DEEP LEARNING-BASED CLASSIFICATION OF URBAN AIR POLLUTION INTO SIX CATEGORIES WITH HIGH ACCURACY

Creative Commons License

Noğay H. S.

3rd INTERNATIONAL CONGRESS ON ENGINEERING AND SCIENCES, 10 - 11 May 2024, pp.82-88, (Full Text)

  • Publication Type: Conference Paper / Full Text
  • Page Numbers: pp.82-88
  • Open Archive Collection: AVESIS Open Access Collection
  • Bursa Uludag University Affiliated: Yes

Abstract

Abstract: Urban air pollution is a pressing environmental issue with profound implications for public health and quality of life. Effective monitoring and classification of air pollution levels are essential for implementing mitigation strategies and safeguarding human health. In this study, we propose an approach to classify urban air pollution into six categories using convolutional neural networks (CNNs). Leveraging transfer learning technique, we design and train a CNN architecture tailored for multi-class classification tasks. Experimental results demonstrate the efficacy of the proposed approach, with the trained model achieving an impressive accuracy rate of 97% on the testing dataset. Our study contributes to the advancement of air quality monitoring systems, providing a valuable tool for policymakers and environmental scientists to assess pollution levels and implement targeted interventions to improve urban air quality.