A Distributed Simulated Annealing Based Decision Tree (DSABDT) for Cancer Classification

A distributed simulated annealing-based decision tree (DSABDT) is proposed for cancer classification. In the proposed algorithm, a decision tree is known to be useful for classification of cancer. The algorithm of simulated annealing adjusted the best values of the parameter for the decision tree. Furthermore, Apache Spark with a distributed framework has been proposed for processing colon cancer data. The data was used for testing the accuracy of the proposed algorithm. 2000 gene expressions of 62 tissue were included in the data that had 22 and 40 cases of general and colon cancer. Simulation results prove that the classification accuracy of the decision tree is ameliorated proposed algorithm.