<![CDATA[The COVID-19 pandemic has emerged as a significant global outbreak, seriously impacting public health. This study examines the influence of air quality on COVID-19 patients in Singapore and Jakarta, utilizing Naive Bayes, Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN) algorithms for data analysis. The findings indicate that better air quality in Singapore contributes to a reduction in disease severity, with 100% accuracy in predicting positive cases and hospitalizations using the SVM algorithm. Additionally, Naive Bayes successfully predicted 100% of mortality cases at a 90/10 ratio, demonstrating that even with relatively good air quality, its impact on patient severity remains significant. Conversely, in Jakarta, where air quality is poorer, there is variability in accuracy results. The K-NN algorithm achieved 100% accuracy for positive cases and isolation, while the SVM only reached 46.15% accuracy for positive case predictions. These findings underscore the significant influence of air quality on the severity and mortality of COVID-19 patients. In countries with better air quality, the impact on severity appears more manageable, whereas in those with poorer air quality, patient severity tends to be higher. This research aims to encourage the Indonesian public to pay closer attention to air quality for public health]]>
Copyrights © 2025
