東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Automatic Methods For Exposure Assessment During Lifting.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Automatic Methods For Exposure Assessment During Lifting./
Author:	Greene, Runyu.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	142 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
Subject:	Industrial engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28715106
ISBN:	9798535558349

Automatic Methods For Exposure Assessment During Lifting.
Greene, Runyu.

Automatic Methods For Exposure Assessment During Lifting. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 142 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2021.

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

As a leading cause of low back pain (LBP), manual lifting is highly prevalent in today's workplace, resulting in significant costs to individuals, organizations, and society. Current lifting assessment methods are dependent on manual observation and measurement and are therefore inadequate to include multiple risk factors or perform measurements for an extended period of time for comprehensive assessment. Computer vision can potentially address this issue by objectively and continuously measuring multiple exposure factors without interfering with work. The objective of my thesis research is to develop computer vision-based automated lifting analysis methods for objective, comprehensive, and robust risk assessment that can be readily adopted in industry.Leveraging a computationally efficient computer vision algorithm that identifies the human using motion-based background subtraction, two lifting assessment methods were developed to estimate lifting postures and trunk kinematics, risk factors of LBP that are difficult to measure in the field. The first method utilized data from computer-generated mannequin lifting postures to train an algorithm to classify lifting postures into stand, stoop, and squat. Using computer vision extracted features, the second method estimates trunk kinematics including trunk flexion angle, speed, and acceleration.Practical computer vision methods have enabled the measurement of LBP risk factors in the workplace for comprehensive lifting assessment. The next study investigated the effects of incorporating trunk kinematics in the Reviser NIOSH Lifting Equation (RNLE) using the diverse database of video recordings, exposure data, and health outcomes collected during a prospective study, ascertaining trunk kinematics using computer vision. Statistical analysis revealed significant correlation between trunk kinematics and LBP, while no significant correlation was observed between trunk kinematics and RNLE variables. Additionally, the addition of trunk kinematics to the revised RNLE improved the predictability of the model for LBP risk associated with lifting.The computer vision methods are expected to be implemented as an automated lifting assessment instrument. Results of a related project of visualizing risk factors of repetitive hand activities are included. To further complement the lifting assessment instrument, the visualization methodology is expected to be incorporated to offer animated data visualization synchronized with video for identifying improvements and facilitating communication.

ISBN: 9798535558349Subjects--Topical Terms:

526216
Industrial engineering.
Subjects--Index Terms:

Risk factors

Automatic Methods For Exposure Assessment During Lifting.
LDR:03707nmm a2200373 4500 001 2348632
005 20220912135622.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798535558349
035 $a (MiAaPQ)AAI28715106
035 $a AAI28715106
040 $a MiAaPQ $c MiAaPQ
100 1 $a Greene, Runyu. $3 3688002
245 1 0 $a Automatic Methods For Exposure Assessment During Lifting.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 142 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Radwin, Robert.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a As a leading cause of low back pain (LBP), manual lifting is highly prevalent in today's workplace, resulting in significant costs to individuals, organizations, and society. Current lifting assessment methods are dependent on manual observation and measurement and are therefore inadequate to include multiple risk factors or perform measurements for an extended period of time for comprehensive assessment. Computer vision can potentially address this issue by objectively and continuously measuring multiple exposure factors without interfering with work. The objective of my thesis research is to develop computer vision-based automated lifting analysis methods for objective, comprehensive, and robust risk assessment that can be readily adopted in industry.Leveraging a computationally efficient computer vision algorithm that identifies the human using motion-based background subtraction, two lifting assessment methods were developed to estimate lifting postures and trunk kinematics, risk factors of LBP that are difficult to measure in the field. The first method utilized data from computer-generated mannequin lifting postures to train an algorithm to classify lifting postures into stand, stoop, and squat. Using computer vision extracted features, the second method estimates trunk kinematics including trunk flexion angle, speed, and acceleration.Practical computer vision methods have enabled the measurement of LBP risk factors in the workplace for comprehensive lifting assessment. The next study investigated the effects of incorporating trunk kinematics in the Reviser NIOSH Lifting Equation (RNLE) using the diverse database of video recordings, exposure data, and health outcomes collected during a prospective study, ascertaining trunk kinematics using computer vision. Statistical analysis revealed significant correlation between trunk kinematics and LBP, while no significant correlation was observed between trunk kinematics and RNLE variables. Additionally, the addition of trunk kinematics to the revised RNLE improved the predictability of the model for LBP risk associated with lifting.The computer vision methods are expected to be implemented as an automated lifting assessment instrument. Results of a related project of visualizing risk factors of repetitive hand activities are included. To further complement the lifting assessment instrument, the visualization methodology is expected to be incorporated to offer animated data visualization synchronized with video for identifying improvements and facilitating communication.
590 $a School code: 0262.
650 4 $a Industrial engineering. $3 526216
650 4 $a Laboratories. $3 531588
650 4 $a Physiology. $3 518431
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Estimates. $3 3561047
650 4 $a Gender. $3 2001319
650 4 $a Risk factors. $3 3543864
650 4 $a Questionnaires. $3 529568
650 4 $a Injuries. $3 3563044
650 4 $a Purchasing. $3 652497
650 4 $a Back pain. $3 3563101
650 4 $a Age. $3 1486010
650 4 $a Variables. $3 3548259
650 4 $a Psychological aspects. $3 1611707
650 4 $a Posture. $3 667530
650 4 $a Biomechanics. $3 548685
653 $a Risk factors
653 $a Lifting postures
653 $a Back pain
653 $a Computer vision methods
690 $a 0546
690 $a 0648
690 $a 0719
690 $a 0354
710 2 $a The University of Wisconsin - Madison. $b Industrial Engineering. $3 2093809
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0262
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28715106