Related Experiment Video
Updated: Jan 9, 2026
04:04
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
885
Fuzzy neural identification and forecasting techniques to process experimental urban air pollution data
Francesco Carlo Morabito1, Mario Versaci
1Faculty of Engineering, University Mediterranea of Reggio Calabria, DIMET, Via Graziella, Feo di Vito, Reggio Calabria, Italy. morabito@unirc.it
Summary
This study models urban air pollution by integrating atmospheric, traffic, and topographic data. It predicts short-term pollutant levels, like hydrocarbons, to prevent dangerous concentrations and inform traffic management strategies.
Area of Science:
- Environmental Science
- Data Science
- Urban Planning
Background:
- Air quality monitoring involves complex interrelations between atmospheric and pollution data.
- Urban air pollution estimation has significant economic and public health implications.
- Traffic and topographic data are crucial for accurate pollution modeling.
Purpose of the Study:
- To develop a model for multivariate relationships in local air quality.
- To predict short-term pollutant evolution and prevent hazardous levels.
- To provide data-driven directives for local traffic management.
Main Methods:
- Processing experimentally measured pollution and atmospheric data.
- Incorporating traffic and topographic information into a predictive model.
- Utilizing fuzzy neural systems for data analysis and prediction.
Main Results:
- Successful short-term prediction of hydrocarbon (HC) concentrations.
- Comparison of different fuzzy neural system methods.
- Development of local models for non-linear interactions among key variables.
Conclusions:
- The developed models can accurately represent local interactions and predict pollutant levels.
- Findings offer a basis for proactive traffic management to mitigate air pollution.
- The study highlights the importance of interdisciplinary approaches for urban environmental challenges.
