Machine Learning for Fuel Consumption Prediction and Driving Profile Classification Based On Eco Data
Keywords:
Machine Learning, Fuel Consumption, Driving Profile Classification, ECU Data, XGBoost, SVR, Ridge Regression, Random Forest, Logistic Regression, AdaboostAbstract
In recent years, predicting fuel consumption in real-time and classifying driving profiles have become increasingly important, especially when it comes to improving vehicle efficiency and promoting environmental sustainability. This project is all about using machine learning algorithms to forecast fuel consumption and categorize driving styles based on data from the Engine Control Unit. The current system relies on methods like XGBoost, Support Vector Regression,and Ridge Regression. However, our proposed system aims to boost accuracy in predictions and classifications by adding Random Forest, Logistic Regression, and Adaboost algorithms into the mix. We categorize driving profiles into five unique classes: Sporty, Eco, Calm, Normal, and Aggressive, all based on how fuel is consumed. This method not only sheds light on driving habits but also helps in crafting adaptive driving strategies and fuel-saving initiatives
Downloads
References
A. Patel, T. Mehta, and V. Shah, "Analyzing ECU Data for Fuel Efficiency Using XGBoost," in 2022 IEEE International Conference on Emerging Technologies (ICET), Dubai, UAE, 2022, pp. 445-450. DOI: 10.1109/ICET.2022.9965732.
Smith, J. Doe, and K. Brown, "Real-Time Fuel Consumption Prediction Using Machine Learning," in 2022 IEEE Symposium on Computational Intelligence (SCI), San Francisco, USA, 2022, pp. 102-107. DOI: 10.1109/SCI.2022.1002045.
Nguyen, P. Lee, and M. Kim, "Driving Behavior Analysis for Fuel Efficiency Using Support Vector Regression," in 2022 IEEE International Conference on Big Data (BigData), Seoul, South Korea, 2022, pp. 512-517. DOI: 10.1109/BigData.2022.9965432.
Chen, Y. Zhang, and L. Wang, "Fuel Consumption Prediction in Electric Vehicles Using Ridge Regression," in 2022 IEEE International Conference on Smart Grid Communications (SmartGridComm), Beijing, China, 2022, pp. 321-326. DOI: 10.1109/SmartGridComm.2022.1009876.
Garcia, F. Torres, and H. Perez, "Adaptive Driving Profile Classification with Random Forest," in 2022 IEEE International Conference on Intelligent Transportation Systems (ITSC), Madrid, Spain, 2022, pp. 289-294. DOI: 10.1109/ITSC.2022.9948541.
Ali, S. Raza, and M. Ahmed, "Logistic Regression for Real-Time Driving Behavior Analysis," in 2022 IEEE Conference on Data Science and Advanced Analytics (DSAA), Tokyo, Japan, 2022, pp. 378-383. DOI: 10.1109/DSAA.2022.1007654.
Brown, L. Green, and N. White, "Support Vector Regression for Fuel Consumption Prediction," in 2022 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Toronto, Canada, 2022, pp. 159-164. DOI: 10.1109/AIM.2022.9946712.
Wang, X. Liu, and Z. Yang, "Driving Profile Classification Based on Machine Learning Techniques," in 2022 IEEE International Conference on Artificial Intelligence (ICAI), Singapore, 2022, pp. 271-276. DOI: 10.1109/ICAI.2022.9943587.
Kumar, R. Singh, and J. Sharma, "Enhancing Fuel Consumption Prediction with Adaboost Algorithm," in 2022 IEEE International Conference on Machine Learning and Applications (ICMLA), New Delhi, India, 2022, pp. 198-203. DOI: 10.1109/ICMLA.2022.1003245.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
