Development of the Edible and Poisonous Mushrooms Classification Model by using the Feature Selection and the Decision Tree Techniques
Sumitra Nuanmeesri1, Wongkot Sriurai2

1SumitraNuameesri*, Assistant Professor, Department of Information Technology, Science and Technology, Suan Sunandha Rajabhat University, Thailand.
2WongkotSriurai, Assistant Professor, Department of Mathematics Statistics and Computer Science Ubon Ratchathani University, Thailand.
Manuscript received on November 12, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 3061-3066 | Volume-9 Issue-2, December, 2019. | Retrieval Number:  B4115129219/2019©BEIESP | DOI: 10.35940/ijeat.B4115.129219
Open Access | Ethics and Policies | Cite | Mendeley
© 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: This research aims to develop a classification model for edible and poisonous mushrooms by applying the feature selection approach together with the decision tree technique. Two feature selection methods were applied, including 1) Chi-square and 2) Information Gain, while the effectiveness of the model was compared by three decision tree methods such as Iterative Dichotomiser3, C4.5 and Random Forest. The data used for classifying the edible and poisonous mushrooms derived from the Encyclopedia of Thai mushrooms and the book entitled “Diversity of Mushrooms and Macrofungi in Thailand”. The results of the model’s effectiveness evaluation revealed that the model using the Information Gain technique alongside with the Random Forest technique provided the most accurate classification outcomes at 94.19%; therefore, this model could be further applied in the future studies.
Keywords: Classification, Feature Selection, Decision Tree, Mushrooms, Poisonous.