Open AccessTRAFFIC POLLUTION ASSESSMENT USING ARTIFICIAL NEURAL NETWORK AND MULTIVARIATE ANALYSIS
Author(s) -
Mario De Luca,
Daiva Žilionienė,
Saulius Gadeikis,
Gianluca Dell’Acqua
Publication year - 2017
Publication title -
the baltic journal of road and bridge engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.259
H-Index - 21
eISSN - 1822-4288
pISSN - 1822-427X
DOI - 10.3846/bjrbe.2017.07
Subject(s) - artificial neural network , multivariate statistics , environmental science , wind speed , data collection , traffic flow (computer networking) , pollutant , pollution , work (physics) , multivariate analysis , computer science , engineering , meteorology , artificial intelligence , machine learning , statistics , mathematics , geography , mechanical engineering , ecology , chemistry , computer security , organic chemistry , biology
The work addressed a study on pollution caused by traffic on the highway. In particular, it was consideredthe concentration of pollutant, resulting from the passage of vehicles on the freeway. Five different stations (sensorsand samples) used to collect data. The data collection period around six months. Also, the following parameters weredetected: wind speed and direction, temperature and traffic flow rate. Data processed with Multivariate Analysis andArtificial Neural Network approach. The best model it obtained with Artificial Neural Network approach. In fact, thismodel presented the best fit to the experimental data.