Authors: Assistant Professor Mrs.G.Sangeetha Lakshmi, Ms.S.Devagi
Abstract: Amid growing concerns about climate change and environmental sustainability, accurately evaluating vehicle CO₂ emissions has become increasingly important. As transportation remains a major source of greenhouse gases, there is a need for advanced, data-driven solutions to monitor and assess emission levels effectively. This project introduces a deep learning model based on Convolutional Neural Networks (CNN) to classify and rate vehicle emissions by analyzing key attributes such as fuel type, engine capacity, mileage, and emission standards. Unlike traditional rule-based or statistical methods that often struggle with complex and large datasets, CNNs excel at automatically extracting meaningful features, leading to higher prediction accuracy and adaptability. Trained on a comprehensive dataset of vehicle emission records, the model classifies vehicles into various emission categories, offering valuable insights for regulators, manufacturers, and consumers. By combining deep learning with data science, this system provides a scalable and automated method for emissions evaluation, promoting the adoption of energy-efficient vehicles and stricter environmental regulations. Furthermore, the model has the potential for real-time emission monitoring, aiding in better air quality management and supporting the shift toward greener transportation technologies.
