Predictive Neural Networks Model for Detection of Water Quality for Human Consumption

Renzo Chafloque, Ciro Rodriguez, Yuri Pomachagua, Manuel Hilario

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Water is an important element that is related to the human being because drinking water is a necessary element for health, also drinking water is considered as an element that also participates in the economy of a society, since it has a defined and industrialized process. Due to the presence of drinking water in different aspects of society, it is important to carry out research that contributes to this topic. The present research work is focused on a predictive analysis using a neural network model, which will allow us to predict and detect whether a given body of water is suitable for human consumption. The proposed model is based on an architecture that uses neural networks that was developed in the Python language, and a dataset obtained from the Kaggle web page was also used. This data set was used for training and validation. Within the preprocessing, the MinMax scaling method obtained from the Sklearn library was used. For the development of the model, the Keras library was used, which provided the necessary methods for the implementation of the seven dense layers that make up the neural network. At the end of the development, a model with an accuracy of approximately 70% was obtained. Finally, we invite for future research, to consider new architectures based on neural networks or other models based on other machine learning classification algorithms.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 13th International Conference on Computational Intelligence and Communication Networks, CICN 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages172-176
Number of pages5
ISBN (Electronic)9781728176956
DOIs
StatePublished - 22 Sep 2021
Externally publishedYes
Event13th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2021 - Lima, Peru
Duration: 22 Sep 202123 Sep 2021

Publication series

NameProceedings - 2021 IEEE 13th International Conference on Computational Intelligence and Communication Networks, CICN 2021

Conference

Conference13th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2021
Country/TerritoryPeru
CityLima
Period22/09/2123/09/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • detection
  • human consumption
  • neural networks
  • pH
  • potability
  • water

Fingerprint

Dive into the research topics of 'Predictive Neural Networks Model for Detection of Water Quality for Human Consumption'. Together they form a unique fingerprint.

Cite this