摘要:
There is a growing recognition that the human microbiome - microbes living in intimate association with us - forms a vital part of our biology, and plays an important role in both health and sickness. A huge amount of data are being generated about these communities, much through metagenomics methods, which sequence DNA without directly identifying which organisms they come from. These data pose a tremendous opportunity for understanding, and a tremendous computational and theoretical challenge. In this paper, we compare several linear and nonlinear methods to explore human microbiome. There is a growing recognition that the human microbiome - microbes living in intimate association with us - forms a vital part of our biology, and plays an important role in both health and sickness. A huge amount of data are being generated about these communities, much through metagenomics methods, which sequence DNA without directly identifying which organisms they come from. These data pose a tremendous opportunity for understanding, and a tremendous computational and theoretical challenge. In this paper, we compare several linear and nonlinear methods to explore human microbiome.
期刊:
2013 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM),2013年:386-391 ISSN:2156-1125
通讯作者:
Zhao, Junmin
作者机构:
[Zhao, Junmin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[He, Tingting; Hu, Xiaohua; Li, Peng; XianjunShen; Zhang, Ming] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Informat Sci & Engn, Philadelphia, PA USA.;[Zhao, Junmin] Henan Univ Urban Construct, Inst Comp Sci & Engn, Pingdingshan, Peoples R China.
通讯机构:
[Zhao, Junmin] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)
会议时间:
DEC 18-21, 2013
会议地点:
Shanghai, PEOPLES R CHINA
会议主办单位:
[Zhao, Junmin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.^[Hu, Xiaohua;He, Tingting;Li, Peng;Zhang, Ming;XianjunShen] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.^[Hu, Xiaohua] Drexel Univ, Coll Informat Sci & Engn, Philadelphia, PA USA.^[Zhao, Junmin] Henan Univ Urban Construct, Inst Comp Sci & Engn, Pingdingshan, Peoples R China.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
关键词:
Protein Complex;Gene co-express;Biological network;Weighted PPI network
摘要:
Recent studies have shown that protein complex is composed of core and attachment proteins, and proteins inside the core are highly co-expressed. Based on this new concept, we reconstruct weighted PPI network by using gene expression data, and develop a novel protein complex identification algorithm from the angle of edge(PCIA-GeCo). First, we select the edge with high co-expressed coefficient as seed to form the preliminary cores. Then, the preliminary cores are filtered according to the weighted density of complex core to obtain the unique core. Finally, the protein complexes are generated by identifying attachment proteins for each core. A comprehensive comparison in term of F-measure, Coverage rate between our method and three other existing algorithms HUNTER, COACH and CORE has been made by comparing the predicted complexes against benchmark complexes. The evaluation results show our method PCIA-GeCo is effective; it can identify protein complexes more accurately.
作者机构:
华中师范大学计算机学院,武汉430079;国家语言资源监测与研究中心网络媒体语言分中心,武汉430079;[何婷婷; 涂新辉; 李芳; 王建文] School of Computer Science, Huazhong Normal University, Wuhan 430079, China, Network Media Branch, National Language Resources Monitoring and Research Center, Wuhan 430079, China
通讯机构:
[Tu, X.] S;School of Computer Science, Huazhong Normal University, China
期刊:
2013 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM),2013年:57-60 ISSN:2156-1125
通讯作者:
Shen, Xianjun
作者机构:
[Yang, Jincai; He, Tingting; Shen, Xianjun; Hu, Xiaohua; Zhao, Yanli; Li, Yanan] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
通讯机构:
[Shen, Xianjun] C;Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)
会议时间:
DEC 18-21, 2013
会议地点:
Shanghai, PEOPLES R CHINA
会议主办单位:
[Shen, Xianjun;Zhao, Yanli;Li, Yanan;Yang, Jincai;He, Tingting;Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.^[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
关键词:
protein complexes;best neighbor node;modularity increment;Protein-Protein Interaction network
摘要:
In order to overcome the limitations of global modularity and the deficiency of local modularity, we introduce a hybrid modularity measure LGQ (Local-Global Quantification) which adopts a suitable modularity adjustable parameter to control the balance of global detecting capability and local search capability in Protein-Protein Interaction (PPI) network. On the other hand, a new protein complex mining algorithm called BN-LGQ has been proposed, which integrates the definitions of best neighbor node and the modularity increment. And by comparison with other known algorithms, the experimental results show BN-LGQ performs a better accuracy on predicting protein complexes and has a higher match with the reference protein complexes. Moreover, it can identify protein complexes with better biological significance in PPI network.
摘要:
In this paper, the logistic regression model is applied to analyze the influence of the factors affecting the Basics of Computer Application and College English B exam results. To model the logistic regression by using the two course exam results as a target variable, the analysis results show that: grade, specialty and learning center have great impact on the Basics of Computer Application, while the grade, learning center, age, specialty and gender are all have very important implications on the College English B exam results..
摘要:
Semantic relatedness measures play important roles in many fields, such as information retrieval and Nature Language Processing. There are mainly two kinds of traditional methods to measure semantic relatedness: dictionary based and corpus based. However, with the development of information technology, web search engine is used to do this work. In this paper, we propose a method integrating page counts and web-based kernel function for measuring semantic relatedness between words. It gets a better result than using page counts and web-based kernel function alone. Experimental results show Spearman rank correlation coefficient can reach 0.63 and Correlation reach 0.724.
期刊:
Journal of Convergence Information Technology,2012年7(2):160-166 ISSN:1975-9320
通讯作者:
Li, H.(fulihua9270@yahoo.com.cn)
作者机构:
[Fu, Lihua; Liu, Zhihui] School of Mathematics and Physics, China University of Geosciences, China;[He, Tingting; Zhang, Meng; Li, Hongwei] Department of Computer Science, Central China Normal University, China
摘要:
In leaf image classification or retrieval fields, hybrid features are widely used to represent the information in various aspects by combining a number of sub-features linearly. However, the importance degrees of sub-features are often ignored by assigning the weights in an ad-hoc fashion without a solid theoretical basis. In this paper, a new type of adaptive hybrid features is proposed by using kernel trick of support vector machine (SVM), in which the weights can be adaptively selected. All weights are obtained by solving an optimization problem to maximize the discriminability of features. Experimental results of leaf image classification show that SVMs with new features significantly outperform those with traditional ones in terms of test accuracy.
作者机构:
[He Tingting] Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.;[Li Fang] Cent China Normal Univ, Engn & Res Ctr Informat Technol Educ, Wuhan 430079, Peoples R China.;[He Tingting; Li Fang] Natl Language Resources Monitoring & Res Ctr, Network Media Branch, Wuhan 430079, Peoples R China.
通讯机构:
[He Tingting] C;Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.
摘要:
This paper focuses on semantic knowledge acquisition from blogs with the proposed tagtopic model. The model extends the Latent Dirichlet Allocation (LDA) model by adding a tag layer between the document and the topic. Each document is represented by a mixture of tags; each tag is associated with a multinomial distribution over topics and each topic is associated with a multinomial distribution over words. After parameter estimation, the tags are used to describe the underlying topics. Thus the latent semantic knowledge within the topics could be represented explicitly. The tags are treated as concepts, and the top-TV words from the top topics are selected as related words of the concepts. Then PMI-IR is employed to compute the relatedness between each tag-word pair and noisy words with low correlation removed to improve the quality of the semantic knowledge. Experiment results show that the proposed method can effectively capture semantic knowledge, especially the polyseme and synonym.
作者:
Abudoulikemu, Yimamu'aishan;Jiang, Rui;He, Ting Ting(何婷婷);Li, Fang;Luo, Chang Ri
期刊:
Journal of Convergence Information Technology,2012年7(23):76-82 ISSN:1975-9320
通讯作者:
Abudoulikemu, Y.
作者机构:
[Abudoulikemu, Yimamu'aishan; Li, Fang; Luo, Chang Ri] National Engineering Research Center for E-learning, Wuhan, Hubei, 430079, China;[Luo, Chang Ri] College of Vocational and Continuing Education, CCNU, Wuhan, 430079, China;[He, Ting Ting] Department of Computer Science, Huazhong Normal University, Wuhan, Hubei, 430079, China;[Abudoulikemu, Yimamu'aishan; Jiang, Rui] College of Information Engineering, Urumqi Vocational University, Urumqi, Xinjiang, 830002, China
摘要:
Information retrieval Uyghur resources construction is still in the blank, based on research and analysis of existing research progress at home and abroad, this paper introduces information retrieval test platform, then it proposes design method of Uyghur web information retrieval testing collection, it analyzes details of Uyghur web information retrieval testing collection construction principles and methods, and it carries out Uyghur web information retrieval testing collection valid statistical analysis and experimental research. The experiment shows the proposed method is effective.
摘要:
The traditional information retrieval (IR) model always only use the BOW (bag-of-words)-based retrieval model or Concepts-based retrieval model. However BOW-based model ignore the rich semantic relations between the words and text, and Concept-based model always bring in the noisy concepts and loss the precision. Pseudo-relevance feedback (PRF) is a widely used method for improving retrieval effectiveness, but it is strongly dependent on the precision of initial retrieval results. In order to solve these issues, this paper proposes a new concept generator called Enrichment-ESA which is the enrichment of the Explicit Semantic Analysis (ESA) method. With the help of Enrichment-ESA, we propose a novel PRF method which combined the BOW-based retrieval model and Concept-based retrieval model together to solve shortcomings of the existing IR model in some degree. The experimental results show that our method improves over the baseline method and performs better than the common PRF method.
作者:
Zhang, Xiaodan*;Hu, Xiaohua;He, Tingting(何婷婷);Park, E. K.;Zhou, Xiaohua
期刊:
IEEE Transactions on Systems, Man, and Cybernetics: Systems,2012年42(5):1167-1182 ISSN:2168-2216
通讯作者:
Zhang, Xiaodan
作者机构:
[Hu, Xiaohua; Zhou, Xiaohua; Zhang, Xiaodan] Drexel Univ, Coll Informat Sci & Technol, Philadelphia, PA 19104 USA.;[He, Tingting; Hu, Xiaohua] Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.;[Park, E. K.] Calif State Univ Chico, Dept Comp Sci, Chico, CA 95929 USA.;[Zhang, Xiaodan] Vertex Pharmaceut Inc, Cambridge, MA 02139 USA.
通讯机构:
[Zhang, Xiaodan] V;Vertex Pharmaceut Inc, Cambridge, MA 02139 USA.
关键词:
Link-based document clustering;Markov random field (MRF);relaxation labeling (RL)
摘要:
With the fast growing number of works utilizing link information in enhancing unsupervised document clustering, it is becoming necessary to make a comparative evaluation of the impacts of different link types on document clustering. Various types of links between text documents, including explicit links such as citation links and hyperlinks, implicit links such as coauthorship and cocitation links, and similarity links such as content similarity links, convey topic similarity or topic transferring patterns, which is very useful for document clustering. In this paper, we adopt a clustering algorithm based on Markov random field and relaxation labeling, which employs both content and linkage information, to evaluate the effectiveness of the aforementioned types of links for document clustering on ten data sets. The experimental results show that linkage information is quite effective in improving content-based document clustering. Furthermore, a series of important findings regarding the impacts of different link types on document clustering is discovered through our experiments.
摘要:
In this paper, we investigate features and propose a method to identify influential users on Sina-Weibo, one of the most famous micro-blogging services in China. We first investigate features such as users' follower number distribution, relation between Weibo number and follower number and analysis of user interaction. Due to the existing methods are not very comprehensive in measuring the influence of user, we propose a new model. In which, we take the three basic actions: following, retweeting and commenting into consideration. Based on the weight and networks of them, we construct a weighted network, then employ Weighted PageRank and Hypertext Induced Topic Selection algorithm to calculate user influence. Compared with other two methods, the experiment results suggest that our model offers a new way to identify influential user, and it is more comprehensive and stable than the other two.
期刊:
2012 IEEE 2nd International Conference on Cloud Computing and Intelligent Systems (CCIS) Vols 1-3,2012年03:1501-1505 ISSN:2376-5933
通讯作者:
Hu, Rong
作者机构:
[He, Tingting; Hu, Po; Hu, Rong] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Li, Fang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
通讯机构:
[Hu, Rong] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
会议名称:
2nd IEEE International Conference on Cloud Computing and Intelligent Systems (CCIS)
会议时间:
OCT 30-NOV 01, 2012
会议地点:
Hangzhou, PEOPLES R CHINA
会议主办单位:
[Hu, Rong;He, Tingting;Hu, Po] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.^[Li, Fang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
会议论文集名称:
International Conference on Cloud Computing and Intelligence Systems
关键词:
Tag recommendation;Tag-topic model
摘要:
With the rapid increase of the social websites, most social tagging systems are allowing users to share and to label various kinds of resources with their favorite tags. However, the uncontrolled use of tags makes the resources attached with some irrelevant even noise tags. To solve the problem, this paper proposes a tag-topic model based approach to recommend tags for resources, which elicits latent topics from resources and maps new resources to these latent topics so as to recommend the most appropriate tags for the resources. The experimental results show the effectiveness of the proposed approach.