期刊:
Journal of Convergence Information Technology,2010年5(9):118-125 ISSN:1975-9320
通讯作者:
Wang, F.(wangfengxia@gmail.com)
作者机构:
[Chang, Xiao; Wang, Fengxia] Department of Computer Science and Technology, Xi'an Jiaotong University, China;[Jin, Huixia] Department of Physics and Telecom Engineering, Hunan City University, Yiyang, 413008, China
摘要:
In recent years, learning ranking function for information retrieval has drawn the attentions of the researchers from information retrieval and machine learning community. In existing approaches of learning to rank, the sparse prediction model only can be learned by support vector learning approach. However, the number of support vectors grows steeply with the size of the training data set. In this paper, we propose a sparse Bayesian kernel approach to learn ranking function. By this approach accurate prediction models can be derived, which typically utilize fewer basis functions than the comparable SVM-based approaches while offering a number of additional advantages. Experimental results on document retrieval data set show that the generalization performance of this approach competitive with two state-of-the-art approaches and the prediction model learned by it is typically sparse.
期刊:
The Journal of Information and Computational Science,2010年7(13):2739-2748 ISSN:1548-7741
通讯作者:
Jin, H.(jinhuixia1980@163.com)
作者机构:
[Jin, Huixia] Department of Physics and Telecommunication Engineering, Hunan City University, Yiyang, 413000, China;[Yang, Gelan] Department of Computer Science, Hunan City University, Yiyang, 413000, China
通讯机构:
Department of Physics and Telecommunication Engineering, Hunan City University, China
关键词:
Clonal selection algorithm;Genetic algorithm;Information retrieval;Parallel genetic immune clonal algorithm;Vector space model
作者机构:
[黄龙杨; 刘慧; 程恩] Key Laboratory of Underwater Acoustic Communication and Marine Information Technology, Xiamen University, Xiamen 361005, Fujian, China;[李梦醒] Department of Physics and Telecommunications, Hunan City University, Yiyang 413000, Hunan, China
通讯机构:
Key Laboratory of Underwater Acoustic Communication and Marine Information Technology, Xiamen University, China
摘要:
It is well known that information retrieval systems based entirely on syntactic contents have serious limitations. In order to achieve high precision and recall on IR systems, the incorporation of natural language processing techniques that provide semantic information is needed. For this reason, by determining the semantic for the constituents of documents, a clustering method is presented in this paper. The goal is to find the conjoined point which can combine the advantages of both textual part and visual part, and to use for IR systems. It can help to well extract the meaning of a term. Thus, we can take the formalized meaning, instead of the lexical term, and consequently resolve the word sense ambiguity. Experimental results show that the proposed SWCSM model significantly improves the average precision and recall and reduces the overall search time.
期刊:
The Journal of Information and Computational Science,2009年6(2):837-844 ISSN:1548-7741
通讯作者:
Shu, W.(shuwanneng@yahoo.com.cn)
作者机构:
[Jin, Huixia; Yang, Gelan] Department of Computer Science, Hunan City University, Yiyang, Hunan, 413000, China;[Shu, Wanneng] College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China;[Wang, Yuanzhi] School of Computer and Information, Anqing Normal College, Anqing 246011, China
通讯机构:
College of Computer Science, South-Central University for Nationalities, China
关键词:
Clonal Selection;Genetic Algorithm;Information Retrieval;Vector Space Model
期刊:
PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9,2009年:2660-2663
通讯作者:
Yang, Gelan
作者机构:
[Yang, Gelan] Hunan City Univ, Dept Comp Sci, Yiyang, Peoples R China.;[Jin, Huixia] Hunan City Univ, Dept Phys & Telecom Engn, Yiyang, Peoples R China.;[Xu, Xue] Univ Sci & Technol China, Dept Automat, Hefei, Peoples R China.
通讯机构:
[Yang, Gelan] H;Hunan City Univ, Dept Comp Sci, Yiyang, Peoples R China.
关键词:
local tangent space alignment;semi-supervise learning;local block coordinate;manifold regression
摘要:
In many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are fairly expensive to obtain. Therefore, semi-supervised learning algorithms have attracted much attention. In this paper, semi-supervised regression via local block coordinate algorithm is proposed. This algorithm preserves more geometrical knowledge of the high-dimensional data by local tangent space alignment, we take the method of automatic alignment of local representations to realize preserving the linear projection between every local coordinate and the global coordinate. Experiments show that method can effectively exploit unlabeled data to improve regression estimates.
作者机构:
[刘泽民; 李梦醒] School of Telecommunication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;[程恩; 黄龙杨] Laboratory of Underwater Acoustic Communication and Marine Information Technology, Ministry of Education, Fujian Xiamen 361005, China;[李梦醒] Department of Physics and Telecommunication Engineering, Hunan City University, Hunan Yiyang 413000, China
通讯机构:
[Li, M.-X.] S;School of Telecommunication Engineering, Beijing University of Posts and Telecommunications, China
关键词:
Bose-Einstein condensation;Gravitational field;Finite number effects
摘要:
Microscopic bouncing balls, i.e., particles confined within a positive one-half-dimensional gravitational potential, display Bose-Einstein condensation (BEC) not only in the thermodynamic limit but also in the case of a finite number of particles, and the critical temperature with a finite number of particles is higher than that in the thermodynamic limit. This system is different from the one-dimensional harmonic potential one, for which the standard result indicates that the BEC is not possible unless the number of particles is finite. (c) 2009 Elsevier B.V. All rights reserved.
摘要:
A multirate nonuniform subband method with general parameter filter banks for wideband beamforming of harmonic nested array is proposed. The harmonic nested array is composed of several uniformly-spaced linear subarrays, each of which processes an octave subband signal. The nonuniform subband signal is generated by general parameter filter banks. Each subarray beamforming is carried out with space-frequency signal processing approach, and four subarrays share the same weights among themselves. Based on this kind of processing architecture, the proposed beamformer splits the wideband signal into several nonuniform narrow subband ones which are processed in parallel, and only one subarray weights are needed. In this way, the proposed beamformer greatly alleviate burden of demanding too many weights for the arrays and hence contributes to significantly decreasing the computational load and improving the speed as well. Simulations show that the proposed beamformer is competent for wideband beamforming with much lower computation complexity.
作者机构:
[祝青; 阳王东] Department of Computer Science and Technology, Hunan City University, Yiyang 413000, China;[何焕民] Shan Tou Lin Baixin Science and Techology School, Shantou 515041, China
通讯机构:
Department of Computer Science and Technology, Hunan City University, China
期刊:
Proceedings of the 2008 International Conference on Computer and Electrical Engineering, ICCEE 2008,2008年:296-299
通讯作者:
Jin, Huixia
作者机构:
[Jin, Huixia] Hunan City Univ, Dept Phys & Telecom Engn, Yiyang 413008, Peoples R China.;[Yang, Gelan; Tu, Li] Hunan City Univ, Dept Comp Sci, Yiyang 413008, Peoples R China.;[Yang, Yatao] Beijing Elect Sci & Technol Inst, Beijing 100070, Peoples R China.
通讯机构:
[Jin, Huixia] H;Hunan City Univ, Dept Phys & Telecom Engn, Yiyang 413008, Peoples R China.
摘要:
The mutual authentication mechanism in the IEEE802.16e can avoid the man-in-middle attack, and can protect the multi-hop WiMax security in efficiency. An improved X.509 certificate based on ECC algorithm is designed, then an enhanced mutual authentication flow was proposed in this paper, which enhances the security and working efficiency of the mutual authentication in multi-hop WiMax system. The proposed scheme heightens the security and practicability of WiMax system, which has better referenced value to the improvement of IEEE 802.16e standards.
期刊:
Microwave and Optical Technology Letters,2008年50(8):2158-2161 ISSN:0895-2477
通讯作者:
Xu, Lan Yun
作者机构:
[Xu, Lan Yun] Hunan City Univ, Dept Phys & Elect Engn, Yiyang 413000, Hunan, Peoples R China.;[Yu, Jian Guo] Beijing No Fiberhome Technol Co Ltd, Beijing 100088, Peoples R China.;[Xu, Hong Yun] S China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510640, Peoples R China.
通讯机构:
[Xu, Lan Yun] H;Hunan City Univ, Dept Phys & Elect Engn, Yiyang 413000, Hunan, Peoples R China.
作者机构:
[Zhang, Guo-Min; Zhu, En; Yin, Jian-Ping; Hu, Chun-Feng] School of Computer Science, National University of Defense Technology, Changsha 410073, China;[Zhang, Jian-Ming] College of Computer and Communication, Hunan University, Changsha 410082, China;[Zhang, Jian-Ming] Department of Computer Science, Hunan City University, Yiyang 413049, China
摘要:
Fingerprint segmentation is an important step in fingerprint recognition and is usually aimed to identify non-ridge regions and unrecoverable low quality ridge regions and exclude them as background so as to reduce the time expenditure of image processing and avoid detecting false features. In high and in low quality ridge regions, often are some remaining ridges which are the afterimages of the previously scanned finger and are expected to be excluded from the foreground. However, existing segmentation methods generally do not take the case into consideration, and often, the remaining ridge regions are falsely classified as foreground by segmentation algorithm with spurious features produced erroneously including unrecoverable regions as foreground. This paper proposes two steps for fingerprint segmentation aimed at removing the remaining ridge region from the foreground. The non-ridge regions and unrecoverable low quality ridge regions are removed as background in the first step, and then the foreground produced by the first step is further analyzed for possible remove of the remaining ridge region. The proposed method proved effective in avoiding detecting false ridges and in improving minutiae detection.
摘要:
Fingerprint segmentation is usually to identify non-ridge regions and unrecoverable low quality ridge regions and exclude them as background so as to reduce the time of image processing and avoid detecting false features. In ridge regions, including high quality and low quality, there are often some remaining ridges which are the afterimage of the previously scanned finger and are expected to be excluded from the foreground. However, existing segmentation methods do not take the case into consideration, and often, the remaining ridge regions are falsely taken as foreground. This paper proposes two steps for fingerprint segmentation aiming to exclude the remaining ridge region from the foreground. The non-ridge regions and unrecoverable low quality ridge regions are removed as background in the first step, and then the foreground produced by the first step is further analyzed so as to remove the remaining ridge region. The proposed method turns out effective in avoiding detecting false ridges and in improving minutiae detection.
作者机构:
[徐志峰] Physics and Information Sciences College, Hunan Normal University, Changsha 410081, China;[徐志峰; 周光辉] Department of Physics, Hunan City College, Yiyang 413000, China
期刊:
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION B-BEAM INTERACTIONS WITH MATERIALS AND ATOMS,2004年222(1-2):44-52 ISSN:0168-583X
通讯作者:
Fan, S
作者机构:
Inst Atom Energy, China Nucl Data Ctr, Beijing 102413, Peoples R China.;Shanghai Univ, Shanghai Appl Radiat Inst, Shanghai 201800, Peoples R China.;Hunan City Univ, Dept Phys, Yiyang 413000, Peoples R China.;NW Univ Xian, Dept Phys, Xian 710006, Peoples R China.;[Fan, S] Inst Atom Energy, China Nucl Data Ctr, POB 275,41, Beijing 102413, Peoples R China.
通讯机构:
[Fan, S] I;Inst Atom Energy, China Nucl Data Ctr, POB 275,41, Beijing 102413, Peoples R China.