Cloud Computing-aided Multi-type Data Fusion with Correlation for Education

As one of the major constitutes of human society, education has been continuously producing a huge amount of data and become an important of sources of big data. Deeply mining and analyzing these big education data are of practical significance for optimizing education resource deployment and improving education quality. However, the big education data are often of diverse types and from multiple parties, which raises a big challenge for accurate and reasonable educational data fusion especially when the educational data are correlated with each other. In view of this challenge, we put forward a novel cloud computing-aided multi-type data fusion approach considering data correlation in education, to accommodate the big volume, diverse types and correlation of educational data. In concrete, the data fusion operation is mainly based on the Mahalanobis distances which can overcome the data diversity in multiple-dimensional data fusion for education. Afterwards, we provide a case study to show the concrete steps of our proposal. At last, a set of experiments are deployed to validate the feasibility of our proposal in this paper. Experimental results prove the effectiveness and efficiency of our approach in dealing with multi-type data fusion with correlation in education.