國立虎尾科技大學 |

Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions./
Author:	Akpobome, Samson.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
Description:	211 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
Contained By:	Dissertations Abstracts International83-11B.
Subject:	Artificial intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971247
ISBN:	9798426822368

Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions.
Akpobome, Samson.

Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 211 p.

Source: Dissertations Abstracts International, Volume: 83-11, Section: B.

Thesis (Ph.D.)--Northcentral University, 2022.

This item must not be sold to any third party vendors.

This research study investigated the low descriptive quality of the traditional univariate time series model on transport vehicle passenger-carrying capacity forecasting despite its robustness in forecast accuracy. The purpose of this quantitative, non-experimental, descriptive, and correlational study was to identify the factors behind the low descriptive quality of the traditional univariate time series model on transport vehicle volume forecasting. The theory of structuration was adopted as the theoretical framework for this study to capture the core concept of the duality of structure using the City of Chicago transit dataset. The quantitative research methodology was applied for this study because of its suitability to understanding the statistically significant correlation between day type variable and the total transport vehicle volume, the statistically significant correlation between the standard univariate forecasting time series model and the regressed univariate forecasting time series model based on the lowest information lost criteria and on the forecasting accuracy, and causative relationship between the bus variable, rail variable, and total variables. The result confirmed a statistically significant correlation between the day type and the total rides variable. The result further showed a statistically significant correlation between the standard univariate forecasting time series model and the regressed univariate forecasting model based on the lowest information lost criteria and forecast accuracy. The Granger causality test established statistically significant bidirectional correlation relationships between the bus, the total rides, and the rail boarding variables. The appreciation by public transportation stakeholders of the bidirectional and other complex multiplicity interaction of system variables requiring a robust and automated resource allocation tool provides practical implications for city planners and policymakers to address urban congestion problems and mobility challenges. Recommendations include developing forecasting models with other exogenous predictor variables to provide descriptive capabilities and using hybrid statistical forecasting models. Future research should include studies on the impacts of the categorical variable levels on the forecast variable and extend the classical univariate forecasting ARIMA model to integrate the variance component analysis (ANOVA) as a hybrid model.

ISBN: 9798426822368Subjects--Topical Terms:

559380
Artificial intelligence.
Subjects--Index Terms:

Data science

Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions.
LDR:03580nam a2200349 4500 001 1104581
005 20230619080054.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798426822368
035 $a (MiAaPQ)AAI28971247
035 $a AAI28971247
040 $a MiAaPQ $c MiAaPQ
100 1 $a Akpobome, Samson. $3 1413443
245 1 0 $a Forecasting Short-Range Transport Vehicle Total Volume to Support Resource Allocation Decisions.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 211 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
500 $a Advisor: Harkiolakis, Nick.
502 $a Thesis (Ph.D.)--Northcentral University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a This research study investigated the low descriptive quality of the traditional univariate time series model on transport vehicle passenger-carrying capacity forecasting despite its robustness in forecast accuracy. The purpose of this quantitative, non-experimental, descriptive, and correlational study was to identify the factors behind the low descriptive quality of the traditional univariate time series model on transport vehicle volume forecasting. The theory of structuration was adopted as the theoretical framework for this study to capture the core concept of the duality of structure using the City of Chicago transit dataset. The quantitative research methodology was applied for this study because of its suitability to understanding the statistically significant correlation between day type variable and the total transport vehicle volume, the statistically significant correlation between the standard univariate forecasting time series model and the regressed univariate forecasting time series model based on the lowest information lost criteria and on the forecasting accuracy, and causative relationship between the bus variable, rail variable, and total variables. The result confirmed a statistically significant correlation between the day type and the total rides variable. The result further showed a statistically significant correlation between the standard univariate forecasting time series model and the regressed univariate forecasting model based on the lowest information lost criteria and forecast accuracy. The Granger causality test established statistically significant bidirectional correlation relationships between the bus, the total rides, and the rail boarding variables. The appreciation by public transportation stakeholders of the bidirectional and other complex multiplicity interaction of system variables requiring a robust and automated resource allocation tool provides practical implications for city planners and policymakers to address urban congestion problems and mobility challenges. Recommendations include developing forecasting models with other exogenous predictor variables to provide descriptive capabilities and using hybrid statistical forecasting models. Future research should include studies on the impacts of the categorical variable levels on the forecast variable and extend the classical univariate forecasting ARIMA model to integrate the variance component analysis (ANOVA) as a hybrid model.
590 $a School code: 1443.
650 4 $a Artificial intelligence. $3 559380
650 4 $a Information technology. $3 559429
653 $a Data science
653 $a Technology
690 $a 0800
690 $a 0489
710 2 $a Northcentral University. $b School of Business and Technology Management. $3 1180957
773 0 $t Dissertations Abstracts International $g 83-11B.
790 $a 1443
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971247