摘要:
Finding fastest driving routes is significant for the intelligent transportation system. While predicting the online traffic conditions of road segments entails a variety of challenges, it contributes much to travel time prediction accuracy. In this paper, we propose O-Sense, an innovative online-traffic-prediction based route finding mechanism, which organically utilizes large scale taxi GPS traces and environmental information. O-Sense firstly exploits a deep learning approach to process spatial and temporal taxi GPS traces shown in dynamic patterns. Meanwhile, we model the traffic flow state for a given road segment using a linear-chain conditional random field (CRF), a technique that well forecasts the temporal transformation if provided with further supplementary environmental resources. O-Sense then fuses previously obtained outputs with a dynamic weighted classifier and generates a better traffic condition vector for each road segment at different prediction time. Finally, we perform online route computing to find the fastest path connecting consecutive road segments in the route based on the vectors. Experimental results show that O-Sense can estimate the travel time for driving routes more accurately.
期刊:
Wireless Personal Communications,2015年82(1):283-292 ISSN:0929-6212
通讯作者:
Wu, Shan
作者机构:
[Hsu, Ching-Fang] Cent China Normal Univ, Comp Sch, Wuhan 430079, Peoples R China.;[Wu, Shan] Wuhan Technol & Business Univ, Wuhan 430065, Peoples R China.;[Harn, Lein] Univ Missouri, Dept Comp Sci Elect Engn, Kansas City, MO 64110 USA.
通讯机构:
[Wu, Shan] W;Wuhan Technol & Business Univ, Wuhan 430065, Peoples R China.
摘要:
With the rapid development of various group-oriented services, multipartite group communications occur frequently in a single network, where a multipartite access structure is defined to be a collection of the subsets of users who may come from different parts of the network such that only users in an authorized subset of users can use their shares to build up a group key for a secure group communication. Most existing group key establishment schemes based on a secret sharing target on building up a group key for a threshold access structure, and need to compute a $$t$$t-degree interpolating polynomial in order to encrypt and decrypt the secret group key. This approach is not suitable and inefficient in terms of computational complexity for multipartite group environments which need to realize the multipartite access structures. In 1991, Brickell et al. proved that an ideal access structure is induced by a matroid and furthermore, an access structure is ideal if it is induced by a representable matroid. In this paper, we study the characterization of representable matroids. By using the connection between ideal secret sharing and matroids and, in particular, the recent results on ideal multipartite access structures and the connection between multipartite matroids and discrete polymatroids, we introduce a new concept on $$R$$R-tuple, which is determined by the rank function of the associated discrete polymatroid. Using this new concept, we come up a new and simple sufficient condition for a multipartite matroid to be representable (in fact, every matroid and every access structure are multipartite). In other words, we have developed a sufficient condition for an access structure to be ideal. These new results can be applied to establish multipartite group keys efficiently in secure group communications. With the rapid development of various group-oriented services, multipartite group communications occur frequently in a single network, where a multipartite access structure is defined to be a collection of the subsets of users who may come from different parts of the network such that only users in an authorized subset of users can use their shares to build up a group key for a secure group communication. Most existing group key establishment schemes based on a secret sharing target on building up a group key for a threshold access structure, and need to compute a $$t$$t-degree interpolating polynomial in order to encrypt and decrypt the secret group key. This approach is not suitable and inefficient in terms of computational complexity for multipartite group environments which need to realize the multipartite access structures. In 1991, Brickell et al. proved that an ideal access structure is induced by a matroid and furthermore, an access structure is ideal if it is induced by a representable matroid. In this paper, we study the characterization of representable matroids. By using the connection between ideal secret sharing and matroids and, in particular, the recent results on ideal multipartite access structures and the connection between multipartite matroids and discrete polymatroids, we introduce a new concept on $$R$$R-tuple, which is determined by the rank function of the associated discrete polymatroid. Using this new concept, we come up a new and simple sufficient condition for a multipartite matroid to be representable (in fact, every matroid and every access structure are multipartite). In other words, we have developed a sufficient condition for an access structure to be ideal. These new results can be applied to establish multipartite group keys efficiently in secure group communications.
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Jin, Shu-Wei] Ecole Normale Super, Dept Phys, F-75231 Paris 5, France.
通讯机构:
[Jin, Cong] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
作者机构:
[崔建群; 马亮; 黄枫] School of Computer, Central China Normal University, Wuhan;430079, China;[Shan, Zhiguang] Informatization Research Department, State Information Center, Beijing;100045, China;[崔建群; 马亮; 黄枫] 430079, China
摘要:
Protein-protein interaction plays an important role in understanding biological processes. In order to resolve the parsing error resulted from modal verb phrases and the noise interference brought by appositive dependency, an improved tree kernel-based PPI extraction method is proposed in this paper. Both modal verbs and appositive dependency features are considered to define some relevant processing rules which can effectively optimize and expand the shortest dependency path between two proteins in the new method. On the basis of these rules, the effective optimization and expanding path is used to direct the cutting of constituent parse tree, which makes the constituent parse tree for protein-protein interaction extraction more precise and concise. The experimental results show that the new method achieves better results on five commonly used corpora.
期刊:
Journal of Communications,2015年10(7):503-511 ISSN:1796-2021
通讯作者:
Liu, Yuhua
作者机构:
[Hu, Fang; Liu, Yuhua] Schoolof Computer Science, Central China Normal University, Wuhan, China;[Hu, Fang] College of Information Engineering, Hubei University of Chinese Medicine, Wuhan, China
通讯机构:
Schoolof Computer Science, Central China Normal University, Wuhan, China
关键词:
Community detection;Density;Infomap-simulated annealing algorithm;Modularity;Simulation test
期刊:
Journal of Algorithms & Computational Technology,2015年9(4):427-448 ISSN:1748-3018
通讯作者:
Liu, Yuhua(yhliu@mail.ccnu.edu.cn)
作者机构:
[Hu, Fang; Liu, Yuhua; Jin, Jianzhi] School of Computer Science, Central China Normal University, Wuhan, China;[Hu, Fang] College of Information Engineering, Hubei University of Chinese Medicine, Wuhan, China
通讯机构:
[Fang Hu; Yuhua Liu*] S;School of Computer Science, Central China Normal University, Wuhan, 430079, China<&wdkj&>College of Information Engineering, Hubei University of Chinese Medicine, Wuhan 430065, China<&wdkj&>School of Computer Science, Central China Normal University, Wuhan, 430079, China
关键词:
Complex network;Important node;Locally linear embedding;Multi-indicator evaluation
摘要:
Identification of important nodes is an emerging hot topic in complex networks over the last few years. Various measures have been proposed to characterize the importance of nodes in complex networks, such as the degree, betweenness, closeness, etc. At present, most algorithms of important node evaluation are based on the single-indicator, which can't reflect the whole condition of the complex network. Therefore, in this paper, after choosing multiple indicators from degree centrality, closeness centrality, eigenvector centrality, information centrality, density/clustering coefficient, mutual-information centrality, etc., and a new multi-indicator evaluation algorithm based on Locally Linear Embedding (LLE) for identifying important nodes in complex network is proposed. This proposed algorithm is compared with some single-indicator algorithms and other mainstream multi-indicator algorithms based on real-world networks. Through comprehensive analysis, the experimental results show that the proposed method performs quite well in evaluating the importance of nodes, and it is rational, effective, integral and accurate.
期刊:
International Journal of Computing Science and Mathematics,2015年6(2):129-138 ISSN:1752-5055
通讯作者:
Dong, Wenyong(dwy@whu.edu.cn)
作者机构:
[Yang Yi; Xianjun Shen] School of Computer, Central China Normal University, Wuhan Hubei, China;[Fan Chen] Department of Computer Science, Hubei Engineering Institute, Huangshi, Hubei, China;[Junyan Li] Department of Computer Science, Austin College, TX, United States;[Shuaiyu Guo] School of Mathematics and Statistics, Beijing Institute of Technology, Beijing, China;[Wenyong Dong] School of Computer, Wuhan University, Wuhan Hubei, China
通讯机构:
School of Computer, Wuhan University, Wuhan Hubei, China
摘要:
For BP neural network has some defects such as slow convergence rate, relatively flat error surface, and easily getting into local minimum. In this paper, it proposes a modified particle swarm optimisation algorithm based on the principle of free entropy minimisation (PSO-FEM), which is used to optimise the BP neural network for face detection. By drawing on the concept of the entropy increase in statistical mechanics, we view the particle swarm as a closed particle system with freedom movement in the solution space, correspond the energy minimisation of the system to the minimum value the particle swarm optimisation algorithm converges to, and correspond the system entropy increase process to the diversified process that the swarm maintains. Simulation results demonstrate that the PSO-FEM algorithm not only obtains ideal recognition results with multiple face image detection in complex background but also has high recognition correctness.
期刊:
Signal Processing,2015年109(C):172-181 ISSN:0165-1684
通讯作者:
Jin, Cong
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Jin, Shu-Wei] Ecole Normale Super, Dept Phys, F-75231 Paris 5, France.
通讯机构:
[Jin, Cong] C;Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.
摘要:
Automatic image annotation (AIA) is a task of assigning one or more semantic concepts to a given image and a promising way to achieve more effective image retrieval and analysis. It is a typical classification problem. Due to the semantic gap between low-level visual features and high-level image semantic, the performances of many existing image annotation algorithms are not satisfactory. This paper presents a novel AIA scheme based on improved quantum particle swarm optimization (IQPSO) algorithm for visual features selection (VFS) and an ensemble stratagem based on boosting technique to improve performance of image annotation approach. To maintain the population diversity, the measure method of population diversity and improvement operation are proposed. To achieve better performance of AIA scheme, the measure of population diversity is as a control condition of VFS process. The classification result of an ensemble classifier is as the final annotation result rather than individual classifier. The experimental results confirm that the proposed AIA scheme is very effectiveness. When using proposed AIA scheme over three image datasets respectively, the annotation results are satisfactory.
期刊:
WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web,2015年:649-654
通讯作者:
Ma, Changlin
作者机构:
[Ma, Changlin; Wang, Meng] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Chen, Xuewen] Wayne State Univ, Dept Comp Sci, Detroit, MI 48202 USA.
通讯机构:
[Ma, Changlin] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
会议名称:
24th International Conference on World Wide Web (WWW)
会议时间:
MAY 18-22, 2015
会议地点:
Florence, ITALY
会议主办单位:
[Ma, Changlin;Wang, Meng] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Chen, Xuewen] Wayne State Univ, Dept Comp Sci, Detroit, MI 48202 USA.
关键词:
LDA;Topic and sentiment unification;Maximum entropy;Fine-grained opinion mining
摘要:
Opinion mining is an important research topic in data mining. Many current methods are coarse-grained, which are practically problemic due to insufficient feedback information and limited reference values. To address these problems, a novel topic and sentiment unification maximum entropy LDA model is proposed in this paper for fine-grained opinion mining of online reviews. In this model, a maximum entropy component is first added to the traditional LDA model to distinguish background words, aspect words and opinion words and further realize both the local and global extraction of these words. A sentiment layer is then inserted between a topic layer and a word layer to extend the proposed model to four layers. Sentiment polarity analysis is done based on the extraction of aspect words and opinion words to simultaneously acquire the sentiment polarity of the whole review and each topic, which leads to, fine-grained topic-sentiment abstract. Experimental results demonstrate the validity of the proposed model and theory.
期刊:
Lecture Notes in Computer Science,2015年9403:336-347 ISSN:0302-9743
通讯作者:
Hu, Po
作者机构:
[Hu, Po; Zhang, Yong] Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.;[He, Jiacong] Medallia Inc, Palo Alto, CA USA.
通讯机构:
[Hu, Po] C;Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.
会议名称:
8th International Conference on Knowledge Science, Engineering and Management (KSEM)
会议时间:
OCT 28-30, 2015
会议地点:
SW Univ, Fac Comp & Informat Sci, Chongqing, PEOPLES R CHINA
会议主办单位:
SW Univ, Fac Comp & Informat Sci
会议论文集名称:
Lecture Notes in Artificial Intelligence
关键词:
Query-focused multi-document summarization;Manifold ranking;Affinity graph construction
摘要:
Manifold ranking is one of the most competitive approaches for query-focused multi-document summarization. Despite its success for this task, it usually constructs a sentence affinity graph first based on inter-sentence content similarity, and then perform manifold ranking on the graph to score each sentence with the assumption that all the sentences live on a single manifold. Actually, for a document set to be summarized, the distribution of the sentences might form different, but related manifolds. This paper aims to generalize the basic manifold-ranking based approach to the more generic setting by introducing a novel affinity graph to estimate the similarity between sentences, which leverages both the local geometric structures and the contents of sentences jointly. Preliminary experimental results on the DUC datasets demonstrate the good effectiveness of the proposed approach.
作者机构:
[He, Tingting; Tu, Xinhui; Zhou, Guangyou; Zhou, Yin; Guo, Xiyue] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Zhou, Guangyou] Cent China Normal Univ, Sch Comp, 152 Luoyu Rd, Wuhan 430079, Peoples R China.
通讯机构:
[Zhou, Guangyou] C;Cent China Normal Univ, Sch Comp, 152 Luoyu Rd, Wuhan 430079, Peoples R China.
关键词:
Sentiment classification;Cross-domain;Topical correspondence transfer
摘要:
Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). In real applications, these users generated sentiment data can span so many different domains that it is difficult to manually label training data for all of them. In this article, we develop a general solution to cross-domain sentiment classification when we do not have any labeled data in a target domain but have some labeled data in a source domain. To bridge the gap between domains, we propose a novel algorithm, called topical correspondence transfer (TCT). This is achieved by learning the domain-specific information from different domains into unified topics, with the help of shared topics across all domains. In this way, the topical correspondences behind the shared topics can be used as a bridge to reduce the gap between domains. We conduct experiments on a benchmark composed of reviews of 4 types of Amazon products. Experimental results show that our proposed TCT significantly outperforms the baseline method, and achieves an accuracy which is competitive with the state-of-the-art methods for cross-domain sentiment classification.
摘要:
A novel uplink data transmission method in electrical code division multiplexing passive optical networks is proposed, simulated and experimentally verified, in which each optical network unit (ONU) is assigned a special multi-level orthogonal code based on wavelet packet transform. Comparing with the normal bi-level orthogonal code by using Walsh code or Gold code, the proposed method can improve the bandwidth utilizations and reduce the optical beat noise. Simulation results show 31 ONUs, of which each data rate is 10 Gb/s and total rate is 310 Gb/s, can be transmitted 30 km. Three ONUs with each data at 622 Mb/s over 50-km single-mode fiber is experimentally demonstrated.
摘要:
Most traditional Wikipedia based methods use only article content information. By organizing Wikipedia articles as a graph, multi-information such as category and structure information can be utilized in our method. In this paper, we propose a novel method to do classification by using knowledge from a conceptual graph which is built from Wikipedia. First, we build a conceptual graph from Wikipedia. Each article is considered as a concept node. Titles, hyperlinks, texts and category information are used as edges to measure the relationship between those concepts. Each text is mapped to its respective set of nodes and Personalized PageRank (random walk) is then used to generate a set of most important node which can represent the text best. Finally the two sets are scored with a measure of vector similarity. We evaluate our techniques on the standard text classification dataset (20newsgroup), the results show the effectiveness of the proposed approach.
作者机构:
[张菲菲; 秦前清; 石强] State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, 430079, China;[谢伟] Computer School, Central China Normal University, Wuhan, 430079, China
通讯机构:
Computer School, Central China Normal University, Wuhan, China