Enhancing the Prediction of Communication Using Support Vector Machine Over Decision Tree for Underwater Wireless Networks

Effort of this research is to enhance our ability to forecast how underwater wireless sensor networks would behave for underwater wireless communication. Materials and to make accurate projections on the functionality of underwater wireless sensor networks (UWSN), it is necessary to put the Support Vector Machine (SVM) and Decision Tree algorithms through their paces by using a wide range of training and testing strategies. A sample size of 20 for both groups is calculated using the Gpower value of 85% (g power setting parameters: =0.05 and power=0.85). The accuracy based on the result suggests that the SVM, has a value of 92.509% than the Decision Tree, having a value of 83.1156%, with a statistically significant value of 0.001 (p<0.05) which is statistically significant and concludes the Support Vector Machine has a higher Accuracy and Loss. When compared to the accuracy of a decision tree, the accuracy of a support vector machine is superior.