Applying computational intelligence to the classification of pollution events

Miguel Melgarejo, Carlos Parra, Nelson Obregon

Research output: Contribution to journalArticle

Abstract

This paper compares three computational intelligence techniques applied to the discrimination of environmental situations associated to low air-quality events regarding the concentration of particulate matter with diameter lower than 10 micrometers. The techniques revised in this work are: Naive Bayesian Classification, Support Vector Machines and Fuzzy systems. A database extracted from the air-quality surveillance network at Bogota (Colombia) is used to train these classifiers. Results show that the support vector machine outperformed the other techniques in terms of exactitude and sensitivity. Although the fuzzy classifier and the Naive Bayes classifier did not achieve the best performances, these techniques offer interpretability about the classification problem.

LanguageEnglish
Article number7273760
Pages2071-2077
Number of pages7
JournalIEEE Latin America Transactions
Volume13
Issue number7
DOIs
Publication statusPublished - Jul 1 2015

Fingerprint

Artificial intelligence
Pollution
Classifiers
Air quality
Support vector machines
Fuzzy systems

Keywords

  • Air-pollution
  • Air-quality
  • Bayes classification
  • Fuzzy Systems
  • Support Vector Machines

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Applying computational intelligence to the classification of pollution events. / Melgarejo, Miguel; Parra, Carlos; Obregon, Nelson.

In: IEEE Latin America Transactions, Vol. 13, No. 7, 7273760, 01.07.2015, p. 2071-2077.

Research output: Contribution to journalArticle

@article{40f303e22cf24317a269b6dcfc4cbf34,
title = "Applying computational intelligence to the classification of pollution events",
abstract = "This paper compares three computational intelligence techniques applied to the discrimination of environmental situations associated to low air-quality events regarding the concentration of particulate matter with diameter lower than 10 micrometers. The techniques revised in this work are: Naive Bayesian Classification, Support Vector Machines and Fuzzy systems. A database extracted from the air-quality surveillance network at Bogota (Colombia) is used to train these classifiers. Results show that the support vector machine outperformed the other techniques in terms of exactitude and sensitivity. Although the fuzzy classifier and the Naive Bayes classifier did not achieve the best performances, these techniques offer interpretability about the classification problem.",
keywords = "Air-pollution, Air-quality, Bayes classification, Fuzzy Systems, Support Vector Machines",
author = "Miguel Melgarejo and Carlos Parra and Nelson Obregon",
year = "2015",
month = "7",
day = "1",
doi = "10.1109/TLA.2015.7273760",
language = "English",
volume = "13",
pages = "2071--2077",
journal = "IEEE Latin America Transactions",
issn = "1548-0992",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - Applying computational intelligence to the classification of pollution events

AU - Melgarejo, Miguel

AU - Parra, Carlos

AU - Obregon, Nelson

PY - 2015/7/1

Y1 - 2015/7/1

N2 - This paper compares three computational intelligence techniques applied to the discrimination of environmental situations associated to low air-quality events regarding the concentration of particulate matter with diameter lower than 10 micrometers. The techniques revised in this work are: Naive Bayesian Classification, Support Vector Machines and Fuzzy systems. A database extracted from the air-quality surveillance network at Bogota (Colombia) is used to train these classifiers. Results show that the support vector machine outperformed the other techniques in terms of exactitude and sensitivity. Although the fuzzy classifier and the Naive Bayes classifier did not achieve the best performances, these techniques offer interpretability about the classification problem.

AB - This paper compares three computational intelligence techniques applied to the discrimination of environmental situations associated to low air-quality events regarding the concentration of particulate matter with diameter lower than 10 micrometers. The techniques revised in this work are: Naive Bayesian Classification, Support Vector Machines and Fuzzy systems. A database extracted from the air-quality surveillance network at Bogota (Colombia) is used to train these classifiers. Results show that the support vector machine outperformed the other techniques in terms of exactitude and sensitivity. Although the fuzzy classifier and the Naive Bayes classifier did not achieve the best performances, these techniques offer interpretability about the classification problem.

KW - Air-pollution

KW - Air-quality

KW - Bayes classification

KW - Fuzzy Systems

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=84943311450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943311450&partnerID=8YFLogxK

U2 - 10.1109/TLA.2015.7273760

DO - 10.1109/TLA.2015.7273760

M3 - Article

VL - 13

SP - 2071

EP - 2077

JO - IEEE Latin America Transactions

T2 - IEEE Latin America Transactions

JF - IEEE Latin America Transactions

SN - 1548-0992

IS - 7

M1 - 7273760

ER -