Time filter

Source Type

Shenzhen, China

Wu J.,Shenzhen Angelshine Co. | Chi H.,Wuhan University | Chi L.,Huazhong University of Science and Technology
Journal of Multimedia | Year: 2011

The process to synthesize feature for human facial expression often implies both fuzziness, randomness and their certain relevance in image data. By using the advantage of cloud model, this paper presents a new approaches and applications for comprehensive analysis of human facial expression synthesis using cloud model, in order to realize the rapid and effective facial expression processing in analysis and application. It gives the comprehensive analysis for the fuzziness and randomness of facial expression feature and the relationship between them based on cloud model, including the new method of facial expression synthesis with the uncertainty. It proposes the method of facial expression feature synthesis by cloud model, using the three numerical characteristics (Expectation, Entropy and Hyper Entropy) as the features and concepts of facial expression with its fuzziness, randomness and certain relevance in them. Through such three numerical characteristics, it introduces the framework of facial expression synthesis and the detail procedures based on cloud model. It puts forward the synthesis method of facial expression and gives the concrete realization and the implementation process. The facial expressions after synthesis can express the different expressions for one person, and it can meet a variety of demands for facial expression. The experimental results show that the proposed method is feasible and effective in facial expression synthesis.

Wu J.,Shenzhen Angelshine Co. | Wu J.,National University of Singapore | Wu Z.,Wuhan University
International Review on Computers and Software | Year: 2012

The high improvement of mobile communication technology and the reduction in cost of hardware have accelerated the wide popularity of mobile application, in which the personalized recommendation is playing a more and more important role in users' preferences and needs. This paper presents a novel approach of location-aware personalized recommendation by clustering-based collaborative filtering, providing recommendation list for users according to their current positions from mobile devices. First, users are partitioned into different clusters by k-means algorithm, in order to speed up the process for searching the nearest neighbors. Second, the location-aware factor is computed according to the user's acceptable distance of items, which is changing over time. Third, the recommendation list is produced by combining location-aware factor with clustering-based collaborative filtering. An application system of hotel recommendation is developed to illustrate and test the feasibility and effectiveness. © 2012 Praise Worthy Prize S.r.l. - All rights reserved.

Deng J.,Zhongshan Ppolytechnic | Hu J.,Zhongshan Ppolytechnic | Li W.,Zhongshan Ppolytechnic | Wu J.,Shenzhen Angelshine Co.
Communications in Computer and Information Science | Year: 2011

Mainly from the angle of computer system, this paper analyzes the negative influence of natural environment caused by the computer system. It presents a novel concept for green computing with generalized aspect and expands the traditional tasks and relationships of green computing research. Firstly, the deep discussion of generalized green computing using hardware and software technology and method is carried out, and the indicative meaning behind it is analyzed, including all kinds of the scheme for research institutions and enterprises. Then, some basic ideas of green computing and generalized methods are put forward in order to establish the necessary foundation for the methods and tools of green computing. © 2011 Springer-Verlag Berlin Heidelberg.

Wu J.,Shenzhen Angelshine Co. | Wu J.,National University of Singapore | Wu Z.,Wuhan University
Research Journal of Applied Sciences, Engineering and Technology | Year: 2013

With rapid development of e-commerce, how to better understand users' needs to provide more satisfying personalized services has become a crucial issue. To overcome the problem, this study presents a novel approach for personalized product recommendation based on Fuzzy C-Means (FCM) clustering. Firstly, the traditional FCM clustering algorithm is improved by membership adjustment and density function, in order to address the issues that the number of clusters is difficult to determine and the convergence of objective function is slow. Then, the personal preferences are divided into different groups, one of which the users have the similar tendencies in. The association rules of user preferences are mined for each group and the personalized knowledge base is established. After that, the recommendation can be generated by knowledge base and historical logs. A case study is illustrated by the proposed approach and the results show that the method of personalized product recommendation is reasonable and efficient with high performance. © Maxwell Scientific Organization, 2013.

Hu J.,Zhongshan Polytechnic | Deng J.,Zhongshan Polytechnic | Wu J.,Shenzhen Angelshine Co.
Journal of Networks | Year: 2011

Image compression is a crucial step in image processing area. Image Fourier transforms is the classical algorithm which can convert image from spatial domain to frequency domain. Because of its good concentrative property with transform energy, Fourier transform has been widely applied in image coding, image segmentation, image reconstruction. This paper adopts Radix-4 Fast Fourier transform (Radix-4 FFT) to realize the limit distortion for image coding, and to discuss the feasibility and the advantage of Fourier transform for image compression. It aims to deal with the existing complex and time-consuming of Fourier transform, according to the symmetric conjugate of the image by Fourier transform to reduce data storage and computing complexity. Using Radix-4 FFT can also reduce algorithm time-consuming, it designs three different compression requirements of nonuniform quantification tables for different demands of image quality and compression ratio. Take the standard image Lena as experimental data using the presented method, the results show that the implementation by Radix- 4 FFT is simple, the effect is ideal and lower time-consuming. © 2011 ACADEMY PUBLISHER.

Discover hidden collaborations