Attribute-oriented Classification with Variable Importance using Random Forest Model
G. Rama Subba Reddy1, Shaik Jaffar Hussain2, K. Dinesh Kumar3
1G. Rama Subba Reddy, Department of CSE, Mother Theresa Institute of Engineering & Technology, Palamaner, (Andhra Pradesh), India.
2Shaik Jaffar Hussain, Department of CSE, Annamacharya Institute of Technology and Science, Rajampet, (Andhra Pradesh), India.
3K Dinesh Kumar, SCSE, VIT University, (Tamil Nadu), India.
Manuscript received on 25 July 2019 | Revised Manuscript received on 03 August 2019 | Manuscript Published on 10 August 2019 | PP: 1630-1635 | Volume-8 Issue-2S3 July 2019 | Retrieval Number: B12970782S319/2019©BEIESP | DOI: 10.35940/ijrte.B1297.0782S319
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 the present century, various classification issues are raised with large data and most commonly used machine learning algorithms are failed in the classification process to get accurate results. Datamining techniques like ensemble, which is made up of individual classifiers for the classification process and to generate the new data as well. Random forest is one of the ensemble supervised machine learning technique and essentially used in numerous machine learning applications such as the classification of text and image data. It is popular since it collects more relevant features such as variable importance measure, Out-of-bag error etc. For the viable learning and classification of random forest, it is required to reduce the number of decision trees (Pruning) in the random forest. In this paper, we have presented systematic overview of random forest algorithm along with its application areas. In addition, we presented a brief review of machine learning algorithm proposed in the recent years. Animal classification is considered as an important problem and most of the recent studies are classifying the animals by taking the image dataset. But, very less work has been done on attribute-oriented animal classification and poses many challenges in the process of extracting the accurate features. We have taken a real-time dataset from the Kaggle to classify the animal by collecting the more relevant features with the help of variable importance measure metric and compared with the other popular machine learning models.
Keywords: Machine Learning, Decision Trees, Random Forests, SVM, Classification.
Scope of the Article: Machine Learning