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

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Machine Learning Applications in Surface Transportation Systems: A Systematic Review.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning Applications in Surface Transportation Systems: A Systematic Review./
作者:	Behrooz, Hojat.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	65 p.
附註:	Source: Masters Abstracts International, Volume: 83-07.
Contained By:	Masters Abstracts International83-07.
標題:	Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28864400
ISBN:	9798762196819

Machine Learning Applications in Surface Transportation Systems: A Systematic Review.
Behrooz, Hojat.

Machine Learning Applications in Surface Transportation Systems: A Systematic Review. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 65 p.

Source: Masters Abstracts International, Volume: 83-07.

Thesis (Master's)--Stevens Institute of Technology, 2021.

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

Surface transportation evolves through technological advancements using parallel knowledge areas such as machine learning (ML). While ML innovations have influenced many industries, the transportation industry has not yet taken full advantage of the ML and processing power capabilities for applied projects. To evaluate the gap, I utilize a systematic review approach to locate, categorize, and synthesize the principal concept of research papers in surface transportation systems using ML algorithms and decompose them into their fundamental elements. I explore more than 100 articles, literature review papers, and books. Results show while 80% of papers concentrate on forecasting, multi-layer perceptions, long-short term memory, supporting vector machine, random forest, K nearest neighbored, K number of centroids clustering (K-mean), supporting vector regression, and fuzzy logic are the most preferred ML algorithms.Sophisticated and powerful ML algorithms, including graph neural networks, generative adversarial network, and variational autoencoder have been minimally used. The root cause analysis shows a lack of effective collaboration between the ML and transportation experts, resulting in the most accessible transportation applications used as a case study to test or enhance a given ML algorithm and not necessarily to enhance a mobility or safety issue. Additionally, the transportation community does not define transportation issues clearly and does not provide transportation datasets publicly. The transportation sector must offer an open-source platform to showcase the sector's concerns and build high-quality, high-frequency open-access integrated spatiotemporal datasets for outside knowledge areas, including artificial intelligence. The plat-form will enable ML experts to use algorithms on applied transportation problems to accelerate technology advancements while directly benefiting society and the economy by resolving mobility and safety issues. This dissertation provides the basis for an open-source platform that re-searchers can utilize to identify the existing literature where ML algorithms have been used to solve a surface transportation problem and identify research opportunities and gaps for further research and development.

ISBN: 9798762196819Subjects--Topical Terms:

586835
Engineering.
Subjects--Index Terms:

Deep learning

Machine Learning Applications in Surface Transportation Systems: A Systematic Review.
LDR:03521nmm a2200397 4500 001 2350039
005 20221020123839.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798762196819
035 $a (MiAaPQ)AAI28864400
035 $a AAI28864400
040 $a MiAaPQ $c MiAaPQ
100 1 $a Behrooz, Hojat. $3 3689481
245 1 0 $a Machine Learning Applications in Surface Transportation Systems: A Systematic Review.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 65 p.
500 $a Source: Masters Abstracts International, Volume: 83-07.
500 $a Advisor: Hayeri, Yeganeh M.
502 $a Thesis (Master's)--Stevens Institute of Technology, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Surface transportation evolves through technological advancements using parallel knowledge areas such as machine learning (ML). While ML innovations have influenced many industries, the transportation industry has not yet taken full advantage of the ML and processing power capabilities for applied projects. To evaluate the gap, I utilize a systematic review approach to locate, categorize, and synthesize the principal concept of research papers in surface transportation systems using ML algorithms and decompose them into their fundamental elements. I explore more than 100 articles, literature review papers, and books. Results show while 80% of papers concentrate on forecasting, multi-layer perceptions, long-short term memory, supporting vector machine, random forest, K nearest neighbored, K number of centroids clustering (K-mean), supporting vector regression, and fuzzy logic are the most preferred ML algorithms.Sophisticated and powerful ML algorithms, including graph neural networks, generative adversarial network, and variational autoencoder have been minimally used. The root cause analysis shows a lack of effective collaboration between the ML and transportation experts, resulting in the most accessible transportation applications used as a case study to test or enhance a given ML algorithm and not necessarily to enhance a mobility or safety issue. Additionally, the transportation community does not define transportation issues clearly and does not provide transportation datasets publicly. The transportation sector must offer an open-source platform to showcase the sector's concerns and build high-quality, high-frequency open-access integrated spatiotemporal datasets for outside knowledge areas, including artificial intelligence. The plat-form will enable ML experts to use algorithms on applied transportation problems to accelerate technology advancements while directly benefiting society and the economy by resolving mobility and safety issues. This dissertation provides the basis for an open-source platform that re-searchers can utilize to identify the existing literature where ML algorithms have been used to solve a surface transportation problem and identify research opportunities and gaps for further research and development.
590 $a School code: 0733.
650 4 $a Engineering. $3 586835
650 4 $a Systems science. $3 3168411
650 4 $a Artificial intelligence. $3 516317
653 $a Deep learning
653 $a Intelligent transportation systems
653 $a Machine learning
653 $a Surface transportation systems
653 $a System engineering
653 $a Systematic review
690 $a 0537
690 $a 0454
690 $a 0800
690 $a 0790
710 2 $a Stevens Institute of Technology. $b School of Systems and Enterprises. $3 3177200
773 0 $t Masters Abstracts International $g 83-07.
790 $a 0733
791 $a Master's
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28864400