Wastewater treatment plant performance prediction with support vector machines

Authors:
Daniel Ribeiro;António Sanfins;Orlando Belo
Affiliations:
ALGORITMI R&D Centre, University of Minho, Portugal;IDITE-Minho, Portugal;ALGORITMI R&D Centre, University of Minho, Portugal
Venue:
ICDM'13 Proceedings of the 13th international conference on Advances in Data Mining: applications and theoretical aspects
Year:
2013

Citing 21
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Data preparation for data mining

Data preparation for data mining
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
An introduction to variable and feature selection

The Journal of Machine Learning Research
A tutorial on support vector regression

Statistics and Computing
Prediction error estimation: a comparison of resampling methods

Bioinformatics
New Support Vector Algorithms

Neural Computation
Lamb Meat Quality Assessment by Support Vector Machines

Neural Processing Letters
Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap

Computational Statistics & Data Analysis
A study of cross-validation and bootstrap for accuracy estimation and model selection

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Effluent Quality Prediction of Wastewater Treatment Plant Based on Fuzzy-Rough Sets and Artificial Neural Networks

FSKD '09 Proceedings of the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 05
Prediction of Effluent Parameters of Wastewater Treatment Plant Based on Improved Least Square Support Vector Machine with PSO

ICISE '09 Proceedings of the 2009 First IEEE International Conference on Information Science and Engineering
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Data Mining: Practical Machine Learning Tools and Techniques

Data Mining: Practical Machine Learning Tools and Techniques
Improved support vector machine generalization using normalized input space

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
An overview of statistical learning theory

IEEE Transactions on Neural Networks
Improvements to the SMO algorithm for SVM regression

IEEE Transactions on Neural Networks
On the choice of the best imputation methods for missing values considering three groups of classification methods

Knowledge and Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Wastewater treatment plants are essential infrastructures to maintain the environmental balance of the regions where they were installed. The dynamic and complex wastewater treatment procedure must be handled efficiently to ensure good quality effluents. This paper presents a research and development work implemented to predict the performance of a wastewater treatment plant located in the northern Portugal, serving a population of about 45,000 inhabitants. The data we used were recorded based on the daily averaged values of the measured parameters during the period of one year. The predictive models were developed supported by two implementations of Support Vector Machines methods for regression, due to the presence of two lines of treatment in the selected case of study, using two of the most relevant output parameters of a wastewater treatment plant: the biochemical oxygen demand and the total suspended solids. We describe here the wastewater treatment plant we studied as well the data sets used in the mining processes, analyzing and comparing the regression models for both predictive parameters that were selected.