CN115545996B - Similarity matrix-based subway abnormal historical passenger flow identification method and device - Google Patents
Similarity matrix-based subway abnormal historical passenger flow identification method and device Download PDFInfo
- Publication number
- CN115545996B CN115545996B CN202211534320.6A CN202211534320A CN115545996B CN 115545996 B CN115545996 B CN 115545996B CN 202211534320 A CN202211534320 A CN 202211534320A CN 115545996 B CN115545996 B CN 115545996B
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- flow data
- historical passenger
- similarity
- historical
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000013480 data collection Methods 0.000 abstract 1
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 238000005206 flow analysis Methods 0.000 abstract 1
- 238000011002 quantification Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G06Q50/40—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention discloses a method and a device for identifying abnormal historical passenger flow of a subway based on a similarity matrix, which specifically comprise the following steps: acquiring AFC historical passenger flow data; dividing the AFC historical passenger flow data into a plurality of groups of historical passenger flow data according to a preset rule; for the same group of historical passenger flow data, calculating the similarity between the historical passenger flow data of each day and the historical passenger flow data of other days to obtain a similarity matrix corresponding to each group; calculating the actual similarity of each day in each group according to the similarity matrix of each group and judging; and when the actual similarity is smaller than a preset threshold value, judging that the current-day historical passenger flow data is abnormal passenger flow data. The method based on the similarity matrix greatly improves the calculation efficiency, thereby improving the reliability of passenger flow data collection, enhancing the effectiveness of passenger flow data analysis, realizing the quantification of passenger flow analysis and improving the accuracy of passenger flow prediction.
Description
Technical Field
The invention relates to the technical field of intelligent security inspection, in particular to a method and a device for identifying abnormal historical passenger flow of a subway based on a similarity matrix.
Background
The urban rail transit is an important component of public traffic, has the characteristics of large traffic volume, high speed, high efficiency, punctuality, small pollution and the like, and has the functions of relieving traffic jam and improving the operation efficiency. With the continuous expansion of urban rail transit network scale and the rapid increase of passenger flow, urban rail transit under networked operation conditions faces sudden accidents from natural disasters, social security, facility equipment failures and the like and high-intensity passenger flow impact. The toughness of the urban rail transit arrival passenger flow is evaluated, the identification of abnormal passenger flow is facilitated, and therefore a manager can make a correct decision conveniently, the method has important significance for risk identification and risk prevention and control of urban rail transit, and meanwhile the safety operation and service level of the urban rail transit are guaranteed.
Most of the current abnormal passenger flow prediction utilizes a target detection algorithm to monitor the passenger flow volume in public transportation in real time, and predicts the passenger flow volume at the future time according to the real-time monitoring result, thereby leading the passenger flow before the abnormal passenger flow of the public transportation occurs. However, the prediction accuracy is not high by using methods such as a target detection algorithm, and it is difficult to visually reflect the abnormal degree of the passenger flow at a certain day.
Disclosure of Invention
The invention aims to provide a method and a device for identifying abnormal historical passenger flow of a subway based on a similarity matrix.
A subway abnormal history passenger flow identification method based on a similarity matrix specifically comprises the following steps:
acquiring AFC historical passenger flow data;
dividing the AFC historical passenger flow data into a plurality of groups of historical passenger flow data according to a preset rule;
for the same group of historical passenger flow data, calculating the similarity between the historical passenger flow data of each day and the historical passenger flow data of other days to obtain a similarity matrix corresponding to each group;
calculating the actual similarity of each day in each group according to the similarity matrix of each group;
judging the magnitude of the actual similarity and a preset threshold value;
and when the actual similarity is smaller than a preset threshold value, judging that the current-day historical passenger flow data is abnormal passenger flow data.
Further, the preset rule is as follows: and dividing the AFC historical passenger flow data into seven groups of historical passenger flow data according to the week.
Further, the similarity matrix S satisfies S X,X =1，S X,Y = S Y,X Said S X,Y The similarity between the historical passenger flow data with the date X and the historical passenger flow data with the date Y.
Further, said S X,Y The ratio of the intersection of the coverage areas of the curve X and the curve Y to the union of the coverage areas of the curve X and the curve Y is shown, wherein the curve X is the curve of the historical traffic data with the date X changing with the time in the day, and the curve Y is the curve of the historical traffic data with the date Y changing with the time in the day.
Further, said S X,Y Is obtained by the following steps:
obtaining historical passenger flow data with the date of X;
uniformly dividing historical passenger flow data with the date of X into a plurality of time periods, and counting the historical passenger flow data X of each time period i with the date of X i ；
Obtaining historical passenger flow data with the date of Y;
uniformly dividing historical passenger flow data with the date of Y into a plurality of time periods, and counting the historical passenger flow data Y of each time period i with the date of Y i ；
The similarity
Where n is the number of time periods in the day.
Further, the actual similarity is an average value of the similarity between the historical passenger flow data of each day and the historical passenger flow data of other days.
Further, the abnormal passenger flow data does not include historical passenger flow data of holidays.
Further, according to the actual similarity, the historical passenger flow data of each day are arranged in a descending order, and according to the actual similarity and the size of a preset threshold value, abnormal passenger flow is output according to the size of the date.
A subway abnormal history passenger flow identification device based on a similarity matrix comprises:
one or more processors;
the storage unit is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors can realize the subway abnormity history passenger flow identification method based on the similarity matrix.
The invention has the following beneficial effects:
1. the method and the system can realize real-time monitoring of urban rail transit passenger flow data, and pre-warn abnormal passenger flow through calculation of a similar matrix, help managers to develop current-limiting measures in time, and evaluate fluctuation conditions of the inbound passenger flow in a time period from disturbance occurrence to normal restoration, thereby evaluating advantages and disadvantages of passenger flow dispersion measures, providing guidance for future passenger flow dispersion work, effectively reducing travel delay caused by abnormal passenger flow occurrence, and improving service level and operation efficiency of urban rail transit;
2. by the method and the system, historical passenger flow can be analyzed and processed, the date of abnormal situations in the passenger flow can be quickly found out in a very short time, and consumed computing resources are very few. According to the test result, the scheme can accurately find out abnormal dates such as sudden large passenger flows, and subway operation companies can accurately position the abnormal dates and summarize abnormal passenger flow rules according to the scheme.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of a curve X and a curve Y according to the present invention;
FIG. 3 is a schematic view of the intersection of the coverage areas of curve X and curve Y;
FIG. 4 is a diagram illustrating a coverage area union of curve X and curve Y according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
In addition, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness. Those of ordinary skill in the art will recognize that various changes and modifications of the examples described herein can be made without departing from the spirit and scope of the disclosure.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
Example 1
As shown in fig. 1, a method for identifying abnormal historical passenger flow of a subway based on a similarity matrix specifically includes the following steps:
acquiring AFC historical passenger flow data;
dividing the AFC historical passenger flow data into a plurality of groups of historical passenger flow data according to a preset rule;
for the same group of historical passenger flow data, calculating the similarity between the historical passenger flow data of each day and the historical passenger flow data of other days to obtain a similarity matrix corresponding to each group;
calculating the actual similarity of each day in each group according to the similarity matrix of each group;
judging the actual similarity and a preset threshold value;
and when the actual similarity is smaller than a preset threshold value, judging that the current-day historical passenger flow data is abnormal passenger flow data.
Optionally, the preset rule is: and dividing the AFC historical passenger flow data into seven groups of historical passenger flow data according to the week.
Optionally, the similarity matrix S satisfies S X,X =1，S X,Y = S Y,X Said S X,Y The similarity between the historical passenger flow data with the date X and the historical passenger flow data with the date Y.
Optionally, the S X,Y The ratio of the intersection of the coverage areas of the curve X and the curve Y to the union of the coverage areas of the curve X and the curve Y is shown in fig. 2, where the curve X is a curve of the historical traffic data with date X changing with time during a day, and the curve Y is a curve of the historical traffic data with date Y changing with time during a day.
Optionally, the S X,Y Is obtained by the following steps:
obtaining historical passenger flow data with the date of X;
uniformly dividing historical passenger flow data with the date of X into a plurality of time periods, and counting the historical passenger flow data X of each time period i with the date of X i ；
Obtaining historical passenger flow data with the date of Y;
calendar with date YThe historical passenger flow data is evenly divided into a plurality of time periods, and the statistical date of the historical passenger flow data Y of each time period i is Y i ；
The similarity
Where n is the number of time periods in the day.
Optionally, the actual similarity is an average of similarities between the historical passenger flow data of each day and the historical passenger flow data of other days.
Optionally, the abnormal passenger flow data does not include historical passenger flow data for holidays.
Optionally, the historical passenger flow data of each day is sorted in a descending order according to the actual similarity, and abnormal passenger flow is output according to the size of the date according to the actual similarity and the size of a preset threshold.
The following are exemplary:
step 1: reading AFC passenger flow historical data and converting the AFC passenger flow historical data into passenger flow data;
acquiring AFC historical inbound passenger flow data:
historical AFC transaction data are extracted from the subway, and the AFC transaction data comprise the station entering time and the station entering name information of each passenger.
Each day is divided into several time periods according to a set time interval T, such as 5 minutes. For example, 6; 6. Note that T may vary, and thus the scope of protection is not limited to a 5 minute time interval.
And mapping the AFC transaction data statistics to the divided time periods, so that historical inbound passenger flow data of the time interval T of each day can be obtained statistically.
Illustratively, the AFC historical inbound traffic data is selected over a 180 day time span.
Step 2: historical data is divided into 7 groups according to weeks;
that is, one group of all historical passenger flow data on Monday, one group of all historical passenger flow data on Tuesday, one group of all historical passenger flow data on Wednesday, and one group of all historical passenger flow data on Wednesday, \ 8230, and so on.
And step 3: a N x N similarity matrix is generated for the days (N days) of traffic in each group, as shown in table 1.
TABLE 1
Where N is the total number of dates (in days) for the historical traffic data in each group, the similarity matrix is generated as follows:
suppose S X,Y As the similarity between Day X and Day Y, S is known X,X =1，S X,Y = S Y,X 。
Wherein S X,Y The calculation method of (2) will be described in detail in the next step.
And 4, step 4: and calculating the similarity between the passenger flow and all other dates every day, and inputting a similarity matrix.
And (3) similarity calculation:
wherein, X i Representing the number of passengers in the period i on the date X curve;
Y i representing the passenger flow quantity of the date Y curve in the period i;
n total number of divided time intervals T in a day;
S X,Y the value can be used as a calculation index for measuring the similarity between the two curves, i.e. calculating the ratio of the intersection of the coverage areas (as shown in fig. 3) of the two curves (the curve of date X and the curve of date Y) to the total coverage area (as shown in fig. 4) of the two curves (as shown in fig. 3), and when the two curves are completely overlapped, the IOU value is 1, and the similarity between the two curves is the highest. The value is in the range of [0,1]]In between, a larger value indicates a higher similarity between the two curves.
Exemplarily, the passenger flow data between the subway business hours 6 to 23According to the following steps of 6 1 Traffic volume for date X in 1 st epoch, X 2 Is the passenger flow volume of date X in the 2 nd time period, \ 8230;, X n The amount of traffic on date X during the nth time period.
For better similarity calculation, according to the discrete data points: x 1 - - (1) period of time, X 2 - - (2 nd time period, \ 8230;, X n -n-th period, performing a curve fitting to obtain a date X curve.
And 5: and carrying out transverse averaging on the similarity matrix, and taking the average as the actual similarity.
And performing horizontal averaging to represent the general condition of the similarity of the passenger flow under the date and all other dates, wherein the higher the similarity is, the lower the probability that the passenger flow under the date is abnormal is represented. The regenerated similarity matrix is shown in table 2:
TABLE 2
Wherein:
…
and so on;
step 6: defining a critical value of the similarity according to actual requirements, and taking historical passenger flow data of a certain day lower than the critical value as abnormal passenger flow data;
according to actual needs, a number between [0,1] can be set as a similarity threshold value, and data higher than the threshold value can be regarded as data with higher similarity and used as normal passenger flow data.
It should be noted that the threshold value needs to be configured according to the specific situation of the selected historical passenger flow data, and an exemplary threshold value may be 0.8.
It should be noted that, the abnormal passenger flow data must be removed from the historical passenger flow data of holidays, and in a real environment, holidays or some major events have a great influence on the passenger flow data, so that the passenger flow data on these dates are very necessary to be provided. Data of holidays, such as dueleven, need to be deleted according to the situation of display. Because the influence degree of each holiday or a known big event on the passenger flow data is different, for example, the spring festival and the national day festival are seven-day holidays, and five-one holidays are three-day holidays.
Illustratively, holiday time data is obtained, thereby determining that certain days are holidays;
and deleting historical passenger flow data corresponding to the holiday time data from the abnormal passenger flow data.
And 7: and performing descending arrangement on each day according to the actual similarity, and outputting abnormal passenger flow according to the date.
Example 2
A subway abnormal history passenger flow identification device based on a similarity matrix comprises:
one or more processors;
the storage unit is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors can realize the subway abnormity history passenger flow identification method based on the similarity matrix.
Embodiment 3 is a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, can implement the method for identifying the abnormal historical passenger flow of the subway based on the similarity matrix.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications, equivalent arrangements, and alternatives falling within the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. A subway abnormal historical passenger flow identification method based on a similarity matrix is characterized by specifically comprising the following steps of:
acquiring AFC historical passenger flow data;
dividing the AFC historical passenger flow data into a plurality of groups of historical passenger flow data according to a preset rule; the preset rule is as follows: dividing the AFC historical passenger flow data into seven groups of historical passenger flow data according to the week;
for the same group of historical passenger flow data, calculating the similarity between the historical passenger flow data of each day and the historical passenger flow data of other days to obtain a similarity matrix corresponding to each group; the similarity matrix S satisfies S X,X =1，S X,Y = S Y,X Said S X,Y Similarity between the historical passenger flow data with the date X and the historical passenger flow data with the date Y;
s is X,Y The ratio of the intersection of the coverage range of a curve X and the coverage range of a curve Y to the union of the coverage range of the curve X and the coverage range of the curve Y is shown, wherein the curve X is a curve of the historical passenger flow data with the date X changing along with the time in one day, and the curve Y is a curve of the historical passenger flow data with the date Y changing along with the time in one day;
calculating the actual similarity of each day in each group according to the similarity matrix of each group; the actual similarity is the average value of the similarity of the historical passenger flow data of each day and the historical passenger flow data of other days;
judging the actual similarity and a preset threshold value;
and when the actual similarity is smaller than a preset threshold value, judging that the historical passenger flow data of the current day is abnormal passenger flow data.
2. The method for identifying abnormal historical passenger flow of subway based on similarity matrix as claimed in claim 1, wherein said S X,Y Obtained by the following steps:
obtaining historical passenger flow data with the date X;
uniformly dividing the historical passenger flow data with the date X into a plurality of time periods, and counting the historical passenger flow data X of each time period i with the date X i ；
Obtaining historical passenger flow data with the date of Y;
uniformly dividing historical passenger flow data with the date of Y into a plurality of time periods, and counting the historical passenger flow data Y of each time period i with the date of Y i ；
The similarity
Where n is the number of time periods in the day.
3. A method as claimed in claim 1, wherein the abnormal passenger flow data does not include historical passenger flow data of holidays.
4. A method as claimed in claim 3, wherein the historical passenger flow identification method based on the similarity matrix is characterized in that the historical passenger flow data of each day is sorted in a descending order according to the actual similarity, and the abnormal passenger flow is output according to the size of the date according to the actual similarity and the size of the preset threshold.
5. The utility model provides a subway unusual historical passenger flow recognition device based on similarity matrix which characterized in that includes:
one or more processors;
a storage unit, configured to store one or more programs, which when executed by the one or more processors, enable the one or more processors to implement the method for identifying abnormal history passenger flows of a subway based on a similarity matrix according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534320.6A CN115545996B (en) | 2022-12-02 | 2022-12-02 | Similarity matrix-based subway abnormal historical passenger flow identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211534320.6A CN115545996B (en) | 2022-12-02 | 2022-12-02 | Similarity matrix-based subway abnormal historical passenger flow identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115545996A CN115545996A (en) | 2022-12-30 |
| CN115545996B true CN115545996B (en) | 2023-03-10 |
Family
ID=84722421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211534320.6A Active CN115545996B (en) | 2022-12-02 | 2022-12-02 | Similarity matrix-based subway abnormal historical passenger flow identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545996B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473337B (en) * | 2023-12-25 | 2024-03-22 | 中国科学院自动化研究所 | Track association method, track association device, track association equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2784729A1 (en) * | 2013-03-25 | 2014-10-01 | Amadeus | Method and system for detecting anomaly in passenger flow |
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN109460871A (en) * | 2018-11-08 | 2019-03-12 | 北京首都国际机场股份有限公司 | Airport passenger amount prediction technique based on the identification of typical day |
| WO2019090753A1 (en) * | 2017-11-13 | 2019-05-16 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring traffic congestion |
| CN109784970A (en) * | 2018-12-13 | 2019-05-21 | 交控科技股份有限公司 | It is a kind of to be ridden the service recommendation method and device of data based on AFC passenger |
| CN111932429A (en) * | 2020-10-14 | 2020-11-13 | 中国矿业大学(北京) | OD-based rail transit station passenger flow structure similarity analysis method and device |
| CN112686428A (en) * | 2020-12-15 | 2021-04-20 | 广州新科佳都科技有限公司 | Subway passenger flow prediction method and device based on subway network station similarity |
| EP3849154A1 (en) * | 2015-06-05 | 2021-07-14 | Cisco Technology, Inc. | Network traffic monitoring system |
-
2022
- 2022-12-02 CN CN202211534320.6A patent/CN115545996B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2784729A1 (en) * | 2013-03-25 | 2014-10-01 | Amadeus | Method and system for detecting anomaly in passenger flow |
| EP3849154A1 (en) * | 2015-06-05 | 2021-07-14 | Cisco Technology, Inc. | Network traffic monitoring system |
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| WO2019090753A1 (en) * | 2017-11-13 | 2019-05-16 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring traffic congestion |
| CN109460871A (en) * | 2018-11-08 | 2019-03-12 | 北京首都国际机场股份有限公司 | Airport passenger amount prediction technique based on the identification of typical day |
| CN109784970A (en) * | 2018-12-13 | 2019-05-21 | 交控科技股份有限公司 | It is a kind of to be ridden the service recommendation method and device of data based on AFC passenger |
| CN111932429A (en) * | 2020-10-14 | 2020-11-13 | 中国矿业大学(北京) | OD-based rail transit station passenger flow structure similarity analysis method and device |
| CN112686428A (en) * | 2020-12-15 | 2021-04-20 | 广州新科佳都科技有限公司 | Subway passenger flow prediction method and device based on subway network station similarity |
Non-Patent Citations (4)
| Title |
|---|
| 地铁客流分析及列车发车间隔优化研究;刘兰芬等;《武汉理工大学学报(交通科学与工程版)》;20151215(第06期);第29-34页 * |
| 城市轨道交通自动售检票系统实时进站客流量异常检测;张见等;《城市轨道交通研究》;20181010(第10期);第27-30+44页 * |
| 城际轨道交通转移客流量预测方法研究;姚智胜等;《交通运输系统工程与信息》;20120228;第119-123页 * |
| 基于AFC数据和RF模型的城轨车站服务功能分类;王子甲等;《交通运输系统工程与信息》;20180815(第04期);第228-234页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115545996A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Moore et al. | Secondary accident rates on Los Angeles freeways | |
| Emam et al. | Using real-life dual-loop detector data to develop new methodology for estimating freeway travel time reliability | |
| US9111442B2 (en) | Estimating incident duration | |
| Xu et al. | Exploring the impacts of speed variances on safety performance of urban elevated expressways using GPS data | |
| CN115545996B (en) | Similarity matrix-based subway abnormal historical passenger flow identification method and device | |
| CN111144727A (en) | Urban rail transit arrival passenger flow toughness evaluation system and method | |
| CN107045786A (en) | The computational methods of traffic accident interval time occur for the driver based on Kaplan Meier methods | |
| CN115409395A (en) | Quality acceptance inspection method and system for hydraulic construction engineering | |
| Qin et al. | Characterization of accident capacity reduction | |
| Harrod et al. | Distribution fitting for very large railway delay data sets with discrete values | |
| CN113780682B (en) | Rail transit system service fault prediction method based on fault markers | |
| CN114997527B (en) | Enterprise assessment and evaluation method, system and terminal based on road transportation dynamic data | |
| CN114066288B (en) | Intelligent data center-based emergency detection method and system for operation road | |
| CN108959596B (en) | Bus step fare prediction method | |
| Tubis et al. | Measurement of punctuality of services at a public transport company | |
| CN114312930A (en) | Train operation abnormity diagnosis method and device based on log data | |
| CN112488568A (en) | Method for evaluating large passenger flow operation risk of subway station and application thereof | |
| Halim et al. | The forecasting of a traffic accident in the pandemic of Covid-19 | |
| Bernhardt et al. | Improving the identification, analysis and correction of high-crash locations | |
| Pennetti et al. | Traveler perception of transportation system performance using kernel density estimation to prioritize infrastructure investments | |
| O'leary | The cost/benefit analysis: it can be a misleading tool for transportation planners | |
| Jagadeesh et al. | Predicting the Impact of Traffic Incidents: An Evaluative Analysis | |
| Karthik et al. | Bus priority lane in Bengaluru: A study on its effectiveness and driver stress | |
| CN116665342B (en) | New energy automobile driving behavior analysis method, system and equipment | |
| Wang et al. | Characteristics analysis and impact cluster on urban rail transit perturbations: a real case in Beijing |
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 |