A hybrid genetic algorithm and linear regression for prediction of NOx emission in power generation plant

Muhammad Afif Bunyamin, Keem Siah Yap, Nur Liyana Afiqah Abdul Aziz, Sheih Kiong Tiong, Shen Yuong Wong, Md Fauzan Kamal

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

This paper presents a new approach of gas emission estimation in power generation plant using a hybrid Genetic Algorithm (GA) and Linear Regression (LR) (denoted as GA-LR). The LR is one of the approaches that model the relationship between an output dependant variable, y, with one or more explanatory variables or inputs which denoted as x. It is able to estimate unknown model parameters from inputs data. On the other hand, GA is used to search for the optimal solution until specific criteria is met causing termination. These results include providing good solutions as compared to one optimal solution for complex problems. Thus, GA is widely used as feature selection. By combining the LR and GA (GA-LR), this new technique is able to select the most important input features as well as giving more accurate prediction by minimizing the prediction errors. This new technique is able to produce more consistent of gas emission estimation, which may help in reducing population to the environment. In this paper, the study's interest is focused on nitrous oxides (NOx) prediction. The results of the experiment are encouraging.

Original languageEnglish
Article number012101
JournalIOP Conference Series: Earth and Environmental Science
Volume16
Issue number1
DOIs
Publication statusPublished - 01 Jan 2013
Event26th IAHR Symposium on Hydraulic Machinery and Systems - Beijing, China
Duration: 19 Aug 201223 Aug 2012

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Environmental Science(all)
  • Earth and Planetary Sciences(all)

Cite this