Frequent Pattern Discovery from Gene Expression Data

Data mining is usually mentioned in the broader setting of knowledge discovery in databases (KDD), and is viewed as a single step in a larger process called the KDD process. Frequent Pattern Mining (FPM) plays a vital role especially in the real time data mining research because of its wide applicability in industry areas, including process control, production data mining and many other important real time data mining tasks. Creating an association between variables is always of interest in genomic studies. FPM has been applied successfully for discovering interesting association patterns between various genes. Motivated by several heuristics to reduce the number of database scans in the context of frequent pattern mining, the concept of fuzziness on the original gene expression data set was provided in order to discretize the value in terms of under expressed and over expressed genes. Certain soft computing approaches were used to optimize the findings and generate frequent patterns based on the fuzzy frequent pattern mining algorithms. It was observed that fuzzy set helped a lot to find better results in terms of number of frequent patterns.

Autorentext

Shruti MishraAssistant Professor, Department of Computer Science & Engineering,Institute of Technical Education and Research,Siksha O Anusandhan Deemed to be University.Dr. Debahuti MishraAssociate Professor, Department of Computer Applications,ITER, SOA Deemed to be UniversitySandeep K. SatapathyAssistant Professor, Department of CSEITER