東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ subject:"Autonomous vehicles." ]

切換: 標籤 | MARC模式 | ISBD

Know Your User: Building a Predictiv...

Milner, Mattie Nicole.

FindBook

Google Book

Amazon

博客來

Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars./
作者:	Milner, Mattie Nicole.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	200 p.
附註:	Source: Dissertations Abstracts International, Volume: 81-11, Section: B.
Contained By:	Dissertations Abstracts International81-11B.
標題:	Transportation. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27838004
ISBN:	9798643171157

Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars.
Milner, Mattie Nicole.

Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 200 p.

Source: Dissertations Abstracts International, Volume: 81-11, Section: B.

Thesis (Ph.D.)--Embry-Riddle Aeronautical University, 2020.

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

INTRODUCTION: This dissertation identifies factors significantly predicting participants' preference for riding in an autonomous vehicle rather than flying on a commercial aircraft. A plethora of research has investigated these two transportation industries independently; however, scarcely any research has considered the impact these two industries will have on each other. Travelers' preference for riding in an autonomous vehicle rather than a commercial aircraft was investigated through four different scenarios.METHOD: A regression equation was created to predict participants' preferred travel method and validated through a two-stage process. Stage 1 involved the creation of the regression equation, and a total of 1,008 participants responded to an online survey, providing information on demographics, travel-related behavior, and their preference for riding in an autonomous vehicle rather than flying on a commercial aircraft. Stage 2 involved validation of the regression equation, and 1,008 participants responded to the same online survey. Stage 2 participants' scores were predicted using the regression equation created in Stage 1. Then, their predicted scores and actual scores were compared to validate the equation throughout four different travel scenarios.RESULTS: In Stage 1, a backward stepwise regression assessed the twenty predictive factors (age, gender, ethnicity, social class, price, perceived value, familiarity, fun factor, wariness of new technology, personality (openness, conscientiousness, extraversion, agreeableness, and neuroticism), general vehicle affect, general airplane affect, vehicle comfort, vehicle external factors, airplane comfort, and airplane external factors). These factors were tested in four different scenarios, which varied only in the length of time participants would spend traveling.CONCLUSION: A predictive model was created for each scenario, and then all four models were validated in Stage 2 using participants' predicted scores and actual scores. Models were validated using a t-test, correlation, and comparison of cross-validated R2. The most robust model was for the four-hour trip, with six variables significantly predicting participants' preferred travel method, which accounted for 50.7% of the variance in the model (50.1% adjusted). Upper Social Class, Vehicle Affect, Airplane Affect, and Vehicle Comfort were the only significant predictors throughout all four scenarios. These four predictors will help other researchers and experts in the vehicle industry identify the first adopters of this new technology. The implications of the results and suggestions for future research are discussed.

ISBN: 9798643171157Subjects--Topical Terms:

555912
Transportation.
Subjects--Index Terms:

Autonomous vehicle preference

Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars.
LDR:03719nmm a2200313 4500 001 2270042
005 20200921070020.5
008 220629s2020 ||||||||||||||||| ||eng d
020 $a 9798643171157
035 $a (MiAaPQ)AAI27838004
035 $a AAI27838004
040 $a MiAaPQ $c MiAaPQ
100 1 $a Milner, Mattie Nicole. $3 3547411
245 1 0 $a Know Your User: Building a Predictive Model of Consumer Preference for Driverless Cars.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 200 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-11, Section: B.
500 $a Advisor: Rice, Stephen.
502 $a Thesis (Ph.D.)--Embry-Riddle Aeronautical University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a INTRODUCTION: This dissertation identifies factors significantly predicting participants' preference for riding in an autonomous vehicle rather than flying on a commercial aircraft. A plethora of research has investigated these two transportation industries independently; however, scarcely any research has considered the impact these two industries will have on each other. Travelers' preference for riding in an autonomous vehicle rather than a commercial aircraft was investigated through four different scenarios.METHOD: A regression equation was created to predict participants' preferred travel method and validated through a two-stage process. Stage 1 involved the creation of the regression equation, and a total of 1,008 participants responded to an online survey, providing information on demographics, travel-related behavior, and their preference for riding in an autonomous vehicle rather than flying on a commercial aircraft. Stage 2 involved validation of the regression equation, and 1,008 participants responded to the same online survey. Stage 2 participants' scores were predicted using the regression equation created in Stage 1. Then, their predicted scores and actual scores were compared to validate the equation throughout four different travel scenarios.RESULTS: In Stage 1, a backward stepwise regression assessed the twenty predictive factors (age, gender, ethnicity, social class, price, perceived value, familiarity, fun factor, wariness of new technology, personality (openness, conscientiousness, extraversion, agreeableness, and neuroticism), general vehicle affect, general airplane affect, vehicle comfort, vehicle external factors, airplane comfort, and airplane external factors). These factors were tested in four different scenarios, which varied only in the length of time participants would spend traveling.CONCLUSION: A predictive model was created for each scenario, and then all four models were validated in Stage 2 using participants' predicted scores and actual scores. Models were validated using a t-test, correlation, and comparison of cross-validated R2. The most robust model was for the four-hour trip, with six variables significantly predicting participants' preferred travel method, which accounted for 50.7% of the variance in the model (50.1% adjusted). Upper Social Class, Vehicle Affect, Airplane Affect, and Vehicle Comfort were the only significant predictors throughout all four scenarios. These four predictors will help other researchers and experts in the vehicle industry identify the first adopters of this new technology. The implications of the results and suggestions for future research are discussed.
590 $a School code: 1076.
650 4 $a Transportation. $3 555912
650 4 $a Artificial intelligence. $3 516317
650 4 $a Autonomous vehicles. $3 2179092
653 $a Autonomous vehicle preference
690 $a 0709
690 $a 0800
710 2 $a Embry-Riddle Aeronautical University. $b Human Factors and Systems. $3 2092350
773 0 $t Dissertations Abstracts International $g 81-11B.
790 $a 1076
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27838004