Using of artificial neural network for evaluation and prediction of some drinking water quality parameters within a water distribution system
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26110%2F11%3APU91296" target="_blank" >RIV/00216305:26110/11:PU91296 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Using of artificial neural network for evaluation and prediction of some drinking water quality parameters within a water distribution system
Original language description
The project is focus on the methods for evaluation the available historical data of water quality and the investigation of the impact for selected physical parameters of water quality and its development in a water distribution system. It will be solved by creating a model using data-driven methods to identify and predict the evolution of selected water quality parameters. The wide open used data-driven methods in water management are Multiple Linear Regression (MLR) based on the least square approach and Multi Layer Perceptron (MLP), which is an Artificial Neural Network (ANN) architecture capable of predict any continues variable. The performance of MLP and MLR are evaluated using 4-years old database set of inputs collected in the city of Našiměřice Czech Republic. The first part of the paper shows a summary of the state of the knowledge in modeling using ANN and the second part describes the collection of data and construction of the models.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JM - Structural engineering
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
JUNIORSTAV 2011
ISBN
978-80-214-4232-0
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
243-253
Publisher name
VUT v Brně, Fakulta stavební
Place of publication
Brno, ČR
Event location
Brno
Event date
Feb 4, 2011
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—