CN109489665A - A kind of people based on resource allocation takes refuge the position predicting method and its system of whereabouts - Google Patents
A kind of people based on resource allocation takes refuge the position predicting method and its system of whereabouts Download PDFInfo
- Publication number
- CN109489665A CN109489665A CN201811317487.0A CN201811317487A CN109489665A CN 109489665 A CN109489665 A CN 109489665A CN 201811317487 A CN201811317487 A CN 201811317487A CN 109489665 A CN109489665 A CN 109489665A
- Authority
- CN
- China
- Prior art keywords
- people
- dimensional model
- distance
- predicting method
- environment body
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to public safety technical field, in particular to a kind of people based on resource allocation takes refuge the position predicting method and its system of whereabouts；The present invention first constructs two-dimensional model；Determined in two-dimensional model again the saturation of environment body, disaster point position, people position and outlet port, may thereby determine that out the position and the position of disaster point position distance S and people and outlet port distance D of people；Then the position of people is calculated at a distance from the available environment body gone；And people is calculated again in the position of subsequent time；Real-time circulation carries out previous step, until obtaining the final position of people settled out；The present invention adds additional the dynamic adjustment of resource, and resource is also dynamic consumption and few using data while ensuring that information change in this way, and practical operation is convenient.
Description
Technical field
The present invention relates to public safety technical field, in particular to a kind of people based on resource allocation takes refuge the positions of whereabouts
Prediction technique and its system.
Background technique
As the growth of China human mortality and social public character are movable frequent occurrence, the in emergency circumstances public in public
Evacuation has reformed into a severe problem.
In densely populated public place, when the emergencies such as fire, explosion, gunslinging occur, riot can occur often for crowd,
Probably there is tread event, if reasonably act of rescue measure can be taken, rationally evacuate crowd, can avert a calamity
Event.
Summary of the invention
It takes refuge the position prediction of whereabouts the invention mainly solves the technical problem of providing a kind of people based on resource allocation
Method, by building two-dimensional model, so as in two-dimensional model it can be seen that everyone position, thus
Receiving crowd is carried out using the environment body in place to take refuge, and be can be convenient commander and separated out the close people of mouth to outlet movement；This
Invention also provides a kind of people based on the resource allocation position prediction system for taking refuge whereabouts.
In order to solve the above technical problems, one technical scheme adopted by the invention is that: it provides a kind of based on resource allocation
People takes refuge the position predicting methods of whereabouts, wherein includes the following steps:
Step S1, two-dimensional model is constructed；
Step S2, saturation, disaster point position, the position of people and the outlet position of environment body are determined in two-dimensional model
It sets, may thereby determine that out the position and the position of disaster point position distance S and people and outlet port distance D of people；
Step S3, the position of people is calculated at a distance from the available environment body gone；
Step S4, people is calculated in the position of subsequent time；
Step S5, circulation carries out step S4, until obtaining the final position of people settled out.
As an improvement of the present invention, in step S2, the saturation C=2 of environment bodyT/10。
As a further improvement of the present invention, in step S2, in two-dimensional model, parameter regulation is carried out: current
Impact factor caused by environment body accumulated number: F (wi)=1-C/Ki, wherein KiThe maximum of current environment body is represent to accommodate
Amount.
As a further improvement of the present invention, position and the available environment body gone in step S3, as forefathers
Distance:Wherein, xcRepresent the position of people.
As a further improvement of the present invention, in step S3, in two-dimensional model, the position and outlet position of people
The definition of the influence utility function for the distance set:
As a further improvement of the present invention, in step S3, in two-dimensional model, the moving rail of the position of people
Mark relation formula:
As a further improvement of the present invention, in step S4, calculating of the particular individual in the position at t-1 moment is public
Formula:
Calculation formula of all individuals in the position at t-1 moment in two-dimensional model:
GBest=max (Fitness (xi))；s.t.
As a further improvement of the present invention, in step S5, the calculation formula for the final position of people settled out:
V (t)=v (t-1)+c1*r1* (gBest-x (t-1))+c2*r2* (pBest-x (t-1))；
X (t)=x (t-1)+v (t).
A kind of people based on resource allocation takes refuge the position prediction systems of whereabouts, wherein includes:
Module is constructed, for constructing two-dimensional model；
Acquisition module, for acquired in two-dimensional model the saturation of environment body, disaster point position, people position and
Outlet port；
Obtain module, for determined according to the information of the acquisition module position of people at a distance from disaster point position and
The position of people is at a distance from outlet port；
Computing module, parameter and calculation formula for two-dimensional model are calculated in conjunction with the information for obtaining module
The position of people is at a distance from the available environment body gone out and people is in the position of subsequent time, so that it is determined that people's settles out
Final position.
As an improvement of the present invention, further includes:
Module is estimated, for estimating in two-dimensional model people in subsequent time according to the information for obtaining module
Position provides information to the computing module.
The beneficial effects of the present invention are: compared with prior art, the present invention adds additional the dynamic adjustment of resource, in this way
Resource is also dynamic consumption and few using data while ensuring that information change, and practical operation is convenient.
Detailed description of the invention
Fig. 1 be the people of the invention based on resource allocation take refuge whereabouts position predicting method method and step block diagram；
Fig. 2 is the coordinatograph schematic diagram of present invention building model；
Fig. 3 is flow diagram of the invention；
Fig. 4 be the people of the invention based on resource allocation take refuge whereabouts position prediction system connection block diagram.
Specific embodiment
Present existing position predicting method be all much half dynamic (variation for being unable to real-time update resource) even some
Method is pure static state, cannot be gone to adjust prediction constantly according to the variation of resource in the process on the final position of prediction crowd movement
Result.
Particle swarm algorithm (Particle Swarm) updates the position of each particle by shared resource mutual between particle
In the hope of reaching best state or best conditions present.Since shared information updates oneself row in this algorithm and crowd
The thinking of route is walked very close to, the present invention by the resource status and dynamic particles group's algorithm for proposing of the application near position
(Particle Swarm Dynamics) is effectively combined, and forms crowd (i.e. particle) movement side in a prediction a period of time
To and the method that determines its during this period of time final position.
Particle swarm algorithm is a kind of heuristic search algorithm based on population optimizing, it has used for reference such thought, each
Particle represents a potential solution in problem search solution space to be solved, it is equivalent to a bird, and " flight information " includes particle
Current two quantity of states of position and speed.Each particle can obtain the information of other individuals in its neighborhood, to being passed through
Position evaluated, and rule is updated according to these information and position and speed, changes two quantity of states of itself, in " flight "
Information is transmitted in the process and is learnt from each other, and goes to better adapt to environment.With the continuous progress of this process, the final energy of population
Enough find the approximate optimal solution of problem；The present invention predicts the position that crowd finally assembles using the result that this process generates.
It is considered that the change in location of crowd is instantaneous and is mutual exchange of information under occasion and disaster, it is assumed here that people
Thinking be substantially rationality and their motion state be to influence each other.
As shown in Figure 1 to Figure 3, the present invention provides a kind of people based on the resource allocation position predicting method for taking refuge whereabouts,
Include the following steps:
Step S1, two-dimensional model is constructed；
Step S2, saturation, disaster point position, the position of people and the outlet position of environment body are determined in two-dimensional model
It sets, may thereby determine that out the position and the position of disaster point position distance S and people and outlet port distance D of people；
Step S3, the position of people is calculated at a distance from the available environment body gone；
Step S4, people is calculated in the position of subsequent time；
Step S5, circulation carries out step S4, until obtaining the final position of people settled out.
Compared with prior art, the present invention adds additional the dynamic adjustment of resource, ensures that information change in this way
Resource is also dynamic consumption and few using data simultaneously, and practical operation is convenient.
In the present invention, variable below is constructed:
(1) Carrying capacity C；
(2) the position F of distance outlet；
(3) the position S of disaster point, refers here to the coordinate in two-dimensional model；
(4) current location and it can choose the distance between position of environment body dist (xc, wi)。
Wherein, environment body can specifically Subjects such as shop, sanctuary, the field that the crowd of can be used as takes refuge
Institute.
The present invention provides the formalization representation of above-mentioned four kinds of dynamic variables (namely resource dynamic change): (1) environment
Saturation C (2) distance outlet position F (3) disaster point (4) current location position S and can choose between environment body away from
From dist (xc, wi), then model a model；Mentioned-above dynamic particles group is recycled to combine four kinds of above-mentioned dynamics
The model of structure's variable provides a crowd position evolutionary process and final position.
Wherein, in step S2, the saturation C=2 of environment bodyT/10, the saturation of environment body is design present system
The quantity for the people that the receiving field estimated in advance can accommodate.
Further, in step S2, in two-dimensional model, carry out parameter regulation: current environment body accumulated number is made
At impact factor: F (wi)=1-C/Ki, wherein KiRepresent the maximum capacity of current environment body.
Further, in step S3, when the position of forefathers is at a distance from the available environment body gone:Wherein, xcRepresent the position of people.
In step S3, in two-dimensional model, influence utility function of the position of people at a distance from outlet port
Definition:
In step S3, in two-dimensional model, the motion track relation formula of the position of people:
It can be convenient dopester by the motion track of the position of above-mentioned people or policymaker make reasonably decision, in time
It is scheduled adjustment, to disperse with making crowd massing, is unlikely to crowd's heap.
Further, in step S4, calculation formula of the particular individual in the position at t-1 moment:
By above-mentioned calculating individual in the position at t-1 moment, people can be predicted in the position of next step, which adopts
It is local optimum mode, prediction is drawn close toward global optimum in next step, during which belongs in entire scheme
Between process, therefore referred to as local optimum.
Calculation formula of all individuals in the position at t-1 moment in two-dimensional model:
GBest=max (Fitness (xi))；s.t.
Further, in step S5, the calculation formula for the final position of people settled out: v (t)=v (t-1)+c1*
r1*(gBest-x(t-1))+c2*r2*(pBest-x(t-1))；
X (t)=x (t-1)+v (t).
By the calculating of above-mentioned final position, the final position of people can be predicted, so as to guide crowd, Bu Huizao
At crowded situation, which combines continually changing situation, while its iterative process is uncomplicated, only depends on front
Process, consequently facilitating prediction, in addition its update mode be supported with particle swarm algorithm, and be added dynamic amount be integrated into
Row, to facilitate calculating, prediction calculates accurate.
The present invention provides one embodiment, and as shown in Figures 2 and 3, specific method detailed is as follows:
Firstly, by everyone (i.e. particle) and environment body (the specifically Subjects such as shop, sanctuary) grid
One content indicated with two-dimensional plane coordinate of chemical conversion, as shown in Fig. 2, each the human and environment body next mentioned has
This position attribution, wherein the position of people changes over time.
As shown in Fig. 2, black dot represents everyone in figure, light rectangle represents environment body, and dark rectangle represents
The position of case point outburst, rectangular frame represent outlet, and all distances measure the calculating that mode is Euclidean distance in space,
As the distance between two object central points to be calculated are indicated with double-head arrow in figure.
As shown in figure 3, (1,2 ... n) represents the position of Different Individual to P in figure.Algorithm can be according to many times resource updates
It is recycled, until reaching the termination condition set, resource refers to the condition information of people's variation herein, that is to say, that ring
The position F and position S apart from disaster point of border saturation C distance outlet, current location and can choose between environment body away from
From shared resource between particle, shared is exactly the information such as position and speed, specifically just says be exactly sharing or to perceive between particle
A kind of variation of (with the crowd and perception) these dynamic amounts, disaster point position is exactly a kind of bad resource, forms negative-feedback；This
Place's termination condition refers to that time or external force stop, such as: if the entire process of taking refuge only lasts for 1 hour, one
Hour is exactly termination condition, and external force stopping means to assume that there is no accident generations for disaster point at this time, or stops, then this
Process just stopped, and setting the condition helps to understand when we terminate from certain time period, for what state,
Help to judge that in disaster, the time lasting is estimated.
1, four kinds of dynamic variable representation methods:
It is environment body saturation C=2 firstT/10, the unit of T is the second here, herein T, this is to represent environment at any time
Body saturation gradually increases, that is to say, that environment body saturation is a function about the time, and still, the time is that have
Limit range.
；The position D=F of distance outlet3, F refers to the distance between environment body and the outlet that everyone wants to go to here,
F is exactly the estimator that people adjusts the distance；The effect generated when distance S between point occurs for the position of forefathers and event or disaster
With function log10S, cooperation formula (5.3) is not linear increase because crowd is to the fear of the position of disaster point herein, and
First to increase, to certain distance after hardly change, this utility function log10S meets this requirement.
；When the position of forefathers is at a distance from the available environment body gone:
X in formula 5.1cThe position that represent people, be one is indicated by the position that (x, y) plane coordinates is constituted, similarly
For the position w of environment bodyiCarry out plane coordinates.
2, the building of the adjustment parameter of model: before Definition Model, we first provide definition some in this way:
(a) impact factor as caused by current environment body accumulated number:
F(wi)=1-C/Ki(5.2)
Wherein, KiEnvironment body maximum capacity is represent, this value is a given constant value, and represent maximum can hold
The number received；Here, F (wi) small, the people gone is just more, such as F (wi) greatly, the people gone is just more, acts on formula (5.4), fitness
Function can become larger, that is, more adapt to, that is to say, that the people gone is more, then the people for perceiving this information is more, also just not
It can go again, for example, earthquake relief point, people is more, and people can change place.
For example, that goes is more, then the people for perceiving this information is more, would not also go again.Like ground
Shake disaster relief point, people is more, and people can change place.The people gone is more, and minuend is bigger, this F will be smaller, if the people gone is few,
This F will become larger, then acting on 5.4 formula, fitness function can become larger, that is, more adapt to.
(b) after having defined (5.2), a comprehensive distance utility function is re-defined:
Wherein, formula 5.3 increases the impact factor F away from outlet distance to actual range first3/ 100, it examines simultaneously
The effect for considering event central point when event occurs, increases a fluctuation factor and is written as log10S, this is also that this model is ingenious
Place, increases very practical and powerful effect factor i.e. formula (5.2) and (5.3) a embodiment, and such increase makes
This method closer to crowd's true position selection course during exercise；Make formula (5.3) that counting accuracy can be improved.
3, the calculating of model: the model mathematics is expressed as follows:
What this model was substantially abstracted is that crowd obtains during exercise and what subjectivity was got is used to judge next time
Information.This fitness model i.e. this function, which will will use, to be calculated evolutionary process in PSD method and predicts final evolution result
On.This fitness model is most important to PSD model, like the engine in automobile.
4, crowd's location updating rule: come the position of real-time update crowd using three rules, because of everyone position
Setting is made of speed (which includes directions) and current location, so operating speed updates regular (formula 5.8), the overall situation
Location updating rule (formula 5.6), local location update regular (formula 5.7) three to determine the position of next moment people.
The formula for updating rule is as follows:
X (t)=x (t-1)+v (t) (5.5)
GBest=max (Fitness (xi))；s.t.
V (t)=v (t-1)+c1*r1* (gBest-x (t-1))+c2*r2* (pBest-x (t-1)) (5.8)
Wherein, gBest represents optimal position in all motion units of t-1 at this time, and pBest represents a certain specific
Body t-1 moment optimal position, by combining formula (5.6) and (5.7) come more new formula (5.8), the existing speed of v (t) at this time
Degree also has direction, then can be obtained by the optimum position of subsequent time t, Huo Zheke in conjunction with formula (5.6), (5.7) and (5.8)
To be expressed as the position that individual will occur.
In this embodiment, we can be simulated any time by providing in conjunction with four dynamic resources i.e. four kinds of variables
It is extensive individual where position, simultaneously as the real-time update of resource and the dynamic of algorithm adjustment, realize mobilism mould
The process of quasi- position.The process determines that final state can first exhaust time conditions or a certain item resource as termination
Condition so far can find out the position that final individual is settled out with resource dynamic change, that is, formula (5.5)
Reflected x (t)；We can be obtained by the predicted position of crowd at this time and final position by calculating x (t).The mistake
Journey is simulated fled from market crisis evacuation or natural calamity in crowd course location and final position (formula
5.5) it, can not only determine pilot process, but also can predict final result.
As shown in figure 4, take refuge the position prediction system of whereabouts the present invention also provides a kind of people based on resource allocation, packet
It includes:
Module is constructed, for constructing two-dimensional model；
Acquisition module, for acquired in two-dimensional model the saturation of environment body, disaster point position, people position and
Outlet port；
Obtain module, for determined according to the information of the acquisition module position of people at a distance from disaster point position and
The position of people is at a distance from outlet port；
Module is estimated, for estimating in two-dimensional model people in subsequent time according to the information for obtaining module
Position provides information to the computing module；
Computing module, parameter and calculation formula for two-dimensional model are calculated in conjunction with the information for obtaining module
The position of people is at a distance from the available environment body gone out and people is in the position of subsequent time, so that it is determined that people's settles out
Final position.
In the present invention, it has the advantages that
1, the present invention is by the calculating of environment body and formula (5.3) and public affairs first compared with traditional particle swarm algorithm
Formula (5.4) adds additional the dynamic adjustment of resource on model, and resource is also dynamic while ensuring that information change in this way
Consumption, practicability is stronger compared with conventional particle group's algorithm.
2, few using data, it is only necessary to the initial position of individual and environment body, and four kinds of initial variables, however this four
Kind variable is all objective fixed numbers, these data once can be obtained by, and greatly reduces data volume, simplifies and simulated
Journey；That is only need case point position, environment body (body of taking refuge) position, objective position coordinates and common crowd's flow etc. basic
Information.
3, in mock disaster crowd position, this traditionally predicts that too difficult (Classical forecast, which considers, many influences people
The factor of group's judgement), and be not easy practical operation, many data have error (previous model, what is used is passageway for fire apparatus,
It is this not look after actual conditions completely close to certain specific resources, it is that in a hurry, just will form this later first under emergency case
Kind rationality aggregation, so just starting the resource of setting, instead causing model over-fitting, error is very big, does not have robustness), originally
What invention was chosen is all objective not error-prone data, and gives a general solution, may be not so good as in precision
Big data calculates accurate, but the function of doing a prediction is very practical and cost very little, sacrifices some precision
Inexpensive prediction is brought；Factor of the invention is concentrated mainly on case point position and Carrying capacity, remaining is all constantly more
New and Particles Moving exchange information obtains.
Mode the above is only the implementation of the present invention is not intended to limit the scope of the invention, all to utilize this
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field is included within the scope of the present invention.
Claims (10)
- The position predicting method of whereabouts 1. a kind of people based on resource allocation takes refuge, which comprises the steps of:Step S1, two-dimensional model is constructed；Step S2, determined in two-dimensional model the saturation of environment body, disaster point position, people position and outlet port, It may thereby determine that out the position and the position of disaster point position distance S and people and outlet port distance D of people；Step S3, the position of people is calculated at a distance from the available environment body gone；Step S4, people is calculated in the position of subsequent time；Step S5, circulation carries out step S4, until obtaining the final position of people settled out.
- 2. position predicting method according to claim 1, which is characterized in that in step S2, the saturation C=2 of environment bodyT /10。
- 3. position predicting method according to claim 2, which is characterized in that in step S2, in two-dimensional model, into Row parameter regulation: impact factor caused by current environment body accumulated number: F (wi)=1-C/Ki, wherein KiIt represents and works as front ring The maximum capacity of border body.
- 4. position predicting method according to claim 3, which is characterized in that in step S3, when forefathers position with for Select the distance of the environment body gone:Wherein, xcRepresent the position of people It sets.
- 5. position predicting method according to claim 4, which is characterized in that in step S3, in two-dimensional model, people Influence utility function of the position at a distance from outlet port definition:
- 6. position predicting method according to claim 5, which is characterized in that in step S3, in two-dimensional model, people Position motion track relation formula:
- 7. position predicting method according to claim 6, which is characterized in that in step S4, particular individual is at the t-1 moment The calculation formula of position:Calculation formula of all individuals in the position at t-1 moment in two-dimensional model:
- 8. position predicting method according to claim 7, which is characterized in that in step S5, settling out for people is final The calculation formula of position: v (t)=v (t-1)+c1*r1* (gBest-xt-1+c2*r2*pBest-xt-1；X (t)=x (t-1)+v (t).
- The position prediction system of whereabouts 9. a kind of people based on resource allocation takes refuge characterized by comprisingModule is constructed, for constructing two-dimensional model；Acquisition module, for acquired in two-dimensional model the saturation of environment body, disaster point position, people position and outlet Position；Module is obtained, for determining the position of people at a distance from disaster point position and people according to the information of the acquisition module Position is at a distance from outlet port；Computing module, parameter and calculation formula for two-dimensional model calculate people in conjunction with the information for obtaining module Position is at a distance from the available environment body gone and people is in the position of subsequent time, so that it is determined that people's settles out most Final position is set.
- 10. position prediction system according to claim 9, which is characterized in that further include:Module is estimated, for estimating in two-dimensional model people in the position of subsequent time according to the information for obtaining module Information is provided to the computing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317487.0A CN109489665B (en) | 2018-11-07 | 2018-11-07 | Method and system for predicting position of people refuge track based on resource allocation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811317487.0A CN109489665B (en) | 2018-11-07 | 2018-11-07 | Method and system for predicting position of people refuge track based on resource allocation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109489665A true CN109489665A (en) | 2019-03-19 |
| CN109489665B CN109489665B (en) | 2020-07-24 |
Family
ID=65693934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811317487.0A Active CN109489665B (en) | 2018-11-07 | 2018-11-07 | Method and system for predicting position of people refuge track based on resource allocation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109489665B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101515309A (en) * | 2009-04-07 | 2009-08-26 | 华中科技大学 | City emergency evacuation simulation system based on multi intelligent agent |
| CN103279800A (en) * | 2013-01-10 | 2013-09-04 | 吉林大学 | Game theory-based optimal escape route generating method for large-scale crowd evacuation |
| CN103679264A (en) * | 2013-12-23 | 2014-03-26 | 山东师范大学 | Crowd evacuation path planning method based on artificial fish swarm algorithm |
| CN103913165A (en) * | 2014-04-18 | 2014-07-09 | 中国地质大学（武汉） | Indoor emergency response and context awareness navigation system and method |
| CN104361178A (en) * | 2014-11-20 | 2015-02-18 | 湖北工业大学 | Indoor evacuation simulating optimization method based on potential energy driving cellular ant colony algorithm |
| CN105550484A (en) * | 2016-02-26 | 2016-05-04 | 武汉大学 | Dynamic data driven modeling and simulation method for crowd evacuation and transportation behaviors in sudden-onset disaster |
| CN107292064A (en) * | 2017-08-09 | 2017-10-24 | 山东师范大学 | A kind of crowd evacuation emulation method and system based on many ant colony algorithms |
| CN107463751A (en) * | 2017-08-10 | 2017-12-12 | 山东师范大学 | A kind of crowd based on DBSCAN clustering algorithms by half is grouped evacuation emulation method and system |
| WO2018136204A1 (en) * | 2017-01-17 | 2018-07-26 | 3AM Innovations LLC | Tracking and accountability device and system |
-
2018
- 2018-11-07 CN CN201811317487.0A patent/CN109489665B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101515309A (en) * | 2009-04-07 | 2009-08-26 | 华中科技大学 | City emergency evacuation simulation system based on multi intelligent agent |
| CN103279800A (en) * | 2013-01-10 | 2013-09-04 | 吉林大学 | Game theory-based optimal escape route generating method for large-scale crowd evacuation |
| CN103679264A (en) * | 2013-12-23 | 2014-03-26 | 山东师范大学 | Crowd evacuation path planning method based on artificial fish swarm algorithm |
| CN103913165A (en) * | 2014-04-18 | 2014-07-09 | 中国地质大学（武汉） | Indoor emergency response and context awareness navigation system and method |
| CN104361178A (en) * | 2014-11-20 | 2015-02-18 | 湖北工业大学 | Indoor evacuation simulating optimization method based on potential energy driving cellular ant colony algorithm |
| CN105550484A (en) * | 2016-02-26 | 2016-05-04 | 武汉大学 | Dynamic data driven modeling and simulation method for crowd evacuation and transportation behaviors in sudden-onset disaster |
| WO2018136204A1 (en) * | 2017-01-17 | 2018-07-26 | 3AM Innovations LLC | Tracking and accountability device and system |
| CN107292064A (en) * | 2017-08-09 | 2017-10-24 | 山东师范大学 | A kind of crowd evacuation emulation method and system based on many ant colony algorithms |
| CN107463751A (en) * | 2017-08-10 | 2017-12-12 | 山东师范大学 | A kind of crowd based on DBSCAN clustering algorithms by half is grouped evacuation emulation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 万江华等: "粒子群算法在应急疏散中的应用研究", 《中国人民公安大学学报（自然科学版）》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109489665B (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11747155B2 (en) | Global path planning method and device for an unmanned vehicle | |
| CN103440645B (en) | A kind of target tracking algorism based on adaptive particle filter and rarefaction representation | |
| Liu et al. | Traffic flow combination forecasting method based on improved LSTM and ARIMA | |
| US20190325334A1 (en) | Method for predicting air quality with aid of machine learning models | |
| CN110222769B (en) | Improved target detection method based on YOLOV3-tiny | |
| CN109558937A (en) | The operating method of nerve network system and nerve network system | |
| CN110481536B (en) | Control method and device applied to hybrid electric vehicle | |
| CN114519302B (en) | Highway traffic situation simulation method based on digital twinning | |
| CN113033712A (en) | Multi-user cooperative training people flow statistical method and system based on federal learning | |
| CN110288160A (en) | A kind of situation dynamic prediction method based on parallel simulation | |
| CN111444786A (en) | Crowd evacuation method, device and system based on unmanned aerial vehicle group and storage medium | |
| CN115329865A (en) | Driving condition identification method based on multi-core learning support vector machine | |
| CN114167898A (en) | Global path planning method and system for data collection of unmanned aerial vehicle | |
| CN113701742A (en) | Mobile robot SLAM method based on cloud and edge fusion calculation | |
| CN114092793A (en) | End-to-end biological target detection method suitable for complex underwater environment | |
| CN117408405A (en) | Edge computing power deconstructing and intelligent scheduling method based on traffic computing network | |
| CN116017476A (en) | Wireless sensor network coverage design method and device | |
| CN112989952B (en) | Crowd density estimation method and device based on mask guidance | |
| CN118012107A (en) | Synchronous coordination control method and system for unmanned aerial vehicle clusters | |
| CN109489665A (en) | A kind of people based on resource allocation takes refuge the position predicting method and its system of whereabouts | |
| CN111273697A (en) | Unmanned aerial vehicle group burst release method | |
| Jamil et al. | A novel hybrid strategy based on Swarm and Heterogeneous Federated Learning using model credibility awareness for activity recognition in cross-silo multistorey building | |
| CN110474803B (en) | Processing method of Internet of vehicles system and related equipment | |
| CN115640106B (en) | Man-machine function distribution method and system for multi-unmanned aerial vehicle command control | |
| CN116817903B (en) | Priori vision guidance-based intelligent robot global positioning method and system |
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 |