Carbon Emission Prediction Through the Harmonization of Extreme Learning Machine and INFO Algorithm

This project focuses on developing a predictive model for carbon emissions from vehicles using a dataset containing features such as model year, make, engine size, and fuel consumption metrics. By leveraging machine learning algorithms like Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost), the study aims to capture complex relationships among features and enhance predictive accuracy. A key aspect of this research is the integration of the Extreme Learning Machine and Info Algorithm, which further refines the model's ability to deliver robust predictions. Additionally, the project explores feature engineering techniques and dataset augmentation to improve model performance. This study not only offers valuable insights into carbon emissions but also emphasizes the importance of leveraging diverse data sources to build comprehensive and reliable models. The findings aim to support the development of environmentally sustainable transportation policies and contribute to global climate change mitigation efforts.

Keywords: carbon emission prediction, co2 emissions, machine learning, support vector machine, LSTM , extreme gradient boosting, info algorithm, environmental sustainability.