<![CDATA[Good air quality is essential for healthy and sustainable living, but increasing air pollution caused by industrialization, urbanization, and motor vehicles has become a serious global issue. Air pollution negatively affects health, the environment, and the quality of life, making air quality monitoring and assessment a priority. The complexity of air quality data renders conventional analytical approaches less effective; therefore, machine learning methods such as Random Forest and Neural Networks have been applied to address these challenges. However, these methods have limitations in handling non-linear patterns or computational efficiency. This study employs the Support Vector Machine (SVM) algorithm with various kernels to classify air quality based on pollution and environmental parameters into categories of Good, Moderate, Poor, and Hazardous. The results indicate that the Polynomial Kernel performs best for the Good category, while the RBF Kernel is also competitive but less optimal for the Hazardous and Poor categories. With parameter optimization using GridSearchCV, the combination of C=10 and Gamma=0.1 or scale achieved an average accuracy of 90.75%. CO concentration and proximity to industrial areas proved to be significant features in classification. This study aims to support air pollution management and mitigate its impacts on society.]]>
Copyrights © 2025
