Analyses of Approaches to Deal with Missing Data in Water Quality Data Set

DOI

10.2991/aebmr.k.220405.184How to use a DOI?

Keywords

Water Quality; Imputation Method; Missing Data; Neuro Network; Data Analysis

Abstract

The water quality model from the Kaggle Dataset provides useful data for predicting the potability of a specific specimen. Dealing with missing values is imperative for computer and data scientists to obtain accurate results. When using datasets with missing values in statistical analysis or hydrological modeling, the findings can be misguided. This research is going to explore several common imputation methods and techniques to handle a large number of data streams by using neural networks and machine learning. The author evaluates various imputation approaches that can be applied to water quality data using the proposed approach. Eventually, the KNN imputation method performs the best and generates the most accurate testing results among other imputation methods.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Ruoqi Yang
PY  - 2022
DA  - 2022/04/29
TI  - Analyses of Approaches to Deal with Missing Data in Water Quality Data Set
BT  - Proceedings of the 2022 7th International Conference on Social Sciences and Economic Development (ICSSED 2022)
PB  - Atlantis Press
SP  - 1102
EP  - 1108
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.220405.184
DO  - 10.2991/aebmr.k.220405.184
ID  - Yang2022
ER  -