A comparison of five commonly used machine learning algorithms applied to potable water detection

Siyuan Liu; Yunfan Yang; Muhan Yao

doi:10.1117/12.2627657

11 March 2022 A comparison of five commonly used machine learning algorithms applied to potable water detection

Siyuan Liu, Yunfan Yang, Muhan Yao

Proceedings Volume 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021); 121601R (2022) https://doi.org/10.1117/12.2627657
Event: International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 2021, Sanya, China

Abstract

Potable water detection is an important issue in human society. Whether human have access to water with drinkable quality is crucial due to health concern. Before developing some techniques to ensure the water quality, it is important to understand some properties of the water, which can give a general view of how water quality is affected. Nowadays, machine learning is getting increasingly popular and it can be applied to many fields and solve plenty of problems in practice. Designing a machine learning predictor based on water properties can be drastically helpful to determine whether a water source is safe to consume. This article is based on the research which uses five common machine learning algorithms: k Nearest Neighbors, Decision Tree, Random Forest, Neural Network, and Support Vector Machine to train a model which predicts whether the water in the dataset is human consumable. By comparing the performance among these five models, as a conclusion, we find Random Forest and Support Vector Machine have the highest accuracy.

Citation Download Citation

Siyuan Liu, Yunfan Yang, and Muhan Yao "A comparison of five commonly used machine learning algorithms applied to potable water detection", Proc. SPIE 12160, International Conference on Computational Modeling, Simulation, and Data Analysis (CMSDA 2021), 121601R (11 March 2022); https://doi.org/10.1117/12.2627657

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available