CN111062545B - Outdoor emergency guiding path indication method - Google Patents
Outdoor emergency guiding path indication method Download PDFInfo
- Publication number
- CN111062545B CN111062545B CN202010049190.1A CN202010049190A CN111062545B CN 111062545 B CN111062545 B CN 111062545B CN 202010049190 A CN202010049190 A CN 202010049190A CN 111062545 B CN111062545 B CN 111062545B
- Authority
- CN
- China
- Prior art keywords
- evacuation
- data
- time
- person
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention discloses an outdoor emergency guiding path indication method, which comprises the following steps: s10, randomly taking values of all characteristic factors in a reasonable range by using factors with larger influence on group evacuation time, including personnel characteristics and path characteristics, and simulating by using an outdoor group evacuation behavior model to obtain evacuation time; s20, grouping the obtained data, and dividing each group of data into 75% of training data and 25% of test data by a split function of a sklearn library for each group of data; s30, preliminarily judging through the relation between the data characteristics and the prediction results, selecting a linear regression prediction method to establish a prediction model, adopting a least square method to establish a loss function, utilizing a scikit-learn of python to establish a model, adopting a minimum gradient method in the optimization process to establish an evaluation function through relative errors to obtain respective adaptive relative error measurement values, obtaining a prediction time parameter matrix, and establishing a time prediction model; s40, analyzing the selection planning of the path based on the outdoor emergency evacuation time prediction model.
Description
Technical Field
The invention belongs to the technical field of emergency guiding identification systems, and particularly relates to an outdoor emergency guiding path indication method.
Background
After the outdoor emergency guiding sign is designed, the space arrangement is particularly important. The meaning of the identification information can be reflected after combining the setting position and the setting mode, so that the setting should firstly ensure that the meaning of each identification is correct, clear and definite, and simultaneously, the identification can rapidly and fully complete the transmission function of the guide information by optimizing the setting method.
The end point of outdoor emergency evacuation is an emergency shelter, and the number of refuges and the service radius of each emergency shelter have certain limits and requirements, so that the setting range of the outdoor emergency guiding mark can be determined according to the design specification of the emergency shelter. Because the environments of all the areas are different, the areas and facilities of the emergency shelter are different, the setting of the outdoor emergency guiding mark action range of different areas is also determined according to specific conditions.
The evacuation time is predicted to effectively plan an evacuation scheme and a path, and casualties can be greatly reduced when emergency occurs.
Disclosure of Invention
In view of the above technical problems, the invention is used for providing an outdoor emergency guiding time prediction method, based on the characteristics of evacuation behaviors of people, an outdoor group evacuation simulation model is created by using the tkilter of python, a certain amount of simulation data is obtained, then an outdoor evacuation time prediction method and an optimal path selection method are obtained based on a linear regression algorithm, and the method is verified by using pathfinder modeling, so that the method has a certain guiding significance for selecting an outdoor optimal evacuation path, and the group evacuation efficiency can be improved.
In order to solve the technical problems, the invention adopts the following technical scheme:
an outdoor emergency guiding path indication method comprises the following steps:
factors with great influence on the group evacuation time comprise personnel characteristics and path characteristics, the characteristic factors are randomly valued in a reasonable range, and the evacuation time is obtained by simulating an outdoor group evacuation behavior model;
grouping the obtained data, and dividing each group of data into 75% of training data and 25% of test data by using a split function of a sklearn library for each group of data;
preliminary judgment is carried out through the relation between the data characteristics and the prediction results, a linear regression prediction method is selected to establish a prediction model, a least square method is adopted to construct a loss function, a scikit-learn of python is adopted to construct a model, a minimum gradient method is adopted in the optimization process, an evaluation function is constructed through relative errors, test data are utilized to calculate and obtain conclusions, respectively adapted relative error measurement values are obtained, a prediction time parameter matrix is obtained, and a time prediction model is established;
based on the outdoor emergency evacuation time prediction model, the selection planning of the path is analyzed:
t s ＝t(l s ，w s ，n，p)
wherein:
t s -an estimated evacuation time for evacuation with only the shortest path s;
l s ，w s -shortest evacuation path length, width, m;
t d -estimated evacuation time for evacuation in two paths s;
l c ，w c -alternative evacuation path length, width, m;
n—number of evacuation path plans;
n-the number of evacuated people in 10 meters in front of the intersection;
p-proportion of person with poor physical ability,%.
Preferably, the outdoor group evacuation behavior model is based on acting force, and it is assumed that during evacuation, a person is subjected to the action F of own forward evacuation force in the x direction, and is simultaneously subjected to the comprehensive resistance F of air, roads and the like to the back and the backward acting force fp applied by the person in front of the model; the y direction is acted by people on the roadside or left and right sides, and the action exists in the form of instantaneous force for simplifying the model, namely only the evacuation direction of the people in the y direction is influenced, the evacuation speed in the y direction is not influenced,
the evacuation acceleration of the ith person at the current moment along the x direction is:
wherein:
a i acceleration in the direction of advance of the ith person, m/s 2 ；
P-evacuated personnel set;
w-evacuation personnel shoulder width, 0.5m;
v i 、v j -speed in the forward direction of the ith, j person, m/s;
x i 、x j -position coordinates of the i, j-th person in the direction of advance, m;
y i 、y k -position coordinates of the i, k th person in the vertical advance direction, m;
v mi -maximum speed in the direction of advance of the ith person, m/s;
t mi the time for the ith person to accelerate from rest to 1m/s is 0.2-1.2 s;
the model was implemented in an interface using the tkilter programming of python.
The resulting data is preferably grouped according to the evacuation path length.
Preferably, the relative error is calculated as follows:
wherein:
δ i -the relative error of the ith prediction;
y reali -ith evacuation time simulation value;
y predi -an ith evacuation time predictor;
delta-the relative error metric;
n 2 -verifying the data volume of the dataset;
N i -discretizing the function;
s-an averaging function.
Preferably, the prediction time parameter matrix is:
where W is the weight vector and b is the intercept.
Preferably, the time prediction model obtained according to the prediction time parameter matrix is:
wherein:
t- -estimated evacuation time, s;
l- -evacuation path length, m;
w 2 -evacuation path width, m;
n- -the number of evacuees within 10 meters before the intersection;
p- -proportion of persons with poor physical ability,%.
The invention has the following beneficial effects: based on the evacuation behavior characteristics of people, an outdoor group evacuation simulation model is created by using tkilter of python, a certain amount of simulation data is obtained, then an outdoor evacuation time prediction method and an optimal path selection method are obtained based on a linear regression algorithm, and verification is carried out on the method by using pathfinder modeling, so that the method has a certain guiding significance for the selection of an outdoor optimal evacuation path, and the group evacuation efficiency can be improved.
Drawings
FIG. 1 is a flow chart of steps of an outdoor emergency guidance time prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an outdoor group evacuation behavior model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an outdoor group evacuation behavior model simulation process according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of simulation time analysis results of an outdoor group evacuation behavior model implemented by the invention;
FIG. 5 is a comparison chart of learning curves according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a pathfinder evacuation simulation model according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an outdoor emergency guiding identifier setting method disclosed in an embodiment of the present invention includes the following steps:
s10, randomly taking values of all characteristic factors in a reasonable range by using factors with larger influence on group evacuation time, including personnel characteristics and path characteristics, and simulating by using an outdoor group evacuation behavior model to obtain evacuation time;
s20, grouping the obtained data, and dividing each group of data into 75% of training data and 25% of test data by a sklearn library split function for each group of data;
s30, preliminarily judging through the relation between data characteristics and a prediction result, selecting a linear regression prediction method to establish a prediction model, adopting a least square method to establish a loss function, adopting a scikit-learn of python to establish a model, adopting a minimum gradient method in the optimization process to establish an evaluation function through relative errors, and calculating through test data to obtain conclusion, obtaining respectively adapted relative error measurement values, obtaining a prediction time parameter matrix, and establishing a time prediction model;
s40, based on an outdoor emergency evacuation time prediction model, analyzing a path selection plan:
t s ＝t(l s ，w s ，n，p)
wherein:
t s -an estimated evacuation time for evacuation with only the shortest path s;
l s ，w s -shortest evacuation path length, width, m;
t d -estimated evacuation time for evacuation in two paths s;
l c ，w c -alternative evacuation path length, width, m;
n—number of evacuation path plans;
n- -the number of evacuees within 10 meters before the intersection;
p-proportion of person with poor physical ability,%.
In a specific application example, unlike indoors, outdoor space is often wider, evacuation distance is longer, and vertical layers are fewer, so that evacuation personnel have a certain difference between speed change and evacuation behavior and indoors in the evacuation process. In order to explore the behavior characteristics of outdoor evacuation, based on cellular automata and social force models, consider the interaction between people and things in the outdoor emergency evacuation process, an outdoor group evacuation behavior model based on acting force is provided, as shown in fig. 2.
The method is characterized in that the x-direction is assumed to be subjected to the forward evacuation force F of a person during evacuation, and is also subjected to the comprehensive resistance F of air, roads and the like to the back of the person and the backward acting force fp applied by the person in front of the person; the y-direction is acted by people on the roadside or left and right sides, and the action exists in the form of instantaneous force for simplifying the model, namely, only the evacuation direction of the people in the y direction is influenced, and the evacuation speed in the y direction is not influenced.
The evacuation acceleration of the ith person at the current moment along the x direction is:
wherein:
a i acceleration in the direction of advance of the ith person, m/s 2 ；
P-evacuated personnel set;
w-evacuation personnel shoulder width, 0.5m;
v i 、v j -speed in the forward direction of the ith, j person, m/s;
x i 、x j -position coordinates of the i, j-th person in the direction of advance, m;
y i 、y k -position coordinates of the i, k th person in the vertical advance direction, m;
v mi -maximum speed in the direction of advance of the ith person, m/s;
t mi the time for the ith person to accelerate from rest to 1m/s is taken to be 0.2-1.2 s.
The model was interfaced using the tkilter programming of python as shown in fig. 3-4.
The group evacuation behavior model integrates the advantages of a social force model and a cellular automaton model which are relatively mature in current evacuation behavior research, namely, interaction among people is reflected in a force form along the x direction, and the speed change of each person in the group evacuation process can be well simulated; the interaction between people and between objects is embodied in a probability form along the y direction, so that the direction selection situation in the group evacuation process can be well simulated. The model programming is realized in an interfacing way, so that situations such as various road lengths, road widths, number of people, personnel characteristic proportion and the like can be simulated, evacuation processes and time prediction can be intuitively displayed, the determination of an actual evacuation command scheme can be guided, and meanwhile, batch acquisition of simulation data is easy to realize, so that a data basis is provided for subsequent data analysis. 10000 sets of data are obtained by using an outdoor group evacuation behavior model, and evacuation time is predicted based on a linear regression algorithm.
Through analysis, factors with great influence on the group evacuation time include personnel characteristics (number of people, physical ability), path characteristics (road length, road width) and the like, each characteristic factor is randomly valued in a reasonable range, and then the evacuation time is obtained by simulating the group evacuation behavior model. 10000 sets of data were obtained in total, as shown in table 1.
Table 1 outdoor group emergency evacuation simulation data table
Through preliminary analysis of data, in order to obtain a time prediction model with wider application range and higher accuracy, the data are divided into 3 groups, namely, the 1 st group is data with the path length within 200m, the 2 nd group is data with the path length within 200-500 m, and the 3 rd group is data with the path length greater than 500 m. Meanwhile, the data quantity with the evacuation prediction time being more than 1000s is considered to be very small, and the evacuation prediction time is deleted in order to avoid the influence on the prediction result.
For each set of data, it was divided into 75% training data and 25% test data by split function of sklearn library.
Constructing a prediction model and a loss function, and preliminarily judging through the relation between data characteristics and a prediction result, and selecting a linear regression prediction method, namely:
y＝X T ·W+b
the loss function using least squares, i.e
Wherein W is a weight vector, b is an intercept, y reali -ith evacuation time simulation value; y is predi -an ith evacuation time predictor.
Model training, using scikit-learn of python to construct a model, and adopting a minimum gradient method in the optimization process.
And (3) evaluating the model, namely constructing an evaluation function for judging the prediction performance of the model on the evacuation time by using the relative error, and calculating by using the test data to obtain a conclusion. Due to the obvious difference of the evacuation time of each group, the respective adaptive relative error measurement value is respectively given according to the application requirement.
Wherein:
δ i -the relative error of the ith prediction;
y real1 -ith evacuation time simulation value;
y predi -an ith evacuation time predictor;
delta-relative error measurement, group 1 takes 0.3, group 2 takes 0.2, and group third takes 0.2;
n 2 -verifying the data volume of the data set.
The prediction results of the three sets of models were evaluated and compared to the raw data fit model, which was not grouped, as shown in table 2.
Table 2 results of accuracy evaluation of time prediction model
Taking Δ=0.3 as an example, the comparative learning curve is shown in fig. 5.
From the learning curve and training/testing scores, it can be seen that the prediction accuracy of the model is improved by data grouping. The test scores of the three groups of data are respectively 0.898, 0.867 and 0.874, and the prediction effect of the model is good in combination with the actual requirements.
The parameter matrix is obtained as follows:
the time prediction model obtained according to the prediction time parameter matrix is as follows:
wherein:
t- -estimated evacuation time, s;
l- -evacuation path length, m;
w 2 -evacuation path width, m;
n- -the number of evacuees within 10 meters before the intersection;
p- -proportion of persons with poor physical ability,%.
In step S50, an environment is taken as an example to illustrate the application of the method and verification thereof:
assuming that two paths A, B can be evacuated at a certain intersection, the basic information of the path A is as follows: 180m long and 8m wide; the basic information of the road B is as follows: 230m long and 5m wide. The number of people in the range of 10m at the crossing is kept about 300 during evacuation, wherein the lower speed accounts for 30 percent. According to the subject study, consider first only the shortest path (way a) evacuation, i.e. t= 145.36s; if two routes are evacuated at the same time, t=165.57 s, so only the shortest route (route a) should be selected for evacuation.
If the basic information of the path A is: 200m long and 10m wide; the basic information of the road B is as follows: 210m long and 5m wide. The number of people in the range of 10m at the road junction is still about 300 during evacuation, wherein the lower speed still accounts for 30 percent. Calculated, t= 158.31s when only way a is used for evacuation; when two routes are simultaneously used for evacuation, t= 147.54s, so the route a and the route B should be selected for evacuation simultaneously.
The two cases were simulated with the pathfinder software, and the simulation procedure is shown in fig. 6.
First case: consider first only shortest path (way a) evacuation, i.e., t=136.8 s; if two routes are evacuated at the same time, t=156.5 s, so only the best route (route a) should be selected for evacuation. Second case: when only way a is used for evacuation, t=148.8 s; when two paths are simultaneously used for evacuation, t=142.5 s, so the path a and the path B should be selected for evacuation together.
The calculation result and the simulation result are compared, and the group simulation model used is different, and the personnel position, the personnel speed and the like have certain randomness, so that the specific time prediction result is not completely the same, but the obtained route selection conclusion is consistent, the applicability of the route selection method is proved, and the group evacuation model adopted by the method is basically consistent with the prediction result of the model adopted by the pathfinder software on the evacuation time within the error acceptable range through further analysis.
It should be understood that the exemplary embodiments described herein are illustrative and not limiting. Although one or more embodiments of the present invention have been described with reference to the accompanying drawings, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims.
Claims (6)
1. An outdoor emergency guiding path indication method is characterized by comprising the following steps:
s10, randomly taking values of all characteristic factors in a reasonable range by using factors with larger influence on group evacuation time, including personnel characteristics and path characteristics, and simulating by using an outdoor group evacuation behavior model to obtain evacuation time;
s20, grouping the obtained data, and dividing each group of data into 75% of training data and 25% of test data by a split function of a sklearn library for each group of data;
s30, preliminarily judging through the relation between data characteristics and a prediction result, selecting a linear regression prediction method to establish a prediction model, adopting a least square method to establish a loss function, adopting a scikit-learn of python to establish a model, adopting a minimum gradient method in the optimization process to establish an evaluation function through relative errors, and calculating through test data to obtain conclusion, obtaining respectively adapted relative error measurement values, obtaining a prediction time parameter matrix, and establishing a time prediction model;
s40, based on an outdoor emergency evacuation time prediction model, analyzing a path selection plan:
t s ＝t(l s ,w s ,n,p)
wherein:
t s -an estimated evacuation time for evacuation with only the shortest path s;
l s ，w s -shortest evacuation path length, width, m;
t d -estimated evacuation time for evacuation in two paths s;
l c ，w c -alternative evacuation path length, width, m;
n, evacuation path planning quantity;
n-the number of evacuated people in 10 meters in front of the intersection;
p-proportion of person with poor physical ability,%.
2. The outdoor emergency guidance path indication method of claim 1, wherein the outdoor group evacuation behavior model is based on acting force, assuming that a person is subjected to a forward evacuation force F of the person in an x direction while being subjected to air, a comprehensive resistance F of the road to the back thereof, and a backward acting force fp applied thereto by a person in front thereof during evacuation; the y direction is acted by people on the roadside or left and right sides, and the action exists in the form of instantaneous force for simplifying the model, namely only the evacuation direction of the people in the y direction is influenced, the evacuation speed in the y direction is not influenced,
the evacuation acceleration of the ith person at the current moment along the x direction is:
wherein:
a i acceleration in the direction of advance of the ith person, m/s 2 ；
P-evacuated personnel set;
w-evacuation personnel shoulder width, 0.5m;
v i 、v j -speed in the forward direction of the ith, j person, m/s;
x i 、x j -position coordinates of the i, j-th person in the direction of advance, m;
y i 、y k -position coordinates of the i, k th person in the vertical advance direction, m;
v mi -maximum speed in the direction of advance of the ith person, m/s;
t mi the time for the ith person to accelerate from rest to 1m/s is 0.2-1.2 s;
the model was implemented in an interface using the tkilter programming of python.
3. The outdoor emergency guide path indication method according to claim 1, wherein the obtained data are grouped according to the evacuation path length.
4. The outdoor emergency guide path indication method according to claim 1, wherein the relative error is calculated as follows:
wherein:
δ i -the relative error of the ith prediction;
y reali -ith evacuation time simulation value;
y predi -an ith evacuation time predictor;
delta-the relative error metric;
n 2 -verifying the data volume of the dataset;
N i -discretizing the function;
s-an averaging function.
5. The outdoor emergency guidance path indication method of claim 1, wherein the predicted time parameter matrix is:
where W is the weight vector and b is the intercept.
6. The outdoor emergency guidance path indication method of claim 5, wherein the time prediction model obtained from the predicted time parameter matrix is:
wherein:
t- -estimated evacuation time, s;
l- -evacuation path length, m;
w 2 -evacuation path width, m;
n- -the number of evacuees within 10 meters before the intersection;
p- -proportion of persons with poor physical ability,%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049190.1A CN111062545B (en) | 2020-01-16 | 2020-01-16 | Outdoor emergency guiding path indication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010049190.1A CN111062545B (en) | 2020-01-16 | 2020-01-16 | Outdoor emergency guiding path indication method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062545A CN111062545A (en) | 2020-04-24 |
| CN111062545B true CN111062545B (en) | 2023-07-25 |
Family
ID=70307422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010049190.1A Active CN111062545B (en) | 2020-01-16 | 2020-01-16 | Outdoor emergency guiding path indication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062545B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170053503A1 (en) * | 2015-08-20 | 2017-02-23 | Tata Consultancy Services Limited | Methods and systems for planning evacuation paths |
| CN106940825A (en) * | 2017-02-09 | 2017-07-11 | 南京邮电大学 | A kind of evacuation planning method and evacuation planning system towards disaster emergency |
-
2020
- 2020-01-16 CN CN202010049190.1A patent/CN111062545B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170053503A1 (en) * | 2015-08-20 | 2017-02-23 | Tata Consultancy Services Limited | Methods and systems for planning evacuation paths |
| CN106940825A (en) * | 2017-02-09 | 2017-07-11 | 南京邮电大学 | A kind of evacuation planning method and evacuation planning system towards disaster emergency |
Non-Patent Citations (3)
| Title |
|---|
| 人员非均匀分布条件下的疏散引导方向优化算法研究;胥旋;《中国安全生产科学技术》;第7卷(第08期);全文 * |
| 大型超市火灾人员疏散路径优化研究;邢志祥 等;《安全与环境学报》;第15卷(第02期);全文 * |
| 突发灾难下大型路网中的人员疏散模型;赵岩 等;《长安大学学报(自然科学版)》;第33卷(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062545A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | Calibration of microsimulation models using nonparametric statistical techniques | |
| CN106781489B (en) | A kind of road network trend prediction method based on recurrent neural network | |
| CN103353923B (en) | Adaptive space interpolation method and system thereof based on space characteristics analysis | |
| CN107677275B (en) | A kind of heterogeneous aircraft paths planning method in mixing spatial domain and device | |
| CN109214581A (en) | A kind of Along Railway wind speed forecasting method considering wind direction and confidence interval | |
| CN107767011B (en) | Pedestrian characteristic acquisition system and service level dynamic evaluation method for railway station | |
| CN107293115A (en) | A kind of traffic flow forecasting method for microscopic simulation | |
| CN105574593A (en) | Track state static-state detection and control system and method based on cloud computing and big data | |
| CN105554873A (en) | Wireless sensor network positioning algorithm based on PSO-GA-RBF-HOP | |
| CN110082716A (en) | A kind of complex hospital environments indoor locating system and localization method | |
| CN110502277A (en) | A kind of bad taste detection method of code based on BP neural network | |
| CN114239371A (en) | Simulation-based parameter calibration method for vehicle delay model at entrance and exit of large parking lot | |
| CN110414803A (en) | The assessment method and device of automated driving system level of intelligence under different net connection degree | |
| CN111274710B (en) | Construction method of nuclear emergency evacuation outlet selection behavior model based on game | |
| CN109190839A (en) | A kind of Along Railway wind speed Intelligent rolling prediction technique merging wind direction | |
| CN110716998B (en) | Fine scale population data spatialization method | |
| CN115422747A (en) | Method and device for calculating discharge amount of pollutants in tail gas of motor vehicle | |
| CN107609706A (en) | Method based on network topology characteristic structure track traffic website Passenger flow forecast model | |
| CN111062545B (en) | Outdoor emergency guiding path indication method | |
| CN109345139B (en) | Airport group efficiency and policy evaluation method based on system dynamics | |
| CN117313931B (en) | Subway platform passenger evacuation time prediction method based on fire scene | |
| CN113628336A (en) | Visual identification method for road traffic potential safety hazard points | |
| CN111291923B (en) | Outdoor emergency guiding time prediction method | |
| CN107230020A (en) | Evaluate and test the method and its correlation technique and system of high ferro dispatcher's job engineering efficiency | |
| CN111274688B (en) | Crowd behavior simulation method considering pedestrian motion statistics characteristics |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201111 Address after: 100084 Tsinghua University, Beijing, Haidian District Applicant after: TSINGHUA University Address before: 100084 Tsinghua University, Beijing, Haidian District Applicant before: TSINGHUA University Applicant before: Beijing Huaxin Vision Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |