Cancer Detection using Frequency Pattern Ant Colony Optimization

Over the past few decades, to computerized diagnostic tools, intended to aid expert in making sense out of the welter of data. Due to improvements in biometric instrumentation and automation, it is easy to collect a lot of experimental data in molecular biology. It is extremely important for Analysis of such data as it leads to knowledge discovery that can be validated by experiments. Several machine learning and data mining techniques are presently applied for identifying cancer using gene expression data. This paper proposes that consecutive application of two algorithms will result in finding the gene causing cancer. Using association rule mining and swarm intelligence will result in finding an accurate gene which is responsible for causing cancer. In this paper we present a system for diagnosis of cancer using FP (frequent pattern mining) growth algorithm. Ant colony optimization to predict the possibility of cancer .Ant colony algorithm is employed as evolutionary algorithm to optimize the obtained set of association rules. We are using FP algorithm to conclude whether the tumour is malignant or benign tumour. Using these two algorithms the usage of memory will also be less. Index Terms Microarray data, frequency pattern, Apriori, ant colony optimization ________________________________________________________________________________________________________