Detrimental Object Detection in Water using Machine Learning: A Review


Authors : Rinkal Chauhan; Bela Shrimali

Volume/Issue : Volume 7 - 2022, Issue 12 - December

Scribd : https://bit.ly/3EUDlzi

DOI : https://doi.org/10.5281/zenodo.7698445

Abstract : Water sources are often polluted due to human intervention. Water pollution may be classified according to its quality, which is governed by factors such as pH, turbidity, the conductivity of dissolved oxygen (DO), nitrate, temperature, and biological oxygen demand (BOD). This research compares water quality categorization methods that use machine learning techniques, namely SVM, Decision Tree and Naïve Bayes. The characteristics considered to determine the quality of water are: pH, DO, BOD and electrical conductivity. Classification models are formed based on the numerical water quality index (WAWQI). After evaluating the results, With an accuracy of 98.50%, the decision tree approach was determined to be a better categorization model.

Keywords : Classification model; decision tree; support vector machine; naïve bayes; water quality index.

Water sources are often polluted due to human intervention. Water pollution may be classified according to its quality, which is governed by factors such as pH, turbidity, the conductivity of dissolved oxygen (DO), nitrate, temperature, and biological oxygen demand (BOD). This research compares water quality categorization methods that use machine learning techniques, namely SVM, Decision Tree and Naïve Bayes. The characteristics considered to determine the quality of water are: pH, DO, BOD and electrical conductivity. Classification models are formed based on the numerical water quality index (WAWQI). After evaluating the results, With an accuracy of 98.50%, the decision tree approach was determined to be a better categorization model.

Keywords : Classification model; decision tree; support vector machine; naïve bayes; water quality index.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe