Sarcasm Detection in News HeadlinesSarcasm Detection in News Headlines

This project focuses on predicting hazardous gas levels and Air Quality Index (AQI) values using various air quality parameters. The goal is to create a predictive model that evaluates the air quality by analyzing factors like CO, NO2, Ozone, and PM2.5 levels in different cities and countries. By leveraging machine learning algorithms, such as LSTM + GRU Hybrid, CNN-LSTM, Stacked Bi-LSTM with Dropout, and Random Forest with time-lagged features, the system predicts AQI values and categories like GOOD, Moderate, Unhealthy, etc. These predictions are presented through XAI (SHAP) plots to ensure transparency and interpretability of the model's decision-making process. The project is built using a Flask-based back-end and a front-end developed with HTML, CSS, and JavaScript. This system aims to provide accurate air quality predictions to aid in better environmental monitoring and health awareness.
Keywords: AQI, air quality prediction, machine learning, Flask, LSTM, GRU, CNN, SHAP, XAI, environment.