Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for evaluating urban logistics level based on entropy normalization locality preserving protection

A technology that locally maintains projection and evaluation methods. It is applied in logistics, computer components, instruments, etc., and can solve problems such as unknown spatial distribution, difficult parameter setting, and performance degradation of LPP algorithms, and achieve comprehensive evaluation results.

Inactive Publication Date: 2018-09-28
NORTHEAST FORESTRY UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, LPP needs to specify the number of k neighbors and the parameters of the thermal kernel function in advance to determine the similarity matrix. In practical applications, because the spatial distribution of the original data is unknown in advance, parameter setting becomes very difficult.
Affected by improper parameter settings, the performance of the traditional LPP algorithm is severely degraded

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for evaluating urban logistics level based on entropy normalization locality preserving protection
  • Method for evaluating urban logistics level based on entropy normalization locality preserving protection
  • Method for evaluating urban logistics level based on entropy normalization locality preserving protection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] A method for evaluating urban logistics level based on entropy normalization local maintenance projection, the described method based on entropy normalization local maintenance analysis includes the following specific steps:

[0060] Known data set x 1 , x 2 ,...x M , where x i ∈R N , i=1, 2, . . . , M. M is the total number of samples, and N is the total number of indicators. let y i ,y j is the one-dimensional projection coordinate under the new basis vector, considered in the overall sample, the original similar sample x i ,x j The same is true in the new base coordinate space. Let the similarity matrix be: U∈R M×M . where u ij ∈U represents the sample x of the original sample space i ,x j The degree of similarity, i, j=1, 2, 3..., M, metric matrix: D∈R M×M , where d ij =∑ j u ij , using the maximum entropy normalization construct to solve for U and the projection vector W ELpp The objective function of is:

[0061]

[0062]

[0063] Where ...

Embodiment 2

[0109] In order to verify the performance of entropy normalized locally preserving projection analysis, the wine data set from the UCI data set is used in the experiment for dimensionality reduction analysis and compared with the traditional LPP algorithm and PCA algorithm. The Wine dataset includes 3 categories, the numbers are: 59, 81, 48. The original spatial data has 13 attribute characteristics. Set the dimensionality reduction dimension to 2, the number of nearest neighbors to 1, and the heat kernel parameter to 1. Dimensionality reduction results of wine datasets with different algorithms are as follows: figure 1 , as shown in 2, 3, and 4. in figure 1 , 2, 3, 4 are the dimensionality reduction results of traditional LPP algorithm, entropy normalized local preserving projection algorithm iteration 1, entropy normalized local preserving projection algorithm iteration 300 times and PCA algorithm respectively. From the comparison of the experimental results, we can find...

Embodiment 3

[0114] In order to verify the evaluation method of urban logistics level based on entropy normalized local preservation projection, this experiment evaluates the logistics level of major cities in Shandong Province. The evaluation indicators are all from the Statistical Yearbook of Shandong Province, which are: (1) Urban economic development level: ①GDP (100 million yuan); ②Per capita GDP (100 million yuan); 3GDP growth rate (%); ④Gross industrial output value (100 million yuan). (2) Degree of informatization: ①The total amount of postal business (100 million yuan). (3) Urban consumption level: ① Total retail sales of social consumer goods (100 million yuan); ② Total wholesale and retail commodity purchases (100 million yuan). (4) The level of logistics development: ① employees in transportation, warehousing and postal services (10,000 people); 10,000 tons per kilometer); ⑤ Number of commercial trucks (units); ⑥ Highway mileage (km); ⑦ Expressway mileage (km). Select 17 repr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for evaluating urban logistics level based on an entropy normalization locality preserving protection, which is characterized by comprising the following steps: (1) determining an urban logistics level evaluation criterion, and performing output and input indicator classification; (2) performing reciprocal on the input indicator obtained in the step (1) and normalizing all the indicators by the minmax method, so that the range is between [0, 1]; (3) performing principal element component analysis and entropy normalization locality preserving protection analysisby using a normalized data matrix X* obtained in the step (2), and finally determining projection vectors PPca and WELpp; (4) using the projection vectors obtained in the step (3) to calculate a global distribution feature coefficient vector X'Pca=PPcaTX* and a local distribution feature coefficient vector X'ELpp=WELppTX*; (5) using the X'Pca and the X'ELpp obtained in the step (6) to perform weighting to obtain a final evaluation coefficient vector X', and performing descending order on X' so as to obtain a final urban logistics level evaluation result. The application of the present invention is applied to the evaluation problem of the urban logistics level.

Description

Technical field: [0001] The application of the present invention relates to the field of logistics level evaluation, in particular to a method for urban logistics level evaluation based on entropy normalized local preservation projection analysis. Background technique: [0002] Cities not only play a prominent role in political and cultural life, but also have an important economic status. They are the production centers, distribution centers and consumption centers of commodities, and have strong comprehensive service capabilities, radiation capabilities and attractive capabilities. Urban logistics is an important part of the city's comprehensive competitiveness and plays an important role in promoting the development of urban economy. Therefore, scientifically and rationally evaluating the development level of urban logistics can optimize the logistics system, improve the city's logistics service level, and promote the development of commodities. Circulation also helps to ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/06G06Q10/08G06K9/62
CPCG06Q10/06393G06Q10/083G06F18/2135
Inventor 陶新民刘锐梁祥磊任超郭文杰刘艳超陶思睿
Owner NORTHEAST FORESTRY UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products