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

2025-01-21

Portuguese Conference on Artificial Intelligence

AI Summary

Addressing the challenges of evaluating fuel efficiency and attributing energy consumption in bus systems, this paper proposes a Gaussian Mixture Model (GMM)-based multidimensional operational feature clustering method. It is the first to apply unsupervised GMM for mining energy-efficiency patterns and identifying inefficient operating conditions in urban bus fleets. By integrating heterogeneous operational data, constructing a fuel-consumption-oriented feature set, and optimizing the number of clusters via silhouette coefficient analysis, the method automatically discovers four distinct, representative operational modes. Evaluated on real-world bus network data, it achieves a 92.3% accuracy in detecting inefficient clusters—substantially outperforming conventional threshold-based approaches. The method ensures both interpretability and engineering applicability, offering a data-driven paradigm for developing fine-grained, fuel-saving dispatch strategies.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Problem

• Public Transportation Optimization
• Fuel Efficiency
• Greenhouse Gas Emissions Reduction

Innovation

• Gaussian Mixture Model
• Fuel Efficiency Analysis
• Public Transportation Optimization