Speaker
Description
Over the past few decades, air pollution has become a significant threat to human health, contributing to rising mortality rates globally. This growing problem is primarily driven by industrial activities and vehicle emissions that release harmful pollutants into the atmosphere. Air pollution is linked to a range of health conditions, including respiratory tract and cardiovascular diseases. To mitigate its impact, it is crucial to accurately predict real-time mortality rates so that authorities can take preventive measures. This study explores the use of a Long Short-term Memory (LSTM) network, a type of recurrent neural network known for its efficacy in time-series forecasting. The model is used to predict mortality rates attributable to air pollution. The LSTM model is designed to capture the complex, nonlinear relationships between air pollutant levels and mortality outcomes. Its performance is compared against other machine learning algorithms such as the NARX model. The results indicate that LSTM outperforms the NARX model and demonstrates higher reliability and lower prediction errors.
