Feature engineering on forest cover type data with ensemble of decision trees

Author

Pruthvi, H.R. ; Nisha, K.K. ; Chandana, T.L. ; Navami, K. ; Biju, R.M.

Author_Institution

Dept. of Inf. Technol., Nat. Inst. of Technol. Karnataka, Surathkal, India

fYear

2015

fDate

12-13 June 2015

Firstpage

1093

Lastpage

1098

Abstract

The paper aims to determine the forest cover type of the dataset containing cartographic attributes evaluated over four wilderness areas of Roosevelt National Forest of Northern Colorado. The cover type data is provided by US Forest service inventory, while Geographic Information System (GIS) was used to derive cartographic attributes like elevation, slope, soil type etc. Dataset was analyzed, pre processed and feature engineering techniques were applied to derive relevant and non-redundant features. A comparative study of various decision tree algorithms namely, CART, C4.5, C5.0 was performed on the dataset. With the new dataset built by applying feature engineering techniques, Random Forest and C5.0 improved the accuracy by 9% compared to the raw dataset.

Keywords

cartography; decision trees; forestry; geographic information systems; pattern classification; C4.5; C5.0; CART; GIS; Roosevelt National Forest of Northern Colorado; US forest service inventory; cartographic attributes; decision tree algorithms; feature engineering; forest cover type data; geographic information system; random forest; Accuracy; Boosting; Decision trees; Feature extraction; Hydrology; Soil; Vegetation;

fLanguage

English

Publisher

ieee

Conference_Titel

Advance Computing Conference (IACC), 2015 IEEE International

Conference_Location

Banglore

Print_ISBN

978-1-4799-8046-8

Type

conf

DOI

10.1109/IADCC.2015.7154873

Filename

7154873