Speeding up frequent itemset mining process on XML data using graphic processor

摘要

XML technology is being extensively used for data exchange between applications on web and hence mining these documents becomes an important area of research. Since XML is extensively used in web, efficient methods are required for knowledge discovery from the enormous collections of XML documents. Also some advanced tools and technologies are required to effectively handle this scalable data. A methodology is proposed to deal with handling such scalable XML data with the help of high performance and low cost computing, the GPU. This paper aims to parallelize the pre-processing stage of deserialization and sorting to make the dataset favorable for mining.