Clustering of public transport operation using K-means

Abstract

This paper describes a methodology for analysing the operation of transport buses, using a simplified generic approach. In recent years, location systems that utilize GPS data have become widespread, including their use for monitoring the operation of buses. In this paper, we simplify the bus routes, monitoring process, present new insights using K-means, and enhance their effectiveness. The primary focus of this work is data collection, subsequent data analysis and reporting, for use in schedule adjustments and resource allocation. The experimental data for this study is obtained from the operation of public transport buses at the main campus of Universiti Kebangsaan Malaysia (UKM), where several buses operate on a 30-minute interval over three different concurrent routes. The proposed approach to data analysis is based on three attributes of the data being collected, namely time, volume and quality. The effectiveness of the proposed approach described and discussed.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 18 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.