ... Nc, wherein | | x-zj| | indicate x and zjEuclidean distance, then x ∈Sj；
    (3) if SjIn sample number Numj<θN, then such is deleted, NcSubtract 1；
    (4) each cluster centre is updated,
    (5) average distance of sample and cluster centre in each class is calculated
    (6) the overall average distance of whole samples is calculatedIf it is super to merge number at this time L is crossed, θ is enabledc=0, (10) are gone to, if(7) are gone to, if the number of iterations is even number or Nc> 2K goes to (10), otherwise Go to (7)；
    (7) standard deviation of the sample on each component in each class, σ are calculatedxjIndicate the abscissa standard deviation of jth class, σyjIndicate jth The ordinate standard deviation of class remembers σj=(σxj, σyj)T, j=1,2 ... Nc；
    (8) the largest component σ in each standard deviation is recordedjmax=max { σj, j=1,2 ... Nc}；
    (9) in any largest component set, if meeting simultaneously:
    σjmax>θS,Nj>2(θN+1)
    Two samples in such are then randomly selected as cluster centre, such is decomposed into two classes, NcAdd 1, goes to (2), it is no Then go to (10)；
    (10) distance of whole cluster centres, D are calculatedij=| | zi-zj| |, i=1,2 ... Nc- 1, j=1,2 ... Nc, i ≠ j will DijBy apart from incremental arrangement；
    It (11) will be apart from for DijAnd Dij<θcCluster centre ziAnd zjMerge, obtain new cluster centre, is labeled as the i-th class, Nc Subtract 1, while updating sample classification,
    (12) if last time iteration, (13) are gone to, otherwise go to (2)；
    (13) sample information that every one kind is included is obtained.
  6. 6. according to the method described in claim 1, it is characterized by: orphan's class refers to only comprising one in the step 2 The class of point.
  7. 7. according to the method described in claim 1, it is characterized by: if the minimum circle-cover refers to comprising the area done most Small circle is distributed in circle or on circumference if these are done.
  8. 8. according to the method described in claim 1, it is characterized by: minimum circle-cover algorithm is specific as follows in the step 3:
    (1) assume to share N number of point, number consecutively P1,P2…Pi,…PN, 1≤i≤N, with P1And P2Justify for diameter work, is set as Cx；
    (2) all the points are successively scanned in order, if all the points are in CxIt is interior, return to CxIt for final result, and exits, otherwise finds Not in CxIt is interior, it is set as Pi, enter step (3)；
    (3) it executes so far, illustrates CxNot comprising Pi, with P1And PiJustify for diameter work, is set as Cy, CyIt not necessarily include P1~PiInstitute A little, all the points are successively scanned in order, if all the points are in CyIt is interior, enable Cx=CyIt returns to (2) to execute, otherwise find not In CyIt is interior, it is set as Pj, centainly have j < i at this time, enter step (4)；
    (4) with P1And PjJustify for diameter work, is set as Cz, CzIt not necessarily include P1~PjAll the points, successively scanning is all in order Point, if all the points are in CzIt is interior, then more new circle Cx=CzIt returns to (2) to execute, otherwise finds a point PkNot in this circle, P at this timei, Pj, PkOne is scheduled on the boundary for updating circle, crosses Pi, Pj, Pk3 points of work circles simultaneously update Cx, return to (2) and execute.
CN201811490660.7A 2018-12-07 2018-12-07 Mosquito-borne infectious disease fever crowd range marking method based on space aggregation Active CN109670541B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811490660.7A CN109670541B (en) 2018-12-07 2018-12-07 Mosquito-borne infectious disease fever crowd range marking method based on space aggregation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811490660.7A CN109670541B (en) 2018-12-07 2018-12-07 Mosquito-borne infectious disease fever crowd range marking method based on space aggregation

Publications (2)

Publication Number Publication Date
CN109670541A true CN109670541A (en) 2019-04-23
CN109670541B CN109670541B (en) 2020-09-29

Family

ID=66143661

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811490660.7A Active CN109670541B (en) 2018-12-07 2018-12-07 Mosquito-borne infectious disease fever crowd range marking method based on space aggregation

Country Status (1)

Country Link
CN (1) CN109670541B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111816297A (en) * 2020-03-31 2020-10-23 复旦大学附属中山医院 Cloud-based nCoV virus diagnosis and treatment system and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080279420A1 (en) * 2004-01-22 2008-11-13 Masticola Stephen P Video and audio monitoring for syndromic surveillance for infectious diseases
CN103093106A (en) * 2013-01-25 2013-05-08 上海市浦东新区疾病预防控制中心 Multi-source communicable disease symptom monitoring and early-warning method in large-scale activity
CN105825049A (en) * 2009-10-19 2016-08-03 提拉诺斯公司 Integrated health data capture and analysis system
CN107256327A (en) * 2017-05-05 2017-10-17 中国科学院深圳先进技术研究院 A kind of infectious disease preventing control method and system
CN108498080A (en) * 2018-04-10 2018-09-07 中山市徕康医疗信息软件技术有限公司 A kind of fever epidemic situation rapid screening and the intelligent public affairs of management defend service system
CN108695003A (en) * 2018-08-07 2018-10-23 中山市徕康医疗信息软件技术有限公司 A kind of cloud management system and method that fever epidemic situation monitors and traces to the source

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080279420A1 (en) * 2004-01-22 2008-11-13 Masticola Stephen P Video and audio monitoring for syndromic surveillance for infectious diseases
CN105825049A (en) * 2009-10-19 2016-08-03 提拉诺斯公司 Integrated health data capture and analysis system
CN103093106A (en) * 2013-01-25 2013-05-08 上海市浦东新区疾病预防控制中心 Multi-source communicable disease symptom monitoring and early-warning method in large-scale activity
CN107256327A (en) * 2017-05-05 2017-10-17 中国科学院深圳先进技术研究院 A kind of infectious disease preventing control method and system
CN108498080A (en) * 2018-04-10 2018-09-07 中山市徕康医疗信息软件技术有限公司 A kind of fever epidemic situation rapid screening and the intelligent public affairs of management defend service system
CN108695003A (en) * 2018-08-07 2018-10-23 中山市徕康医疗信息软件技术有限公司 A kind of cloud management system and method that fever epidemic situation monitors and traces to the source

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵恒: "山东地区罕见疾病流行病学现状调差研究及分析", 《中国优秀硕士论文全文数据库（电子期刊）》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111816297A (en) * 2020-03-31 2020-10-23 复旦大学附属中山医院 Cloud-based nCoV virus diagnosis and treatment system and method

Also Published As

Publication number Publication date
CN109670541B (en) 2020-09-29

Similar Documents

Publication Publication Date Title
Wang et al. Privacy-enhanced data collection based on deep learning for internet of vehicles
Houssein et al. Improved manta ray foraging optimization for multi-level thresholding using COVID-19 CT images
Liu et al. Classifying urban land use by integrating remote sensing and social media data
Grubesic On the application of fuzzy clustering for crime hot spot detection
Yin et al. Region search based on hybrid convolutional neural network in optical remote sensing images
US10460252B2 (en) System and method of chaining algorithms for global object recognition to improve probability of correctness and reduce processing load
Oyewole et al. Data clustering: application and trends
Du et al. Representation and discovery of building patterns: A three-level relational approach
CN110738247A (en) fine-grained image classification method based on selective sparse sampling
CN112749743B (en) Track space-time clustering method, system and storage device
US20230089148A1 (en) Systems and methods for interactive image scene graph pattern search and analysis
Yu et al. Predicting protein complex in protein interaction network-a supervised learning based method
CN113807399A (en) Neural network training method, neural network detection method and neural network detection device
Peters Quadtree-and octree-based approach for point data selection in 2D or 3D
Wang et al. Pulmonary diffuse airspace opacities diagnosis from chest X-ray images using deep convolutional neural networks fine-tuned by whale optimizer
Oku et al. Tweet-mapping method for tourist spots based on now-tweets and spot-photos
CN110489613B (en) Collaborative visual data recommendation method and device
Liu et al. Auto-sharing parameters for transfer learning based on multi-objective optimization
Wei et al. Linear building pattern recognition in topographical maps combining convex polygon decomposition
Zeng et al. Modeling spatial nonstationarity via deformable convolutions for deep traffic flow prediction
Gao et al. Quantifying animal trajectories using spatial aggregation and sequence analysis: a case study of differentiating trajectories of multiple species
Dong et al. Browsing behavior modeling and browsing interest extraction in the trajectories on web map service platforms
CN109670541A (en) A kind of mosquito matchmaker&#39;s infectious disease fever crowd&#39;s range flags method based on spatial clustering
CN111506832B (en) Heterogeneous object completion method based on block matrix completion
Poccia et al. SIMDMS: Data management and analysis to support decision making through large simulation ensembles

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant