Improvement of transportation cost estimation for prefabricated construction using geo-fence-based large-scale GPS data feature extraction and support vector regression

Sang Jun Ahn, Sang Uk Han, Mohamed Al-Hussein

Research output: Contribution to journalArticle

Abstract

In panelized construction, transportation is an essential process linking a manufacturing facility to a project's jobsite using hauling equipment (e.g., trucks and trailers). Accordingly, the cost associated with transportation operations is considerable compared to a traditional stick build. Nevertheless, transportation cost estimation has often relied on a fixed-cost approach, regarding the cost as part of the overhead cost, rather than conducting detailed estimation of actual transportation operations. This is because operation-level data might be challenging to collect and analyze in practice. In this regard, the prevalent use of GPS devices for construction equipment may provide an automated means of monitoring the operations of transportation equipment, and large and detailed spatial and temporal data can be generated from multiple pieces of equipment in multiple construction projects on a daily basis or even in real time. This study thus proposes a spatial and temporal data filtering and abstracting approach to transportation cost estimation using fleet GPS data which extracts equipment activities from the GPS data and accordingly predicts the transportation demands required for an individual project. From large-scale GPS data, key operation information, such as the number of trailers and durations required (i.e., transportation demands), is extracted using a geo-fence and a rule-based equipment operation analysis algorithm. Then, the extracted transportation demand information, along with related project specifications, is used to train support vector regression (SVR) models for the purpose of predicting the transportation demand in new projects, which is in turn utilized to estimate the transportation cost using the relevant transportation unit cost of the equipment. To evaluate the performance, GPS datasets collected from 221 panelized residential projects over a period of 8 months are used to train the prediction model and are compared with actual transportation costs estimated in practice. The results show that the SVR model has an accuracy of 86% and 88% in predicting the number of trailers and the duration, respectively. For the cost estimation performance, the results reveal that the average cost difference of 57% between the fixed cost and the actual transportation cost was reduced to 14% by implementing the GPS-data-based method in various project locations and for projects of various sizes. The GPS-data-based estimation approach thus is found to provide a more accurate transportation cost estimation result for various panelized construction projects, and the method improves the understanding of large-scale spatial and temporal equipment data while increasing the utilization of the GPS data already available.

Original languageEnglish
Article number101012
JournalAdvanced Engineering Informatics
Volume43
DOIs
StatePublished - 2020 Jan

Fingerprint

Prefabricated construction
Fences
Global positioning system
Feature extraction
Costs
Light trailers
Construction equipment

Keywords

  • Fleet activity recognition
  • Global positioning system (GPS) data
  • Panelized construction
  • SVR
  • Transportation cost

Cite this

@article{8aa11d2a52ba4428b4c57c3f5c637c17,
title = "Improvement of transportation cost estimation for prefabricated construction using geo-fence-based large-scale GPS data feature extraction and support vector regression",
abstract = "In panelized construction, transportation is an essential process linking a manufacturing facility to a project's jobsite using hauling equipment (e.g., trucks and trailers). Accordingly, the cost associated with transportation operations is considerable compared to a traditional stick build. Nevertheless, transportation cost estimation has often relied on a fixed-cost approach, regarding the cost as part of the overhead cost, rather than conducting detailed estimation of actual transportation operations. This is because operation-level data might be challenging to collect and analyze in practice. In this regard, the prevalent use of GPS devices for construction equipment may provide an automated means of monitoring the operations of transportation equipment, and large and detailed spatial and temporal data can be generated from multiple pieces of equipment in multiple construction projects on a daily basis or even in real time. This study thus proposes a spatial and temporal data filtering and abstracting approach to transportation cost estimation using fleet GPS data which extracts equipment activities from the GPS data and accordingly predicts the transportation demands required for an individual project. From large-scale GPS data, key operation information, such as the number of trailers and durations required (i.e., transportation demands), is extracted using a geo-fence and a rule-based equipment operation analysis algorithm. Then, the extracted transportation demand information, along with related project specifications, is used to train support vector regression (SVR) models for the purpose of predicting the transportation demand in new projects, which is in turn utilized to estimate the transportation cost using the relevant transportation unit cost of the equipment. To evaluate the performance, GPS datasets collected from 221 panelized residential projects over a period of 8 months are used to train the prediction model and are compared with actual transportation costs estimated in practice. The results show that the SVR model has an accuracy of 86{\%} and 88{\%} in predicting the number of trailers and the duration, respectively. For the cost estimation performance, the results reveal that the average cost difference of 57{\%} between the fixed cost and the actual transportation cost was reduced to 14{\%} by implementing the GPS-data-based method in various project locations and for projects of various sizes. The GPS-data-based estimation approach thus is found to provide a more accurate transportation cost estimation result for various panelized construction projects, and the method improves the understanding of large-scale spatial and temporal equipment data while increasing the utilization of the GPS data already available.",
keywords = "Fleet activity recognition, Global positioning system (GPS) data, Panelized construction, SVR, Transportation cost",
author = "Ahn, {Sang Jun} and Han, {Sang Uk} and Mohamed Al-Hussein",
year = "2020",
month = "1",
doi = "10.1016/j.aei.2019.101012",
language = "English",
volume = "43",
journal = "Advanced Engineering Informatics",
issn = "1474-0346",

}

TY - JOUR

T1 - Improvement of transportation cost estimation for prefabricated construction using geo-fence-based large-scale GPS data feature extraction and support vector regression

AU - Ahn, Sang Jun

AU - Han, Sang Uk

AU - Al-Hussein, Mohamed

PY - 2020/1

Y1 - 2020/1

N2 - In panelized construction, transportation is an essential process linking a manufacturing facility to a project's jobsite using hauling equipment (e.g., trucks and trailers). Accordingly, the cost associated with transportation operations is considerable compared to a traditional stick build. Nevertheless, transportation cost estimation has often relied on a fixed-cost approach, regarding the cost as part of the overhead cost, rather than conducting detailed estimation of actual transportation operations. This is because operation-level data might be challenging to collect and analyze in practice. In this regard, the prevalent use of GPS devices for construction equipment may provide an automated means of monitoring the operations of transportation equipment, and large and detailed spatial and temporal data can be generated from multiple pieces of equipment in multiple construction projects on a daily basis or even in real time. This study thus proposes a spatial and temporal data filtering and abstracting approach to transportation cost estimation using fleet GPS data which extracts equipment activities from the GPS data and accordingly predicts the transportation demands required for an individual project. From large-scale GPS data, key operation information, such as the number of trailers and durations required (i.e., transportation demands), is extracted using a geo-fence and a rule-based equipment operation analysis algorithm. Then, the extracted transportation demand information, along with related project specifications, is used to train support vector regression (SVR) models for the purpose of predicting the transportation demand in new projects, which is in turn utilized to estimate the transportation cost using the relevant transportation unit cost of the equipment. To evaluate the performance, GPS datasets collected from 221 panelized residential projects over a period of 8 months are used to train the prediction model and are compared with actual transportation costs estimated in practice. The results show that the SVR model has an accuracy of 86% and 88% in predicting the number of trailers and the duration, respectively. For the cost estimation performance, the results reveal that the average cost difference of 57% between the fixed cost and the actual transportation cost was reduced to 14% by implementing the GPS-data-based method in various project locations and for projects of various sizes. The GPS-data-based estimation approach thus is found to provide a more accurate transportation cost estimation result for various panelized construction projects, and the method improves the understanding of large-scale spatial and temporal equipment data while increasing the utilization of the GPS data already available.

AB - In panelized construction, transportation is an essential process linking a manufacturing facility to a project's jobsite using hauling equipment (e.g., trucks and trailers). Accordingly, the cost associated with transportation operations is considerable compared to a traditional stick build. Nevertheless, transportation cost estimation has often relied on a fixed-cost approach, regarding the cost as part of the overhead cost, rather than conducting detailed estimation of actual transportation operations. This is because operation-level data might be challenging to collect and analyze in practice. In this regard, the prevalent use of GPS devices for construction equipment may provide an automated means of monitoring the operations of transportation equipment, and large and detailed spatial and temporal data can be generated from multiple pieces of equipment in multiple construction projects on a daily basis or even in real time. This study thus proposes a spatial and temporal data filtering and abstracting approach to transportation cost estimation using fleet GPS data which extracts equipment activities from the GPS data and accordingly predicts the transportation demands required for an individual project. From large-scale GPS data, key operation information, such as the number of trailers and durations required (i.e., transportation demands), is extracted using a geo-fence and a rule-based equipment operation analysis algorithm. Then, the extracted transportation demand information, along with related project specifications, is used to train support vector regression (SVR) models for the purpose of predicting the transportation demand in new projects, which is in turn utilized to estimate the transportation cost using the relevant transportation unit cost of the equipment. To evaluate the performance, GPS datasets collected from 221 panelized residential projects over a period of 8 months are used to train the prediction model and are compared with actual transportation costs estimated in practice. The results show that the SVR model has an accuracy of 86% and 88% in predicting the number of trailers and the duration, respectively. For the cost estimation performance, the results reveal that the average cost difference of 57% between the fixed cost and the actual transportation cost was reduced to 14% by implementing the GPS-data-based method in various project locations and for projects of various sizes. The GPS-data-based estimation approach thus is found to provide a more accurate transportation cost estimation result for various panelized construction projects, and the method improves the understanding of large-scale spatial and temporal equipment data while increasing the utilization of the GPS data already available.

KW - Fleet activity recognition

KW - Global positioning system (GPS) data

KW - Panelized construction

KW - SVR

KW - Transportation cost

UR - http://www.scopus.com/inward/record.url?scp=85075261912&partnerID=8YFLogxK

U2 - 10.1016/j.aei.2019.101012

DO - 10.1016/j.aei.2019.101012

M3 - Article

AN - SCOPUS:85075261912

VL - 43

JO - Advanced Engineering Informatics

JF - Advanced Engineering Informatics

SN - 1474-0346

M1 - 101012

ER -