CN108364060A - A kind of classification design method of highway - Google Patents
A kind of classification design method of highway Download PDFInfo
- Publication number
- CN108364060A CN108364060A CN201810095827.3A CN201810095827A CN108364060A CN 108364060 A CN108364060 A CN 108364060A CN 201810095827 A CN201810095827 A CN 201810095827A CN 108364060 A CN108364060 A CN 108364060A
- Authority
- CN
- China
- Prior art keywords
- highway
- neural network
- grey
- town site
- town
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013461 design Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 31
- 238000010835 comparative analysis Methods 0.000 claims abstract description 7
- 238000010276 construction Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 7
- 230000001373 regressive effect Effects 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000013278 delphi method Methods 0.000 claims description 4
- 210000002569 neuron Anatomy 0.000 claims description 4
- 210000004205 output neuron Anatomy 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 12
- 230000006870 function Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of classification design methods of highway：Establish differential weights Grey BP Neural Network built-up pattern；Utilize differential weights Grey BP Neural Network Combined model forecast nonagricultural population's quantity；Estimation prediction year town site newly increased requirement amount S1 (n=i)；Determine the town site area S that practical maximum can increase2；Pass through S1 (n=i)And S2Comparative analysis, divide highway type.The present invention carries out classification refinement to highway type, to different types of highway using the new designing concept for adapting to the development of periphery plot, highway programming and distribution is made to develop in harmony with neighboring area urbanization process.
Description
Technical field
The present invention relates to the classification design methods of the highway of traffic transport industry, and more specifically, it relates to one kind
The classification design method of highway.
Background technology
Conventional high rate planning of highways layout principle thinks that highway is a closed autonomous system, and main function is to protect
The traffic conversion passed by and entered and left the border is demonstrate,proved, and not according to residing position, classification refinement is carried out to its type, it is public to ignore high speed
Road is laid out the relationship between the development of surrounding cities.But as Urbanization in China is accelerated, more and more highways are cut
City plot is split, town site expansion is seriously hindered.
Invention content
Purpose of the invention is to overcome the shortcomings in the prior art, provides a kind of classification design side of highway
Method carries out classification refinement to highway type, is set to different types of highway using the new of periphery plot development is adapted to
Meter theory makes highway programming and distribution develop in harmony with neighboring area urbanization process.
The purpose of the present invention is what is be achieved through the following technical solutions.
A kind of classification design method of highway, includes the following steps：
Step 1 establishes differential weights Grey BP Neural Network built-up pattern；
Step 2, nonagricultural population's prediction：Utilize differential weights Grey BP Neural Network Combined model forecast nonagricultural population
Quantity；
Step 3, estimation prediction year town site newly increased requirement amount S1 (n=i)：Using nonagricultural population's quantity, in conjunction with
《Standard for classification of urban land and for planning of constructional land GB50137-2011》, local land policy, obtain prediction year urban construction
Land used newly increased requirement amount；
Step 4 determines the town site area S that practical maximum can increase2：With present situation (or planning) highway
It is boundary that line position, region, which can utilize the Geographic line of construction land, and closed geometry figure is drawn on map, obtains reality most
The town site area that can increase greatly；
Step 5 passes through S1 (n=i)And S2Comparative analysis, divide highway type.
Differential weights Grey BP Neural Network built-up pattern establishes process in step 1：
(1) original grey forecasting model is established
Establish original data sequence：
X(0)={ x(0)(1),x(0)(2),...,x(0)(n)}
According to the following formula
Single order is carried out to original data sequence to add up, and generates 1-AGO sequences：
X(1)={ x(1)(1),x(1)(2),...,x(1)(n)}
(2) original grey forecasting model differential weights optimization
Original grey forecasting model is optimized using analytic hierarchy process (AHP), each factor is compared two-by-two using Delphi method, is carried out
Assessment determines that recent times sequence weights are λ respectively1, weight at a specified future date is λ2, original grey forecasting model differential weights are optimized for：
And then generate differential weights 1-AGO series models：
X′(1)={ x '(1)(1),x′(1)(2),...,x′(1)(n)}
(4) BP neural network designs
Establish a three-layer network containing input layer, hidden layer, output layer：
1. the access time sequential value { x ' in differential weights 1-AGO series models(1)(1),x′(1)(2),...,x′(1)(m)}
The input layer of (m ＜ n) as BP neural network；
2. with x '(1)(m+1) as the output layer of BP neural network；
3. hidden node is according to formulaIt calculates and determines, m is the number for inputting neuron, and p is output god
Number through member, q are the constant between 1~10；
4. being predicted using trained BP neural network, forecasting sequence will be obtained using regressive reduction to future
Predicted value.
Nonagricultural population predicts that process is specially in step 2：
The nonagricultural population's quantity over the years for collecting the city estimation ranges Zhong Suo forms original time series：
It is added up using improved differential weights grey forecasting model, obtains improving the cumulative sequence of nonagricultural population：
The optimal knot that in gained sequence inputting to trained BP neural network, BP neural network will be calculated
Fruit carry out regressive reduction to get to prediction year nonagricultural population's predicted value.
S in step 51 (n=i)And S2Comparative analysis：
(1) if the prediction year town site newly increased requirement amount that highway is predicted after building up 5 years is not less than reality
The town site area that maximum can increase, i.e.,：S1 (n=5)≥S2, then the highway belong to " city highway "；
(2) if highway builds up the prediction year town site newly increased requirement amount predicted after 5-20 and is not less than in fact
The town site area that border maximum can increase, i.e.,：S1 (n=5~20)≥S2, then the highway belong to " outskirts of a town highway ".
Compared with prior art, advantageous effect caused by technical scheme of the present invention is：
(1) present invention establishes differential weights Grey BP Neural Network built-up pattern, and trend is expanded in predicted city, obtains prediction year
Town site newly increased requirement amount S1 (n=i), draw the town site model under present situation (planning) highway influence of arrangement
It encloses, obtains the town site area S that practical maximum can increase2, to S1 (n=i)And S2The two is compared, and clearly predicts year
The affiliated type of highway provides foundation for highway programming and distribution optimization or modified threshold decision.
(2) present invention is different from the highway of traditional sense, and refinement is classified to highway type, it is proposed that
" city highway " is respectively adopted corresponding theory and is designed with " outskirts of a town highway " new concept according to its position feature,
In planning, design process, influence of the highway cloth exchange line position for neighboring area urbanization is fully considered, for newly-built high speed
Planning of highways addressing, present situation highway extension project program decisions provide technical support.
Description of the drawings
Fig. 1 is neural metwork training figure of the present invention；
Fig. 2 is neural network fitted figure；
Fig. 3 is Tianjin construction land planning chart；
Fig. 4 is Dongli District future construction land measuring and calculating figure.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings.
The classification design method of the highway of the present invention, it is proposed that " city highway " and " outskirts of a town highway "
New concept expands range in the design phase in conjunction with neighboring area town site, specifies Expressway Development positioning, to refer to
It leads and highway planning and modified threshold offer technical support is provided.Detailed process is as follows：
One, differential weights Grey BP Neural Network built-up pattern is established；
(1) original grey forecasting model is established
Establish original data sequence：
X(0)={ x(0)(1),x(0)(2),...,x(0)(n)} (1)
(2) according to the following formula
To original data sequence X(0)It is cumulative to carry out single order, generates 1-AGO sequences：
X(1)={ x(1)(1),x(1)(2),...,x(1)(n)} (3)
(2) original grey forecasting model differential weights optimization
It is cumulative that original grey forecasting model only the power such as carries out to original series, considers time factor for prediction result
Influence, and in a practical situation, the time series information contained amount closer to prediction year is bigger, can more embody future development
Trend, distributed weight also should be bigger.Therefore original grey forecasting model is advanced optimized using analytic hierarchy process (AHP), is invited
Please expert each factor is compared two-by-two using Delphi method, assessed, determine that recent times sequence weights are λ respectively1, at a specified future date
Weight be λ2, original grey forecasting model differential weights are optimized for：
And then generate differential weights 1-AGO series models：
X′(1)={ x '(1)(1),x′(1)(2),...,x′(1)(n)} (5)
(5) BP neural network designs
Establish a three-layer network containing input layer, hidden layer, output layer：
1. the access time sequential value { x ' in differential weights 1-AGO series models(1)(1),x′(1)(2),...,x′(1)(m)}
The input layer of (m ＜ n) as BP neural network；
2. with x '(1)(m+1) as the output layer of BP neural network；
3. hidden node can be according to formulaIt calculates and determines, m is the number for inputting neuron, and p is output
The number of neuron, q are the constant between 1~10；
4. being predicted using trained BP neural network, forecasting sequence will be obtained using regressive reduction to future
Predicted value.
Two, nonagricultural population predicts：Utilize differential weights Grey BP Neural Network Combined model forecast nonagricultural population's quantity.
The nonagricultural population's quantity over the years for collecting the city estimation ranges Zhong Suo forms original time series：
Note：For nonagricultural population's investigation value over the years.
It is added up using improved differential weights grey forecasting model, obtains improving the cumulative sequence of nonagricultural population：
Note：Gained is calculated by formula (4).
The optimal knot that in gained sequence inputting to trained BP neural network, BP neural network will be calculated
Fruit carries out regressive reduction, you can obtains nonagricultural population's predicted value in prediction year.
Three, estimation prediction year town site newly increased requirement amount S1 (n=i)：
Using the predicted value of above-mentioned nonagricultural population's quantity, in conjunction with《Standard for classification of urban land and for planning of constructional land
GB50137-2011》, local land policy, obtain prediction year town site newly increased requirement amount S1 (n=i)。
Four, the town site area S that practical maximum can increase is determined2：
It is usually expanded from the central area suitable for development to city edge in Development of Urbanization direction.It is high with present situation (or planning)
It is boundary that fast identitypath position, region, which can utilize the geographical line of demarcation of the correlation of construction land, and closed geometry figure is drawn on map,
The area of the geometric figure is after highway is built, and when urban development to high speed both sides of highway, the practical maximum in city can
The town site area S of growth2。
Five, highway type is divided：
The design period of general highway is 20 years, and under normal circumstances, newly-built highway is ensureing that massless asks
In the case of topic and overload and oversize problem, it will not be rebuild on a large scale in 5 years.Therefore it is built up with highway 5 after runing
Year and 20 years are node, pass through S1 (n=i)And S2Comparative analysis, divide highway type.
S1 (n=i)And S2Comparative analysis：
(1) if the prediction year town site newly increased requirement amount that highway is predicted after building up 5 years is not less than reality
The town site area that maximum can increase, i.e.,：S1 (n=5)≥S2.Illustrate that this highway will invade the row closed on quickly
Administrative division domain hinders the urbanization process of neighboring area, belongs to " city highway ", needs using " city highway " related reason
It reads and carries out planning and designing.
(2) if highway builds up the prediction year town site newly increased requirement amount predicted after 5-20 and is not less than in fact
The town site area that border maximum can increase, i.e.,：S1 (n=5~20)≥S2.Although illustrating the highway within a certain period of time
Will not hinder city hair, but within design period will enter city, belong to " " outskirts of a town highway ", need use " outskirts of a town
Highway " correlation theory is designed.
Highway programming and distribution optimization or modified threshold optimization are carried out according to the result of above scheme.
Embodiment：
Tianjin Dongli District is located in the main shaft of Jin Bin development, and east connects Binhai New District core space, and west connects inner city, is Tianjin
The critical function area of inner city and Binhai New District.The development model of Tianjin is that main city zone and Binhai New District Shuangcheng develop, two
Dongli District between city just becomes the main development region of Tianjin.Ji Shan highway arises from Expressway between Beijing and Tianjin, and terminal is connected to
Honor crow high speed (Tianjin Shanxi high speed) in National Highway road network, passes through eastern beautiful, 3rd area Jin Nan, Xi Qing, be open to traffic fortune in 2016 on the way
Battalion.According to the planning direction of Urbanization in Tianjin City, beautiful section of Ji Shan highway east very likely enters city within design period,
Ji Shan highway is judged and classified below with the method that this patent proposes.
From《Tianjin statistical yearbook》The middle nearly 20 years nonagricultural population's numbers in acquisition Dongli District, i.e. n=20；It is true using Delphi method
Determine recent times sequence weights λ1=0.65, weight at a specified future date is λ2=0.35.
City nonagricultural population is predicted using the differential weights Grey BP Neural Network built-up pattern of optimization, wherein institute
The training function of choosing is trainlm, and first layer transmission function is tansig, and second layer transmission function is purelin, training error
It is 0.0001, learning rate 0.1.
By testing repeatedly, prediction effect is best when determining parameter m=8, p=1, q=10.Training figure is as shown in Figure 1, quasi-
Figure is closed as shown in Fig. 2, statistical data and prediction result are as shown in table 1.
1 Tianjin Dongli District population prediction result of table and error
According to Tianjin Dongli District development plan, the control of town site Per capita area is drafted in 100m in Dongli District2/
People, by《Standard for classification of urban land and for planning of constructional land GB50137-2011》Obtain Tianjin Per Capita Urban Land rule
Mould value range is 75~100m2/ people, it is 90m to choose planning Per Capita Urban Land value2/ people, according to above-mentioned population
The predicted value of quantity is calculated from after being open to the traffic 5 years and 10 years Ji Shan highway, the urban construction of Tianjin Dongli District
Land area increment is respectively S1 (n=5)=8.19km2And S1 (n=10)=18.19km2。
It is planned according to Tianjin construction land, the urbanization direction of Dongli District is by inner city east expansion, with Ji Shan high speed
Highway and be boundary using the geographical line of demarcation of correlation of construction land, Dongli District may develop into the range of construction land
As shown in Figure 3, Figure 4.It is found that S2=16.38km2。
Known to comparison：S1 (n=5)＜ S2, S1 (n=10)＞ S2, explanation：(1) after Ji Shan high speed is open to traffic 5 years, Dongli District
The incrementss of town site are small compared with measuring and calculating area, and highway periphery soil is still to develop into town site；(2) but with
The quickening of urbanization process, Ji Shan high speed were open to traffic after 10 years, and Dongli District will gradually be expanded eastwards, town site
Demand has been over calculated area, i.e. Ji Shan highway layout will hinder the urbanization process of Dongli District, belong to
In " outskirts of a town highway ", its following influence to Dongli District urban sprawl need to be considered in modified threshold decision.
Although the function and the course of work of the present invention are described above in conjunction with attached drawing, the invention is not limited in
Above-mentioned concrete function and the course of work, the above mentioned embodiment is only schematical, rather than restrictive, ability
The those of ordinary skill in domain under the inspiration of the present invention, is not departing from present inventive concept and scope of the claimed protection situation
Under, many forms can also be made, all of these belong to the protection of the present invention.
Claims (4)
1. a kind of classification design method of highway, which is characterized in that include the following steps：
Step 1 establishes differential weights Grey BP Neural Network built-up pattern；
Step 2, nonagricultural population's prediction：Utilize differential weights Grey BP Neural Network Combined model forecast nonagricultural population's quantity；
Step 3, estimation prediction year town site newly increased requirement amount S1 (n=i)：Using nonagricultural population's quantity, in conjunction with《City
Land use class and planning construction standard for land use GB50137-2011》, local land policy, it is new to obtain prediction year town site
Increase demand；
Step 4 determines the town site area S that practical maximum can increase2：With present situation (or planning) highway line position,
It is boundary that region, which can utilize the Geographic line of construction land, closed geometry figure is drawn on map, obtaining practical maximum can
The town site area of growth；
Step 5 passes through S1 (n=i)And S2Comparative analysis, divide highway type.
2. the classification design method of highway according to claim 1, which is characterized in that differential weights grey in step 1
BP neural network built-up pattern establishes process：
(1) original grey forecasting model is established
Establish original data sequence：
X(0)={ x(0)(1),x(0)(2),...,x(0)(n)}
According to the following formula
Single order is carried out to original data sequence to add up, and generates 1-AGO sequences：
X(1)={ x(1)(1),x(1)(2),...,x(1)(n)}
(2) original grey forecasting model differential weights optimization
Original grey forecasting model is optimized using analytic hierarchy process (AHP), each factor is compared two-by-two using Delphi method, is assessed,
Determine that recent times sequence weights are λ respectively1, weight at a specified future date is λ2, original grey forecasting model differential weights are optimized for：
And then generate differential weights 1-AGO series models：
X′(1)={ x '(1)(1),x′(1)(2),...,x′(1)(n)}
(3) BP neural network designs
Establish a three-layer network containing input layer, hidden layer, output layer：
1. the access time sequential value { x ' in differential weights 1-AGO series models(1)(1),x′(1)(2),...,x′(1)(m) } (m ＜
N) as the input layer of BP neural network；
2. with x '(1)(m+1) as the output layer of BP neural network；
3. hidden node is according to formulaIt calculates and determines, m is the number for inputting neuron, and p is output neuron
Number, q be 1~10 between constant；
4. being predicted using trained BP neural network, forecasting sequence is obtained using regressive reduction to following prediction
Value.
3. the classification design method of highway according to claim 1, which is characterized in that nonagricultural population in step 2
Prediction process is specially：
The nonagricultural population's quantity over the years for collecting the city estimation ranges Zhong Suo forms original time series：
It is added up using improved differential weights grey forecasting model, obtains improving the cumulative sequence of nonagricultural population：
By in gained sequence inputting to trained BP neural network, optimal result that BP neural network is calculated into
Row regressive reduction to get to prediction year nonagricultural population's predicted value.
4. the classification design method of highway according to claim 1, which is characterized in that S in step 51 (n=i)And S2
Comparative analysis：
(1) if the prediction year town site newly increased requirement amount that highway is predicted after building up 5 years is not less than practical maximum
The town site area that can increase, i.e.,：S1 (n=5)≥S2, then the highway belong to " city highway "；
(2) if highway builds up the prediction year town site newly increased requirement amount predicted after 5-20 and is not less than reality most
The town site area that can increase greatly, i.e.,：S1 (n=5~20)≥S2, then the highway belong to " outskirts of a town highway ".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810095827.3A CN108364060A (en) | 2018-01-31 | 2018-01-31 | A kind of classification design method of highway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810095827.3A CN108364060A (en) | 2018-01-31 | 2018-01-31 | A kind of classification design method of highway |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108364060A true CN108364060A (en) | 2018-08-03 |
Family
ID=63007498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810095827.3A Pending CN108364060A (en) | 2018-01-31 | 2018-01-31 | A kind of classification design method of highway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108364060A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763600A (en) * | 2010-01-12 | 2010-06-30 | 武汉大学 | Land use supply and demand prediction method based on model cluster |
| CN102073785A (en) * | 2010-11-26 | 2011-05-25 | 哈尔滨工程大学 | Daily gas load combination prediction method based on generalized dynamic fuzzy neural network |
| US9547821B1 (en) * | 2016-02-04 | 2017-01-17 | International Business Machines Corporation | Deep learning for algorithm portfolios |
-
2018
- 2018-01-31 CN CN201810095827.3A patent/CN108364060A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763600A (en) * | 2010-01-12 | 2010-06-30 | 武汉大学 | Land use supply and demand prediction method based on model cluster |
| CN102073785A (en) * | 2010-11-26 | 2011-05-25 | 哈尔滨工程大学 | Daily gas load combination prediction method based on generalized dynamic fuzzy neural network |
| US9547821B1 (en) * | 2016-02-04 | 2017-01-17 | International Business Machines Corporation | Deep learning for algorithm portfolios |
Non-Patent Citations (3)
| Title |
|---|
| 刘同星等: "基于PSO算法的加权累加生成GM(1,1)模型在结构损伤识别中的应用", 《建筑科学》 * |
| 姚瑶等: "人地挂钩下城镇建设用地需求量预测——以伊宁市为例", 《天津农业科学》 * |
| 陈永忠: "重庆市内环快速路公交车安全运营模式探析", 《重庆交通大学学报( 社科版)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105070042B (en) | A kind of modeling method of traffic forecast | |
| CN114372685B (en) | Urban storm waterlogging risk assessment method based on SWMM model | |
| Ghodsi et al. | Developing a stochastic conflict resolution model for urban runoff quality management: application of info-gap and bargaining theories | |
| CN106780089B (en) | Permanent basic farmland planning method based on neural network cellular automaton model | |
| Babapour et al. | Forest road profile optimization using meta-heuristic techniques | |
| CN110889562B (en) | Dynamic city model system based on scenario planning | |
| CN112699610A (en) | Sponge city optimization design method based on high-dimensional multi-objective evolutionary algorithm | |
| CN113222271B (en) | Medium and small airport site selection layout method under comprehensive transportation system | |
| CN104320789A (en) | Game theory-based vehicle networking RSU optimal configuration method | |
| CN114943484B (en) | Rail passenger flow capacity matching method, electronic equipment and storage medium thereof | |
| CN106370198A (en) | Route selection method taking outgoing delayed reaction into account | |
| Shrestha et al. | A multi-objective analysis of a rural road network problem in the hilly regions of Nepal | |
| CN108388970A (en) | A kind of bus station site selecting method based on GIS | |
| CN110232472A (en) | A kind of low Multipurpose Optimal Method for influencing Development allocation | |
| CN105913134A (en) | SOA technical method for city industry layout space optimization analysis | |
| CN112184282A (en) | Cinema site selection model establishing method, cinema site selection method and cinema site selection platform | |
| Goyal et al. | Flash flood risk management modeling in indian cities using IoT based reinforcement learning | |
| CN104821086B (en) | Method for positioning low-efficient road section combination in large-scale traffic network | |
| CN113743766A (en) | Decision evaluation method and system for sponge city planning construction | |
| Wang et al. | Offline optimization of sluice control rules in the urban water system for flooding mitigation | |
| CN107169589A (en) | A kind of low pressure grid based on KNN and roulette algorithm becomes more meticulous load forecasting method | |
| CN110210667A (en) | O-D spatial and temporal distributions prediction technique based on mutative scale Geographical Weighted Regression Model | |
| CN113393104A (en) | Method for evaluating influence of rail transit running state on peripheral public bicycles | |
| CN108364060A (en) | A kind of classification design method of highway | |
| CN113554221B (en) | Method for simulating and predicting town development boundary under view angle of' flow space |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180803 |
|
| RJ01 | Rejection of invention patent application after publication |