Yang Ke-wei

Notice of Retraction Study on Method of Word Segmentation in Feature Selection in Chinese Text Categorization

Since the automatic word segmentation of Chinese text will bring the lack of information, method of word segmentation according to lexical chunk as segmentation unit are proposed. Use traditional segmentation method segment Chinese text based calculate mutual information between two lexical entries and adjacent frequency of two or more lexical entries, according to this calculated value judge and sign the lexical chunk by relevant words. The experimentation shows that after the word combination, the lexical chunk bear much more feature information which shares a better effect of the process. It also has proved the effect of feature selection in Chinese text categorization and enhanced the capability of text classification.

Research on capability evaluation modeling of armored system-of-systems

Representing the capability of armored system-of-systems (ASoS) and modeling the evaluation process standardly are the foundations for capability evaluation of ASoS and also the difficulty in ASoS demonstration. Based on the various generation principles of ASoS capability, six capability models are analyzed, including function capability model, mission capability Portfolio model, fire unit capability model, process capability model, mixed capability model and other capability model. Then based on the proposed capability models, a capability evaluation framework based on the executable model is given to guide capability evaluation of ASoS, which helps to deepen the understanding of the capability evaluation problem of ASoS.

Comprehensive Analysis Method on the 2-mode Network of Expert Consultation

Expert consultation is a group decision making method often used in the argumentation. This paper proposes a 2-mode network for the expert consultation, and gives a procedure to study the network in static and dynamic way. The procedure includes a series of analytical methods such as correspondence analysis, cluster analysis, multi dimensional scaling, degree analysis and centrality analysis. Case study proves that those methods can help the chairman know the attention on each opinion, the contribution of each expert and the correspondence relationship between opinions and experts in a quantitative and visualized way, which can help us find the evolution of the opinion groups and catch the innovative ideas.