Authors:
Rakesh Chandrashekar, Jayasheel Kumar, M. Arunadevi Thirumalraj, S. Sharan Jeev

Addresses:
Department of Mechanical Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Automobile Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, Karunya Institute of Technology and Science, Coimbatore, Tamil Nadu, India. Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Cybersecurity, University of Texas at Dallas, Richardson, Texas, United States of America.

Abstract:

Worldwide, but notably in developed and emerging countries, urban pollution is a huge issue. Modern cities' outward appearance is a major source of visual pollution, which, in turn, causes a variety of problems, including physical and mental health issues, distracted driving, environmental dangers, and emotional discomfort among residents. The need for easy, accurate air quality monitoring has arisen because air pollution poses a serious risk to human health. A station in Belfast city centre provided the data used in the study, which is open to the public. The study was conducted in Northern Ireland. It is a tool for measuring air pollution. An innovative method for converting text to images is suggested, which can take the input data and produce miniature images. To enable deep mining of global information via a self-attention mechanism, this study proposes a DSSAM that integrates spectral and spatial information. This study presents the KOA, a novel bio-inspired metaheuristic for hyper-parameter optimisation that mimics the behaviour of kookaburras. Part I presents the mathematical modelling based on simulating prey hunting, and Part II presents the modelling based on simulating kookaburra behaviour, that is, ensuring their prey is slain. Predictions of five air pollutants—Nitrogen Dioxide (NO2), Ozone (O3), Particulate Matter (PM2.5, and PM10)—achieved 94.67% accuracy, 88.42% precision, 88.18% recall, and 88.25% F1-score.

Keywords: Urban Air Pollution; Environmental Dangers; Global Information; Distracted Driving; Kookaburra Optimisation Algorithm (KOA); Nitrogen Dioxide; Air Pollutants Concentration; Dual-Stream Self-Attention Fusion Mechanism (DSSAM).

Received on: 23/10/2024, Revised on: 27/12/2024, Accepted on: 13/02/2025, Published on: 14/09/2025

DOI: 10.69888/FTSESS.2025.000540

FMDB Transactions on Sustainable Environmental Sciences, 2025 Vol. 2 No. 3, Pages: 137-150

• Views : 88
• Downloads : 8

Download PDF