CN114923512A - Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks - Google Patents
Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks Download PDFInfo
- Publication number
- CN114923512A CN114923512A CN202111579036.6A CN202111579036A CN114923512A CN 114923512 A CN114923512 A CN 114923512A CN 202111579036 A CN202111579036 A CN 202111579036A CN 114923512 A CN114923512 A CN 114923512A
- Authority
- CN
- China
- Prior art keywords
- taxi
- data
- monitoring
- air quality
- sensor
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Abstract
The invention discloses a mobile monitoring and optimizing method for urban air quality, which is used for realizing the functions of regional air quality real-time monitoring and traceability analysis and providing data support for grid supervision. The mobile monitoring is that atmospheric monitoring equipment is installed on a taxi and a sharing single car, the pollutant content is continuously collected and monitored 24 hours all day, the position of the taxi and monitoring data are uploaded to a cloud server by utilizing a wireless communication technology, the cloud server is subjected to unified data fusion processing and analysis, and a combination scheme of the taxi and the sharing single car or the taxi and a fixed monitoring station is determined through an optimization algorithm according to the effective network coverage rate of taxis in different cities. According to the method, the mobility characteristic of the shared bicycle is fully considered, the data accuracy requirements of national control and provincial control environment air monitoring points are met, visual supervision is formed, and the technical problem that the accuracy of collecting air quality data only by means of a single vehicle type is low in the prior art is solved.
Description
The technical field is as follows:
the invention relates to the field of environmental detection, in particular to an urban pollutant monitoring method based on shared bicycle and taxi movement tracks.
Background art:
in recent years, with the increasing level of motorization, the problem of exhaust emissions due to intensive use and aggregation has gradually attracted a high degree of attention from city managers and citizens. The traditional fixed monitoring station has the problems of limited monitoring range, less data volume, insufficient monitoring result precision and the like. In view of the defects of the fixed monitoring mode, domestic cities begin to explore and utilize the rotating characteristic of a connecting shaft of a taxi, environment quality monitoring sensors are installed on the taxi, and the taxi environment monitoring sensors are tried in the cities of Beijing, Shanghai, Xian and the like, and achieve better effects. However, taxis are usually gathered in areas with large passenger flow, the data collected by the fleet has certain defects, and the weakness is made up by the high mobility and high coverage of the shared single vehicle. In order to improve the fine level of atmospheric pollution control and promote the continuous improvement of the air quality of urban environment, form more fine grid supervision, an environment quality sensor is arranged by utilizing the moving track characteristics of a shared bicycle and a taxi, the ground air environment data is collected in real time, and powerful data support is provided for improving and guaranteeing the air quality.
At present, the domestic city air quality monitoring data mainly come from a fixed air monitoring station, and a gridding air quality detection system consisting of the fixed air quality detection stations has the following defects: the method has the advantages that the site construction cost is high, the monitoring area is limited, the data acquisition quantity is low, the monitoring result has deviation to a certain extent, and the fixed point monitoring data represent that the air quality of the whole city is lack of credibility.
With the continuous development of internet technology, monitoring technologies such as remote sensing monitoring and mobile monitoring are emerging. The principle is that a plurality of data packets are collected and analyzed through air quality monitoring mobile sensors deployed in various areas. The atmosphere monitoring technology based on the sensor method is developing towards intellectualization, low cost and miniaturization, and the monitoring technology change taking big data as drive can greatly improve the capability of coping with and solving environmental problems of human beings. Meanwhile, a new idea is provided for perfecting the traditional air pollutant monitoring method.
At present, the carriers adopted by the urban air quality mobile monitoring at home and abroad mainly comprise taxies and buses. The bus route is fixed, the range of covered road sections is limited, and the bus route can only be monitored on the road and the surrounding air quality data; the urban coverage rate of taxis is high, but taxis are often gathered in areas with large passenger flow, collected data may have errors or incompleteness, an air quality sensor cannot be installed on each taxi in reality, and the accessibility of the taxis is also limited by road conditions; the shared bicycle can be used as a supplement for monitoring blind spots, and can be used as an environment monitoring mobile sensor carrier due to the advantages of high coverage rate, mobility and the like, the GPS positioning module in the intelligent lock assembly of the shared bicycle can upload position information in real time, and the air quality of a reachable area of the shared bicycle in a city can be detected in real time, so that the actual air quality condition of the whole city can be reflected more accurately.
With the more and more refined city management, the requirement on data quality is higher and higher.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects in the prior art, the invention provides the urban pollutant monitoring method based on the shared bicycle and taxi movement tracks, which is low in cost, high in urban coverage rate and increased in result credibility, and realizes the maximum utilization of the sensor.
The embodiment of the invention provides an urban pollutant monitoring method based on a shared bicycle and taxi moving track, which is used for realizing distributed air quality moving real-time monitoring of an urban built-up area. The method comprises the steps that taxi distribution can not cover 90% of road sections of a required monitoring area (the number of taxis with huge quantity is required for covering 90% of road sections of the required monitoring area), the information (position, quantity, coverage rate, data acquisition quantity and the like) of the existing air monitoring stations of a city is investigated, the current air quality situation (main pollutant content and distribution), the scale of a road network, the utilization of urban land, urban industrial mechanisms, relevant laws and regulations for urban atmospheric control and the like are investigated, and the city is subjected to regional division treatment. And then, analyzing the running characteristics of the urban taxies and the time-space characteristic analysis of the traveling of the shared single taxi, and obtaining the time-space distribution characteristics of the taxi by adopting a big data preprocessing technology. In addition, the sensor, the monitoring sensor and the air quality monitoring sensor all belong to the same air quality monitoring sensor.
Furthermore, the space-time distribution characteristics of the vehicle are obtained by analyzing track data obtained by a GPS positioning module and a vehicle positioning GPS system of the shared bicycle. The shared bicycle GPS positioning module is connected with a vehicle GPS positioning system to share track data position information in real time. The track data position information of the shared bicycle and the taxi is sent to a cloud server through a wireless communication module of the vehicle for data processing, when the coverage rate of an effective taxi track sailing road section in a required monitoring area is less than 90 percent (90 percent of taxis with quite large quantity are required), the combination of the taxi and the shared bicycle carried with an air quality monitoring sensor is adopted for air monitoring in the required monitoring area, so that the coverage rates of the effective taxi track sailing road sections of two vehicles reach 90 percent, and the optimal combination mode of the two vehicles is selected through a data analysis technology. And obtaining the taxi and the sharing bicycle under the optimal combination state.
Further, air quality monitoring sensors are mounted on the taxi and the sharing single car in the optimal combination state, the taxi and the sharing single car in the optimal combination state are arranged on the air quality monitoring sensors on the taxi and the sharing single car and are used for acquiring air quality data, and the air quality data around the taxi is acquired by fully utilizing the high mobility characteristics of the sharing single car and the taxi.
Further, the taxi and the sharing single car in the optimal combination state are provided with air quality monitoring sensors which comprise a power supply and CO 2 The device comprises a gas detection module, a PM2.5 detection module, a nitrogen oxide detection module, a sulfide gas detection module, a data processor and a wireless communication module. Further, the air quality data collected by the air quality monitoring sensors arranged on the taxi and the sharing single car under the optimal combination state comprises: PM2.5 data, CO 2 Data, nitrogen oxide data, sulfide data. And a power supply of the air quality monitoring sensor is communicated with a taxi and a sharing single-car power generation source to supply power for the air quality monitoring sensor.
Furthermore, the data processor of the air quality monitoring sensor is used for preprocessing the air quality data collected by the air quality monitoring sensor, and the wireless communication module of the air quality monitoring sensor is used for sending the data preprocessed by the data processor of the air quality monitoring sensor to the cloud server.
Further, it includes to send the air quality data after processing through data processing module in the air quality monitoring sensor to the high in the clouds server through wireless communication module: and the air quality monitoring sensor is connected with the cloud server through a wireless communication network, and the air quality monitoring sensor sends data to the cloud server in time by utilizing the existing network communication technology. Meanwhile, track data collected by the taxi GPS positioning system and the sharing single-car GPS module in the optimal combination state are sent to a cloud server through a communication module of the taxi and combined with air quality data to generate an air quality map.
The embodiment of the invention also provides an air quality monitoring method based on the moving track of the taxi and the shared bicycle and the air environment quality monitoring station. The method includes that taxi distribution can cover 90% of the required monitoring area road sections (no large number of vehicles are required to reach 90%). The method comprises the steps of investigating the information (position, quantity, coverage rate, data acquisition amount and the like) of the existing air monitoring stations of the city, the current situation of air quality (main pollutant content and distribution), the scale of a road network, the utilization of urban land, urban industrial institutions, relevant laws and regulations for urban atmospheric control and the like to perform regional treatment on the city; and then, analyzing the running characteristics of the urban taxies and the travel time-space characteristic analysis of the shared single taxi, and obtaining the time-space distribution characteristics of the taxi by adopting a big data preprocessing technology.
Furthermore, the space-time distribution characteristics of the vehicle are obtained by analyzing track data obtained by a GPS positioning module and a vehicle positioning GPS system of the shared bicycle. The shared bicycle GPS positioning module is connected with a vehicle GPS positioning system to share track data position information in real time. The track data position information of the shared bicycle and the taxi is sent to a cloud server through a wireless communication module of the bicycle for data processing, when the taxi track sails an effective road section, the coverage rate of the effective road section in a required monitoring area reaches 90 percent (90 percent is reached without a large number of taxis), and the required monitoring area is subjected to air monitoring and a combined mode of carrying an air quality monitoring sensor on the taxi and an existing fixed air environment quality monitoring point is adopted.
Furthermore, the taxi is provided with an air quality monitoring sensor, and the air quality monitoring sensor arranged on the taxi is used for acquiring air quality data and acquiring air quality data around the taxi. And sending the air quality data collected by the taxi and the data obtained by monitoring the fixed air environment quality monitoring station to a cloud server, wherein the cloud server is communicated with the fixed air environment quality monitoring station. Further, taxi GPS positioning system sends to high in the clouds server through the communication module of vehicle self-band, and high in the clouds server draws fixed air environment quality monitoring station site position through the map, with the taxi set up in the air quality data that air quality monitoring sensor on the taxi gathered and the air quality data that air environment monitoring station gathered combine, generate the air quality map.
Compared with the prior art, the invention has the following beneficial effects:
firstly, the taxi and the shared bicycle are simultaneously used as the urban air pollutant monitoring mobile carrier, so that the limitation of insufficient coverage rate of the fixed monitoring station is made up, and the accuracy of the monitoring result is improved. The taxi continuous-taking-and-turning characteristic and the sharing high mobility of the single taxi can be used as the supplement of taxi monitoring blind spots and the like, so that the urban pollutant monitoring range and the data volume can be greatly improved, and data support is provided for grid supervision.
Secondly, the cost is low and the economic benefit is high. The taxi and the shared bicycle are used as urban pollution data acquisition carriers, so that the construction cost of a fixed monitoring station can be reduced, the urban atmosphere treatment level is improved, and the green sustainable development of cities is promoted.
And thirdly, the data utilization rate is greatly improved by means of the fusion of the prior art.
And fourthly, a communication module in the air quality monitoring device is combined with a GPS system of the vehicle, the concentration of particulate matters in the area can be monitored in real time, and a city pollutant distribution map can be generated by processing through a cloud server, so that the gridding supervision is refined to a smaller area or a certain road section.
And fifthly, the urban pollutant monitoring method based on the shared bicycle and taxi movement tracks can be gradually popularized and used for monitoring other urban environmental pollution, such as noise pollution and light pollution. The method can accumulate a large amount of environmental data every day, and provides decision support for realizing fine management of urban environment.
And sixthly, reasonably selecting a scheme according to the actual situation of the required monitoring area, so that the monitoring means is more flexible and more reasonable.
Drawings
FIG. 1 is a flow chart of the overall implementation of the present invention
FIG. 2 is a flowchart of the method exploration and implementation
FIG. 3 is a hypothetical urban area map
FIG. 4 is a flow chart of region monitoring scheme selection
FIG. 5 is an undirected weighted graph of a hypothetical urban area graph
FIG. 6 predator algorithm flow diagram
FIG. 7 is a graph showing the effect of the relationship between the aid-enhancing models
FIG. 8 is a flowchart of the effect evaluation of the monitoring optimization scheme
FIG. 9 is a diagram of a three-layer perceptron neural network model established by the cloud server processing sensor data
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings and the specific embodiments, and all other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative work belong to the protection scope of the present invention.
Examples are given.
As shown in fig. 1, a flow chart of a city pollutant monitoring method based on sharing the moving tracks of a bicycle and a taxi is provided according to an embodiment of the present invention. Carrying out regional division processing on a city according to the scale of a city road network, if the coverage rate of a taxi track covering a road section of a region to be monitored is less than 90% (90% of the number of taxis with huge number is required), analyzing the track conditions of the taxis and shared single-taxi to obtain the optimal combination structure of the taxis, so as to obtain the number of sensors installed on the taxis and the shared single-taxi, and the moving track can maximally cover the number of the road sections of the region to be monitored; installing air quality monitoring sensors on a taxi and a shared bicycle, and monitoring the content of air pollutants near the taxi by taking the shared bicycle and the taxi as mobile carriers; and transmitting data obtained by monitoring of the sensor to the cloud server for processing to generate a real-time monitoring map of the air quality in the required monitoring area.
The method can adjust a vehicle combination scheme according to the vehicle track coverage condition, and if the coverage rate of the taxi track coverage required monitoring area road section reaches 90% (the number of taxis with huge number is not required), the air pollutant content in the required monitoring area is monitored by adopting the combination of a taxi carrying sensor and a fixed air environment quality monitoring station; and transmitting the data obtained by monitoring to a cloud server to generate a real-time monitoring map of the air quality in the required monitoring area.
The system comprises a taxi, a sharing bicycle, a fixed air environment quality monitoring station, an air quality monitoring sensor and a cloud server.
FIG. 2 is a flowchart of a method exploration and implementation,
And analyzing the scale of the urban road network, dividing the city into four types of super-large cities, I-type large cities and II-type large cities according to the scale of the city by taking the road network density of the built-up area of the city as a division standard. Wherein the average road network density of the ultra-large city is 7.4Km/Km 2 The average road network density of the super-huge city is 6.3Km/Km 2 The average road network density of the I-type big city is 5.9Km/Km 2 The average road network density of II type big cities is 5.8Km/Km 2 For cities with similar road network density of each administrative district, integral division is carried out, andand analyzing the overall vehicle track space-time characteristics in one step. And for cities with large area difference of the road networks of the administrative areas, dividing each administrative area into one area so as to finish the work of dividing the urban areas, and analyzing the space-time characteristics of the vehicle tracks in the areas of the divided areas.
And analyzing the time-space characteristics of travel in the required monitoring area by using the taxi and the shared bicycle track data. Because there is certain error through GPS positioning data, so need be through carrying out preliminary treatment to vehicle orbit data in order to ensure the reliability of vehicle orbit data analysis result, need to fall to some data and make an uproar, the unusual value in the orbit acquisition process of aim at getting rid of.
Secondly, data compression is carried out, the workload of a server is increased due to the fact that the transmission data volume is increased due to massive GPS data, and the graphic data points are compressed by adopting a Douglas-Puck thinning algorithm to extract effective data points.
It should be noted that, the process of implementing rarefaction by the algorithm is as follows:
1) connecting a straight line to the first and last points of the curve, calculating the distance between all the points on the curve and the straight line, and finding out the maximum distance value d max By d max Compared with a predetermined threshold value D.
2) If d is max <D, completely cutting off the middle point on the curve; the straight line segment is used as an approximation of the curve and the curve segment is processed. If d is max Not less than D, retention of D max Dividing the curve into two parts by taking the corresponding coordinate point as a boundary, and repeatedly using the method for the two parts, namely repeating the steps 1) and 2) until all d is reached max Are all made of<D, completing the thinning of the curve.
It should be noted that why 90% coverage is selected as the criterion
Firstly, urban road network simplification and feature processing are carried out
As shown in step 201, the city is divided into regions according to the road network density, and each administrative region is divided into one region for the cities with large difference in road network density in each administrative region.
The data used below are the thinned and denoised taxi and shared-bicycle data in step 202.
And carrying out estimation partitioning on the urban road network with similar daily traffic by using taxis and shared single-car track data, and regarding the partitioned areas as homologous emission areas.
Daily traffic estimation zoning: according to the track data of the rented vehicles and the shared vehicles in the daily city, the characteristics of the city road network, the time and the space are combined for partitioning. And areas with similar traffic volume and traffic characteristics are considered to be homogenous discharge areas.
A homologous discharge region: the air quality and the air composition in this region are considered to be the same.
And for the cities with the well-divided homologous emission regions, the homologous emission regions are connected with the nearest roads in the city road network according to the Euclidean distance algorithm.
Euclidean distance algorithm: the method is a determination method for the characteristic distance with high similarity adopted by the urban road network, the situation of road connection is better when the Euclidean distance is smaller, and the situation of road connection is worse when the Euclidean distance is larger.
And dividing the points of the road well connected with the homologous emission area, wherein each two adjacent points represent a road section, and the air quality on the road section does not change along with the space-time change.
The effect graph shown after the completion of the above 3 steps is as shown in the assumed urban area graph of fig. 3.
Specifically, as shown in fig. 3, assuming an urban area map, red points represent point locations, blue portions represent water areas, yellow points represent fixed monitoring stations, and coordinates represent the positional relationship between each point location and a road section thereof.
And then comparing the coverage rate of the effective road section for the sailing of the used taxi track.
Specifically, the coverage rate of the effective road section during cruising refers to the coverage rate of the taxis and shared single cars obtained after the processing in the step2 in the road network obtained in the step.
The composition characteristics of the traffic volume in different areas in the city are different, namely the track navigation effective road section coverage rate of the single car and the taxi in different areas is different. Therefore, after step 203, the alternatives are not exclusive and vary according to the urban traffic specifications.
The coverage rate of the effective navigation road section in the city is considered in the following four conditions:
1. residential areas and residential areas in cities occupy areas with large specific gravity.
2. The commercial area and the active area in the city occupy a relatively heavy area.
3. Tourist attraction, scenic spot account for the area of great weight in the city.
4. Suburbs in a city.
Aiming at the travel characteristics and the activity mode of people in different areas in the city, the optimized monitoring mode is changed accordingly.
The model establishment solving and the optimization composition schemes used in different urban areas are different.
As shown in the flow chart of the region monitoring scheme selection of fig. 4.
Residential areas and residential areas in cities are large in specific gravity, people are greatly influenced by getting on and off duty in the morning and evening when going out, the taxi driving amount in the areas is small in most of the time, the fluctuation range of the shared single-car usage amount along with the time is small, and therefore the combination of the shared single-car and the taxi is adopted for optimal monitoring in most of the time.
In a city, a commercial area and an active area occupy a region with a large specific gravity, and the driving quantity of a taxi in the region and the using quantity of a shared single taxi are not large in fluctuation range along with time, so that an optimized combined monitoring mode is determined according to the coverage rate of a cruising effective road section of the taxi.
The areas with large specific weight of tourist attractions and scenic spots in cities are generally small in specific weight of the areas in the cities, the traffic volume in holidays is large, the total fluctuation range of the driving volume of taxis in the areas and the usage volume of shared single vehicles along with time is small, and therefore the air quality is obtained by monitoring by setting a fixed city monitoring station.
In suburbs of cities, the running amount of taxis in the area is larger than the using amount of shared single taxis, and the fluctuation range of the taxis along with time is not large, so that the air quality is monitored by combining the taxis and fixed city monitoring stations.
And step 204, adopting an optimized combination scheme of carrying air quality monitoring sensors on taxis and sharing single cars.
After the step 203 is completed, combining the characteristics of different areas of the city, and when the coverage rate of the taxi to the area needing to be monitored is less than 90% (90% of the taxis with large quantity are needed) under the condition of the city road network, configuring the sensor for the combination of the taxi and the shared single taxi.
Step 205 adopts a scheme of carrying an air quality monitoring sensor and fixing air environment quality monitoring points for a taxi.
After the step 203 is completed, combining the characteristics of different areas of the city, and combining the monitoring sensor carried by the taxi with a fixed monitoring station when the coverage rate of the taxi to the required monitoring area reaches 90% under the condition of the city road network.
Step 204 and step 205 are to establish scheme models for different areas to obtain a combined scheme according to coverage rates of effective road sections of different areas and characteristics of urban road networks, so that the targets of good monitoring effect and low economic cost are achieved.
Specifically, the required monitoring area needs to determine an optimized monitoring effect index for selecting a monitoring scheme. The optimization monitoring index can be determined through an algorithm, so that the reasonability and the applicability of the optimized combination scheme used in different areas in the urban road network are judged. If the optimization effect of the initially adopted optimization combination scheme is not ideal, other optimization combination schemes are adopted, and therefore the most appropriate optimization combination scheme is determined.
It should be noted how different optimization combination schemes are specifically established.
Before model building, determining the hypothesis conditions for optimizing the model building of the combination scheme:
1. the number of lanes of the road is assumed to be even.
2. The taxi is assumed to be driven in a constant running amount within a certain continuous 4 hours.
3. It is assumed that taxis are starting at each intersection for each selected time period.
4. It is assumed that the taxi does not have a car fault during driving.
5. It is assumed that the taxi is not limited by road blockage during traveling.
6. Suppose that after passing through the segmentation point, a taxi goes out according to the original route.
7. It is assumed that the taxi is traveling at a variable speed but the average speed is maintained.
Firstly, the specific establishment of a model (a scheme of carrying an air quality monitoring sensor and fixing air environment quality monitoring points on a taxi) is explained.
Because the position of the fixed monitoring station is not influenced by time, the model is established by taking a taxi provided with a sensor as a main influence factor. The key road section in the optimized combination scheme model of the taxi carrying air quality monitoring sensor and the fixed air environment quality monitoring station refers to a road section with larger vehicle driving quantity, which is determined by the determined key road section according to the obtained traffic survey data of the area; the time interval is determined according to the composition and the space-time characteristics of the traffic volume of different urban areas in the selected time interval.
The taxi sensor configuration optimization scheme meets the following requirements as much as possible:
1. the proportion of taxi passing through the road section point set on the regional road network in a certain time interval (taking 10 minutes as an example) is not less than 90%, and the time of taxi passing through the key road section point must be within (taking 5 minutes as an example).
2. The optimized monitoring effect is more remarkable
3. And under the condition that the proportion of taxis passing through road point positions arranged on the road network of the region is not lower than 90% within 10 minutes and the time of arriving at key road point positions must be within 5 minutes, the number of the taxis needing to be provided with the sensors in the region is the least.
The taxi sensor configuration optimization scheme solving principle is as follows:
principle one: it is assumed that the air quality on the road section defined by the adjacent points does not change over time.
Principle two: in order to quickly improve the monitoring period, the initial position of the taxi at the beginning of each time period is set at each intersection.
Principle three: the variable speed running in the taxi traveling process aims to reach all the crossed roads simultaneously.
For the effective road network map of the urban area shown in fig. 3, taxis can walk along two directions of the street and are abstracted into an undirected graph. Each street in the road network graph can be regarded as an edge of an undirected graph, and intersections in the road network graph can be regarded as nodes of the undirected graph. The effective road network graph in the attached figure 3 is symbolized as an undirected graph G (V) (G), E (G)), and nodes in the effective road network in the attached figure 3 are used as intersections and sides are used as urban streets. Wherein:
v (g) is the number of finite non-empty top points in the graph, i.e. the crossing v (g) ═ v in the effective road network graph 1 ,v 2 ,…,v N And N represents the number of all intersections in the effective road network graph.
(G) is a finite set of edges in the graph, i.e. street E (G) is equal to { e) } in the effective road network graph 1 ,e 2 ,…,e M M represents the number of all streets in the effective road network graph, and the weight value of the side represents the length of the street, namely the length of the street j is S j 。
After the selected urban effective road network graph is abstracted into an undirected weighted graph, as shown in the attached figure 5, the problem of the number of taxis configured with sensors can be converted into coverage problems of nodes, edges and the like of the graph in graph theory.
The main idea of the model is as follows: and finding initial point positions (optimal solutions under static conditions) of taxis on the regional road network by using a greedy algorithm, and then realizing taxi movement by using predation search iterative operation to achieve the purpose of dynamic grouping so as to obtain a sensor configuration scheme of the taxis meeting the conditions.
It should be noted here that the model processes relevant data by using the Floyd algorithm.
The specific implementation process of the Floyd algorithm is as follows: recursion generates a matrix sequence A 0 ,A 1 ,…,A k ,…,A n Wherein A is k (i, j) represents the intersection node v from the active road network graph i To the intersection node v in the effective road network graph j The serial number of the nodes passing through the path of (b) is not more than the shortest path length of k.
The iterative formula is used in the calculation: a. the k (i,j)＝min(A k-1 (i,j),A k-1 (i,k)+A k-1 (k,j))。
And (4) solving the shortest path between each pair of intersection nodes by using a Floyd algorithm to obtain an adjacent distance matrix of each intersection, thereby deducing the shortest path required by the taxi to pass through each intersection node under the condition of meeting the requirement of a configuration optimization scheme.
It should be noted that greedy algorithm is applied to find the initial point location of taxi on regional road network (optimal solution under static condition)
The greedy strategy is mainly solved by applying a greedy algorithm, and the main idea of the used strategy is as follows: the selection is made that appears best at the present time. That is, rather than being considered globally optimal, it makes only a locally optimal solution in some sense.
The greedy algorithm solving steps are as follows:
1) and converting the optimal configuration problem of the taxi sensor into a target problem, namely making a selection first and then solving the sub-problems of the remaining target problem.
2) After greedy selection of the target problem, the remaining sub-problems of the target problem have one property: namely, the optimal solution of the subproblem of the target problem is combined with the greedy selection, so that an optimal solution of the original problem can be obtained.
3) The original problem is always proved to have an optimal solution obtained by greedy selection, thereby explaining the safety of the greedy selection.
The model greedy strategy objective problem:
1) the time for the taxi to arrive at the key point of the road must be within 5 minutes as a priority object and must be satisfied first.
2) Based on the description of the first principle of the modeling idea above (assuming that the air quality on the road section defined by the assumed neighboring points does not change with time). ) The proportion that the number of the roads which can be reached by the taxi in 10 minutes accounts for not less than 90% of the total number of the roads is understood as that the proportion that the taxi passes through the road point of the road section arranged on the regional road network in 10 minutes is not less than 90%.
3) The coverage problem of the number of the researched roads is converted into the coverage problem of the nodes of the researched intersections, and the requirement that the coverage range of the number of the roads is not lower than is met by adjusting the coverage rate of the nodes.
4) For the problem that the taxi needs to be configured with the minimum sensors under the satisfied condition, the vehicles which are required to be configured and sensed in the static state, namely, the taxi needs to be configured and sensed in a fixed-point trip, so that the vehicles can be configured with the minimum sensors required in the static state.
Grouping intersections; and grouping the intersections according to greedy strategy target problems, and grouping by using a greedy algorithm so as to solve the taxi positions on the road network of the initialization area.
The intersection grouping algorithm flow is as follows:
finding out the intersection points of the car journey 5 minutes away from the key road section point, and dividing the intersection points into key road section point position groups and non-key road section point position groups.
Finding out the intersection points on the road sections which meet the condition that the proportion of the taxi passing through the road section points on the regional road network is not lower than 90% within 10 minutes from the to-be-grouped to carry out maximum grouping, and deleting the grouping points from the to-be-grouped.
If the total number of the intersection points occupied by the grouping points is larger than the total number of the intersection points and the coverage rate of the number of the roads is not lower than 90%, stopping; otherwise, jumping to the second step. And selecting the local maximum group every time to obtain the optimal solution.
And solving by utilizing matlab 2009a software according to the Floyd algorithm and the greedy algorithm flow. The solving process finds that the travel road coverage of n taxis with sensors does not reach 90% of the conditions through finite iterations, and the travel road coverage of n +1 taxis with sensors is higher than 90%, so that the sensors are at least required to be configured for the n +1 taxis, and then the accuracy of the conclusion is proved according to the coverage rate of the road number when the predator algorithm simulates the taxis to move.
It should be noted that the taxi movement is realized by using predation search iterative operation, and the purpose of dynamic grouping is achieved
The characteristic of dynamic grouping is realized when the number of taxis is determined, so that the greedy algorithm and the predator algorithm can be used for solving, namely, the greedy algorithm is used for finding the initial point position (the optimal solution under the static condition) of the taxis on the regional road network, and then predation search iterative operation is used for realizing taxi movement, so that the accuracy of the minimum sensor configuration under the condition of meeting the requirement is obtained.
The initial point positions obtained by the greedy algorithm are as follows: x is the number of 1 ,x 2 ,x 3 ,…,x n
It is noted that the general process of the predator algorithm is illustrated in the flow chart of the predator algorithm of fig. 6. :
step1, search an initial point by using greedy algorithm, s ═ x 1 ,x 2 ,…,x n )；
Step2, randomly generating a new solution according to the existing solution and calculating an adaptive value function;
step3, selecting the solution with the maximum adaptation value, and moving the taxi one Step;
step4, judging the stop condition if m 2 > 0.9 and move n times to stop the computation, otherwise jump to Step 1.
The predator algorithm is specifically transformed as follows:
1) the combinatorial optimization problem is defined as a binary set (Ω, Z), where Ω is the set of solutions and the function Z: Ω → R represents the transformation of each solution to the corresponding fitness value. Suppose there is a neighborhood for each solution s
Definition of
Where N'(s) comprises 5% of the elements in N(s). The transformation of one solution to another in n(s) becomes a shift.
2) In the problem of configuring sensors for n taxis on a scale, one taxi with a sensor is represented by each element in the set of n natural numbers from 1 to n, and the intersection is represented by x, e.g., the state s ═ x (x) 1 ,x 2 ,…,x n ) And the vector represents the position of n taxis with sensors.
3) One solution is the state of the urban area positions of all taxies, and one solution s is given as (x) 1 ,x 2 ,…,x n ) According to the known road link data, each vehicle selects an intersection to move by one step to obtain a new solution s ═ x' 1 ,x' 2 ,…,x' n ) The combination of intersections selectable by all vehicles results in a neighborhood of s, N(s).
4) The main iteration of the algorithm is from the movement of the taxi position, the sample size is taken from the neighborhood at any time, the adaptive value is calculated according to the preset index weights, and the s ' -x ' with the maximum adaptive value is selected ' 1 ,x' 2 ,…,x' n ) A mobile taxi equipped with a sensor.
Through the operation, the taxi + fixed monitoring station optimized combination scheme model can obtain the minimum number of taxi configured sensors in any continuous time period every day.
Secondly, explaining [ optimal combination scheme for monitoring sensor of air quality carried by taxi and shared bicycle ] model establishment
And for urban road network areas which do not meet the coverage rate of taxis, sharing single cars with sensors are reasonably added by adopting an enhancement model to carry out optimized combination.
It should be noted that, the process of solving the reinforcement model is as follows:
firstly, the implementation idea of model establishment is as follows:
1) when no taxi with a sensor passes through in a certain road j time period, calculating the total number of the taxis with the sensorSharing a single vehicle to a point j _ p included in a road j i And (i is 1,2 and 3 … n), and then selecting n required sharing bicycles according to the sequence of the distances from small to large to make the n sharing bicycles go to the enhanced aid road j along the calculated shortest path. The problem therefore translates into how to find each shared bicycle to point j _ p i (i equals 1,2,3 … n) to determine the optimal number of shared vehicles equipped with sensors.
2) For any road j, the distance between two intersections is determined, and the point j _ p of the shared bicycle at any position is added to the point j _ p of the road j i (i-1, 2,3 … n), the bicycle must be driven from v j1 ,v j2 And a certain intersection enters the road.
3) So that a certain shared bicycle i is calculated to point j _ p i (i ═ 1,2,3 … n) can be translated into a calculation of shared bicycle i to intersection v j1 The shortest distance plus the intersection v j1 To point j _ p i ( i 1,2,3 … n) and sharing the distance from the bicycle i to the intersection v j2 Is added to the intersection v j2 To point j _ p i (i ═ 1,2,3 … n), and then the minimum between these two distances is found.
4) Similarly, if the shared bicycle i is exactly at a certain intersection, calculating the shared bicycle i to the intersection v j1 ,v j2 The shortest distance is converted into the shortest distance between the calculated intersections, so that an algorithm can be directly used;
if the sharing bicycle i is not at the intersection but at a certain road k, the sharing bicycle i can only be taken from two intersections v connected to the road k, as analyzed above k1 ,v k2 Go out and reinforce point j _ p i (i ═ 1,2,3 … n), then the shared bicycle i is calculated to the intersection v j1 ,v j2 The shortest distance can be converted into the calculation of the intersection v k1 ,v k2 V. to the intersection j1 ,v j2 The shortest distance of (c).
Through the discussion processing, the shared bicycle i is calculated to the point j _ p i The shortest distance (i ═ 1,2,3 … n) actually translates into:
s represents a distance
Then calculate the point j _ p from each shared bicycle to the road j i The shortest path (i is 1,2,3 … n) can be converted into a path from the intersection node at the two ends of the road where each shared bicycle is located to the two-end node v of the road j where the event occurs j1 ,v j2 The shortest path of (2). Point j _ p on road j i (i-1, 2,3 … n), and intersection node v j1 ,v j2 The relational effect is shown in the relational effect graph of the reinforcement model in FIG. 7.
The algorithm and the specific flow are explained next:
1) when the number of times that the taxi passes through the node in a certain road j is less, the taxi i closest to the road is set as an organizer of the rescue task. The taxi i firstly estimates whether the node passing through the street j needs to share the single car for assistance, if the node does not need to share the single car for assistance, the taxi i directly solves the case, and the taxi i is recovered to be in a trip state after the case is solved. And if the shared bicycle is needed for increasing the aid, estimating the number of the shared bicycles needing the aid, and establishing an aid task union.
2) And calculating the shortest path and the shortest distance from each sharing bicycle in the traveling state to the node, selecting the redundant sharing bicycles according to the sequence of the distances from near to far and the number of the sharing bicycles required for redundant, and informing the selected sharing bicycles to participate in the redundant task alliance. And if the organizer finds that the number of the shared vehicles in the traveling state is not enough to complete the rescue task, the rescue alliance is released, the state of the organizer is converted into the traveling state, and the organizer continues to travel.
3) Each sharing bicycle in the traveling state obtains the summoning information from the organizer, sets the state of each sharing bicycle as a rescue aiding state, and forwards the state along the calculated shortest path to complete the rescue aiding task;
4) once all the shared bicycles required for the rescue are up to the point position on the required rescue road, the rescue task organizer considers that the rescue is completed, the organizer should distribute the alliance to be released, all the members (taxis and shared bicycles) in the original alliance are converted into a trip state, and the trip task is continued.
Through the aid model algorithm, the number of the bicycles with the least sensors is obtained. The shared-bicycle mounted sensor is to supplement a street or city roadway that a taxi cannot reach. And obtaining the minimum installation number of the required sensors (taxi and sharing single vehicle carrying air quality monitoring sensor optimized combination scheme).
And if the coverage rate of the effective sailing road section of the taxi and the shared single-car carrying the sensor can reach 95%, the next step is further carried out, and if the coverage rate of the effective sailing road section of the taxi and the shared single-car carrying the sensor cannot reach 95%, the installation quantity of the sensors is further adjusted.
Specifically, when the vehicle track coverage reaches 95% or more, and the sensor has a certain monitoring range, the obtained monitoring data can already represent all the air quality in the monitoring area.
It should be noted how to determine the optimized monitoring effect evaluation index in this embodiment.
As shown in the flow chart of fig. 8 for evaluating the effect of the monitoring optimization scheme.
For the index for evaluating the significance degree of the monitoring effect, the purpose of monitoring taxies and shared single taxies in real time is to improve the quality of air monitoring, so the index for measuring the significance degree of the dynamic monitoring effect is determined around the purpose, and the node coverage rate m of the taxi allocation scheme is selected according to the requirement of the percentage of the segmentation points which can be reached by the taxies in a determined time range 1 Road coverage m 2 The number m of different nodes that the unit vehicle passes within the specified time 3 And the number m of different roads that the unit vehicle passes within the specified time 4 And 4 indexes are used for describing the remarkable degree of the monitoring effect.
a)m 1 Determining the number of nodes covered in a time period by a taxi provided with a sensor in a configuration schemeIn proportion to the total number of nodes.
b)m 2 The proportion of the number of covered roads in the specified time period of the taxi with the sensor in the configuration scheme to the total number of covered roads.
c)m 3 The total number of different nodes that a unit vehicle can traverse within a specified period of time.
d)m 4 The total number of different roads that can be traversed by a unit vehicle within a specified certain period of time.
For the purpose of evaluating the monitoring effect, the method is mainly used for proving the correctness of the required minimum configuration sensor quantity obtained by different sensor optimization combination schemes so as to obtain the optimal monitoring effect.
Specifically, for the algorithm setting for evaluating the monitoring effect: solving is carried out by utilizing a greedy algorithm and a predator algorithm, namely, the greedy algorithm is used for finding the initial point position (the optimal solution under the static condition) of the taxi, and then predation search iterative operation is used for realizing taxi movement.
208, collecting and processing air pollutant data
And collecting monitoring data obtained after the optimal combined monitoring schemes are used in different areas in the city. After data collection is completed, the data are fused through the cloud server, and therefore the effects of denoising and cleaning are achieved.
Step 9, monitoring regional pollution to generate a map
And generating a city pollutant distribution map by a visualization technology, realizing real-time monitoring on air pollutants, and generating an air quality real-time monitoring map.
It should be noted how the cloud server performs data fusion processing in step 8.
Based on the existing software technology, the air quality data obtained by the taxi and the shared bicycle sensor are fused, and the fusion of the shared bicycle data can be realized by adopting the following method:
a) collecting data collected by N sensors from taxis and single cars in the same time period and the same street;
b) according to the optimized track distribution map of taxis and single cars on the same street at the same time, carrying out feature extraction transformation on output data of the sensor, and extracting a feature vector representing observation data;
c) carrying out pattern recognition processing on the characteristic vectors, and adopting a clustering algorithm to complete the description of each sensor about the target;
d) the description data of each sensor about the target is grouped according to the same target, namely, the description data is related;
e) establishing a three-layer perceptron neural network model (a multilayer feedforward neural network): and the grouped data is subjected to primary processing according to the first hidden layer neuron function, and a processing result is sent to a cluster head node of a cluster where the processing result is located. The second hidden layer neuron function and the output layer neuron function are further processed. And finally, the cluster head node sends the processing result to the sink node. As shown in fig. 9.
f) And repeating the test for multiple times, and reducing the influence of misleading the sensor to the error data so as to obtain a result.
And finally, generating an urban pollutant distribution map through a visualization technology, finally realizing real-time monitoring on air pollutants, and generating an air quality real-time monitoring map.
The invention has the following effects:
1. the urban pollutant monitoring and real-time releasing can be realized, and remote data transmission and real-time processing can be realized.
2. Based on a big data analysis technology, the urban pollutant fine control is realized, decision support is provided for an urban manager to control air pollution, and a significant value is brought to the environmental protection service industry.
3. The urban pollutant monitoring method based on the shared bicycle and taxi moving tracks can be gradually popularized and used for monitoring other urban environmental pollution, such as noise pollution and light pollution. The method can accumulate a large amount of environmental data every day, and provides decision support for realizing fine management of urban environment.
4. The invention provides a favorable technology in a certain range for the future automatic driving of the automobile to enter the market and the large-scale use. The system provides another approach for unmanned application, and provides a more convenient and accurate means for air quality monitoring of road sections.
5. The model adopted in the invention has an evaluation and adjustment function, can check out the combination inconvenience in time, further optimize the combination and select the optimal scheme.
In general, the invention has the advantages that the taxi is combined with the sharing single car, and the air quality detection is facilitated by utilizing the self-running characteristics of the sharing single car and the taxi.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. Those skilled in the art will appreciate that the invention is not limited to the specific embodiments described herein and that various obvious changes, adaptations and substitutions are possible, without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above-described embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (13)
1. A city pollutant monitoring optimization method based on shared bicycle and taxi movement tracks is characterized in that the method system comprises the following steps: the system comprises a taxi, a sharing bicycle, a fixed air environment quality monitoring station, an air quality monitoring sensor, a wireless communication module and a cloud server.
2. The method according to claim 1, wherein the system comprises air quality monitoring sensor devices installed on the taxi and the sharing bicycle and used for acquiring air quality information of different places in the urban area through the driving of the taxi and the sharing bicycle; the air quality information comprises PM2.5, PM10, and CO in the air 2 Waiting for pollutant content information, taxi and shared bicycle real-time position information and acquisition time;
the air quality sensor specifically includes: the device comprises a power supply, a GPS positioning module, a CO2 gas detection module, a PM2.5 detection module, a PM10 detection module, a nitrogen oxide detection module, a sulfide gas detection module and a data processor.
The air quality monitoring sensor is connected with the cloud server through a wireless communication network, and uploads collected air quality data to the cloud server at intervals.
3. The cloud server of claim 2, being in communication with an environmental quality monitoring site. And the cloud server generates an air quality real-time monitoring map after data processing is carried out on the data. The preprocessing stage in the data processing employs a Douglas-Pock thinning algorithm that is used to compress a large number of redundant graphic data points to extract the necessary data points.
The cloud server is used for carrying out data processing and analysis on pollutant acquisition data sent by a taxi and a sharing bicycle, and is characterized in that the data processing and analysis are based on the existing software technology and are used for fusing air quality data obtained by sensors of the taxi and the sharing bicycle.
4. The method for monitoring urban pollutants based on shared bicycle and taxi movement tracks as claimed in claim 1, wherein said urban shared bicycle comprises a carane bicycle and a kumquat bicycle.
5. The air quality monitoring sensor of claim 2, further comprising a communication module;
the communication module is connected with the cloud server through a network and is connected with the data processor; the data processor sends the preprocessed data to the cloud server through a communication module; and the cloud server is used for carrying out data processing and analysis on pollutant acquisition data sent by the taxies and the shared bicycle to generate urban air quality real-time information.
6. The urban pollutant monitoring method based on the movement tracks of the shared bicycle and the taxi according to claim 1, wherein the taxi and the shared bicycle are monitored by taking an optimal combination mode as a moving carrier. The optimal combination takes the minimum equipment quantity as an optimization target, and can realize a wider monitoring range by clustering, fitting, identifying and topologically constructing the GPS positioning point data of the vehicles and combining taxi-mounted pollutant sensors meeting the minimum monitoring effective road segment number of the voyage with a certain quantity of shared single vehicles carrying the sensors according to taxi running characteristics and the existing data research results. And adopting a Douglas-Puck thinning algorithm for preprocessing the taxi track data and the shared bicycle track data. And the track data is processed to obtain the optimal combination for maximizing the urban road section number.
7. The urban pollutant monitoring method based on the shared bicycle and the taxi moving track according to claim 1, wherein the method comprises two monitoring schemes, wherein the two monitoring schemes are a scheme that taxi and the shared bicycle carry an air quality monitoring sensor optimization combination scheme and a scheme that taxi carries the air quality monitoring sensor and a fixed air environment quality monitoring station scheme.
8. The method for monitoring urban pollutants based on shared bicycle and taxi movement tracks as claimed in claim 1, wherein the judgment basis of whether the coverage rate of the taxi effective cruising track section can reach 90% is taken as a judgment basis for adopting two different schemes.
9. The scheme of [ taxi-mounted air quality monitoring sensor + fixed air environment quality monitoring station ] according to claim 7, wherein for the scheme, a model is established, the model is that a greedy algorithm is used to find taxi initial points (optimal solution under a static condition) on a regional road network, then predation search iterative operation is used to realize taxi movement, the purpose of dynamic grouping is achieved, and then a sensor configuration scheme of taxis meeting conditions is solved. The model processes the relevant data using the Floyd algorithm.
10. The [ taxi + shared-bicycle-carried air quality monitoring sensor optimal combination scheme ] according to claim 7, wherein for urban road network areas which do not meet taxi coverage, an enhancement model is adopted to reasonably increase shared bicycles with sensors for optimal combination.
11. The urban pollutant monitoring method based on shared bicycle and taxi movement tracks according to claim 1, characterized in that, for evaluating the monitoring effect of the method, an algorithm is adopted to realize, and for evaluating the monitoring effect, the algorithm is set as follows: solving is carried out by utilizing a greedy algorithm and a predator algorithm, namely, the greedy algorithm is used for finding the initial point position (the optimal solution under the static condition) of the taxi, and then the taxi is moved by utilizing predation search iterative operation.
12. The evaluation monitoring effect according to claim 11, wherein the purpose of the evaluation monitoring effect is mainly to prove the correctness of the required minimum configuration sensor number obtained by different sensor optimization combination schemes so as to obtain the optimal monitoring effect.
13. The method for fusing air quality data obtained from a taxi and a shared single-car sensor according to claim 3, wherein the data fusion is performed by the following method:
a) collecting data collected by N sensors from taxis and single cars in the same time period and the same street;
b) according to the optimized track distribution map of taxis and single cars on the same street at the same time, carrying out feature extraction transformation on output data of the sensor, and extracting a feature vector representing observation data;
c) carrying out pattern recognition processing on the characteristic vectors, and adopting a clustering algorithm to complete the description of each sensor about the target;
d) the description data of each sensor about the target is grouped according to the same target, namely, the description data is related;
e) establishing a three-layer perceptron neural network model (a multilayer feedforward neural network): and performing primary processing on the grouped data according to a first hidden layer neuron function, and sending a processing result to a cluster head node of a cluster where the processing result is located. The second hidden layer neuron function and the output layer neuron function are further processed. And finally, the cluster head node sends the processing result to the sink node.
And finally, outputting a result to obtain fused data for sharing the optimal combination work of the single car and the taxi.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111579036.6A CN114923512A (en) | 2021-12-22 | 2021-12-22 | Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111579036.6A CN114923512A (en) | 2021-12-22 | 2021-12-22 | Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114923512A true CN114923512A (en) | 2022-08-19 |
Family
ID=82804060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111579036.6A Pending CN114923512A (en) | 2021-12-22 | 2021-12-22 | Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114923512A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358904A (en) * | 2022-10-20 | 2022-11-18 | 四川国蓝中天环境科技集团有限公司 | Dynamic and static combined urban area air quality monitoring station site selection method |
-
2021
- 2021-12-22 CN CN202111579036.6A patent/CN114923512A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358904A (en) * | 2022-10-20 | 2022-11-18 | 四川国蓝中天环境科技集团有限公司 | Dynamic and static combined urban area air quality monitoring station site selection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657843B (en) | Integrated planning decision support system of urban plug-in bus system | |
| CN100580735C (en) | Real-time dynamic traffic information processing method based on car detecting technique | |
| Davies et al. | Scalable, distributed, real-time map generation | |
| CN100357987C (en) | Method for obtaining average speed of city rode traffic low region | |
| CN106297357B (en) | Real-time route planning and POI information searching system and method based on car networking | |
| CN107490384B (en) | Optimal static path selection method based on urban road network | |
| CN113065074B (en) | Track destination prediction method based on knowledge graph and self-attention mechanism | |
| Li et al. | Emission pattern mining based on taxi trajectory data in Beijing | |
| CN112784000B (en) | Passenger searching method based on taxi track data | |
| CN109612488B (en) | Big data micro-service-based mixed travel mode path planning system and method | |
| CN102087788A (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN110992233B (en) | Emergency evacuation method and system for urban gathering event | |
| CN106017496A (en) | Real-time navigation method based on road condition | |
| CN112991743A (en) | Real-time traffic risk AI prediction method based on driving path and system thereof | |
| CN113837446B (en) | Airport land side area traffic situation prediction method based on multi-source heterogeneous data | |
| CN102800212A (en) | Intelligent parking system in environment of internet of things | |
| CN113435777A (en) | Planning method and system for electric operating vehicle charging station | |
| CN114330106A (en) | Urban public traffic planning method | |
| CN104599499A (en) | Distributed statistic method and device for traffic position | |
| CN114923512A (en) | Urban pollutant monitoring optimization method based on shared bicycle and taxi movement tracks | |
| CN115714957A (en) | Subway trip identification method, device, equipment and medium based on mobile phone signaling | |
| CN110132298A (en) | The shortest path of garbage removing cart determines method | |
| CN113903171B (en) | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network | |
| CN109754606A (en) | A method of based on taxi location prediction congestion in road situation | |
| CN114676917A (en) | Empty taxi space distribution evaluation method and system |
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 |