Fuel Efficiency Analysis of the Public Transportation System Based on the Gaussian Mixture Model Clustering

TL;DR

This study uses Gaussian mixture models and a combined index approach to cluster bus trips based on fuel efficiency, revealing key factors like driving habits and routes that influence efficiency.

Contribution

The paper introduces an integrated clustering method combining multiple indices to determine optimal clusters for fuel efficiency analysis in public transportation.

Findings

Driving habits significantly affect fuel efficiency.

Route conditions influence fuel consumption.

Four distinct fuel efficiency categories were identified.

Abstract

Public transportation is a major source of greenhouse gas emissions, highlighting the need to improve bus fuel efficiency. Clustering algorithms assist in analyzing fuel efficiency by grouping data into clusters, but irrelevant features may complicate the analysis and choosing the optimal number of clusters remains a challenging task. Therefore, this paper employs the Gaussian mixture models to cluster the solo fuel-efficiency dataset. Moreover, an integration method that combines the Silhouette index, Calinski-Harabasz index, and Davies-Bouldin index is developed to select the optimal cluster numbers. A dataset with 4006 bus trips in North Jutland, Denmark is utilized as the case study. Trips are first split into three groups, then one group is divided further, resulting in four categories: extreme, normal, low, and extremely low fuel efficiency. A preliminary study using visualization analysis is conducted to investigate how driving behaviors and route conditions affect fuel efficiency. The results indicate that both individual driving habits and route characteristics have a significant influence on fuel efficiency.