Abstract
Applications of learning algorithms in knowledge discovery are promising and relevant area of research. The classification algorithms of data mining have been successfully applied in the recent years to predict Egyptian rice diseases. Various classification algorithms can be applied on such data to devise methods that can predict the occurrence of diseases. However, the accuracy of such techniques differ according to the learning and classification rule used. Identifying the best classification algorithm among all available is a challenging task. In this study, a comprehensive comparative analysis of a tree-based different classification algorithms and their performance has been evaluated by using Egyptian rice diseases data set. The experimental results demonstrate that the performance of each classifier and the results indicate that the decision tree gave the best results.
Highlights
Processing the huge data and retrieving meaningful information from it is a difficult task
The aim of this paper is to evaluate the tree-based classifiers to select the classifier which more probably achieves the best performance for the Egyptian rice diseases which cause losses that estimated by 15% from the yield, malformation of the leaves or dwarfing of the plants
We have focused on the Bayesian network, random forest algorithms, comparing its performances with a decision tree using a variety of performance metrics
Summary
Processing the huge data and retrieving meaningful information from it is a difficult task. The term Data Mining, known as Knowledge Discovery in Databases (KDD) refers to the non trivial extraction of implicit, previously unknown and potentially useful information from data in databases [1]. Since decision trees have the described advantages, they have proven to be effective tools in classification of Egyptian rice www.ijarai.thesai.org (IJARAI) International Journal of Advanced Research in Artificial Intelligence, Vol 5, No.1, 2016 disease problems [7]. The transfer of experts from consultants and scientists to agriculturists, extends workers and farmers represent a bottleneck for the development of agriculture on the national This information can be used as part of the farmers decision-making process to help to improve crop production. The following sections briefly explain about each of these algorithms
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have