CN115238079A - Epidemic situation early warning analysis method and system based on real-time traffic flow data - Google Patents
Epidemic situation early warning analysis method and system based on real-time traffic flow data Download PDFInfo
- Publication number
- CN115238079A CN115238079A CN202111327997.8A CN202111327997A CN115238079A CN 115238079 A CN115238079 A CN 115238079A CN 202111327997 A CN202111327997 A CN 202111327997A CN 115238079 A CN115238079 A CN 115238079A
- Authority
- CN
- China
- Prior art keywords
- data
- entity
- real
- early warning
- entities
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Library & Information Science (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to an epidemic situation early warning analysis method and system based on real-time traffic flow data, and belongs to the technical field of traffic big data. The mass data based on the network appointment data, the urban vehicle track data and the public traffic data are subjected to real-time data fusion, modeling and calculation, and the knowledge network map and the risk level of an epidemic entity are output in real time, so that the method has important guiding significance for preventing epidemic spread.
Description
Technical Field
The invention relates to an epidemic situation early warning analysis method and system based on real-time traffic flow data, and belongs to the technical field of traffic big data.
Background
The epidemic risk detection has important significance for urban traffic management, the epidemic often realizes large-area propagation in a short time, the propagation condition cannot be known, monitoring cannot be realized, and the epidemic infection control difficulty cannot be further increased due to the fact that prediction cannot be realized, the existing epidemic early warning analysis is based on manual epidemic flow adjustment, hidden risks cannot be found in advance by manual epidemic flow adjustment for urban-level mass data, the possible infection sources cannot be effectively detected quickly, serious hysteresis exists in the control of the epidemic based on T +1 delay, and early warning cannot be performed quickly.
Chinese patent document CN112131392A discloses a public health epidemic situation early warning system and method based on knowledge map, belonging to the technical field of computer network, the key point of the technical scheme is that the method comprises the following steps: s1, constructing an early warning model based on a public health epidemic situation knowledge graph; s2, acquiring entities and relations required by the public health epidemic situation knowledge graph; s3, extracting knowledge on the basis of information acquisition through an information extraction and semantic analysis technology, and accessing the extracted knowledge into a public health epidemic situation knowledge map for use; and S4, knowledge reasoning, namely excavating and reasoning the acquired relation between the entities through the existing knowledge mechanism, and obtaining the authenticity of the information through a weight algorithm. The method judges the authenticity of epidemic situations, and can not carry out rapid early warning, distribution and control on patients diagnosed with infectious diseases and people in contact with the patients.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an epidemic situation early warning analysis method and system based on real-time traffic flow data, which can quickly calculate the danger degree of urban mass data, perform real-time data fusion, modeling and calculation based on mass data of network appointment data, urban vehicle track data and public traffic data, output knowledge network maps and risk levels of epidemic entities in real time, and have important guiding significance for preventing epidemic situation diffusion.
The technical scheme of the invention is as follows:
an epidemic situation early warning analysis method based on real-time traffic flow data comprises the following steps:
(1) Collecting network appointment data, structured checkpoint data, road data and regional data (such as main urban business circles, hospitals and scenic spots), and performing modeling and data classification processing according to six different data fields of police, vehicles, people, things, roads and events;
(2) Carrying out spatial relationship matching on the classified network appointment data, the classified checkpoint data, the classified road data and the classified area data;
(3) Constructing relation data between the entities by using the matched spatial data;
(4) Synchronizing the relation data into a graph database, converting the relation data into a triple format, namely an entity-relation-entity through a program in the synchronization process, wherein if (a car with a license plate number of 123 is owned by a king automobile), a knowledge network graph is constructed by taking the entity as a point and the relation as a line, and the influence relation of the entity is marked through an arrow;
(5) And the front end retrieves and inquires the danger index of the entity and actively sends out early warning to the entity exceeding the threshold value.
Preferably, in step (1), the structured bayonet data is: extracting picture information into text information through a third party manufacturer by data acquired by a road camera, wherein the text information comprises license plate numbers and longitude and latitude coordinate information;
the network appointment data comprise license plate numbers and tracks;
the road data comprises line-shaped points consisting of longitude and latitude points of the road;
the regional data comprises surface shape points consisting of the boundary points of the business circles, the hospitals and the schools.
Preferably, in step (1), the modeling means: and fusing the networked car booking data, the structured checkpoint data, the road data and the area data, and putting the fused data into corresponding police, car, people, objects, roads and event data fields. (the data are classified into vehicles, the network car booking data belong to the vehicles, the track data of the network car booking are stored in the vehicle domain, the structured checkpoint data are stored in the object domain, and the road data and the area data are stored in the road domain.)
Preferably, in the step (1), the classification processing is: the data is divided into three types of factual time sequence data, static dimension data and change state data. If the network appointment track data are fact time sequence data, license plate numbers of the network appointment vehicles are static dimension data, payment states of the network appointment vehicles are changed state data, and the three types of data are stored in a table.
The fact time series data refers to: data is generated continuously and does not change with time, such as the net appointment track does not change with time.
Static dimension data refers to: the natural attributes of an object or person and do not change over a period of time. Such as road information, mobile phone numbers, identification number.
The change state data means: the status of an event may change over time for a short period of time, such as the payment status of an order.
Preferably, in step (2), the spatial relationship matching means: and performing spatial association including distance according to the longitude and latitude track data and the static road data of the vehicle, wherein the association method is to judge the distance from the vehicle track point to the road, the distance value depends on the width of the road, and if the distance value is smaller than the road width, the vehicle passes through the road.
Preferably, in the step (3), the entities are divided into static entities and dynamic entities;
dynamic entity: individuals who can move in space, such as people, cars;
static entity: individuals who cannot move in space, such as roads, malls, hospitals.
Preferably, in step (3), the relationship data refers to relevant contact information between entities, such as a certain person riding a certain car and a certain person living in a certain cell.
Preferably, in step (4), the graph database refers to a database storing and querying data in a graph structure.
A graph database is a database that uses graph structures for semantic queries, which use nodes, edges, and attributes to represent and store data. The key concept of the system is a graph, which directly associates data items in storage with data nodes and sets of edges between nodes representing relationships. These relationships allow the data in the storage area to be linked together directly and, in many cases, retrieved through one operation. The graph database takes relationships between data as priorities. Querying relationships in a graph database is fast because they are permanently stored in the database itself. Relationships can be visually displayed using graph databases, which are commonly known as titan, neo4j, orientDB, janussgraph, hugagraph, trinity, making them very useful for highly interconnected data.
Preferably, in the step (5), the risk index is divided into a real-time dynamic entity risk index and a real-time static entity risk index, and the calculation method is as follows:
real-time dynamic entity danger index = dynamic entity in-degree + dynamic entity out-degree
Real-time static entity danger index = (static entity in-degree + static entity out-degree) × (tti)
Degree of entry: the number of times an entity is affected by other entities, out degree: the number of times one entity affects other entities, tti, is the congestion index of an area or road. (tti is calculated)
And when the danger index is larger than or equal to the average value, giving an early warning to the entity, wherein the average value is the ratio of the sum of the danger indexes of the entities to the number of the entities in a 3-degree relation.
An epidemic situation early warning analysis system based on real-time traffic flow data comprises a data collection module, a spatial relation matching module, a relation data construction module, a relation data synchronization module and an early warning module, wherein,
the data collection module is used for collecting and classifying and collecting the network car booking data, the structured checkpoint data, the road data and the region data;
the spatial relationship matching module is used for carrying out spatial relationship matching on the classified network appointment data, the classified gate data, the classified road data and the classified area data;
the relational data construction module is used for constructing the relational data between the entities;
the relational data synchronization module is used for synchronizing the relational data into a graph database, and the relational data are converted into a triple format through a program in the synchronization process;
the early warning module is used for inquiring the danger index of the entity and actively sending out early warning to the entity exceeding the threshold value.
The invention has the beneficial effects that:
1. the method can quickly calculate the danger degree of the city-level mass data, clearly understand the epidemic situation of the whole city, and has important guiding significance for preventing the spread of the epidemic situation.
2. The method rapidly calculates the dangerous program of the entity through a real-time calculation technology, and provides a more accurate and effective basis for epidemic spread compared with the traditional method.
3. The invention can carry out deep excavation and analysis on key point propagation nodes and family gathering propagation information.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is an exemplary diagram of a knowledge network graph of the present invention;
fig. 3 is a medical record activity trace diagram in embodiment 1 of the present invention.
Detailed Description
The present invention will be further described by way of examples, but not limited thereto, with reference to the accompanying drawings.
Example 1:
as shown in fig. 1-3, the present embodiment provides an individual with the following social activity, urban behavior track: departure place in city (riding), net car (approach), certain road section (stay), market (infectious disease contact person B staying in the market);
an epidemic situation early warning analysis method based on real-time traffic flow data comprises the following steps:
(1) Collecting network car booking data, structured checkpoint data, road data and regional data (such as main urban business circles, hospitals and scenic spots), and performing modeling and data classification processing according to six different data fields of police, cars, people, things, roads and events;
(2) Carrying out spatial relationship matching on the classified network appointment data, the classified gate data, the classified road data and the classified area data;
(3) Constructing relation data between the entities by using the matched spatial data;
(4) Synchronizing the relation data into a graph database, converting the relation data into a triple format, namely an entity-relation-entity through a program in the synchronization process, wherein if (a car with a license plate number of 123 is owned by a king automobile), a knowledge network graph is constructed by taking the entity as a point and the relation as a line, and the influence relation of the entity is marked through an arrow;
(5) And the front end searches and inquires the danger index of the entity and actively sends out early warning to the entity exceeding the threshold value.
In the step (1), the bayonet data after structuring refers to: extracting picture information into text information through a third party manufacturer by data acquired by a road camera, wherein the text information comprises license plate numbers and longitude and latitude coordinate information;
the network appointment data comprise license plate numbers and tracks;
the road data comprises line-shaped points consisting of longitude and latitude points of the road;
the regional data comprises surface shape points formed by boundary points of a business circle, a hospital and a school.
In the step (1), the modeling means: and fusing the networked car booking data, the structured checkpoint data, the road data and the region data, and putting the fused data into corresponding police, car, people, objects, roads and event data fields. (the data are classified into vehicles, the network car booking data belong to the vehicles, the track data of the network car booking are stored in the vehicle domain, the structured checkpoint data are stored in the object domain, and the road data and the area data are stored in the road domain.)
In the step (1), the classification processing means: the data is divided into three types of factual time sequence data, static dimension data and change state data. If the network appointment track data are fact time sequence data, license plate numbers of the network appointment vehicles are static dimension data, payment states of the network appointment vehicles are changed state data, and the three types of data are stored in a table.
The fact time series data refers to: data is generated continuously and does not change along with the increase of time, such as the net appointment track does not change along with the generation of time.
Static dimension data refers to: the natural attributes of an object or person and do not change over time. Such as road information, mobile phone numbers, identification card numbers.
The change state data refers to: the status of an event may change over time for a short period of time, such as the payment status of an order.
In the step (2), the spatial relationship matching means: and performing space association including distance according to the longitude and latitude track data and the static road data of the vehicle, wherein the association method is to judge the distance from the track point of the vehicle to the road, the distance value depends on the width of the road, and if the distance value is smaller than the width of the road, the vehicle passes through the road.
In the step (3), the entities are divided into static entities and dynamic entities;
dynamic entity: individuals who can move in space, such as people and cars;
static entity: individuals who cannot move in space, such as roads, malls, hospitals.
In the step (3), the relationship data refers to the relevant contact information between the entities, such as a certain person riding a certain vehicle and a certain cell where the certain person lives.
In step (4), the graph database refers to a database in which data is stored and queried in a graph structure.
A graph database is a database that uses graph structures for semantic queries, which use nodes, edges, and attributes to represent and store data. The key concept of the system is a graph, which directly associates data items in storage with data nodes and sets of edges between nodes representing relationships. These relationships allow the data in the storage area to be directly linked together and, in many cases, retrieved through one operation. The graph database takes the relationship between data as priority. Querying relationships in a graph database is fast because they are permanently stored in the database itself. Relationships can be visually displayed using graph databases, which are commonly known as titan, neo4j, orientDB, janussgraph, hugagraph, trinity, making them very useful for highly interconnected data.
In the step (5), the risk index is divided into a real-time dynamic entity risk index and a real-time static entity risk index, and the calculation mode is as follows:
real-time dynamic entity danger index = dynamic entity in-degree + dynamic entity out-degree
Real-time static entity risk index = (static entity in-degree + static entity out-degree) × tti
In-degree: the number of times an entity is affected by other entities, out degree: the number of times one entity affects other entities, tti, is the congestion index of an area or road. (tti is calculated)
And when the danger index is larger than or equal to the average value, giving an early warning to the entity, wherein the average value is the ratio of the sum of the danger indexes of the entity to the number of the entity in the 3-degree relation.
As shown in FIG. three, assume that cell tti is 1.5 and mall tti is 2
Risk index = in + out =0+2= 2+ for someone a
Danger index of cell = (1 + 0) } cell tti =1.5 (one degree relationship)
Risk index =1+1=2 (one degree relation) of net appointment vehicle
Risk index =1+0=1 on xx road (two-degree relation)
Danger index of xx market = (1 + 1)' market tti =4 (two degree relationship)
Infectious disease contact person B =0+1=1 (three degree relation)
The average value = (2 +1.5+2+1+4+ 1)/6 =1.91, and real-time early warning is sent to a person A, a network appointment car and a market.
Note: tti minimum value is 1.
Example 2:
an epidemic situation early warning analysis method based on real-time traffic flow data comprises the steps of embodiment 1, and is characterized in that in the triple format in the step (4), entities are used as points, a knowledge network map is constructed by taking a relation as a line, and influence relations of the entities are marked by arrows, as shown in an example of fig. 2.
Example 3:
the embodiment provides an epidemic situation early warning analysis system based on real-time traffic flow data, which comprises a data collection module, a spatial relationship matching module, a relationship data construction module, a relationship data synchronization module and an early warning module, wherein,
the data collection module is used for collecting and classifying the collected network car booking data, the structured checkpoint data, the road data and the area data;
the spatial relationship matching module is used for carrying out spatial relationship matching on the classified network appointment data, the classified gate data, the classified road data and the classified area data;
the relational data construction module is used for constructing the relational data between the entities;
the relational data synchronization module is used for synchronizing the relational data into a graph database, and the relational data are converted into a triple format through a program in the synchronization process;
the early warning module is used for inquiring the danger index of the entity and actively sending out early warning to the entity exceeding the threshold value.
Claims (10)
1. An epidemic situation early warning analysis method based on real-time traffic flow data is characterized by comprising the following steps:
(1) Collecting network car booking data, structured checkpoint data, road data and region data, and performing modeling and data classification processing according to six different data fields of police, cars, people, things, roads and events;
(2) Carrying out spatial relationship matching on the classified network appointment data, the classified gate data, the classified road data and the classified area data;
(3) Constructing relationship data between entities by using the matched spatial data;
(4) Synchronizing the relational data into a graph database, converting the relational data into a triple format, namely entity-relation-entity, constructing a knowledge network graph by taking the entity as a point and the relation as a line, and marking the influence relation of the entity through an arrow;
(5) And the front end searches and queries the danger indexes of the entities and actively sends out early warning to the entities exceeding the threshold value.
2. The epidemic situation early warning analysis method based on real-time traffic flow data as claimed in claim 1, wherein in step (1), the structured checkpoint data is: extracting data picture information acquired by a road camera into text information, wherein the text information comprises license plate number and longitude and latitude coordinate information;
the network appointment data comprises license plate numbers and tracks;
the road data comprises line-shaped points consisting of longitude and latitude points of the road;
the regional data comprises surface shape points consisting of the boundary points of the business circles, the hospitals and the schools.
3. An epidemic situation early warning analysis method based on real-time traffic flow data as claimed in claim 1, wherein in the step (1), modeling means: and fusing the networked car booking data, the structured checkpoint data, the road data and the region data, and putting the fused data into corresponding police, car, people, objects, roads and event data fields.
4. The epidemic situation early warning analysis method based on real-time traffic flow data as claimed in claim 1, wherein in the step (1), the classification processing means: dividing data into three types of fact time sequence data, static dimension data and change state data;
the fact time series data refers to: data is continuously generated and does not change with the increase of time;
the static dimension data refers to: natural attributes of an object or person, and will not change within a period of time;
the change state data means: the state of an event may change over time for a short period of time.
5. The real-time traffic flow data-based epidemic situation early warning analysis method according to claim 1, wherein in the step (2), the spatial relationship matching means: and performing space correlation including distance according to the longitude and latitude track data and the static road data of the vehicle, wherein the correlation method is to judge the distance from the vehicle track point to the road.
6. The epidemic situation early warning analysis method based on real-time traffic flow data as claimed in claim 1, wherein in step (3), the entities are divided into static entities and dynamic entities;
dynamic entity: individuals who can move in space;
static entity: individuals who cannot move in space.
7. The real-time traffic flow data-based epidemic situation early warning analysis method according to claim 1, wherein in the step (3), the relationship data refers to the related contact information between the entities.
8. The real-time traffic flow data-based epidemic situation early warning analysis method according to claim 1, wherein in the step (4), the database refers to a database for storing and querying data in a graph structure.
9. The real-time traffic flow data-based epidemic situation early warning analysis method according to claim 1, wherein in the step (5), the risk indexes are divided into real-time dynamic entity risk indexes and real-time static entity risk indexes, and the calculation method is as follows:
real-time dynamic entity risk index = dynamic entity in-degree + dynamic entity out-degree;
real-time static entity risk index = (static entity in-degree + static entity out-degree) × tti;
degree of entry: the number of times an entity is affected by other entities, out degree: the number of times one entity affects other entities, and tti is the congestion index of one area or road;
and when the danger index is larger than or equal to the average value, giving an early warning to the entity, wherein the average value is the ratio of the sum of the danger indexes of the entities to the number of the entities in a 3-degree relation.
10. An epidemic situation early warning analysis system based on real-time traffic flow data is characterized by comprising a data collection module, a spatial relation matching module, a relation data construction module, a relation data synchronization module and an early warning module, wherein,
the data collection module is used for collecting and classifying the collected network car booking data, the structured checkpoint data, the road data and the area data;
the spatial relationship matching module is used for carrying out spatial relationship matching on the classified network appointment data, the classified gate data, the classified road data and the classified area data;
the relational data construction module is used for constructing relational data between the entities;
the relation data synchronization module is used for synchronizing the relation data into the graph database, and the relation data are converted into a triple format in the synchronization process;
the early warning module is used for inquiring the danger index of the entity and actively sending out early warning to the entity exceeding the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111327997.8A CN115238079A (en) | 2021-11-10 | 2021-11-10 | Epidemic situation early warning analysis method and system based on real-time traffic flow data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111327997.8A CN115238079A (en) | 2021-11-10 | 2021-11-10 | Epidemic situation early warning analysis method and system based on real-time traffic flow data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115238079A true CN115238079A (en) | 2022-10-25 |
Family
ID=83666653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111327997.8A Pending CN115238079A (en) | 2021-11-10 | 2021-11-10 | Epidemic situation early warning analysis method and system based on real-time traffic flow data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115238079A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167616A (en) * | 2022-12-29 | 2023-05-26 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
-
2021
- 2021-11-10 CN CN202111327997.8A patent/CN115238079A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167616A (en) * | 2022-12-29 | 2023-05-26 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
| CN116167616B (en) * | 2022-12-29 | 2023-07-28 | 北京交通大学 | Urban rail transit risk point quantification method under data-driven emergency |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hirschfield et al. | Mapping and analysing crime data: Lessons from research and practice | |
| Ratcliffe | Crime mapping: Spatial and temporal challenges | |
| WO1999052057A1 (en) | Expert system and method of performing crime site analysis | |
| Ahmadi | Crime mapping and spatial analysis | |
| Chen | Analysis and forecast of traffic accident big data | |
| Moiseeva et al. | Semiautomatic imputation of activity travel diaries: use of global positioning system traces, prompted recall, and context-sensitive learning algorithms | |
| El Abdallaoui et al. | Decision support system for the analysis of traffic accident Big Data | |
| Santtila et al. | Testing the utility of a geographical profiling approach in three rape series of a single offender: A case study | |
| CN115238079A (en) | Epidemic situation early warning analysis method and system based on real-time traffic flow data | |
| Peng et al. | The agent-based spatial simulation to the burglary in Beijing | |
| Tompson et al. | Hot routes: Developing a new technique for the spatial analysis of crime | |
| Wo et al. | Unintended consequences? The effects of neighbourhood walkability on crime in nine US cities | |
| CN109753541A (en) | A kind of relational network construction method and device, computer readable storage medium | |
| Sun et al. | Secondary accident data fusion for assessing long-term performance of transportation systems | |
| CN116013084A (en) | Traffic management and control scene determining method and device, electronic equipment and storage medium | |
| Silva et al. | Predicting road traffic accident severity using decision trees and time-series calendar heatmaps | |
| Sukhaia et al. | Understanding geographical variations in road traffic fatalities in South Africa | |
| Ceccato et al. | Short and medium term dynamics and their influence on acquisitive crime rates in the transition states of Estonia, Latvia and Lithuania | |
| Chamikara et al. | SL-SecureNet: intelligent policing using data mining techniques | |
| Adrees et al. | A proposed framework for using GIS to enhance traffic safety in Sudan: a case study | |
| Bonner et al. | Measuring disproportionate treatment in policing: One department’s experience | |
| Oliver | Spatial network data: concepts and techniques for summarization | |
| Barman et al. | An approach to GIS-based traffic information system using Spatial Oracle | |
| CN115035722B (en) | Road safety risk prediction method based on combination of space-time characteristics and social media | |
| Tayebi et al. | Spatial patterns of offender groups |
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 |