Comparison of Decision Tree Algorithm and Support Vector Machine for Efficient Soil Data Classification in Terms of Accuracy

Abstract

Aim: The proposed work aims to classify the soil data using the support vector machine algorithm and compare its  performance  with the decision tree algorithm. Materials and Methods: The study setting of the proposed work utilizes two groups The group 1 is a Support Vector Machine (SVM) algorithm and group  2 is a Decision Tree (DT) algorithm. The sample size for each group is measured as 20 using Gpower of 80%. Results: The experimental results show that the Decision tree algorithm has T-test accuracy (65.95) which is less compared with the Support vector  algorithm (76.47). There exists no statistically significant difference among the groups with (P=0.521, >0.05). Conclusion: The obtained results show that the SVM algorithm is performing better than the Decision Tree in terms of accuracy.