%0 Journal Article
%T Efficient Frequent Pattern Mining Techniques of Semi Structured data: a Survey
%A Leena A Deshpande
%A R.S. Prasad
%J International Journal of Advanced Computer Research
%D 2013
%I Association of Computer Communication Education for National Triumph (ACCENT)
%X Semi-structured data are a huge amount of complexand heterogeneous data sets.Such models capturedata that are not intentionally structured, but arestructured heterogeneously. These databasesevolve so quickly like run time report generated byERPs, World-Wide Web with its HTML pages, textfiles, bibliographies, various logs generated etc.These huge and varied becomedifficultto retrieverelevant information User is often interestedinintegrating various formats (like in biomedical datatext, image or structured) that are generally realizedas files, and also wants to access them in anintegrated fashion.Users not only query the data tofind a particular piece ofinformation, but he is alsokeen in knowing better understanding of the query.Because of this variety, semi-structured DBs do notcome with a conceptual schema. To make thesedatabases more accessible to users a rich conceptualmodel is needed. Traditional retrieving techniquesare not directly applied on these databases.Unfortunately the tools and methodologies used forRDBMS do not give efficient results and so fail tobridge the gap. Henceefficient andscalablemethods for mining the semi-structured data isneeded, via discovering rule or patterns from thehuge semi-structured databases. These databasesare modelled by trees and graphs.
%K Semi structured database
%K XML
%K Association rule
%K Classif ication
%K rule based association
%U http://www.theaccents.org/ijacr/papers/conference/icacc2013/31.pdf