PAC: Partial Area Cluster for adjusting the distribution of transportation platforms in modern cities

TL;DR

This paper introduces PAC, a clustering-based method to optimize transportation platform distribution in cities, significantly increasing public transport utilization.

Contribution

The paper presents a novel partial area cluster (PAC) method based on K-means to improve platform distribution efficiency in urban transportation systems.

Findings

Public transport utilization increased by 20%

PAC effectively optimizes platform placement

The method is practical for city transportation planning

Abstract

In the modern city, the utilization rate of public transportation attached importance to the efficiency of public traffic. However, the unreasonable distribution of transportation platforms results in a low utilization rate. In this paper, we researched and evaluated the distribution of platforms -- bus and subway -- and proposed a method, called "partial area cluster" (PAC), to improve the utilization by changing and renewing the original distribution. The novel method was based on the K-means algorithm in the field of machine learning. PAC worked to search the suitable bus platforms as the center and modified the original one to the subway. Experience has shown that the use of public transport resources has increased by 20%. The study uses a similar cluster algorithm to solve transport networks' problems in a novel but practical term. As a result, the PAC is expected to be used extensively in the transportation system construction process.