CLASSIFICATION OF MUSHROOM IN MYANMAR USING NAIVE BAYESIAN CLASSIFIER

Abstract

Mushrooms are the most recognizable scrumptious food which is cholesterol free as well as plentiful in nutrients and minerals. Numerous types of mushrooms have been figured out all through the earth. Distinguishing palatable or harmful mushrooms through the unaided eye is very difficult, so mushroom species should have to arrange eatable and noxious. This framework will be arranged the sort of mushroom by utilizing Naive Bayesian classifier and K-Nearest Neighbor Method to foster helpful subset of mushroom highlights for characterization task. This system can classify the edible and poisonous mushrooms from mushroom dataset by using Naive Bayes Classifier. In this system, performance comparison of the two algorithms are used Naïve Bayesian classifiers and K-Nearest neighbor (KNN) by using confusion matrix. The Naive Bayesian classifiers have been perhaps the most loved approaches as premise of numerous grouping technique both hypothetically and basically. K-closest neighbor (KNN) is a regulated learning calculation where the consequence of new case inquiry is ordered in light of greater part of K-closest neighbor class. This system is implemented by using C# programming language with Microsoft Visual 2013 and Microsoft SQL Server as the system database engine.