Research on classification of highway service areas based on multifactor clustering

Xi’an University of Architecture and Technology, Department of civil engineering, Xi’an, 710055, China

^* Corresponding author: 2578474368@qq.com

Abstract

This article proposes a classification method for highway service areas. POI (Point of Interest) data and surveys provide information on the area of highway service areas, distance from city centers, regional economic conditions, and population data. The clustering tendencies are analyzed using the Hopkins statistic, the number of clusters is determined using the elbow method, and the advantages and disadvantages of K-Means, FCM (fuzzy c-means), and HC (Hierarchical Clustering) are assessed using the CH (Calinski Harabasz), SC (Silhouette Coefficient), and DB (Davies-Bouldin) index. Using data from 95 highway service areas in Shaanxi Province as an example, The research findings indicate that the K-Means outperforms the FCM and HC according to all three evaluation indicators. Therefore, the article employs the K-Means to classify the 95 highway service areas in Shaanxi Province into three categories. The classification results obtained from this study provide a basis for the comprehensive development of highway service areas and the surrounding land.