Sign in Subscribe
Artificial intelligence

Advances in Machine Learning for Vehicle Efficiency

Strategic Insights

— 1 min read

Researchers from Polytechnic University in Quito, Ecuador, have developed a machine learning algorithm that can accurately classify gear shifts in M1 category vehicles, improving fuel efficiency and overall vehicle performance. The algorithm, based on data acquired through the onboard diagnostic system (OBD II) and GPS, analyzes identification parameters such as manifold absolute pressure, revolutions per minute, and vehicle speed to determine the efficiency and behavior of the vehicle in each gear.

Key Takeaways:

  • The researchers implemented an unsupervised K-means algorithm to analyze vehicle gear changes and identify driving patterns, segmenting the data into meaningful groups.
  • Machine learning techniques, including K-Nearest Neighbors (KNN), decision trees, logistic regression, and Support Vector Machines (SVMs), were employed to classify gear shifts accurately.
  • The KNN (Fine KNN) model achieved an accuracy of 99.7%, an error rate of 0.3%, a precision of 99.8%, a recall of 99.7%, and an F1-score of 99.8%, outperforming other models.
  • A multiple linear regression model was developed to estimate instantaneous fuel consumption using the gear predicted by the KNN algorithm and other relevant variables.
  • Results showed that higher gears (3, 4, and 5) are associated with lower fuel consumption, while a neutral gear presented the highest levels of consumption and variability.
  • The algorithm was integrated with a driver assistance system (ADAS) to optimize gear shift timing based on dynamic factors like road conditions, traffic density, and driver behavior.
  • The researchers propose exploring the applicability of this algorithm in autonomous vehicles to enhance real-time decision making.

Statistics:

  • The algorithm analyzed over 66,000 valid observations to estimate instantaneous fuel consumption.
  • The R-squared value for the multiple linear regression model was 0.897.
  • The root mean square error (RMSE) for the model was 2.06.
  • The accuracy of the KNN (Fine KNN) model was 99.7%.
  • The error rate of the KNN (Fine KNN) model was 0.3%.

Sources:

  • Driving Pattern Analysis, Gear Shift Classification, and Fuel Efficiency in Light-Duty Vehicles: A Machine Learning Approach Using GPS and OBD II PID Signals. Sensors, 2025, 25(13): 4043. (Sensors - http://www.mdpi.com/journal/sensors).
  • NewsRx. New Findings from Polytechnic University Describe Advances in Machine Learning (Driving Pattern Analysis, Gear Shift Classification, and Fuel Efficiency in Light-Duty Vehicles: A Machine Learning Approach Using GPS and OBD II PID Signals). Energy Weekly News. August 1, 2025; p 191.

Read more