There is always a complex relationship between expert pages, while these relationships is the foundation of expert name disambiguation, traditional graph clustering method only consider the simple binary relation betw...
详细信息
There is always a complex relationship between expert pages, while these relationships is the foundation of expert name disambiguation, traditional graph clustering method only consider the simple binary relation between expert pages, but this method always ignore multi relation between pages which are more complex, In order to utilize the relationship between expert pages efficiently, a Chinese expert name disambiguation approach based on hypergraph partitioning is proposed. Firstly, extract the characteristic attribute of expert in expert page. Secondly, construct a similarity matrix between the documents on different expert pages with the utilization of the attributes features and the associated relationship of the expert pages. Finally, set two kinds of constraints which are strong connection and negative connection, construct an expert page hypergraph model and use the method based on hypergraph partitioning to achieve expert name disambiguation. Through the contrast experiment in the Chinese expert disambiguation, it turns out that the disambiguation effect is much better with the adoption of hypergraph partitioning method.
Support vector machine (SVM) is good at classifying high dimensional data. Parameter setting in the SVM training procedure, along with the feature selection, significantly influences the classification accuracy. An im...
详细信息
ISBN:
(纸本)9781450353489
Support vector machine (SVM) is good at classifying high dimensional data. Parameter setting in the SVM training procedure, along with the feature selection, significantly influences the classification accuracy. An improved algorithm based on particle swarm optimization (PSO) for feature selection and parameters optimization of SVM (GPSO-SVM) is proposed to improve the classification accuracy and select the number of features as little as possible. This method introduces crossover and mutation operator from genetic algorithm (GA), which allows the particle to carry out crossover and mutation operations after iteration and update to avoid the problem of falling into local optimum and premature maturation in
This paper proposes a dependency-enhanced pre-reordering method for Chinese-English statistical machine translation(SMT).Firstly,two kinds of dependency structure-based rules are extracted based on the source-side dep...
详细信息
ISBN:
(纸本)9781509009107
This paper proposes a dependency-enhanced pre-reordering method for Chinese-English statistical machine translation(SMT).Firstly,two kinds of dependency structure-based rules are extracted based on the source-side dependency tree and corresponding word alignments between the source-side and the target-side *** a maximum entropy classifier is used to calculate the orientation probability in terms of swap or monotone between two *** a result,a reordering rule set is *** different ways are proposed to filter out the rule ***,the dependency parsing trees of the training data,development set and the test set are traversed,and if the syntactic sub-tree structure matches the rules in the rule set,the word orders will be ***,a reordered source-side sentence is generated and then fed into an SMT system for *** conducted on NIST Chinese-English MT data sets show that the proposed method significantly improves translation performance by 0.46 BLEU compared to the baseline system.
Research on software quality has a very important strategic and practical significance to improve software quality, and promote the healthy and orderly development of software industry. This paper study and realize th...
详细信息
Research on software quality has a very important strategic and practical significance to improve software quality, and promote the healthy and orderly development of software industry. This paper study and realize the visualization of software quality, combined the change and complexity of program, based on existing research.
Research of Unmanned Aerial Vehicle (UAV) formation is a hot spot in the field of UAV applications. Based on the fountain code, an encoding communication scheme using unequal level coding Lu by Transform (ULC-LT) code...
详细信息
Research of Unmanned Aerial Vehicle (UAV) formation is a hot spot in the field of UAV applications. Based on the fountain code, an encoding communication scheme using unequal level coding Lu by Transform (ULC-LT) code and stepwise unequal error protection Lu by Transform (SUEP-LT) code are proposed for the UAV formation communication. Simulation results reveal that the proposed coding scheme can reduce the decoding bit error rate and provide strong unequal error protection property across sources.
Research on software quality has a very important strategic and practical significance to improve software quality,and promote the healthy and orderly development of software *** paper study and realize the visualizat...
详细信息
Research on software quality has a very important strategic and practical significance to improve software quality,and promote the healthy and orderly development of software *** paper study and realize the visualization of software quality,combined the change and complexity of program,based on existing research.
In this paper, a method for a sort of nonlinear system identification with stochastic time-varying parameter is investigated. This kind of nonlinear systems is referring to the system where probability density functio...
详细信息
ISBN:
(纸本)9781509009107
In this paper, a method for a sort of nonlinear system identification with stochastic time-varying parameter is investigated. This kind of nonlinear systems is referring to the system where probability density functions(PDFs) of the parameters are known. This parameter identification and states estimation method is realized based on expectation maximization(EM) algorithm and particle filter. Firstly, parameter particles are generated randomly according to the PDF of parameter. Secondly, the particle filter is employed to estimate system states corresponding to each group of the parameters, and the weight of each group parameters is calculated according to the Bayesian theory. Then the new iteration of parameter is obtained by adopting the expectation maximization algorithm. Lastly, the real parameters are obtained along with system operation. Numerical illustrations are presented to exhibit the effectiveness of the method proposed herein, and the performance of the method is examined.
Coordination shall be deemed to the result of interindividual interaction among natural gregarious animal groups. However, revealing the underlying interaction rules and decision-making strategies governing highly coo...
详细信息
Coordination shall be deemed to the result of interindividual interaction among natural gregarious animal groups. However, revealing the underlying interaction rules and decision-making strategies governing highly coordinated motion in bird flocks is still a long-standing challenge. Based on analysis of high spatial-temporal resolution GPS data of three pigeon flocks, we extract the hidden interaction principle by using a newly emerging machine learning method, namely the sparse Bayesian learning. It is observed that the interaction probability has an inflection point at pairwise distance of 3–4 m closer than the average maximum interindividual distance, after which it decays strictly with rising pairwise metric distances. Significantly, the density of spatial neighbor distribution is strongly anisotropic, with an evident lack of interactions along individual velocity. Thus, it is found that in small-sized bird flocks, individuals reciprocally cooperate with a variational number of neighbors in metric space and tend to interact with closer time-varying neighbors, rather than interacting with a fixed number of topological ones. Finally, extensive numerical investigation is conducted to verify both the revealed interaction and decision-making principle during circular flights of pigeon flocks.
Aiming to the feature of the modern stage scenery, combined with 3DGANs technology, we make research into the creation of creative stage scenes to rapidly display problem scene design, reduce the cost of stage design ...
详细信息
Network structure image, such as retinal blood vessels, has many important applications in medicine, biometric identification and other fields. The traditional image segmentation methods for network structure images u...
详细信息
Network structure image, such as retinal blood vessels, has many important applications in medicine, biometric identification and other fields. The traditional image segmentation methods for network structure images usually face the challenge that the region of interest (ROI) is broken. To tackle this challenge, this paper presents a mechanism of random walk walker movement based on the central gravity of ROI. The proposed approach exploits the gravity of the seed point in the walker's visual field, and the continuity of the ant movement path, to segment the network structure region without broken. Experimental results are presented to show the superior performance of the proposed approach against the conventional image segmentation approaches.
暂无评论