Advances in Computer Science and Engineering © 2014 Pushpa Publishing House, Allahabad, India Published Online: November 2014 Available online at http://pphmj.com/journals/acse.htm Volume 13, Number 1, 2014, Pages 65-68 Received: June 10, 2014; Accepted: July 14, 2014 Keywords and phrases: machine learning, multilabel classification, regression, air pollution. COMPARING ADVANCED REGRESSION METHODS FOR THE PREDICTION OF PM2.5 AIR POLLUTION H. F. Jelinek 1 , A. V. Kelarev 1 , A. Kolbe 2 , S. Heidenreich 3 and T. Oakman 4 1 Centre for Research in Complex Systems and School of Community Health Charles Sturt University P. O. Box 789, Albury, NSW 2640, Australia e-mail: hjelinek@csu.edu.au andreikelarev-charlessturtuniversity@yahoo.com 2 Faculty of Science Charles Sturt University Wagga Wagga, Locked Bag 588, NSW 2678, Australia e-mail: akolbe@csu.edu.au 3 New South Wales Office of Environment and Heritage Gunnedah Research Centre Gunnedah, P. O. 20, NSW 2380, Australia e-mail: stephan.heidenreich@environment.nsw.gov.au 4 New South Wales Public Health Unit P. O. Box 3095, Albury, NSW 2640, Australia e-mail: tracey.oakman@gsahs.health.nsw.gov.au Abstract In this article, we present new results of experiments comparing the effectiveness of regression methods in their ability to predict the NSW