Comparison of Machine Learning Algorithms and Fruit Classification using Orange Data Mining Tool

With the hype about Artificial Intelligence, Machine Learning has become a trending topic these days. Lots of tools are available for data visualization, yet most of the model training is dependent on scripting languages. Orange Data Mining tool provides the flexibility with data pre-processing, visualization and model training and test in a single software. The proposed paper applies machine learning algorithms to a fruit image dataset and perform a comparative study of the algorithms to determine which algorithm has the highest Classification Accuracy and Precision score. Decision making is based on the images used to train the algorithm to learn the specific features derived from those trained images. Cross validation is performed in order to evaluate the results for Classification Accuracy. The difference between actual and predicted values is evaluated to determine the number of instances predicted correctly.