Comparative Analysis For Cancer Prediction Using Genetic Algorithm To Other Machine Learning Algorithms

Authors

  • Rishm
  • Misha Mittal
  • Dinesh kumar
  • Ashwani Sethi

Keywords:

Cancer, Genome, Genetic, targeted sequencing, Prediction, Machine Learning

Abstract

—Cancer is one of the leading causes of death these days. There are number of reasons which cause cancer but classification and predicting of cancer at the right stage is very important. This research work mainly focuses on early prediction of cancer using different approaches of machine learning in comparison with genetic algorithm to predict cancer at early stage. Genetic Algorithm optimizes the neural network by involving connection weights. The Breast Cancer Wisconsin (Original) Data Set is taken from UCI machine learning repository and it is trained and tested by applying different algorithm like Random forest, Naïve Bayes, Artificial neural network and Genetic algorithm. Random forest is used as an ensemble learning algorithm which is applied on the microarray data of cancer to achieve good accuracy and reliable performance, For predictive modeling Naïve Bayes algorithm is also used based on weight concept by assigning weight on dataset of breast cancer taken from UCI machine learning repository and Artificial neural network uses back propagation algorithm which has different neurons in hidden layer to analyze output by calculating the error using weight adjustment method ,it reduces error between the required and actual output. From experimental analysis genetic algorithm provides topmost accuracy of 97% where as other algorithms like artificial neural network provides accuracy of 96%, Naïve bayes provides accuracy of 94% and Random forest provides accuracy of 95%.

Downloads

Published

2023-12-20

How to Cite

Rishm, Misha Mittal, Dinesh kumar, & Ashwani Sethi. (2023). Comparative Analysis For Cancer Prediction Using Genetic Algorithm To Other Machine Learning Algorithms. Elementary Education Online, 19(2), 1643–1660. Retrieved from https://ilkogretim-online.org/index.php/pub/article/view/6734

Issue

Section

Articles