Classification Models and Hybrid Feature Selection Method to Improve Crop Performance
U. Muthaiah1, S. Markkandeyan2, Y. Seetha3
1U. Muthaiah, Department of CSE, Sri Shanmugha College of Engineering and Technology, Sankari, Salem (Tamil Nadu), India.
2Dr. S. Markkandeyan, Sri Shanmugha College of Engineering and Technology, Sankari, Salem (Tamil Nadu), India.
3Dr. Y. Seetha, Associate Professor, Department of Physics, Aurora’s Scientific Technological & Research Academy, Hyderabad (Telangana), India.
Manuscript received on 06 September 2019 | Revised Manuscript received on 15 September 2019 | Manuscript Published on 26 October 2019 | PP: 323-326 | Volume-8 Issue-11S2 September 2019 | Retrieval Number: K105209811S219/2019©BEIESP | DOI: 10.35940/ijitee.K1052.09811S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper classification models and hybrid feature selection methods are implanted on benchmark dataset on the Mango and Maize. Particle Swarm Optimization–Support Vector Machine (PSO-SVM) classification algorithm for the selection of important features from the Mango and Maize datasets to analysis and also compare with the novel classification techniques. Various experiments conducted on these datasets, provide more generated rules and high selection of features using PSO-SVM algorithm and Fuzzy Decision Tree. The proposed method yield high accuracy output as compared to the existing methods with minimum Error Rate and Maximum Positive Rate.
Keywords: Classification, Feature Selection, PSO-SVM, Decision Tree.
Scope of the Article: Classification