CLASSIFICATION OF SPECT HEART DATASET USING EFFICIENT MODIFIED RANDOM FOREST ALGORITHM

K. Ammulu

Abstract


Data mining is one of the most powerful technique and which is embedded in many applications. The scholar is working in data mining domain proposed many solutions to solve classification problems. Random forest algorithm is a one of the ensemble learning method used for data classification and regression of dataset. Random forest algorithm facing classification problem and it is not classifying dataset accurately. In this paper, we propose modified random forest algorithm to merge random forest algorithm and particle swarm optimization algorithm. To analyze the performance of proposed method, SPECT heart dataset with 17 variables and 10299 instances of data is taken as an input from UCI repository, confusion matrix is used to measure accuracy, recall, F1, and precision. Compare with random forest algorithm proposed method exhibit better results. 

Keywords: Data Mining, Classification, Modified Random Forest Algorithm, SPECT Heart Dataset, Prediction


Full Text:

PDF

Refbacks

  • There are currently no refbacks.


© 2017 International Journal of Global Research in Computer Science (JGRCS)
Copyright Agreement & Authorship Responsibility