Blue collar laborers’ travel pattern recognition: Machine learning classifier approach

Aya Hasan Alkhereibi,Shahram Tahmasseby,Semira Mohammed,Deepti Muley

doi:10.1016/j.trip.2021.100506

Aya Hasan Alkhereibi, Shahram Tahmasseby + Show 2 more

Open Access

https://doi.org/10.1016/j.trip.2021.100506

Copy DOI

Abstract

This paper proposes a pattern recognition model to develop clusters of homogenous activities for blue-collar workers in the State of Qatar. The activity-based data from the travel diary of 1051 blue-collar workers collected by the Ministry of Transportation and Communication (MoTC) in Qatar was used for analysis. A pattern recognition model is applied to a revealed preference (RP) survey obtained from the Ministry of Transportation and Communication (MoTC) in Qatar for the travel diary for blue-collar workers. Raw data preprocessing and outliers detection and filtering algorithms were applied at the first stage of the analysis, and consequently, an activity-based travel matrix was developed for each household. The research methodology undertaken in this paper comprises a combination of different machine learning techniques, predominantly by applying clustering and classification methods. A bagged Clustering algorithm was employed to identify the number of clusters, then the C-Means algorithm and the Pamk algorithm were implemented to validate the results. Meanwhile, the interdependencies between the resulted clusters and the socio-demographic attributes for the households were examined using crosstabulation analysis. The study results show significant diversity amongst the clusters in terms of trip purpose, modal split, destination choice, and occupation. Furthermore, whilst the Bagged Clusters and Pamk Clusters techniques on the three attributes yielded similar results, the Cmeans Clusters differed significantly in a number of the clusters. Applying such pattern recognition models on big and complex activity datasets could assist transport planners to understand the travel needs of segments of the population well and formulating better-informed strategies.

Highlights

Transport modeling is applied as an effective tool to manage sus tainable development in most developed countries
The activity-based approach is mainly derived from the analysis of activity sequences that are distributed in different areas and places. It highlights the effect of demographic attributes such as gender, income, and occupation, as well as spatial characteristics on individual travel behavior. As such the activity-based travel analysis can give an index on the reliability of the urban network and transportation infrastructure since it evaluates the travel sequences for a defined purpose of activities, which is influenced by place distributions, and travel modes
It appears that CMeans and Pamk bring about an even distribution compared to the Bagged Clustering technique

Summary

Introduction

Transport modeling is applied as an effective tool to manage sus tainable development in most developed countries. Considerable in vestments have been made in transportation planning and policy development to observe travel behaviors and forecast future travel de mand These forecasting tools must integrate the design of transport systems, based on global infrastructures and the inclusion of the travel behavior of the inhabitants of the study area. The activity-based approach is mainly derived from the analysis of activity sequences that are distributed in different areas and places It highlights the effect of demographic attributes such as gender, income, and occupation, as well as spatial characteristics on individual travel behavior. As such the activity-based travel analysis can give an index on the reliability of the urban network and transportation infrastructure since it evaluates the travel sequences for a defined purpose of activities, which is influenced by place distributions, and travel modes

Objectives

Methods

Results

Conclusion