An Innovative Method for Optimal Detection and Analysis of Phosphate Level in Tamilnadu Water Resources using Extreme Learning Machine Algorithm and Comparing with SVM based on Accuracy and Mean Squared Error Rate

Abstract

Aim: The Aim of the works involves the predict the structure of function to Improve Innovative Optimal Detection and analysis of phosphate in water resources using an Extreme Learning Machine algorithm (ELM) over Support Vector Machine algorithm (SVM) founded on accuracy and Mean Squared Error rate (MSE). Methods and materials: In this method have taken two algorithms with data samples of each size is $N=5$ and testing and comparing with two algorithms will show greater accuracy. G power 80 % threshold 0.05 %, CI is 95 %. Results and Discussion: Based on the measurement of data, statistical analysis, and independent sample T-test, the significant level is ($P < 0.03$) to produce better accuracy, lower mean squared error rate using ELM algorithm (92%) while comparing to SVM (88%). Conclusion: The method shows reasonable accuracy, selectivity, and comparable extreme learning machine than support vector machine which allows it for nitrate determination in natural water.