-
Sparse Spectral Hashing for Content-Based Image Retrieval
Issue:
Volume 4, Issue 2-2, March 2015
Pages:
1-4
Received:
7 January 2015
Accepted:
10 January 2015
Published:
13 February 2015
DOI:
10.11648/j.ijiis.s.2015040202.11
Downloads:
Views:
Abstract: In allusion to similarity calculation difficulty caused by high maintenance of image data, this paper introduces sparse principal component algorithm to figure out embedded subspace after dimensionality reduction of image visual words on the basis of traditional spectral hashing image index method so that image high-dimension index results can be explained overall. This method is called sparse spectral hashing index. The experiments demonstrate the method proposed in this paper superior to LSH, RBM and spectral hashing index methods.
Abstract: In allusion to similarity calculation difficulty caused by high maintenance of image data, this paper introduces sparse principal component algorithm to figure out embedded subspace after dimensionality reduction of image visual words on the basis of traditional spectral hashing image index method so that image high-dimension index results can be e...
Show More
-
A User Interest Model Based on the Analysis of User Behaviors
Issue:
Volume 4, Issue 2-2, March 2015
Pages:
5-8
Received:
7 January 2015
Accepted:
10 January 2015
Published:
13 February 2015
DOI:
10.11648/j.ijiis.s.2015040202.12
Downloads:
Views:
Abstract: Understanding the users' interest is the base for the industralization of website. In order to provide individualized service better for the users, on the basis of analyzing the users' browse behavioral characteristics and according to the users' retention time in the page, and users' click frequency to the hyperlink and page, a model of computer user interest degree is established, and a neutral network is proposed to describe their correlation, and the reasonableness and effectiveness of this model are verified through experiment. The experiemtn result shows aathat this model can accurately find out the page that the users are interested in.
Abstract: Understanding the users' interest is the base for the industralization of website. In order to provide individualized service better for the users, on the basis of analyzing the users' browse behavioral characteristics and according to the users' retention time in the page, and users' click frequency to the hyperlink and page, a model of computer u...
Show More
-
APLSSVM: Hybrid Entropy Models for Image Retrieval
Li Jun-yi,
Li Jian-hua,
Zhu Jin-hua,
Chen Xiao-hui
Issue:
Volume 4, Issue 2-2, March 2015
Pages:
9-14
Received:
8 November 2014
Accepted:
12 November 2014
Published:
5 May 2015
DOI:
10.11648/j.ijiis.s.2015040202.13
Downloads:
Views:
Abstract: Aiming at properties of remote sensing image data such as high-dimension, nonlinearity and massive unlabeled samples, a kind of probability least squares support vector machine (PLSSVM) classification method based on hybrid entropy and L1 norm was proposed. Firstly, hybrid entropy was designed by combining quasi-entropy with entropy difference, which was used to select the most “valuable” samples to be labeled from massive unlabeled sample set. Secondly, a L1 norm distance measuring was used to further select and remove outliers and redundant data from the sample set to be labeled. Finally, based on originally labeled samples and screened samples, PLSSVM was gained through training. Experimental results on classification of ROSIS hyperspectral remote sensing images show that the overall accuracy and Kappa coefficient of the proposed classification method reach 89.90% and 0.8685 respectively. The proposed method can obtain higher classification accuracy with few training samples, which is much applicable to classification problem of remote sensing images.
Abstract: Aiming at properties of remote sensing image data such as high-dimension, nonlinearity and massive unlabeled samples, a kind of probability least squares support vector machine (PLSSVM) classification method based on hybrid entropy and L1 norm was proposed. Firstly, hybrid entropy was designed by combining quasi-entropy with entropy difference, whi...
Show More
-
The Operation of the Cross-Border e-commerce Logistics in China
Xiaojun Liu,
Dongyan Chen,
Jieshan Cai
Issue:
Volume 4, Issue 2-2, March 2015
Pages:
15-18
Received:
9 February 2015
Accepted:
10 February 2015
Published:
10 June 2015
DOI:
10.11648/j.ijiis.s.2015040202.14
Downloads:
Views:
Abstract: According to the cross-border e-commerce background, the article is analyzed its operation on the cross-border e-commerce logistics in china. Firstly, this paper illustrates the operation characteristics of cross-border e-commerce logistics, then analyzes some aspects of the cross-border e-commerce logistics, like operations, logistics cost management and so on. Secondly, this paper analyzes existing problems in cross-border e-commerce logistics from the development of electronic commerce logistics cross-border in China. Finally, some suggestions were put forward on cross-border e-commerce logistics operation from the two aspects of macro level of cross-border e-commerce and micro level of cross-border e-commerce enterprise.
Abstract: According to the cross-border e-commerce background, the article is analyzed its operation on the cross-border e-commerce logistics in china. Firstly, this paper illustrates the operation characteristics of cross-border e-commerce logistics, then analyzes some aspects of the cross-border e-commerce logistics, like operations, logistics cost managem...
Show More
