Monitoring AI-Based Processing for Predicting Poisonous Gas Emissions in Smart Cities Using Novel Temporal Dynamics Prediction Model
K. Jaisharma, N. Deepa, T Devi
Abstract
Smart cities, driven by technological advancements, face challenges related to environmental pollution, including poisonous gas emissions. Existing systems often struggle to efficiently monitor and predict these emissions, leading to limitations in accurately assessing and mitigating air quality issues. This study proposes a groundbreaking solution, the Novel Temporal Dynamics Prediction (NTDP) model, designed to overcome the limitations of current systems. By harnessing the NTDP model’s innovative approach, smart cities can enhance their capability to analyze and forecast poisonous gas emissions, thereby improving the effectiveness of environmental management. The NTDP model offers a promising avenue for the future, revolutionizing the way smart cities address and mitigate the impact of toxic pollutants on air quality. The NTDP model achieved an accuracy of 99.1%, sensitivity of 98.9% and RMSE training 1.6 and testing 1.54 ug/m3. The results affirm the robustness and effectiveness of our optimized implementation, positioning it as a standout solution in disease prediction compared to commonly used machine learning techniques.