Prediction of Eco-Driving Efficiency Score Using Artificial Neural Networks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
In this study, an Artificial Neural Network (ANN) basedprediction model was developed to evaluate eco-driving behaviors, which arecritical in terms of environmental sustainability and fuel efficiency. Usingthe Eco-Driving Behavior Dataset, the overall eco-driving efficiency score ofdrivers was predicted. Five key features were used as input parameters in thestudy: rpm variation, harsh braking count, idling time, fuel consumption, andacceleration smoothness. The dataset was scaled to the [0, 1] range using themin-max normalization method and divided into three subsets: 70% training, 15%validation, and 15% testing. A multilayer feedforward ANN model with a5-8-15-8-1 architecture was designed for the study. This architecture consistsof five input neurons, three hidden layers (with 8, 15, and 8 neurons,respectively), and one output neuron. Three different algorithms were used totrain the model: Levenberg-Marquardt, Scaled Conjugate Gradient, and ResilientBackpropagation. The Mean Square Error (MSE), Root Mean Square Error (RMSE),Mean Absolute Error (MAE), and Coefficient of Determination (R²) metrics wereused for performance evaluation. Experimental results have shown that all threetraining algorithms provide high prediction accuracy. Actual and predicted valueswere compared on 50 randomly selected samples from the test set, demonstratingthat the model can successfully predict eco-driving scores. This studydemonstrates that machine learning techniques can be used as an effective toolfor analyzing driving behavior and evaluating eco-friendly driving habits. Thedeveloped model is applicable in intelligent transportation systems and driverfeedback systems.
Fields of Study & Subjects
Vehicle emissions and performance
Human-Automation Interaction and Safety
Traffic Prediction and Management Techniques
Publication details
- Journal / source
- Erciyes University - AVESIS
- Publication date
- 20 March 2026
- Language
- EN