[Objective] This paper aims to construct an improved fuzzy decision tree which is based on clustering,and researches into its application in the screening of maize germplasm.[Method] A new decision tree algorithm base...[Objective] This paper aims to construct an improved fuzzy decision tree which is based on clustering,and researches into its application in the screening of maize germplasm.[Method] A new decision tree algorithm based upon clustering is adopted in this paper,which is improved against the defect that traditional decision tree algorithm fails to handle samples of no classes.Meanwhile,the improved algorithm is also applied to the screening of maize varieties.Through the indices as leaf area,plant height,dry weight,potassium（K） utilization and others,maize seeds with strong tolerance of hypokalemic are filtered out.[Result] The algorithm in the screening of maize germplasm has great applicability and good performance.[Conclusion] In the future more efforts should be made to compare improved the performance of fuzzy decision tree based upon clustering with the performance of traditional fuzzy one,and it should be applied into more realistic problems.展开更多
In this paper, an improved algorithm, named STC-I, is proposed for Chinese Web page clustering based on Chinese language characteristics, which adopts a new unit choice principle and a novel suffix tree construction p...In this paper, an improved algorithm, named STC-I, is proposed for Chinese Web page clustering based on Chinese language characteristics, which adopts a new unit choice principle and a novel suffix tree construction policy. The experimental results show that the new algorithm keeps advantages of STC, and is better than STC in precision and speed when they are used to cluster Chinese Web page. Key words clustering - suffix tree - Web mining CLC number TP 311 Foundation item: Supported by the National Information Industry Development Foundation of ChinaBiography: YANG Jian-wu (1973-), male, Ph. D, research direction: information retrieval and text mining.展开更多
The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic l...The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic load balancing is a technique for the parallel implementation of problems, which generate unpredictable workloads by migration work units from heavily loaded processor to lightly loaded processors at run time. This paper proposed an efficient load balancing method in which parallel tree computations depth first search (DFS) generates unpredictable, highly imbalance workloads and moves through different phases detectable at run time, where dynamic load balancing strategy is applicable in each phase running under the MPI(message passing interface) and Unix operating system on cluster of workstations parallel platform computing.展开更多
To address the problems that input variables should be reduced as much as possible and explain output variables fully in building neural network model of complicated system, a variable selection method based on cluste...To address the problems that input variables should be reduced as much as possible and explain output variables fully in building neural network model of complicated system, a variable selection method based on cluster (analysis) was investigated. Similarity coefficient which describes the mutual relation of variables was defined. The methods of the highest contribution rate, part replacing whole and variable replacement are put forwarded and deduced by information theory. The software of the neural network based on cluster analysis, which can provide many kinds of methods for defining variable similarity coefficient, clustering system variable and evaluating variable cluster, was developed and applied to build neural network forecast model of cement clinker quality. The results show that all the network scale, training time and prediction accuracy are perfect. The practical application demonstrates that the method of selecting variables for neural network is feasible and effective.展开更多
To better understand different users' accessing intentions, a novel clustering and supervising method based on accessing path is presented. This method divides users' interest space to express the distribution...To better understand different users' accessing intentions, a novel clustering and supervising method based on accessing path is presented. This method divides users' interest space to express the distribution of users' interests, and directly to instruct the constructing process of web pages indexing for advanced performance.展开更多
Saving energy and increasing network lifetime are significant challenges in wireless sensor networks （WSNs）. In this paper, we propose a mechanism to distribute the responsibility of cluster-heads among the wireless...Saving energy and increasing network lifetime are significant challenges in wireless sensor networks （WSNs）. In this paper, we propose a mechanism to distribute the responsibility of cluster-heads among the wireless sensor nodes in the same cluster based on the ZigBee standard, which is the latest WSN standard. ZigBee supports ad hoc on-demand vector （AODV） and cluster-tree routing protocols in its routing layer. However, none of these protocols considers the energy level of the nodes in the network establishing process or in the data routing process. The cluster-tree routing protocol supports single or multi-cluster networks. However, each single cluster in the multi-cluster network has only one node acting as a cluster head. These cluster-heads are fixed in each cluster during the network lifetime. Consequently, using these cluster-heads will cause them to die quickly, and the entire linked nodes to these cluster-heads will be disconnected from the main network. Therefore, the proposed technique to distribute the role of the cluster head among the wireless sensor nodes in the same cluster is vital to increase the lifetime of the network. Our proposed technique is better in terms of performance than the original structure of these protocols. It has increased the lifetime of the wireless sensor nodes, and increased the lifetime of the WSN by around 50% of the original network lifetime.展开更多
文摘[Objective] This paper aims to construct an improved fuzzy decision tree which is based on clustering,and researches into its application in the screening of maize germplasm.[Method] A new decision tree algorithm based upon clustering is adopted in this paper,which is improved against the defect that traditional decision tree algorithm fails to handle samples of no classes.Meanwhile,the improved algorithm is also applied to the screening of maize varieties.Through the indices as leaf area,plant height,dry weight,potassium（K） utilization and others,maize seeds with strong tolerance of hypokalemic are filtered out.[Result] The algorithm in the screening of maize germplasm has great applicability and good performance.[Conclusion] In the future more efforts should be made to compare improved the performance of fuzzy decision tree based upon clustering with the performance of traditional fuzzy one,and it should be applied into more realistic problems.
文摘In this paper, an improved algorithm, named STC-I, is proposed for Chinese Web page clustering based on Chinese language characteristics, which adopts a new unit choice principle and a novel suffix tree construction policy. The experimental results show that the new algorithm keeps advantages of STC, and is better than STC in precision and speed when they are used to cluster Chinese Web page. Key words clustering - suffix tree - Web mining CLC number TP 311 Foundation item: Supported by the National Information Industry Development Foundation of ChinaBiography: YANG Jian-wu (1973-), male, Ph. D, research direction: information retrieval and text mining.
基金Natural Science Foundation of China (No.60 173 0 3 1)
文摘The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic load balancing is a technique for the parallel implementation of problems, which generate unpredictable workloads by migration work units from heavily loaded processor to lightly loaded processors at run time. This paper proposed an efficient load balancing method in which parallel tree computations depth first search (DFS) generates unpredictable, highly imbalance workloads and moves through different phases detectable at run time, where dynamic load balancing strategy is applicable in each phase running under the MPI(message passing interface) and Unix operating system on cluster of workstations parallel platform computing.
文摘To address the problems that input variables should be reduced as much as possible and explain output variables fully in building neural network model of complicated system, a variable selection method based on cluster (analysis) was investigated. Similarity coefficient which describes the mutual relation of variables was defined. The methods of the highest contribution rate, part replacing whole and variable replacement are put forwarded and deduced by information theory. The software of the neural network based on cluster analysis, which can provide many kinds of methods for defining variable similarity coefficient, clustering system variable and evaluating variable cluster, was developed and applied to build neural network forecast model of cement clinker quality. The results show that all the network scale, training time and prediction accuracy are perfect. The practical application demonstrates that the method of selecting variables for neural network is feasible and effective.
文摘To better understand different users' accessing intentions, a novel clustering and supervising method based on accessing path is presented. This method divides users' interest space to express the distribution of users' interests, and directly to instruct the constructing process of web pages indexing for advanced performance.
文摘Saving energy and increasing network lifetime are significant challenges in wireless sensor networks （WSNs）. In this paper, we propose a mechanism to distribute the responsibility of cluster-heads among the wireless sensor nodes in the same cluster based on the ZigBee standard, which is the latest WSN standard. ZigBee supports ad hoc on-demand vector （AODV） and cluster-tree routing protocols in its routing layer. However, none of these protocols considers the energy level of the nodes in the network establishing process or in the data routing process. The cluster-tree routing protocol supports single or multi-cluster networks. However, each single cluster in the multi-cluster network has only one node acting as a cluster head. These cluster-heads are fixed in each cluster during the network lifetime. Consequently, using these cluster-heads will cause them to die quickly, and the entire linked nodes to these cluster-heads will be disconnected from the main network. Therefore, the proposed technique to distribute the role of the cluster head among the wireless sensor nodes in the same cluster is vital to increase the lifetime of the network. Our proposed technique is better in terms of performance than the original structure of these protocols. It has increased the lifetime of the wireless sensor nodes, and increased the lifetime of the WSN by around 50% of the original network lifetime.
