CN110543975B - Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy - Google Patents
Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy Download PDFInfo
- Publication number
- CN110543975B CN110543975B CN201910745402.7A CN201910745402A CN110543975B CN 110543975 B CN110543975 B CN 110543975B CN 201910745402 A CN201910745402 A CN 201910745402A CN 110543975 B CN110543975 B CN 110543975B
- Authority
- CN
- China
- Prior art keywords
- evacuation
- algorithm
- entropy
- crowd
- correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a crowd evacuation path optimization method based on a group intelligent algorithm and an evacuation entropy, which is executed by a computer and comprises the following specific steps: step S1: constructing an evacuation environment; step S2: initializing parameters of an evacuated crowd and an evacuation path; step S3: dividing the population into a plurality of small populations based on a k-means clustering algorithm; step S4: all individuals perform position updating based on a hybrid artificial bee colony-bat algorithm; step S5: all individuals carry out position correction based on evacuation entropy; step S6: obstacle avoidance is carried out on all individuals; step S7: and if the algorithm does not reach the end condition, returning to the step S4, otherwise, ending the algorithm and finishing evacuation. Compared with the prior art, the invention has the advantages of richer evacuation behaviors, more accordance evacuation motion with the real situation, higher evacuation efficiency and the like.
Description
Technical Field
The invention relates to a crowd evacuation method, in particular to a crowd evacuation path optimization method based on a group intelligent algorithm and an evacuation entropy.
Background
The occurrence of the crowded trampling event often causes the serious casualties of property personnel, so that the research on the crowd evacuation problem has very important significance and value. Due to the particularity of the evacuation problem, actual evacuation data under various emergency situations are difficult to obtain, for example, under a real fire, most of video data are damaged, so that the real data are difficult to store quantitatively. The evacuation drilling is difficult to simulate the psychological and other conditions of the evacuated people under the real condition, so that certain difference exists between the drilling data and the real data. Therefore, it is necessary to simulate the evacuation behavior of people by using a computer means.
At present, crowd evacuation models are mainly divided into microscopic models, mesoscopic models and macroscopic models. The micro model is a mainstream model in the evacuation model because the micro model well delineates the evacuation individuals. However, due to the complexity of evacuation, no model can comprehensively describe all behaviors in the evacuation process, so that the physiological and psychological characteristics of the evacuated people are analyzed, and a more comprehensive crowd evacuation model is established in combination with the surrounding environment to become a trend. In the existing evacuation model, the influence of the chaos degree on the evacuation behavior is rarely considered, and the model does not comprehensively consider the crowd chaos degree, the leader behavior, the small group aggregation behavior and the like.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a crowd evacuation path optimization method based on a group intelligence algorithm and evacuation entropy.
The purpose of the invention can be realized by the following technical scheme:
a crowd evacuation path optimization method based on a group intelligent algorithm and evacuation entropy is executed by a computer system and comprises the following specific steps:
step S1: constructing an evacuation environment;
step S2: initializing the evacuation crowd and related parameters;
step S3: dividing the population into a plurality of small populations based on a k-means clustering algorithm;
step S4: all individuals perform position updating based on a hybrid artificial bee colony-bat algorithm;
step S5: all individuals carry out position correction based on evacuation entropy;
step S6: obstacle avoidance is carried out on all individuals;
step S7: and if the algorithm does not reach the end condition, returning to the step S4, otherwise, ending the algorithm and finishing evacuation.
The step S1 of constructing the evacuation environment specifically means that matlab is used to construct a two-dimensional rectangular area, so as to construct walls, exits and obstacles of the evacuation space, and perform meshing processing on the space.
The step S2 of initializing the evacuation people specifically refers to determining the number of people needing evacuation, abstracting the evacuation individuals into round particles, and randomly distributing the round particles in the evacuation space constructed in the step S1.
The relevant parameters initialized in the step S2 include particle parameters, bat algorithm parameters, evacuation entropy correction parameters, and obstacle avoidance parameters.
The process of performing location update in step S4 specifically includes:
step S401: in each group, dividing the evacuated group into leading bees and observation bees according to the individual fitness value based on an artificial bee colony algorithm;
step S402: leading bees to update the location based on the bat algorithm, and observing bees to update the location based on the artificial bee colony algorithm.
The position correction in step S5 includes determining whether or not correction is performed, determining a correction direction, determining a correction probability, and controlling the evacuating individuals to select the correction direction with the determined correction probability, and performing position correction.
The obstacle avoidance in step S6 is specifically to determine the acceptable probability of the next step by using a cost function, and when the acceptable probability is 0, that is, the new position is unacceptable, perform obstacle avoidance by using a peripheral search method.
And if the new position is not acceptable, selecting a random angle with the direction deviation of-10 degrees as the new direction, and repeating the steps until the next position can be reached.
The end condition in the step S7 means that all evacuated individuals reach the exit or the algorithm reaches the maximum number of iterations.
Compared with the prior art, the invention has the following beneficial effects:
1. in the crowd evacuation modeling method, the k-means clustering algorithm is used for simulating the small crowd gathering behavior in the evacuation process, the leading bees and the observation bees in the swarm algorithm are used for simulating the following leader behavior in the evacuation process, the evacuation entropy is used for correcting the tendency of crowding towards the stable and ordered evacuation direction in the simulation evacuation process, at least three crowd evacuation behaviors are simulated, and the crowd evacuation route can be reflected more truly.
2. Compared with PSO and ACO algorithms, the artificial bee colony algorithm and the bat algorithm are used as novel swarm intelligent algorithms, have higher convergence speed and higher precision, and can effectively improve the crowd evacuation efficiency.
3. The invention uses the evacuation entropy to correct the position of the crowd, guides the crowd to move forward to the direction with low evacuation entropy (stable and ordered evacuation area), avoids the crowd from gathering on the same route, can achieve the function of dispersing the crowd flow, and further reduces the evacuation time.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of a hybrid artificial bee colony-bat algorithm location update module of the present invention;
FIG. 3 is a flow chart of an evacuation entropy position correction module according to the present invention;
fig. 4 is a schematic diagram illustrating the solution of the evacuation entropy in the evacuation space according to the present invention;
fig. 5 is a schematic diagram of direction correction of the evacuation entropy according to the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
As shown in fig. 1, a crowd evacuation path optimization method based on a group intelligence algorithm and evacuation entropy is executed by a computer system, and specifically includes the following steps:
step S1: constructing an evacuation environment;
step S2: initializing the evacuation crowd and related parameters;
step S3: dividing the population into a plurality of small populations based on a k-means clustering algorithm;
step S4: all individuals perform position updating based on a hybrid artificial bee colony-bat algorithm;
step S5: all individuals carry out position correction based on the evacuation entropy;
step S6: obstacle avoidance is carried out on all individuals;
step S7: and if the algorithm does not reach the end condition, returning to the step S4, otherwise, ending the algorithm and finishing evacuation.
The step S1 of constructing the evacuation environment specifically means that matlab is used to construct a two-dimensional rectangular area, so as to construct walls, exits and obstacles of the evacuation space, and perform meshing processing on the space to prepare for calculating the evacuation entropy.
The initializing of the evacuation people in step S2 is to determine the number of people to be evacuated, abstract the evacuation individuals into round particles, and randomly distribute them in the evacuation space constructed in step S1.
The relevant parameters initialized in step S2 include particle parameters, bat algorithm parameters, evacuation entropy correction parameters and obstacle avoidance parameters, wherein the particle parameters include particle radius R and maximum step length S max The bat algorithm parameters include a minimum frequency f min Maximum frequency f max Loudness control parameter alpha, pulse emissivity control parameter gamma and maximum pulse emissivity r i 0 The evacuation entropy correction parameters comprise an evacuation entropy threshold value entropy _ threshold and a grid size block _ size, and the obstacle avoidance parameters comprise an obstacle weight coefficient C during fitness value calculation obs The behavior constant k in the obstacle avoidance mechanism, and the specific parameter size is shown in table 1:
table 1 relevant evacuation parameter values
The k-means clustering algorithm in step S3 is based on euclidean distances, specifically, randomly initializing population centers, assigning the remaining individuals to the centers based on euclidean distances, recalculating the average value of each population and updating the population centers, and repeating the process until the criterion function converges, wherein the criterion function is specifically as follows:
E＝∑∑||x i -m j || 2
wherein E is a clustering distance criterion, x i Is the position of the individual i, m j Is the center of population j, i.e., the mean of population j.
As shown in fig. 2, the process of performing the location update in step S4 specifically includes:
step S401: in each group, based on an artificial bee colony algorithm, the first 50 percent of evacuated individuals with high fitness are determined as leading bees, and the remaining 50 percent are observed bees;
step S402: leading bees to update the location based on the bat algorithm, and observing bees to update the location based on the artificial bee colony algorithm.
The location updating based on the bat algorithm specifically comprises the steps of leading bees to update the speed and the location, searching locally, and updating the pulse frequency and the loudness.
The positions and the speeds of the leading bees are updated specifically as follows:
f i ＝f min +(f max -f min )β
wherein f is i Pulse frequency, f, for leading bee i min 、f max Is the minimum and maximum frequency, the value is constant, and the value of beta is [0,1 ]]A random function of the number of bits in between,
the position of leading bee i at the time t, x is the position of the evacuated individual with the best fitness in the whole space,
is a unit vector of the direction in which the leading bee i points to the globally optimal individual at time t,
for the direction of the speed of the leading bee i at time t,
the value range of the speed of leading bee i at the time t is [0, S ] max ]Influenced by the position of the obstacle.
The local search specifically includes:
wherein the content of the first and second substances,
for the search direction of leading bee i at time t, [ epsilon ] is the value [ -1,1]Random number in between, A t Is the average value of the loudness of all leading bees at time t,
is the search position of the leading bee i at time t.
The pulse emissivity and loudness updating specifically comprises:
wherein the content of the first and second substances,
loudness r of leading bee i at time t i 0 Maximum pulse emissivity, r, for leading bee i i t Alpha and gamma respectively represent control parameters of loudness and pulse emissivity, and the numerical value is a constant.
And updating the position based on an artificial bee colony algorithm, namely selecting leading bees by the observation bees according to a roulette algorithm, and further updating the position along with the leading bees.
The probability of leading bees being selected based on the roulette algorithm is specifically:
wherein p is c,i Probability of being selected for leading bee i in the group c, fit c,i And n represents the number of the leading bees in the group c.
The fitness value in this embodiment is specifically as follows:
wherein cost (p, q) is the cost function, fit (p) is the fitness of the particle p, and (p) x ，p y ) Is the position of the particle p, (q) x ，q y ) The position (sigma) of dynamic obstacle (other evacuated individuals in the evacuation process) or static obstacle (obstacle in artificially set scene, such as wall or square column, etc.) px ，σ qx ) Is the particle size of the sparse individual p (σ) py ，σ qy ) Is the coverage area of the obstacle in the evacuation scene, O represents all dynamic and static obstacles, g represents the location of the exit, C obs Representing the weight coefficient of the obstacle, C obs The larger the obstacle has a greater influence on the path selection for the particle to travel.
The position updating of the observation bees is specifically as follows:
wherein x is igosd To observe the following target location of bee i,
the position of bee i is observed for time t,
is a unit vector of the direction of the observation bee i pointing to the leading bee igos at the moment t,
the direction of the velocity of bee i is observed for time t,
the speed of the bee i is observed at the time t, and the value range is [0, S ] max ]The position of the obstacle is influenced, and the position of the obstacle,
is a value of [0,1]Random variable in between.
As shown in fig. 3, the position correction in step S5 includes determining whether or not correction is to be performed, determining a correction direction, determining a correction probability, and controlling the evacuating individual to select the correction direction with the determined correction probability to perform position correction.
The evacuation entropy is used for judging the evacuation chaos degree by calculating the consistency of the speed direction and the size of the crowd, and each particle needs to calculate the evacuation entropy value of the adjacent 9 regions, as shown in fig. 4, and is mapped into an evacuation entropy diagram. Firstly discretizing an evacuation space, respectively discretizing the speed direction and the size of the crowd in each discrete grid into 8 equally-spaced intervals, then calculating an evacuation entropy value by counting the total number of evacuation individuals in each interval, and finally mapping the evacuation entropy value of each discrete grid to an evacuation scene according to the size of the evacuation entropy, so as to obtain an evacuation entropy diagram.
The evacuation entropy is specifically calculated as follows:
E n ＝α 1 E n1 +α 2 E n2
wherein E is n1 、E n2 、E n Expressing the entropy of the direction of the movement speed, the entropy of the size of the speed and the total evacuation entropy in each discrete grid, and the sum is [1,8 ]]Natural number in between, N represents the total number of individuals in each discretized grid, N i Denotes the total number of individuals in each speed direction section, m j Representing the total number of individuals, alpha, over each discretized velocity interval 1 And alpha 2 Representing weight coefficients, typically taken as alpha 1 ＝α 2 ＝0.5。
As shown in fig. 5, when the evacuation entropy correction is performed, the region having the lowest evacuation entropy value among the 5 adjacent spaces in the field of view is selected as the correction direction. In fig. 5, normal corrections are shown in order from left to right, and the case where there are a plurality of regions with the lowest evacuation entropy value is corrected and correction is not performed.
The correction probability is determined according to whether the evacuation individual sees the exit, if the evacuation individual cannot see the exit, the correction probability is 0.6, otherwise, the correction probability is 0.05.
In step S6, the obstacle avoidance specifically includes determining the acceptable probability of the next step by using a cost function, and when the acceptable probability is 0, that is, the new position is unacceptable, performing obstacle avoidance by using a peripheral search method. And if the new position is not acceptable, selecting a random angle with the direction deviation of-10 degrees as the new direction, and repeating the steps until the next position can be reached.
The determination of the next acceptable probability by using the cost function is specifically as follows:
where prob (f) is the next acceptable probability, f is the target obstacle cost value (including static obstacles and other evacuating individual dynamic obstacles), k is a behavior constant expressing the magnitude of obstacle avoidance, and k ═ 1 is a boundary value, that is, when a particle is tangent to or intersects with an obstacle, the next acceptable probability is 0.
The end condition in step S7 means that all evacuated individuals reach the exit or the algorithm reaches the maximum number of iterations.
Claims (6)
1. A crowd evacuation path optimization method based on a group intelligent algorithm and evacuation entropy is characterized in that the method is executed by a computer system and comprises the following specific steps:
step S1: constructing an evacuation environment;
step S2: initializing evacuation crowd and evacuation path parameters;
step S3: dividing the population into a plurality of small populations based on a k-means clustering algorithm;
step S4: all individuals perform position updating based on a hybrid artificial bee colony-bat algorithm;
step S5: all individuals carry out position correction based on evacuation entropy;
step S6: obstacle avoidance is carried out on all individuals;
step S7: if the algorithm does not reach the end condition, returning to the step S4, otherwise, ending the algorithm and finishing evacuation;
the evacuation path parameters initialized in the step S2 include particle parameters, bat algorithm parameters, evacuation entropy correction parameters and obstacle avoidance parameters, wherein the particle parameters include a particle radius R and a maximum step length S max The bat algorithm parameters include a minimum frequency f min Maximum frequency f max Loudness control parameter alpha, pulse emissivity control parameter gamma and maximum pulse emissivity
The evacuation entropy correction parameters comprise an evacuation entropy threshold value entropy _ threshold and a grid size block _ size, and the obstacle avoidance parameters comprise an obstacle weight coefficient C during fitness value calculation obs A behavior constant k in the obstacle avoidance mechanism;
the process of performing location update in step S4 specifically includes: step S401: in each group, dividing the evacuated group into leading bees and observation bees according to the individual fitness value based on an artificial bee colony algorithm; step S402: leading bees to update the positions based on a bat algorithm, and observing bees to update the positions based on an artificial bee colony algorithm;
the positions and the speeds of the leading bees are updated specifically as follows:
f i ＝f min +(f max -f min )β
wherein f is i Pulse frequency, f, for leading bee i min 、f max Is the minimum and maximum frequency, the value is constant, and the value of beta is [0,1 ]]A random function of the number of bits in between,
for the location of the leading bee i at time t, x * Is the position of the evacuation individual with the best fitness in the whole space,
is a unit vector of the direction in which the leading bee i points to the globally optimal individual at time t,
for the speed direction of the leading bee i at time t,
the value range of the speed of leading bee i at the time t is [0, S ] max ]Influenced by the position of the obstacle;
the position correction in step S5 includes determining whether or not correction is performed, determining a correction direction, determining a correction probability, and controlling the evacuating individuals to select the correction direction with the determined correction probability, and performing position correction.
2. The crowd evacuation path optimization method according to claim 1, wherein the step S1 of constructing an evacuation environment specifically means constructing a two-dimensional rectangular area by using matlab, further constructing walls, exits and obstacles of an evacuation space, and performing meshing processing on the space.
3. The crowd evacuation path optimizing method based on group intelligence algorithm and evacuation entropy according to claim 1, wherein the initializing the evacuated crowd in step S2 specifically includes: the number of people to be evacuated is determined and the evacuated individuals are abstracted into round particles, which are randomly distributed in the evacuation space constructed at step S1.
4. The crowd evacuation path optimization method based on the group intelligence algorithm and the evacuation entropy according to claim 1, wherein the obstacle avoidance in step S6 is specifically to determine an acceptable probability of the next step by using a cost function, and when the acceptable probability is 0, that is, a new position is unacceptable, adopt a peripheral search mode to avoid an obstacle.
5. The crowd evacuation path optimization method based on the group intelligence algorithm and the evacuation entropy according to claim 4, wherein the peripheral search mode is that if the new position is not acceptable, a random angle with a direction deviation of-10 degrees to 10 degrees is selected as the new direction, and the rest is done in sequence until the next position is reached.
6. The crowd evacuation path optimization method based on group intelligence algorithm and evacuation entropy of claim 1, wherein the end condition in step S7 means that all evacuated individuals reach exit or the algorithm reaches maximum number of iterations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745402.7A CN110543975B (en) | 2019-08-13 | 2019-08-13 | Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745402.7A CN110543975B (en) | 2019-08-13 | 2019-08-13 | Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110543975A CN110543975A (en) | 2019-12-06 |
| CN110543975B true CN110543975B (en) | 2022-09-20 |
Family
ID=68711493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910745402.7A Active CN110543975B (en) | 2019-08-13 | 2019-08-13 | Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543975B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111400963B (en) * | 2020-03-04 | 2023-04-18 | 山东师范大学 | Crowd evacuation simulation method and system based on chicken swarm algorithm and social force model |
| CN111930121B (en) * | 2020-08-10 | 2022-10-25 | 哈尔滨工程大学 | Mixed path planning method for indoor mobile robot |
| CN114545932B (en) * | 2022-01-28 | 2023-06-06 | 北京交通大学 | Path correction method, device, equipment and readable storage medium |
| CN117146833B (en) * | 2023-10-31 | 2024-01-05 | 北京卓翼智能科技有限公司 | Unmanned aerial vehicle path planning method and device based on improved bat algorithm |
| CN117631667B (en) * | 2023-11-29 | 2024-05-14 | 北京建筑大学 | Dynamic guiding obstacle avoidance evacuation method applied to multi-storey building personnel |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108492608A (en) * | 2018-03-12 | 2018-09-04 | 北京航空航天大学 | A kind of analysis method and system of the bus passenger flow volume based on cloud model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016157279A1 (en) * | 2015-03-27 | 2016-10-06 | 三菱重工業株式会社 | Evacuation guiding system and method for ship |
-
2019
- 2019-08-13 CN CN201910745402.7A patent/CN110543975B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108492608A (en) * | 2018-03-12 | 2018-09-04 | 北京航空航天大学 | A kind of analysis method and system of the bus passenger flow volume based on cloud model |
Non-Patent Citations (2)
| Title |
|---|
| "基于疏散熵的人群疏散PSO建模";赵子骏、王坚、陈晓薇;《中国公共安全(学术版)》;20180630(第2期);第41-46页 * |
| "基于粒子群算法的疏散仿真框架";蔡培川等;《2014年IEEE进化计算大会(CEC)》;20140711;第1944-1950页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110543975A (en) | 2019-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110543975B (en) | Crowd evacuation path optimization method based on group intelligent algorithm and evacuation entropy | |
| CN108491598B (en) | Crowd evacuation simulation method and system based on path planning | |
| CN113449864B (en) | Feedback type impulse neural network model training method for image data classification | |
| CN107463751B (en) | Crowd grouping evacuation simulation method and system based on binary DBSCAN clustering algorithm | |
| CN110514206A (en) | A kind of unmanned plane during flying path prediction technique based on deep learning | |
| Fong et al. | Towards enhancement of performance of K‐means clustering using nature‐inspired optimization algorithms | |
| Putra et al. | Estimation of parameters in the SIR epidemic model using particle swarm optimization | |
| CN112469050B (en) | WSN three-dimensional coverage enhancement method based on improved wolf optimizer | |
| CN112036540A (en) | Sensor number optimization method based on double-population hybrid artificial bee colony algorithm | |
| CN110181508A (en) | Underwater robot three-dimensional Route planner and system | |
| CN101763528A (en) | Gene regulation and control network constructing method based on Bayesian network | |
| CN111121784B (en) | Unmanned reconnaissance aircraft route planning method | |
| CN111404731B (en) | SDN network controller deployment method and system based on double heuristic algorithm | |
| CN111882047A (en) | Rapid empty pipe anti-collision method based on reinforcement learning and linear programming | |
| Kannan et al. | Particle swarm optimization for minimizing assembly variation in selective assembly | |
| Serrien et al. | Issues in using self-organizing maps in human movement and sport science | |
| CN115620870A (en) | Automatic planning method and system based on dose prediction and parameter optimization | |
| CN113128617B (en) | Spark and ASPSO based parallelization K-means optimization method | |
| CN113255893A (en) | Self-evolution generation method of multi-agent action strategy | |
| Sayed et al. | Hybrid Quantum Salp Swarm Algorithm for Contrast Enhancement of Natural Images. | |
| Tsurushima | Multi-objective Risk Analysis for Crowd Evacuation Guidance using Multiple Visual Signs. | |
| CN110766072A (en) | Automatic generation method of computational graph evolution AI model based on structural similarity | |
| CN109523838B (en) | Heterogeneous cooperative flight conflict solution method based on evolutionary game | |
| CN111382896B (en) | WTA target optimization method of self-adaptive chaotic parallel clone selection algorithm | |
| CN115100233A (en) | Radar target tracking method based on generation of confrontation network resampling particle filter |
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 |