Technical Paper
Comparative Analysis of Clustering Algorithms Based on Driver Steering Characteristics
2024-04-09
2024-01-2570
Driver steering characteristic clustering aims to deeply understand the driver's behavior and decision-making process through cluster analysis of the driver's turning data. It seeks to gain a better understanding of the diverse steering characteristics exhibited by drivers, providing valuable insights for road safety, driver assistance systems, and traffic management. The primary objective of this study is to delve into the practical application of various clustering algorithms in processing driver steering data, as well as to compare their performance and applicability. In this paper, principal component analysis is employed to reduce the dimensionality of the selected steering feature parameters. Following that, we apply K-means, Fuzzy C-means, Density-Based Spatial Clustering of Applications with Noise, and other algorithms for clustering analysis. Subsequently, the evaluation of clustering results is conducted using the Calinski-Harabasz Score and Silhouette Coefficient.