CN107067727A - A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matchings - Google Patents

A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matchings Download PDF

Info

Publication number
CN107067727A
CN107067727A CN201710421757.1A CN201710421757A CN107067727A CN 107067727 A CN107067727 A CN 107067727A CN 201710421757 A CN201710421757 A CN 201710421757A CN 107067727 A CN107067727 A CN 107067727A
Authority
CN
China
Prior art keywords
mrow
msub
road traffic
data
mtd
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.)
Granted
Application number
CN201710421757.1A
Other languages
Chinese (zh)
Other versions
CN107067727B (en
Inventor
徐东伟
王永东
张贵军
郭海锋
何德峰
周晓根
郝小虎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201710421757.1A priority Critical patent/CN107067727B/en
Publication of CN107067727A publication Critical patent/CN107067727A/en
Application granted granted Critical
Publication of CN107067727B publication Critical patent/CN107067727B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Game Theory and Decision Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Biomedical Technology (AREA)
  • Fuzzy Systems (AREA)
  • Molecular Biology (AREA)
  • Analytical Chemistry (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matchings, sets up road traffic features reference sequences, obtains the road traffic reference data under different modalities；Road traffic training data is extracted, road traffic difference data is obtained based on reference data, the feature for obtaining training data is handled by thresholding；By road traffic service level Fuzzy processing, combined training data characteristics completes the structure of knowledge base；Extract road traffic test data；By KNN Feature Correspondence Algorithms, k feature nearest with test data characteristic distance in knowledge base is chosen, and obtain the service level of corresponding obfuscation；The service level of k group obfuscations is added, the corresponding service level of maximum probability, the as affiliated service level of current signature is drawn, road traffic evaluation of running status is completed.The present invention realizes simple, it is not necessary to which the data for carrying out large amount of complex are calculated, and can effectively improve processing speed.

Description

Road traffic service level evaluation method based on fuzzy KNN feature matching
Technical Field
The invention belongs to the field of road traffic service level evaluation, relates to analysis and evaluation of road traffic data, and discloses a method for evaluating road traffic service level.
Background
With the development of social economy, the holding capacity of automobiles is continuously increased, road traffic problems become more severe, and the road traffic service level must be correctly evaluated to process the traffic problems before the traffic problems occur, so that the occurrence of events such as traffic jam, accidents and the like is avoided, and a basis is provided for making decisions by traffic management departments.
Currently, most studies on evaluation of road traffic service level are being conducted for traffic congestion. The relatively mature traffic service level evaluation indexes comprise connectivity, travel time reliability and road network capacity reliability. Other traffic service level evaluation researches comprise a traffic jam evaluation weighting model, a road network overall adaptability analysis method, a space saturation index, road network dynamic traffic flow state estimation and the like. The research is mainly carried out on the road network level, the traffic service level of a single road section is not considered, and the implementation process is complex.
Disclosure of Invention
In order to overcome the defects of the existing road traffic service level evaluation method, the invention provides a road traffic service level evaluation method based on fuzzy KNN feature matching and with a simplified algorithm.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a road traffic service level evaluation method based on fuzzy KNN feature matching comprises the following steps:
1) establishing a road traffic characteristic reference sequence, and acquiring road traffic reference data in different modes;
2) extracting road traffic training data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the training data through thresholding;
3) fuzzification processing is carried out on the existing road traffic service level, and the construction of a knowledge base is completed by combining the characteristics of training data;
4) extracting road traffic test data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the test data through thresholding;
5) selecting k features which are closest to the test data features in the knowledge base through a KNN feature matching algorithm, and solving the corresponding fuzzified service level;
6) and adding the k groups of fuzzified service levels to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and finishing the evaluation of the road traffic service level.
Further, in the step 1), establishing a road traffic characteristic reference sequence to obtain road traffic reference data in different modes includes the following steps:
1.1) Structure of reference sequence for designing road traffic characteristics
If the collection period of the road traffic state data is set to be Δ t, the time format of the road traffic information template is shown in fig. 1.
The table format of the road traffic characteristic reference sequence is shown in table 1 and table 2.
TABLE 1 road traffic characteristic reference sequence information Table
TABLE 2 road traffic characteristic reference sequence description table
1.2) establishing a road traffic operation characteristic reference sequence through related data preprocessing
The road traffic operation mode is divided into two layers, namely a road network layer and a road section layer, the road traffic operation mode is divided into g seed modes by setting the division identification of the road network layer traffic operation mode, the road traffic operation mode is divided into h seed modes by the division identification of the road section layer traffic operation mode, and the road traffic operation modes are divided into g × h types in total and recorded as a set Mode＝{M11，M12，…，MghValues of g and h are determined according to the division identification of the selected traffic operation mode;
and acquiring representative road traffic state data of the target road section, preprocessing the data, and inputting the road traffic state data subjected to data preprocessing into a road traffic characteristic reference sequence so as to establish the road traffic characteristic reference sequence.
Further, in the step 2), the road traffic training data is extracted, the road traffic difference data is obtained based on the road traffic reference data in the same mode, and the features of the training data are obtained through thresholding, wherein the general expression of the features is as follows:
wherein M isghIs modal; delta t is the acquisition period of road traffic state data; (m × Δ t) is the mth road traffic state data acquisition period, m is more than or equal to 0 and less than or equal to N, and N represents the number of traffic information acquired every day;represents the training data at time (m × Δ t);reference data representing the time (m × Δ t); s (m × Δ t) represents difference data between the training data and the reference data at the time (m × Δ t);representing a modality MghDifference data of training data and reference data in a period from lower delta t to (m x delta t);represents a threshold value;representing a modality MghDifference data after threshold processing in a time period from Δ t to (m × Δ t) is the characteristics of training data;representing traffic status data and characteristicsThe mapping rule of (3).
Furthermore, in the step 3), the construction of the knowledge base is completed by fuzzy division of the existing road traffic data and road traffic service level and combining the characteristics of the training data, and the general expression is as follows:
wherein phi represents the mapping relation between the current road traffic state and the fuzzified traffic service level, LosmRepresenting the obscured road traffic service level.
In combination with (4) and (5), the relationship between the traffic running state and the characteristics can be obtained:
Losm＝ω(hem) (6)
wherein, ω represents the mapping rule between the fuzzified service level and the traffic running characteristic, thereby completing the construction of the knowledge base.
Further, in the step 4), the road traffic test data is extracted, the road traffic difference data is obtained based on the road traffic reference data in the same mode, and the features of the test data are obtained through thresholding, wherein the general expression of the features is as follows:
whereinRepresenting road traffic test data at time (m × Δ t); MS (m × Δ t) represents difference data between the test data and the reference data at the time (m × Δ t);data representing the difference between the test data and the reference data for a time period from Δ t to (m × Δ t);and representing the difference data after threshold processing, namely the characteristics of the test data.
Furthermore, in the step 5), k features closest to the test data features in the knowledge base are selected through a KNN feature matching algorithm, and the corresponding fuzzified service level is obtained, wherein the process is as follows:
5.1) calculating the distance between the features of the training data and the features of the test data
dist(m)＝||TheMgh(m)-heMgh(m)|| (10)
DN(m)＝[dist1(m)dist2(m)…distN(m)](11)
Wherein, | | | represents to find Euclidean distance, dist (m) represents the distance between the features of the test data and the features in the knowledge base from the time interval of delta t to (m × delta t), N represents the group number of the training data, D representsN(m) represents a set of feature distances of features of the N sets of test data to the N sets of training data over a time period Δ t to (m × Δ t).
5.2) finding out the corresponding features of k nearest distances, and setting the k features as s1，s2，…skAccording to the mapping relation between the characteristics and the fuzzified service level, the characteristics are
(L1，L2，…Lk)＝ω(s1，s2，…sk) (12)
Wherein L is1，L2，…LkRespectively represents s1，s2，…skCorresponding obfuscated service level. Wherein, respectively represent modes MghAnd the probability of smooth, general congestion and severe congestion in the period from Δ t to (m × Δ t) is lower.
In the step 6), the k groups of fuzzified service levels are added to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and the evaluation of the road traffic service level is completed, wherein the process is as follows:
adding the fuzzy service level probabilities corresponding to the k features to obtain
Wherein, SuAK，SuAK，SuAKAnd respectively representing the corresponding smooth, general congestion and severe congestion probabilities after the k characteristics are integrated. SuAK，SuAK，SuAKThe service level corresponding to the highest probability value in the data set is the service level to which the current feature belongs.
The technical conception of the invention is as follows: a road traffic service level evaluation method based on fuzzy KNN feature matching is provided. And extracting road traffic data in the same time period, and dividing the road traffic data into reference data, training data and test data. And carrying out thresholding treatment on the difference value data of the training data and the reference data to obtain the characteristics of the training data. And fuzzifying the road traffic service level, and constructing a knowledge base consisting of training data characteristics and the road traffic service level by combining the current traffic running state. And performing thresholding processing on the difference data of the test data and the reference data to obtain the characteristics of the test data, and solving the Euclidean distance between the characteristics of the test data and the characteristics of the training data. And selecting fuzzified service levels corresponding to the nearest k nearest distances based on a KNN algorithm. And adding the fuzzified service levels corresponding to the k nearest distances, and obtaining the service level corresponding to the maximum probability, namely the current service level, so as to realize the evaluation of the road traffic service level.
The method only performs subtraction processing among data, obtains traffic operation characteristics, constructs a knowledge base, and realizes road traffic service level evaluation by combining characteristic matching with a fuzzy KNN algorithm. The method is simple to implement, does not need to carry out a large amount of complex data calculation, and can effectively improve the processing speed.
The invention has the following beneficial effects: by combining the same mode MghPerforming thresholding processing on the difference data of the road traffic training data and the reference data to obtain the characteristics of the training data, and combining the fuzzified road traffic service level to realize the construction of a training data knowledge base; and acquiring the characteristics of the test data in the same mode, and calculating the distance between the test data characteristics and the training data characteristics through a KNN algorithm. And selecting the fuzzified service levels corresponding to the minimum k groups of distances for addition, and selecting the service level with the maximum probability as the current road traffic service level to finish the evaluation of the road traffic service level.
Drawings
Fig. 1 is a schematic diagram of a time format of a road traffic information template.
Fig. 2 is a schematic diagram of road traffic operation modal division.
Fig. 3 is a flow chart of road traffic service level evaluation based on fuzzy KNN feature matching.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 to 3, a road traffic service level evaluation method based on fuzzy KNN feature matching includes the following steps:
1) the method for establishing the road traffic characteristic reference sequence and acquiring the road traffic reference data under different modes comprises the following steps:
1.1) Structure of reference sequence for designing road traffic characteristics
If the collection period of the road traffic state data is set to be Δ t, the time format of the road traffic information template is shown in fig. 1.
The table format of the road traffic characteristic reference sequence is shown in table 1 and table 2, where table 1 is a road traffic characteristic reference sequence information table, and table 2 is a road traffic characteristic reference sequence description table.
TABLE 1
TABLE 2
1.2) establishing a road traffic operation characteristic reference sequence through related data preprocessing
The road traffic operation mode is divided into two layers, namely a road network layer and a road section layer, the road traffic operation mode is divided into g seed modes by setting the division identification of the road network layer traffic operation mode, the road traffic operation mode is divided into h seed modes by the division identification of the road section layer traffic operation mode, and the road traffic operation modes are divided into g × h types in total and recorded as a set Mode＝{M11，M12，…，MghValues of g and h are determined according to the division identification of the selected traffic operation mode;
and acquiring representative road traffic state data of the target road section, preprocessing the data, and inputting the road traffic state data subjected to data preprocessing into a road traffic characteristic reference sequence so as to establish the road traffic characteristic reference sequence.
2) Extracting road traffic training data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the training data through thresholding, wherein the general expression of the characteristics is as follows:
wherein M isghIs modal; delta t is the acquisition period of road traffic state data; (m × Δ t) is the mth road traffic state data acquisition period, m is more than or equal to 0 and less than or equal to N, and N represents the number of traffic information acquired every day;training data representing time (m × Δ t) and m × Δ t;is represented by (m × Δ t) time; s (m × Δ t) represents difference data between the training data and the reference data at the time (m × Δ t);representing a modality MghDifference data of training data and reference data in a period from lower delta t to (m x delta t);represents a threshold value;representing a modality MghDifference data after threshold processing in a time period from Δ t to (m × Δ t) is the characteristics of training data;a mapping rule representing traffic status data and characteristics.
3) The construction of a knowledge base is completed by fuzzy division of the existing road traffic data and road traffic service level and combination of the characteristics of training data, and the general expression is as follows:
wherein phi represents the mapping relation between the current road traffic state and the fuzzified traffic service level, LosmRepresenting the obscured road traffic service level.
In combination with (4) and (5), the relationship between the traffic running state and the characteristics can be obtained:
Losm＝ω(hem) (6)
wherein, ω represents the mapping rule between the fuzzified service level and the traffic running characteristic, thereby completing the construction of the knowledge base.
4) Extracting road traffic test data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the test data through thresholding, wherein the general expression of the characteristics is as follows:
whereinRepresenting road traffic test data at time (m × Δ t); MS (m × Δ t) represents difference data between the test data and the reference data at the time (m × Δ t);data representing the difference between the test data and the reference data for a time period from Δ t to (m × Δ t);and representing the difference data after threshold processing, namely the characteristics of the test data.
5) Selecting k features nearest to the test data features in the knowledge base through a KNN feature matching algorithm, and solving the corresponding fuzzified service level, wherein the process is as follows:
5.1) calculating the distance between the features of the training data and the features of the test data
dist(m)＝||TheMgh(m)-heMgh(m)|| (10)
DN(m)＝[dist1(m)dist2(m)…distN(m)](11)
Wherein, | | | represents to find Euclidean distance, dist (m) represents the distance between the features of the test data and the features in the knowledge base from the time interval of delta t to (m × delta t), N represents the group number of the training data, D representsN(m) represents a set of feature distances of features of the N sets of test data to the N sets of training data over a time period Δ t to (m × Δ t).
5.2) finding out the corresponding features of k nearest distances, and setting the k features as s1，s2，…skAccording to the mapping relation between the characteristics and the fuzzified service level, the characteristics are
(L1，L2，…Lk)＝ω(s1，s2，…sk) (12)
Wherein L is1，L2，…LkRespectively represents s1，s2，…skCorresponding obfuscated service level. Wherein, respectively represent modes MghAnd the probability of smooth, general congestion and severe congestion in the period from Δ t to (m × Δ t) is lower.
6) And adding the k groups of fuzzified service levels to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and finishing the evaluation of the road traffic service level, wherein the process is as follows:
adding the fuzzy service level probabilities corresponding to the k features to obtain
Wherein, SuAK，SuAK，SuAKAnd respectively representing the corresponding smooth, general congestion and severe congestion probabilities after the k characteristics are integrated. SuAK，SuAK，SuAKThe service level corresponding to the highest probability value in the data set is the service level to which the current feature belongs.
The road traffic service level evaluation method based on fuzzy KNN feature matching comprises the following steps:
1) establishing a road traffic characteristic reference sequence, and acquiring road traffic reference data under different modes
Because the road traffic flows of the same road section and corresponding time have similarity, road traffic speed data of 7 working days (15,16,21,22,23,24 and 28) in 6 months and 7 days in 2011 of Beijing 5 express roads are selected to establish a road traffic characteristic reference sequence. The acquisition interval delta t of the road traffic state data is 2 min. The link specific information is shown in table 3.
Road section ID Road section name
HI2075a Central music college-western door bridge
HI3002b Devictory gate bridge-pool bridge
HI7008a White bridge street-wide canal gate bridge
HI7051a Lunar altar north bridge-lunar altar south bridge
HI7060b Entrance of east straight gate bridge-small street bridge east
TABLE 3
Taking the road traffic speed data of 15 days as a reference data set; and establishing a knowledge base by using the road traffic speed data of the same modality for 16,21,22,23 and 24 days as training data. And (5) performing algorithm verification by taking the road traffic speed data of 28 days as an experimental data set.
2) Extracting road traffic training data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the training data through thresholding, wherein the general expression of the characteristics is as follows:
wherein M isghIs modal; delta t is the acquisition period of road traffic state data; (m × Δ t) is the mth road traffic state data acquisition period, m is more than or equal to 0 and less than or equal to N, and N represents the number of traffic information acquired every day;training data representing time (m × Δ t) and m × Δ t;reference data representing the time (m × Δ t); s (m × Δ t) represents difference data between the training data and the reference data at the time (m × Δ t);representing a modality MghDifference data of training data and reference data in a period from lower delta t to (m x delta t);represents a threshold value;representing a modality MghDifference data after threshold processing in a time period from Δ t to (m × Δ t) is the characteristics of training data;a mapping rule representing traffic status data and characteristics.
3) The construction of a knowledge base is completed by fuzzy division of the existing road traffic data and road traffic service level and combination of the characteristics of training data, and the general expression is as follows:
wherein phi represents the mapping relation between the current road traffic state and the fuzzified service level, LosmRepresenting the obscured road traffic service level.
In combination with (4) and (5), the relationship between the traffic running state and the characteristics can be obtained:
Losm＝ω(hem) (6)
wherein, ω represents the mapping rule between the fuzzified service level and the traffic running characteristic, thereby completing the construction of the knowledge base.
4) Extracting road traffic test data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the test data through thresholding, wherein the general expression of the characteristics is as follows:
whereinRepresenting road traffic test data at time (m × Δ t); MS (m × Δ t) represents difference data between the test data and the reference data at the time (m × Δ t);data representing the difference between the test data and the reference data for a time period from Δ t to (m × Δ t);and representing the difference data after threshold processing, namely the characteristics of the test data.
5) Selecting k features nearest to the test data features in the knowledge base through a KNN feature matching algorithm, and solving the corresponding fuzzified service level, wherein the process is as follows:
5.1) calculating the distance between the features of the training data and the features of the test data
dist(m)＝||TheMgh(m)-heMgh(m)|| (10)
DN(m)＝[dist1(m)dist2(m)…distN(m)](11)
Wherein, | | | represents to find Euclidean distance, dist (m) represents the distance between the features of the test data and the features in the knowledge base from the time interval of delta t to (m × delta t), N represents the group number of the training data, D representsN(m) represents a set of feature distances of features of the N sets of test data to the N sets of training data over a time period Δ t to (m × Δ t).
5.2) finding out the corresponding features of k nearest distances, and setting the k features as s1，s2，…skAccording to the mapping relationship between the characteristics and the service level, the method comprises
(L1，L2，…Lk)＝ω(s1，s2，…sk) (12)
Wherein L is1，L2，…LkRespectively represent a feature s1，s2，…skCorresponding obfuscated service level. Wherein, respectively represent modes MghAnd the probability of smooth, general congestion and severe congestion in the period from Δ t to (m × Δ t) is lower.
6) And adding the k groups of fuzzified service levels to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and finishing the evaluation of the road traffic running state, wherein the process is as follows:
adding the fuzzy service level probabilities corresponding to the k features to obtain
Wherein, SuAK，SuAK，SuAKAnd respectively representing the corresponding smooth, general congestion and severe congestion probabilities after the k characteristics are integrated.
7) Determining parameters of a road traffic service level evaluation method based on fuzzy KNN feature matching;
in the process of the road traffic service level evaluation method based on the fuzzy KNN feature matching algorithm, the following parameters are designed:
can be prepared fromAndthe acquisition step is carried out by the user,can be prepared fromAnd determining that the value of k is between 3 and 10, and the value can be obtained through training, wherein the parameter setting is only about influence analysis on the evaluation of the road traffic running state based on the KNN algorithm.
Since the parameters have influence on the accuracy of the algorithm, and the influence of each parameter on the accuracy of the algorithm cannot ensure the optimal algorithm by analyzing the influence of each parameter alone, the influence of all the parameters on the evaluation of the road traffic running state should be considered simultaneously when the algorithm is analyzed.
Introducing a deviation rate as an evaluation index of the road traffic running state, wherein the calculation formula is as follows:
wherein PE represents a deviation ratio, Nsr≠smNumber of traffic service levels, N, representing test-to-reality differencesrRepresenting the number of traffic service levels actually tested.
I.e. for the differencesThere is a corresponding NMAE. So the following equation exists:
namely, it isHaving a distribution relation f with NMAE, finding the one corresponding to the minimum NMAENamely the optimal parameter setting process. The following model can be obtained:
finally, the product is processedThe value of (a) can be determined by training of road traffic reference data and training data.
7) Results of the experiment
Obtaining optimal parameters based on road traffic reference data and training data of the same modeThe experimental result is mainly used for evaluating the road traffic service level according to the vehicle speed value of the road section. And extracting road traffic test data, and realizing evaluation of the test state based on a KNN algorithm.
And selecting the deviation rate as an evaluation index of the road traffic service level, wherein the calculation is shown as a formula (13). Statistical analysis of the deviation of the speed values of the experimental section 2011 at 6 months and 28 days is shown in table 4 below.
Road section ID Time of day Deviation ratio
HI2075a 2011-6-28 11.53％
HI3002b 2011-6-28 5.83％
HI7008a 2011-6-28 10.00％
HI7051a 2011-6-28 5.69％
HI7060b 2011-6-28 12.22％
Table 4.

Claims (7)

1. A road traffic service level evaluation method based on fuzzy KNN feature matching is characterized by comprising the following steps: the evaluation method comprises the following steps:
1) establishing a road traffic characteristic reference sequence, and acquiring road traffic reference data in different modes;
2) extracting road traffic training data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the training data through thresholding;
3) fuzzification processing is carried out on the existing road traffic service level, and the construction of a knowledge base is completed by combining the characteristics of training data;
4) extracting road traffic test data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the test data through thresholding;
5) selecting k features which are closest to the test data features in the knowledge base through a KNN feature matching algorithm, and solving the corresponding fuzzified service level;
6) and adding the k groups of fuzzified service levels to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and finishing the evaluation of the road traffic service level.
2. The road traffic service level evaluation method based on fuzzy KNN feature matching as claimed in claim 1, characterized in that: in the step 1), a road traffic characteristic reference sequence is established, and road traffic reference data in different modes are obtained, which includes the following steps:
1.1) Structure of reference sequence for designing road traffic characteristics
Setting the acquisition period of road traffic state data to be delta t, wherein the table formats of road traffic characteristic reference sequences are shown in table 1 and table 2, wherein table 1 is a road traffic characteristic reference sequence information table, and table 2 is a road traffic characteristic reference sequence description table;
TABLE 1
TABLE 2
1.2) establishing a road traffic operation characteristic reference sequence through data preprocessing
The road traffic operation mode is divided into two levels: road network layer and road segment layer, setting division identification of traffic operation mode of road network layer to cross roadThe operation modes are divided into g seed modes, the traffic operation modes of the road are divided into h seed modes by the division identification of the traffic operation modes of the road section layer, and then the traffic operation modes of the road are divided into g × h types in total and recorded as a set Mode＝{M11，M12，…，MghValues of g and h are determined according to the division identification of the selected traffic operation mode;
and acquiring representative road traffic state data of the target road section, preprocessing the data, and inputting the road traffic state data subjected to data preprocessing into a road traffic characteristic reference sequence so as to establish the road traffic characteristic reference sequence.
3. The road traffic service level evaluation method based on fuzzy KNN feature matching as claimed in claim 1 or 2, characterized in that: in the step 2), extracting road traffic training data, acquiring road traffic difference data based on road traffic reference data in the same mode, and performing thresholding processing to acquire the characteristics of the training data, wherein the general expression of the training data is as follows:
<mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>ST</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>SB</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </mrow>1
<mrow> <msub> <mi>e</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mn>2</mn> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mo>...</mo> </mtd> <mtd> <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>2</mn> <mo>)</mo> </mrow> </mrow>
<mrow> <msub> <mi>he</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>0</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msub> <mi>e</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>&lt;</mo> <msub> <mi>E</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>e</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msub> <mi>e</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>&gt;</mo> <msub> <mi>E</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>3</mn> <mo>)</mo> </mrow> </mrow>
wherein M isghIs modal; delta t is the acquisition period of road traffic state data; (m × Δ t) is the mth road traffic state data acquisition period, m is more than or equal to 0 and less than or equal to N, and N represents the number of traffic information acquired every day;represents the training data at time (m × Δ t);reference data representing the time (m × Δ t); s (m × Δ t) represents difference data between the training data and the reference data at the time (m × Δ t);representing a modality MghDifference data of training data and reference data in a period from lower delta t to (m x delta t);represents a threshold value;representing a modality MghDifference data after threshold processing in a time period from Δ t to (m × Δ t) is the characteristics of training data;a mapping rule representing traffic status data and characteristics.
4. The road traffic service level evaluation method based on fuzzy KNN feature matching as claimed in claim 3, characterized in that: in the step 3), the construction of a knowledge base is completed by fuzzy division of the existing road traffic data and road traffic service level and combination of the characteristics of training data, and the general expression is as follows:
<mrow> <msub> <mi>Los</mi> <mi>m</mi> </msub> <mo>=</mo> <mi>&amp;phi;</mi> <mrow> <mo>(</mo> <msub> <mi>ST</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mo>(</mo> <mi>m</mi> <mo>)</mo> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>5</mn> <mo>)</mo> </mrow> </mrow>
wherein phi represents the mapping relation between the current road traffic state and the fuzzified service level, LosmRepresenting the obscured road traffic service level.
And combining (4) and (5) to obtain the relation between the traffic running state and the characteristics:
Losm＝ω(hem) (6)
wherein, ω represents the mapping rule between the fuzzified service level and the traffic running characteristic, thereby completing the construction of the knowledge base.
5. The road traffic service level evaluation method based on fuzzy KNN feature matching as claimed in claim 4, characterized in that: in the step 4), extracting road traffic real-time data, acquiring road traffic difference data based on road traffic reference data in the same mode, and acquiring the characteristics of the real-time data through thresholding, wherein the general expression is as follows:
<mrow> <mi>M</mi> <mi>S</mi> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>SM</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>SB</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>7</mn> <mo>)</mo> </mrow> </mrow>
<mrow> <msub> <mi>err</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mrow> <mi>M</mi> <mi>S</mi> <mrow> <mo>(</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <mi>M</mi> <mi>S</mi> <mrow> <mo>(</mo> <mn>2</mn> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mo>...</mo> </mtd> <mtd> <mrow> <mi>M</mi> <mi>S</mi> <mrow> <mo>(</mo> <mi>m</mi> <mo>*</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>8</mn> <mo>)</mo> </mrow> </mrow>
<mrow> <msub> <mi>The</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>0</mn> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msub> <mi>err</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>&lt;</mo> <msub> <mi>E</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>err</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>,</mo> </mrow> </mtd> <mtd> <mrow> <msub> <mi>err</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>&gt;</mo> <msub> <mi>E</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>9</mn> <mo>)</mo> </mrow> </mrow>
whereinRepresenting road traffic real-time data at the time (m × Δ t); MS (m × Δ t) represents difference data between the real-time data and the reference data at the time (m × Δ t);difference data representing real-time data and reference data for a time period from Δ t to (m × Δ t);and representing the difference data after threshold processing, namely the characteristics of the real-time data.
6. The road traffic service level evaluation method based on fuzzy KNN feature matching as claimed in claim 5, characterized in that: in the step 5), k features closest to the real-time data features in the knowledge base are selected through a KNN feature matching algorithm, and the corresponding fuzzified service level is solved, wherein the process is as follows:
5.1) calculating the distance between the features of the training data and the features of the real-time data
dist(m)＝||TheMgh(m)-heMgh(m)|| (10)
DN(m)＝[dist1(m)dist2(m)…distN(m)](11)
Wherein, | | | represents that the Euclidean distance is calculated,dist (m) represents the distance between the features of the real-time data from time Δ t to time (m × Δ t) and the features in the knowledge base, N represents the number of groups of training data, DN(m) a set of feature distances representing features of the N sets of real-time data to the N sets of training data over a time period Δ t to (m × Δ t);
5.2) finding out the corresponding features of k nearest distances, and setting the k features as s1，s2，…skAccording to the mapping relationship between the characteristics and the service level, the method comprises
(L1，L2，…Lk)＝ω(s1，s2，…sk) (12)
Wherein L is1，L2，…LkRespectively represents s1，s2，…skCorresponding obfuscated service level. Wherein, respectively represent modes MghAnd the probability of smooth, general congestion and severe congestion in the period from Δ t to (m × Δ t) is lower.
7. The road traffic running state evaluation method based on fuzzy KNN feature matching as claimed in claim 6, characterized in that: in the step 6), the k groups of fuzzified service levels are added to obtain a service level corresponding to the maximum probability, namely the service level to which the current feature belongs, and the evaluation of the road traffic service level is completed, wherein the process is as follows:
adding the fuzzy service level probabilities corresponding to the k features to obtain
<mrow> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mrow> <msub> <mi>Su</mi> <mrow> <mi>A</mi> <mi>k</mi> </mrow> </msub> </mrow> </mtd> <mtd> <mrow> <msub> <mi>Su</mi> <mrow> <mi>B</mi> <mi>k</mi> </mrow> </msub> </mrow> </mtd> <mtd> <mrow> <msub> <mi>Su</mi> <mrow> <mi>C</mi> <mi>k</mi> </mrow> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mrow> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>k</mi> </munderover> <msub> <mi>u</mi> <mrow> <mi>A</mi> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <msub> <mi>ST</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>k</mi> </munderover> <msub> <mi>u</mi> <mrow> <mi>B</mi> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <msub> <mi>ST</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> <mtd> <mrow> <munderover> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>k</mi> </munderover> <msub> <mi>u</mi> <mrow> <mi>C</mi> <mi>i</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <msub> <mi>ST</mi> <msub> <mi>M</mi> <mrow> <mi>g</mi> <mi>h</mi> </mrow> </msub> </msub> <mrow> <mo>(</mo> <mi>m</mi> <mo>)</mo> </mrow> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>13</mn> <mo>)</mo> </mrow> </mrow>
Wherein, SuAK，SuAK，SuAKAnd respectively representing the corresponding smooth, general congestion and severe congestion probabilities after the k characteristics are integrated. SuAK，SuAK，SuAKThe service level corresponding to the highest probability value in the data set is the service level to which the current feature belongs.
CN201710421757.1A 2017-06-07 2017-06-07 A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matching Active CN107067727B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710421757.1A CN107067727B (en) 2017-06-07 2017-06-07 A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710421757.1A CN107067727B (en) 2017-06-07 2017-06-07 A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matching

Publications (2)

Publication Number Publication Date
CN107067727A true CN107067727A (en) 2017-08-18
CN107067727B CN107067727B (en) 2019-07-05

Family

ID=59615749

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710421757.1A Active CN107067727B (en) 2017-06-07 2017-06-07 A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matching

Country Status (1)

Country Link
CN (1) CN107067727B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107767023A (en) * 2017-09-20 2018-03-06 浙江工业大学 A kind of road traffic service level evaluation method based on the matching of fuzzy KNN space characteristics
CN109816271A (en) * 2019-02-25 2019-05-28 东南大学 Cycle track service level evaluation method based on shared bicycle track data
CN110858334A (en) * 2018-08-13 2020-03-03 北京中科蓝图科技有限公司 Road safety assessment method and device and road safety early warning system
CN112801373A (en) * 2021-01-29 2021-05-14 南方电网调峰调频发电有限公司 Water regime forecast information system based on big data analysis

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101866543A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Multi-granularity analysis evaluation method and evaluation system for regional traffic service level
CN101866143A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Road traffic service level prediction method based on space-time characteristic aggregation
CN101866550A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Road traffic emulation technique method based on service level
US20100332189A1 (en) * 2009-06-30 2010-12-30 Sun Microsystems, Inc. Embedded microcontrollers classifying signatures of components for predictive maintenance in computer servers
CN103593545A (en) * 2012-08-16 2014-02-19 同济大学 Intersection multi-mode integrated service level evaluation method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101866543A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Multi-granularity analysis evaluation method and evaluation system for regional traffic service level
CN101866143A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Road traffic service level prediction method based on space-time characteristic aggregation
CN101866550A (en) * 2009-04-14 2010-10-20 北京宏德信智源信息技术有限公司 Road traffic emulation technique method based on service level
US20100332189A1 (en) * 2009-06-30 2010-12-30 Sun Microsystems, Inc. Embedded microcontrollers classifying signatures of components for predictive maintenance in computer servers
CN103593545A (en) * 2012-08-16 2014-02-19 同济大学 Intersection multi-mode integrated service level evaluation method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107767023A (en) * 2017-09-20 2018-03-06 浙江工业大学 A kind of road traffic service level evaluation method based on the matching of fuzzy KNN space characteristics
CN110858334A (en) * 2018-08-13 2020-03-03 北京中科蓝图科技有限公司 Road safety assessment method and device and road safety early warning system
CN109816271A (en) * 2019-02-25 2019-05-28 东南大学 Cycle track service level evaluation method based on shared bicycle track data
CN112801373A (en) * 2021-01-29 2021-05-14 南方电网调峰调频发电有限公司 Water regime forecast information system based on big data analysis

Also Published As

Publication number Publication date
CN107067727B (en) 2019-07-05

Similar Documents

Publication Publication Date Title
CN107067727B (en) A kind of road traffic service level evaluation method based on fuzzy KNN characteristic matching
CN109448370B (en) Traffic control subarea division method based on vehicle track data
CN108022012A (en) Vehicle location Forecasting Methodology based on deep learning
Assemi et al. Developing and validating a statistical model for travel mode identification on smartphones
CN110993106A (en) Liver cancer postoperative recurrence risk prediction method combining pathological image and clinical information
KR100866909B1 (en) Method for estimating soil ecological quality from existing soil environmental data
CN106530706B (en) A kind of regional traffic safe evaluation method based on connectivity Spatial weight matrix
CN104809255A (en) Load shape acquisition method and system
CN105374209A (en) Urban region road network running state characteristic information extraction method
CN107845260A (en) A kind of recognition methods of user&#39;s bus trip mode
CN105809193A (en) Illegal operation vehicle recognition method based on Kmeans algorithm
CN106055689A (en) Spatial clustering method based on time sequence correlation
CN107633035A (en) A kind of shared transport services reorder predictor methods based on K Means＆LightGBM models
CN107274066A (en) A kind of shared traffic Customer Value Analysis method based on LRFMD models
Hassan et al. Quantitative description of genomic evolution of olfactory receptors
CN103310027B (en) Rules extraction method for map template coupling
CN103970651A (en) Software architecture safety assessment method based on module safety attributes
CN105890600A (en) Subway passenger position inferring method based on mobile phone sensors
CN107767023A (en) A kind of road traffic service level evaluation method based on the matching of fuzzy KNN space characteristics
CN112801181B (en) Urban signaling traffic flow user classification and prediction method, storage medium and system
CN105139037A (en) Integrated multi-objective evolutionary automatic clustering method based on minimum spinning tree
CN110826623B (en) Classification method and device based on meteorological data, computer equipment and storage medium
CN116469570A (en) Malignant tumor complication analysis method based on electronic medical record
Furukawa et al. A study on a fuzzy clustering for mixed numerical and categorical incomplete data
CN116313111A (en) Breast cancer risk prediction method, system, medium and equipment based on combined model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant