دانلود رایگان مقاله انگلیسی شبکه توزیع شده معنایی قابل قیاس برای مدیریت دانش در سیستم فیزیکی سایبری - الزویر 2018

Abstract

The remarkable growth of emerging technologies and computing paradigms in cyberspace and the cyber physical systems generate a huge mass of data sources. These different autonomous and heterogeneous data sources can contain complementary or semantically equivalent information stored under different formats that vary from structured, semi structured, to unstructured. These heterogeneities influence on data semantics and meaning. Therefore, knowledge management became more and more difficult and sometimes fruitless. In this paper, we propose a new scalable model, named Distributed Semantic Network (DSN), for heterogeneous data representation and can extract more semantic information from different data sources. We use the prior knowledge of WordNet and Wikipedia to scale out DSN horizontally and vertically. Furthermore, we proposed a MapReduce based framework to construct the knowledge base more effectively in Parallel and Distributed Computing (PDC). The experimental results show that DSN can better model the semantic information in the text. It can extract a larger amount of information from the text with a higher precision, achieving 34% increase in quantity and 15% promotion on precision than the best-performing alternative method on same datasets. On the three datasets, our proposed PDC framework shorten the process time by 5.8-11.5 times.

7. Conclusion

We presented scalable DSN for express distributed semantics implied in data and semantic information extraction. Based on the extracted information, a knowledge parallel extraction framework with MapReduce for knowledge base construction from heterogeneous data was proposed. It first deals with heterogeneous textual data by MOSP to extract the semantic information, and then uses the extracted semantic information and existing semantic database (WordNet and Wikipedia) to construct the DSN and expose implicit semantic information by horizontal expansion and vertical expansion. Finally, all extracted and fused semantic information was used to construct the knowledge base based on MapReduce PDC framework. Experimental results show that our method outperforms the three state-of-the-art systems both on precision and the amount of correct knowledge. The PDC framework can greatly improve the efficiency of knowledge base construction.

The next step in our research is to adjust the PDC framework for performance improvement. There is also some target relational information not directly resolved in MOSP, which requires our system not only to improve the relevant rules for semantic information but also to cover semantic information on the non-standard statements as much as possible.