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

Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior./
作者:	Cordova, Eduardo.
面頁冊數:	1 online resource (99 pages)
附註:	Source: Masters Abstracts International, Volume: 84-01.
Contained By:	Masters Abstracts International84-01.
標題:	Remote sensing. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29261677click for full text (PQDT)
ISBN:	9798837528491

Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior.
Cordova, Eduardo.

Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior. - 1 online resource (99 pages)

Source: Masters Abstracts International, Volume: 84-01.

Thesis (M.S.)--San Diego State University, 2022.

Includes bibliographical references

In the past few decades, there has been an explosion of spatial data, analysis methodologies and vehicular technology's that have influenced policy and safety technology to protect drivers' lives all over the world. This research focuses on adding to the growing body of work by creating a new methodology to detect, measure and study Deviant Driving (DD) behavior. DD behavior refers to driving actions that deviate from normal driving behavior and can include aggressive, risky, and unintentional driving actions. The new methodology is called the Deviant Driving Detector (DDD), and it unifies multiple driving aspects into a single measurable variable to aid in the understanding of how and why DD is geographically distributed. The DDD was created using data acquired from the Safety Pilot Model Deployment (SPMD) initiative which created a vast and comprehensive naturalistic driving dataset (NDD). The NDD contains data from Volunteer drivers who had their driving behavior recorded in real world circumstances. The naturalistic data allowed for normal driving to be quantitatively defined in order for DD to be detected. The main objectives are to develop a novel methodological framework to detect and measure DD from naturalistic driving data for analysis. To evaluate the DDD, the geographic distribution of DD instances was compared to crash data acquired from the National Highway Traffic Safety Administration (NHTSA). Results highlight areas of interest that are susceptible to DD such as intersections and driving patterns such as familiar roads among small groups of drivers, both which are supported by existing literature. There are many benefits to detecting and curving abnormal driving behavior in terms of economic efficiency and human safety. Understanding how DD occurs can facilitate the development of new technologies, new policies, improved infrastructure, aid in the development of automated vehicles, or driver monitoring systems. Existing methods and technologies can also benefit from a new automated approach to detect changes on the road, and reduce the time needed to detect driving events from vast amounts of naturalistic driving data.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798837528491Subjects--Topical Terms:

535394
Remote sensing.
Subjects--Index Terms:

Deviant DrivingIndex Terms--Genre/Form:

542853
Electronic books.

Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior.
LDR:03515nmm a2200397K 4500 001 2357090
005 20230512095859.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798837528491
035 $a (MiAaPQ)AAI29261677
035 $a AAI29261677
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Cordova, Eduardo. $3 3697610
245 1 0 $a Detecting and Examining Spatiotemporal Patterns of Deviant Driving Behavior.
264 0 $c 2022
300 $a 1 online resource (99 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-01.
500 $a Advisor: Nara, Atsushi.
502 $a Thesis (M.S.)--San Diego State University, 2022.
504 $a Includes bibliographical references
520 $a In the past few decades, there has been an explosion of spatial data, analysis methodologies and vehicular technology's that have influenced policy and safety technology to protect drivers' lives all over the world. This research focuses on adding to the growing body of work by creating a new methodology to detect, measure and study Deviant Driving (DD) behavior. DD behavior refers to driving actions that deviate from normal driving behavior and can include aggressive, risky, and unintentional driving actions. The new methodology is called the Deviant Driving Detector (DDD), and it unifies multiple driving aspects into a single measurable variable to aid in the understanding of how and why DD is geographically distributed. The DDD was created using data acquired from the Safety Pilot Model Deployment (SPMD) initiative which created a vast and comprehensive naturalistic driving dataset (NDD). The NDD contains data from Volunteer drivers who had their driving behavior recorded in real world circumstances. The naturalistic data allowed for normal driving to be quantitatively defined in order for DD to be detected. The main objectives are to develop a novel methodological framework to detect and measure DD from naturalistic driving data for analysis. To evaluate the DDD, the geographic distribution of DD instances was compared to crash data acquired from the National Highway Traffic Safety Administration (NHTSA). Results highlight areas of interest that are susceptible to DD such as intersections and driving patterns such as familiar roads among small groups of drivers, both which are supported by existing literature. There are many benefits to detecting and curving abnormal driving behavior in terms of economic efficiency and human safety. Understanding how DD occurs can facilitate the development of new technologies, new policies, improved infrastructure, aid in the development of automated vehicles, or driver monitoring systems. Existing methods and technologies can also benefit from a new automated approach to detect changes on the road, and reduce the time needed to detect driving events from vast amounts of naturalistic driving data.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Remote sensing. $3 535394
650 4 $a Geographic information science. $3 3432445
650 4 $a Behavioral sciences. $3 529833
650 4 $a Transportation. $3 555912
653 $a Deviant Driving
653 $a Unsafe driving
653 $a Spatiotemporal patterns
653 $a Driving behavior
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0370
690 $a 0799
690 $a 0602
690 $a 0709
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a San Diego State University. $b Geography. $3 3177545
773 0 $t Masters Abstracts International $g 84-01.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29261677 $z click for full text (PQDT)