Lianhong Ding

Beijing Wuzi University, Peping, Beijing, China

Are you Lianhong Ding?

Claim your profile

Publications (14)0 Total impact

  • Lianhong Ding, Peng Shi
    [Show abstract] [Hide abstract]
    ABSTRACT: Conception of centrality comes from structural sociology. It has become a fundamental concept in network analysis since its introduction. Bulletin board system is a popular manner for human communication. Right moderators influence the running efficiency of the BBS. It's very prevalent, for bulletin board system of university, to appoint moderator for each board manually. Moderators appointed may not be good at their work. This paper introduces centrality measures into the appointment of moderator for bulletin board systems. To fulfill above aim, a network named BBS network is built. Each node denotes a user for the bulletin board system. Several methods are used to compute centrality value of each node in the BBS network. The nodes with highest centrality may be the right users to play the moderator roles. The computing results can also be used to judge if current moderators work well.
    01/2011;
  • Lianhong Ding, Peng Shi
    [Show abstract] [Hide abstract]
    ABSTRACT: A social network is a map of the relationships between individuals where we can observe their social activities. Conception of centrality comes from structural sociology. It is a fundamental method in the social network analysis. Centrality is a fundamental concept in network analysis. It usually is used to identify the "most important" ones in a social network. Bulletin board system is an important way for human communication. It is important to appoint appropriate moderator for each board in the bulletin board system. It'll influence the running efficiency of the BBS from several aspects. This paper introduces centrality measures into the appointment of moderator for bulletin board systems. To fulfill above aim, a social network named BBS network is built for each board in a bulletin board system. Each node denotes a user for the bulletin board system. Several methods are used to compute centrality value of each node in the BBS network. The nodes with highest centrality may be the right users to play the moderator roles. The computing results can also be used to judge if current moderators work well.
    01/2011;
  • Lianhong Ding, Peng Shi, Bingwu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Information, objects and people are three major macro elements in the human society. Their inner relations can be reflected by the Internet, the Internet of Things and social network, respectively. Normally, these three networks do not work together. This paper proposes a platform to cluster the Internet, the Internet of Things and social network together. The clustering will promote the developing of the Internet of Things and social network. With the clustered platform, most macro elements in human society can be tracked and summarized. Thus it is easy for scientists to analyze the behaviors of objects and people as data. The future applications of the clustered platform are also discussed in this paper.
    Knowledge Acquisition and Modeling (KAM), 2010 3rd International Symposium on; 11/2010
  • Lianhong Ding, Bingwu Liu, Qi Tao
    [Show abstract] [Hide abstract]
    ABSTRACT: Personalized recommendation in an e-learning system can actively introduce useful learning resources for learners. It is a “push” mechanism in contrast to the “pull” way like Web searching. At the same time it is also a very efficient way especially when users can not describe their needs exactly. This paper put forward an approach to recommend right learning resources for users with different learning needs by hybrid filtering method. Learning resources are organized by learning topics through text analysis. Users with similar learning interests are found out to form different common interest groups by user behavior tracing and recording. Then, two-level user profiles are built based on common interest group detection and text analysis. At last, learning resources are introduced to users according to user profiles by collaborative filtering and content-based filtering respectively. A time factor is also introduced into the building of user profiles, which makes user profiles adapt to user’s interest shifting.
    Education Technology and Computer Science, International Workshop on. 03/2010; 3:177-180.
  • Lianhong Ding, Peng Shi
    [Show abstract] [Hide abstract]
    ABSTRACT: Introducing e-learning can obviously improve the learning efficiency. How to introduce profit contents to users is the key issue. An available way is to introduce the same contents to the users with similar interest and study ability. Community detection can divide users into several subgroups with similar interest and study ability. An e-learning system can determine the introducing contents for users based on community structure. This paper proposes an introducing e-learning approach based on community detection. With this approach, users belong to a same community can share the proper learning contents easily. E-learning system will get higher efficiency by introducing right learning contents to right users at right time.
    Education Technology and Computer Science, 2009. ETCS '09. First International Workshop on; 04/2009
  • Lianhong Ding, Peng Shi, Bingwu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Appropriate locations for distribution centers benefit both distribution centers and their clients. Many location models of distribution centers base on the assumption that the companies that the distribution center serves are known. Few literatures touch on the issue that if the right companies have been found as the service objects for the distribution center. This paper believes the better way is to find the right service clients first, and then, build location model based on it. And this paper focuses on the identification of the service clients and other decisions can be made based on the identification result. In order to find the right clients for distribution centers a network which can reflects the transport relationships among companies is created first. Then the companies that should share logistics service are identified through community detection method. The companies belonging to a same community of the network may become the right service clients for a distribution center.
    Knowledge Acquisition and Modeling Workshop, 2008. KAM Workshop 2008. IEEE International Symposium on; 01/2009
  • Peng Shi, Changjun Hu, Lianhong Ding
    [Show abstract] [Hide abstract]
    ABSTRACT: Material service safety is very important for public security. Researchers and engineers have devoted themselves to establishing models for material service behavior. Utilizing these models to predict material service behavior and assess service safety is an efficient and idealized way. However, material service behavior is quite complicated. Only simple material behavior models have been established until now, which can't satisfy the complicated demands for service safety assessment. This paper proposes a dynamic model combination method to construct complex model using multiple simple models. Different combined models can describe varied material service behaviors in different service environments. A use case is also proposed to show the obvious benefits from this method for material service safety assessment.
    Information Science and Engineering, 2008. ISISE '08. International Symposium on; 01/2009
  • Peng Shi, Lianhong Ding, Bingwu Liu
    [Show abstract] [Hide abstract]
    ABSTRACT: Web page is the main contents on the World Wide Web. Similarity of Web pages is very helpful for Web content analysis. Text similarity, usually called similarity computation, has been investigated for decades in artificial intelligence area. Some similarity computation methods have been used to compare Web pages. However, text based similarity computation methods are incompetent for Web page comparing, because Web page consists of not only text but also multimedia contents, such as image, audio, video and so on. This paper proposes a new approach to evaluate the similarity of Web pages considering all the contents on them. It can make Web page similarity computation exactly and bring benefits for Web analysis.
    Knowledge Acquisition and Modeling Workshop, 2008. KAM Workshop 2008. IEEE International Symposium on; 01/2009
  • Lianhong Ding, Qi Tao, Peng Shi
    [Show abstract] [Hide abstract]
    ABSTRACT: Personalized e-learning is a hot research topic. It can obviously improve the learning efficiency. A perfect e-learning system can recommend right learning content for right learner at right time. In order to find profit contents for different users, a network which describes the relationships among learners is constructed first. Then, the learners owning similar learning interests are found by community detection. At last, right contents are recommended to learners by the collaborative filtering method. This paper also proposes a method to introduce one or several persons to help a learner when he/she meets difficulty by link analysis. With our methods, users belonging to one community can share the proper learning contents and a learner can get valid help as well. E-learning systems can further improve their efficiencies through these methods.
    Computational Intelligence and Natural Computing, International Conference on. 01/2009; 1:125-128.
  • Peng Shi, Changjun Hu, Yuemin Ni, Lianhong Ding
    [Show abstract] [Hide abstract]
    ABSTRACT: Web topic indicates the topic from Web pages on the Internet. Traditional methods to describe a Web topic come from text mining. However, Web page consists of not only text but also multimedia contents, such as image, audio, video and so on. The multimedia contents of Web topic can't be denoted by text-based representation methods. This paper proposes a new approach, named multi-layer representation model, to represent Web topic with all the contents that Web page contains. The model is composed of several semantic layers, including text layer, image layer, audio layer, video layer and other extensible layers. Web resources are located on different layers according to their types. Their relationships within one layer and between layers are represented by inner-layer links and cross-layer links respectively. This method can exactly describe Web topic with richer resource semantics and bring benefits for the similarity computing between Web topics.
    PACIIA 2008, Volume 2, 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application, 19-20 December 2008, Wuhan, China; 01/2008
  • Lianhong Ding, Peng Shi
    [Show abstract] [Hide abstract]
    ABSTRACT: Order picking is the most labour-intensive and costly activity for almost every warehouse. In general, travel time of pickers during the order picking process is the dominant component of the total order picking time. This paper proposes an approach to decrease travel time by sharply cut down the step time in each picking operation. The reduction of step time is fulfilled by putting the goods nearby, which appear in a single order with higher probability. Social network and community detection are introduced into the discovering of the items which may be picked together in one picking operation. This method can bring higher efficiency and lower operation cost for distribution centers, and consequently for the whole supply chain.
    01/2008;
  • Peng Shi, Lianhong Ding
    [Show abstract] [Hide abstract]
    ABSTRACT: Service safety appraisement of engineering materials is important for public security. This paper describes a data sharing platform for safety appraisement based on material scientific data. The data sharing platform consists of three layers: data collection layer, data organization layer and data application layer. The data collection layer integrates the methods, standards and data, including physical and simulation experiment data, material basic properties and service environment parameters. The data organization layer constructs the relationships among data objects and properties through uniform data models, based on ontology and the object-oriented technology. The data application layer satisfies the demands of research and application such as intelligent materials selection, service life prediction and maintenance strategy making. Researchers can attain new rules of materials service safety and engineers can also make optimal decisions based on the data sharing platform. An application case is presented to show the intelligent procedure of materials selection based on the platform with materials data.
    Proceedings of the 9th International Conference for Young Computer Scientists, ICYCS 2008, Zhang Jia Jie, Hunan, China, November 18-21, 2008; 01/2008
  • Peng Shi, Changjun Hu, Ruopeng Zhao, Lianhong Ding
    [Show abstract] [Hide abstract]
    ABSTRACT: Web topic is the theme indicated by Web pages. Some methods have been proposed to represent Web topic based on text mining. However, these methods can’t denote multimedia contents on Web page, such as images, audios, videos and so on. Consequently, text-based methods can't represent Web topic exactly because most Web pages consist of many multimedia contents. This paper proposes a new approach, named multi-layer semantic model, to represent Web topic. Using this model, the semantics of varied contents contained by Web page can be involved. The model is composed of several semantic layers, including text layer, image layer, audio layer, video layer and other extensible layers. Web resources are located on different layers according to their types. Their relationships within one layer and between layers are represented by inner-layer links and cross-layer links respectively. This method can also bring benefits for the similarity computing between Web topics.
    Information Science and Engieering, International Symposium on. 01/2008; 2:244-247.
  • Lianhong Ding, Qi Tao
    [Show abstract] [Hide abstract]
    ABSTRACT: Materials service safety is very important for public security. Materials service cases study is an efficient way for researchers and engineers to assess current and future service safety of both the case itself and other similar service cases. Generally, material service cases are stored in relational database. Service cases are retrieved based on keywords with little semantics. Case study is manually executed by domain experts according to retrieved results, which may include some unrelated cases. It's a burdensome and time-consuming task. This paper proposes an ontology based case representation and retrieval method to improve the efficiency and accuracy of materials service case study. OWL and RDF is adopted to represent service cases. Cases are retrieved by SPARQL. Use cases are proposed to show the obvious benefits from this method for materials service case study.