CN114493363A - Urban bus accident risk factor analysis method - Google Patents
Urban bus accident risk factor analysis method Download PDFInfo
- Publication number
- CN114493363A CN114493363A CN202210170341.8A CN202210170341A CN114493363A CN 114493363 A CN114493363 A CN 114493363A CN 202210170341 A CN202210170341 A CN 202210170341A CN 114493363 A CN114493363 A CN 114493363A
- Authority
- CN
- China
- Prior art keywords
- accident
- bus
- urban
- module
- risk factors
- 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.)
- Pending
Links
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000000556 factor analysis Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000010365 information processing Effects 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000004891 communication Methods 0.000 claims description 12
- 238000007477 logistic regression Methods 0.000 claims description 11
- 208000027418 Wounds and injury Diseases 0.000 claims description 6
- 230000006378 damage Effects 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 6
- 208000014674 injury Diseases 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 6
- 238000012502 risk assessment Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G06Q50/40—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Abstract
The invention belongs to the technical field of urban public transport safety monitoring, and particularly relates to an urban public transport accident risk factor analysis method. The bus accident information processing system used by the method comprises a central processing unit, a data conversion module, a database, a clock module, a gateway module, an information display module, an internet module, a satellite positioning module, an encoder and an automatic camera which are integrally installed on an urban road intelligent lamp bar; the method comprises the steps of data acquisition and preprocessing, selecting risk factors from four aspects of people, vehicles, roads and environment to determine the characteristics of the bus accident, establishing a bus accident Logistic model, determining significant factors influencing the safety of the urban bus, associating the bus accident risk factors by adopting an Apriori algorithm and the like. The urban bus accident risk factor analysis and assessment method can be used for rapidly and accurately analyzing and assessing urban bus accident risk factors.
Description
Technical Field
The invention belongs to the technical field of urban public transport safety monitoring, and particularly relates to an urban public transport accident risk factor analysis method.
Background
The research of Harbin Industrial university, Mayixin, written major paper, urban traffic accident risk analysis method based on dynamic fault tree, develops risk analysis research on urban road traffic accidents according to dynamic fault tree theory. The basic content of the urban traffic accident risk analysis method disclosed in the paper is as follows:
(1) the original accident data is orderly sorted and counted, and a research object, a main accident type and a main accident form are determined according to distribution characteristics such as accident occurrence places, types and forms. Meanwhile, direct reasons recorded in the accident recognition book are counted, basic probability is given, potential factors with weak relevance are eliminated from the four aspects of people, vehicles, roads and environment according to two-term distribution statistical test, prominent potential influence factors with obvious influence are identified, the obtained main influence factors and the prominent potential influence factors serve as urban road traffic accident risk factors, and a foundation is laid for establishment of a follow-up model.
(2) And constructing an effective risk analysis model to carry out risk analysis on the traffic accident. Firstly, on the basis of comparing advantages and disadvantages of the conventional risk analysis method and the application range, a dynamic fault tree method is selected in a targeted manner. And then, constructing a dynamic fault tree model of the urban road traffic accident according to the accident occurrence mechanism.
(3) And preprocessing and simplifying the model, modularly decomposing the simplified model, and identifying all module subtrees. And (3) writing a corresponding ite structure expression by adopting a recursion method aiming at the static subtrees, converting the subtrees into a binary decision diagram, and further determining a minimum cut set and an occurrence probability. And for the dynamic subtree, converting the dynamic subtree into a Markov chain based on a Markov process, further judging a fault mode of the dynamic subtree, and calculating to obtain probability importance. And then modularly synthesizing each subtree to obtain a main accident cause chain.
(4) A Bow-tie model is introduced to describe the whole process from the origin of the accident, to the occurrence of the accident and then to the consequence of the accident. Firstly, an event tree model is constructed by analyzing the generation process of accident consequences. And determining the fuzzy probability of each event chain by combining an expert scoring method with the triangular fuzzy number. And combining the risk matrix to obtain a high risk event chain. Docking main accident cause chains in the fault tree with high-risk event chains in the event tree to construct a Bow-tie model, wherein the left side of the Bow-tie model provides a corresponding prevention and solution scheme for 5 main accident cause chains; the right side of the Bow-tie model is based on 2 high-risk event chains, and a targeted accident consequence coping scheme is provided.
The method has positive effects on the analysis and evaluation of urban traffic accident risks, but has certain defects which are mainly shown in the following three aspects:
(1) the data related to the urban traffic accidents, which are aimed at by the method, are mainly historical data, and the acquisition and processing of real-time data are lacked.
(2) The coding implementation difficulty in the data processing process is high, and especially, the complex protocol configuration and analysis are difficult to implement.
(3) Particularly, the method is not targeted for the specific item of analyzing the urban bus accident risk factors.
Disclosure of Invention
The invention aims to provide an efficient and convenient analysis method capable of reflecting the dynamic change of urban bus accident risk factors in time, thereby overcoming the defects of the prior art. The purpose of the invention is realized by the following technical scheme:
a city bus accident risk factor analysis method, the bus accident information processing system used in the method includes the central processing unit, data conversion module, database, clock module, gateway module, information display module, internet module, satellite positioning module, encoder and automatic camera installed on the city road intelligent light bar; the satellite positioning module and the encoder are in communication connection with the central processing unit through the data conversion module; the wired internet module and the information display module are in communication connection with the central processing unit through the gateway module, and the database, the clock module and the automatic camera are directly in communication connection with the central processing unit; the central processing unit is in communication connection with a control center of a city public transportation management department through a gateway module and an internet module; the method comprises the following steps:
step 1, collecting road traffic accident data information related to a bus, manufacturing a sample data set according to related risk factors and accident types, and performing data preprocessing;
step 2, selecting risk factors from four aspects of people, vehicles, roads and environment, and intuitively analyzing the influence degree of each risk factor by adopting a correlation statistical analysis means so as to determine the characteristics of the bus accident;
step 3, establishing a public transport accident Logistic model by taking the risk factors in the selected sample data set as independent variables and the accident type as dependent variables, and determining the significant factors influencing the urban public transport safety;
step 4, associating the risk factors of the bus accident by adopting an Apriori algorithm, and mining the influence of the association of the risk factors of people, vehicles, roads and environment on the type of the bus accident;
and 5, analyzing risk factors influencing the urban bus safety by combining the influence of single factors analyzed by the Logistic regression model on the bus accident type and the influence of the correlation of multiple factors mined by the Apriori algorithm on the accident type.
The basic concept of the invention is as follows: the method is characterized in that a bus accident information processing system is installed by using intelligent lamp bars on two sides of an urban road (especially an accident multi-occurrence section or intersection) or a roundabout, bus accident information is collected, analyzed and processed in real time, and urban bus accident risk factors are analyzed and evaluated quickly and accurately by using a Logistic model and an Apriori algorithm in combination with bus accident history information stored by a control center of an urban bus management department.
On the basis of the technical scheme, the invention can be additionally provided with the following technical means so as to better realize the aim of the invention:
and (3) when the step 1 is executed, obtaining information in the aspects of personnel characteristics, vehicle characteristics, road conditions, accident occurrence time, environment information and accident types through data screening.
Further, when the step 2 is executed, the current situation of the bus accident is analyzed in four aspects of the accident occurrence time, the accident occurrence position, the driver, the road and the environment, the occurrence situation and the development trend of the bus accident are known on the whole, and the time-space distribution characteristics of the accident are found.
Further, when the step 3 is executed, variables in risk factors in four aspects of the driver attribute, the vehicle, the road and the environment are selected from the bus accident data as independent variables, the accident type is taken as a dependent variable, and the accident type is divided into four types of non-casualty, light injury, heavy injury and death.
Further, step 3 comprises step 301 and step 302, wherein step 301 adopts an ordered multivariate Logistic regression model to establish the relationship between the accident type and each variable, so as to identify risk factors influencing the urban bus operation safety; step 302, solving the model by using Matlab software to solve the regression coefficients of the variables
。
The invention has the following beneficial effects:
(1) the public transport accident information processing system is arranged by utilizing the existing intelligent lamp bar (such as the intelligent lamp bar described in the patent application specification of CN 112378373A), so that the public transport accident information processing system not only can collect, analyze and process the urban public transport accident information in real time, but also has low implementation cost.
(2) By establishing a public transport accident Logistic model and adopting an Apriori algorithm, the invention greatly reduces the difficulty of coding realization in the urban public transport accident data processing process, effectively solves the configuration and analysis of a complex protocol in the urban public transport accident data processing process, and can quickly and accurately analyze and evaluate urban public transport accident risk factors.
Drawings
Fig. 1 is a block diagram of a bus accident information processing system according to an embodiment of the present invention.
Detailed Description
In order to facilitate those skilled in the art to understand the technical solution of the present invention, an embodiment of the present invention is described below with reference to the accompanying drawings.
As shown in fig. 1, the bus accident information processing system used in the urban bus accident risk factor analysis method of the present invention comprises a central processing unit, a data conversion module, a database, a clock module, a gateway module, an information display module, an internet module, a satellite positioning module, an encoder and an automatic camera, which are integrally installed on an urban road intelligent light bar; the satellite positioning module and the encoder are in communication connection with the central processing unit through the data conversion module; the wired internet module and the information display module are in communication connection with the central processing unit through the gateway module, and the database, the clock module and the automatic camera are directly in communication connection with the central processing unit; the central processor is in communication connection with a control center (not shown in the figure) of the urban public transportation management department through a gateway module and an internet module.
The urban bus accident risk factor analysis method comprises the following steps:
step 1, collecting road traffic accident data information related to a bus, screening to obtain information such as personnel characteristics, vehicle characteristics, road conditions, accident occurrence time, environmental information, accident types and the like in the data, making a sample data set according to related risk factors and the accident types, and performing data preprocessing.
And 2, selecting risk factors from the four aspects of people, vehicles, roads and environment, and intuitively analyzing the influence degree of each risk factor by adopting a correlation statistical analysis means so as to determine the characteristics of the bus accident.
Step 3, selecting variables in risk factors of the driver attribute, the vehicle, the road and the environment from the bus accident data as independent variables, establishing a bus accident Logistic model by taking the accident type as a dependent variable, and determining the significance factor influencing the urban bus safety; the accident types are classified into four types, non-casualty, light injury, heavy injury and death. Step 3 comprises step 301 and step 302, wherein in step 301, an ordered multivariate Logistic regression model is adopted to establish the relationship between the accident type and each variable, so that risk factors influencing the urban bus operation safety are identified; step 302, solving the model by using Matlab software to solve the regression coefficient beta of each variable.
Step 4, associating the risk factors of the bus accident by adopting an Apriori algorithm, and mining the influence of the association of the risk factors of people, vehicles, roads and environment on the type of the bus accident;
and 5, analyzing risk factors influencing the urban bus safety by combining the influence of single factors analyzed by the Logistic regression model on the bus accident type and the influence of the correlation of multiple factors mined by the Apriori algorithm on the accident type.
The road traffic accident data information comprises public traffic accident historical information stored in a control center of a city public traffic management department and information collected by a public traffic accident information processing system in real time. The analysis of the bus accident risk factors of the local road sections of the city is completed by a central processing unit in a bus accident information processing system, the analysis of the bus accident risk factors of the whole city is completed by a control center of a city bus management department, and in the process, the control center of the city bus management department communicates information with the central processing unit in the bus accident information processing system.
The bus accident information processing system and the basic working steps used in one embodiment of the present invention are introduced above, and the data processing method used in this embodiment is further described below;
in step 301, the first or last category is generally selected as the reference category, and if the Kth category is used to represent the reference category, the multivariate Logistic regression model can be represented in the form of K-1 binary Logistic regression models:
…
in the formula (I), the compound is shown in the specification,
is as followsiAn observation caseIs an explanatory variable ofJAn explanatory variable, the parameter of the logistic regression model of the kth class is
Only haveJ +1 parameters, where the first parameter is the intercept term. From this, the coefficients of a multi-term Logistic regression model can be seen
Power exponent of
The method is an important index for measuring the influence degree of the explanation variable on the dependent variable, is the ratio of the occurrence probability and the non-occurrence probability of an event, and can judge the relative risk degree according to the ratio.
Interpreted as interpreting variables under the control of other interpreting variables
The influence of the unit change ratio of (2) on the comparison of the class and the reference class. The occurrence ratio indicates the change of the probability of each type of distribution without increasing or decreasing the influence factor by one unit, i.e.
<1 occurrence ratio decrease;
occurrence ratio of =1 is unchanged;
>1 occurs with an increase in the ratio.
When step 302 (model solution using Matlab software) is executed, the equation (1) is exponentially transformed, and the probability of each class can be expressed as the probability of the reference class, that is:
since the sum of the probabilities of all classes is 1, the probability of the reference class can be found from equation (2) as:
by substituting the probability of the reference class in equation (3) into equation (2), the probability of each class can be obtained:
solving the multiple Logistic regression model by adopting a maximum likelihood method, wherein the likelihood function is expressed as:
then the parameter estimation can be found as:
in step 4, the invention employs Apriori algorithm. The Apriori algorithm is a classical approach to association rule data mining, which exploits the set of k terms to explore the (k + 1) term set using a layer-by-layer search iteration. First, the geometry of the frequent 1 item set, denoted L, is determined1Determining a set L of frequent 2-item sets using L12By means of L2Determination of L3…, and so on, iterating layer by layer until a frequent k term set cannot be found, determining L for each iterationkOne database scan is required. All non-empty subsets of the frequent item set must also be of a frequent nature and can be used to compress the search space, thereby increasing the efficiency of layer-by-layer generation of the frequent item set. Secondly, the Apriori algorithm requires three specific steps of connection, pruning and association rule generation when generating the association rule. Therefore, in this embodiment, step 4 is performedThe method comprises the following three steps:
step 401, connect, in order to findL k (all frequent)kCollection of item sets), by combiningL k-1(all frequent)kSet of-1 item sets) to join with itself to generate candidateskCollections of item sets, candidate collections are notedC k . Is provided withl 1Andl 2is thatL k-1Is a member of (1). Note the bookl i [j]To representl iTo (1)jAn item. Assume that the Apriori algorithm lexicographically orders terms in a transaction or set of terms, i.e., fork-1) item setl i，l i [1] < l i [2] < l i [k-1]Will beL k-1Is connected with itself ifl 1 [1] = l 2 [1]）&&（l 1 [2] = l 2 [2]）&&…&&（l 1 [k-2] = l 2 [k-2]）&&（l 1 [k-1] = l 2 [k-1]) Then it is considered asl 1Andl 2are connectable. Connection ofl 1Andl 2is as a result of l 1 [1], l 1 [1], …, l 1 [1], l 1 [1]}
Step 402, the pruning,C k is thatL k A superset of (i), i.e.C k May or may not be frequent. By scanning all transactions, determiningC k The count of each candidate is judged whether the count is smaller than the minimum support count, and if the count is larger than the minimum support count, the candidate member is considered to be frequent.
Step 403, for each frequent item setlGenerating alAll non-empty subsets of (a). For thelEach non-empty subset ofsIf, if
Then output the rule
. Wherein the content of the first and second substances,
is the minimum confidence threshold. The Apriori algorithm is used for data mining, a minimum confidence coefficient and a minimum support degree are required to be set firstly, the confidence coefficient and the support degree of the rule are both between 0% and 100%, and the two parameters are required to be debugged in an emphasized mode so as to achieve the purpose of reducing the number of the rule.
The technical scheme of one embodiment of the invention is introduced above, and the results obtained when the invention is tested in Buddha city and Zen city are further described by two tables as follows:
table 1 shows the results of the Logistic model
Table 2 shows the combined results of the related influence factors of the bus accidents
Claims (5)
1. A city bus accident risk factor analysis method is characterized by comprising the following steps: the bus accident information processing system used by the method comprises a central processing unit, a data conversion module, a database, a clock module, a gateway module, an information display module, an internet module, a satellite positioning module, an encoder and an automatic camera which are integrally installed on an urban road intelligent lamp bar; the satellite positioning module and the encoder are in communication connection with the central processing unit through the data conversion module; the internet module and the information display module are in communication connection with the central processing unit through the gateway module, and the database, the clock module and the automatic camera are directly in communication connection with the central processing unit; the central processing unit is in communication connection with a control center of a city public transportation management department through a gateway module and an internet module; the method comprises the following steps:
step 1, collecting road traffic accident data information related to a bus, making a sample data set according to related risk factors and accident types, and performing data preprocessing;
step 2, selecting risk factors from four aspects of people, vehicles, roads and environment, and intuitively analyzing the influence degree of each risk factor by adopting a correlation statistical analysis means so as to determine the characteristics of the bus accident;
step 3, establishing a public transport accident Logistic model by taking the risk factors in the selected sample data set as independent variables and the accident type as dependent variables, and determining the significant factors influencing the urban public transport safety;
step 4, associating the risk factors of the bus accident by adopting an Apriori algorithm, and mining the influence of the association of the risk factors of people, vehicles, roads and environment on the type of the bus accident;
and 5, analyzing risk factors influencing the urban bus safety by combining the influence of single factors analyzed by the Logistic regression model on the bus accident type and the influence of the correlation of multiple factors mined by the Apriori algorithm on the accident type.
2. The urban bus accident risk factor analysis method according to claim 1, characterized in that: and (3) when the step 1 is executed, obtaining information in the aspects of personnel characteristics, vehicle characteristics, road conditions, accident occurrence time, environment information and accident types through data screening.
3. The urban bus accident risk factor analysis method according to claim 1, characterized in that: and (3) when the step 2 is executed, analyzing the current situation of the bus accident in four aspects of the accident occurrence time, the accident occurrence position, the driver, the road and the environment, integrally knowing the occurrence situation and the development trend of the bus accident and finding the time-space distribution characteristics of the accident.
4. The urban bus accident risk factor analysis method according to claim 1, characterized in that: and 3, selecting variables in risk factors of the driver attribute, the vehicle, the road and the environment from the bus accident data as independent variables, and taking the accident type as a dependent variable, wherein the accident type is divided into four types of non-casualty, light injury, heavy injury and death.
5. The urban bus accident risk factor analysis method according to claim 4, characterized in that: step 3 comprises step 301 and step 302, wherein in step 301, an ordered multivariate Logistic regression model is adopted to establish the relationship between the accident type and each variable, so that risk factors influencing the urban bus operation safety are identified; step 302, solving the model by using Matlab software to solve the regression coefficients of the variables
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210170341.8A CN114493363A (en) | 2022-02-24 | 2022-02-24 | Urban bus accident risk factor analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210170341.8A CN114493363A (en) | 2022-02-24 | 2022-02-24 | Urban bus accident risk factor analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114493363A true CN114493363A (en) | 2022-05-13 |
Family
ID=81484850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210170341.8A Pending CN114493363A (en) | 2022-02-24 | 2022-02-24 | Urban bus accident risk factor analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114493363A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980451A (en) * | 2023-09-25 | 2023-10-31 | 北京智城联合科技发展有限公司 | Urban safety protection early warning platform system |
-
2022
- 2022-02-24 CN CN202210170341.8A patent/CN114493363A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980451A (en) * | 2023-09-25 | 2023-10-31 | 北京智城联合科技发展有限公司 | Urban safety protection early warning platform system |
| CN116980451B (en) * | 2023-09-25 | 2023-12-22 | 北京智城联合科技发展有限公司 | Urban safety protection early warning platform system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108417033B (en) | Expressway traffic accident analysis and prediction method based on multi-dimensional factors | |
| CN113723632A (en) | Industrial equipment fault diagnosis method based on knowledge graph | |
| CN114048870A (en) | Power system abnormity monitoring method based on log characteristic intelligent mining | |
| CN113222442B (en) | Real-time traffic air pollution emission list calculation method and decision-making auxiliary method | |
| CN106021545A (en) | Method for remote diagnoses of cars and retrieval of spare parts | |
| CN106054858A (en) | Decision tree classification and fault code classification-based vehicle remote diagnosis and spare part retrieval method | |
| CN111538741B (en) | Deep learning analysis method and system for big data of alarm condition | |
| Jeong et al. | A systemic approach to exploring an essential patent linking standard and patent maps: Application of generative topographic mapping (GTM) | |
| CN110555565A (en) | Decision tree model-based expressway exit ramp accident severity prediction method | |
| CN114298412A (en) | Enterprise safety standardized operation method based on artificial intelligence and big data | |
| CN114493363A (en) | Urban bus accident risk factor analysis method | |
| CN110598747B (en) | Road classification method based on self-adaptive K-means clustering algorithm | |
| CN114299742B (en) | Speed limit information dynamic identification and update recommendation method for expressway | |
| Yan et al. | The identification algorithm and model construction of automobile insurance fraud based on data mining | |
| Jiang et al. | Improvement of random forest by multiple imputation applied to tower crane accident prediction with missing data | |
| Watanabe et al. | A method for the estimation of coexisting risk-inducing factors in traffic scenarios | |
| CN109447306B (en) | Subway accident delay time prediction method based on maximum likelihood regression tree | |
| Kang et al. | Model establishment of decision tree algorithm and its application in vehicle fault prediction analysis | |
| CN115240145A (en) | Method and system for detecting illegal operation behaviors based on scene recognition | |
| CN113849656A (en) | Technical text mining method and system based on clustering graph | |
| CN114003638A (en) | Intelligent interconnected big data processing system | |
| CN113807704A (en) | Intelligent algorithm platform construction method for urban rail transit data | |
| CN106056223A (en) | Platform for vehicle remote diagnosis and spare part retrieval | |
| Koduru | Prediction Of Severity Of An Accident Based On Extent Of Injury Using Machine Learning | |
| CN116878531B (en) | Intelligent navigation method based on road resource prediction |
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 |