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

Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation./
作者:	Lee, Min Hun.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	165 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28648408
ISBN:	9798538136599

Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation.
Lee, Min Hun.

Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 165 p.

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

Thesis (Ph.D.)--Carnegie Mellon University, 2021.

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

Rapid advances in machine learning (ML) have made it applicable to healthcare practices. However, the deployment of these ML models remains a challenge due to the lack of user-centered designs and model interpretability and adaptability. This thesis introduces an interactive hybrid approach that combines an ML model with a rule-based model from experts to support transparent interactions with a user, but also iteratively be tuned with user inputs (e.g. therapist's feedback or patient's motions) to improve AI and robotic systems. Through iterative engagements with therapists and post-stroke patients, we explore how humans and artificial intelligence (AI) and robotic systems can collaborate to improve practices of physical stroke rehabilitation therapy: 1) human-AI collaborative decision-making on rehabilitation assessment for therapists and (2) human-robot collaborative rehabilitation therapy for post-stroke survivors. For human-AI collaborative decision-making, we found that our interactive system with transparent, patient-specific analysis significantly reduces therapists' efforts and improves their agreement level on rehabilitation assessment. In addition, therapists can provide feedback on our system for a more personalized prediction and a more efficient development of ML models. For human-robot collaborative rehabilitation therapy, we found that our system can be tuned with post-stroke survivor's data to generate personalized corrective feedback. Both therapists and post-stroke survivors appreciated the potential benefits of our system to achieve more systematic management and improve post-stroke survivors' self-efficacy and motivation in rehabilitation. Overall, this thesis discusses the value of iterative engagement with stakeholders and making a system explainable and interactive to create effective human-AI/robot collaboration on a complex task.

ISBN: 9798538136599Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Explainable and Interactive Machine Learning

Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation.
LDR:03261nmm a2200397 4500 001 2348070
005 20220906075157.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798538136599
035 $a (MiAaPQ)AAI28648408
035 $a AAI28648408
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lee, Min Hun. $3 3687390
245 1 0 $a Interactive Hybrid Intelligence Systems for Human-AI/Robot Collaboration: Improving the Practices of Physical Stroke Rehabilitation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 165 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Siewiorek, Daniel P.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Rapid advances in machine learning (ML) have made it applicable to healthcare practices. However, the deployment of these ML models remains a challenge due to the lack of user-centered designs and model interpretability and adaptability. This thesis introduces an interactive hybrid approach that combines an ML model with a rule-based model from experts to support transparent interactions with a user, but also iteratively be tuned with user inputs (e.g. therapist's feedback or patient's motions) to improve AI and robotic systems. Through iterative engagements with therapists and post-stroke patients, we explore how humans and artificial intelligence (AI) and robotic systems can collaborate to improve practices of physical stroke rehabilitation therapy: 1) human-AI collaborative decision-making on rehabilitation assessment for therapists and (2) human-robot collaborative rehabilitation therapy for post-stroke survivors. For human-AI collaborative decision-making, we found that our interactive system with transparent, patient-specific analysis significantly reduces therapists' efforts and improves their agreement level on rehabilitation assessment. In addition, therapists can provide feedback on our system for a more personalized prediction and a more efficient development of ML models. For human-robot collaborative rehabilitation therapy, we found that our system can be tuned with post-stroke survivor's data to generate personalized corrective feedback. Both therapists and post-stroke survivors appreciated the potential benefits of our system to achieve more systematic management and improve post-stroke survivors' self-efficacy and motivation in rehabilitation. Overall, this thesis discusses the value of iterative engagement with stakeholders and making a system explainable and interactive to create effective human-AI/robot collaboration on a complex task.
590 $a School code: 0041.
650 4 $a Computer science. $3 523869
650 4 $a Robotics. $3 519753
650 4 $a Physical therapy. $3 588713
650 4 $a Collaboration. $3 3556296
650 4 $a Artificial intelligence. $3 516317
653 $a Explainable and Interactive Machine Learning
653 $a Human AI/Robot Interaction
653 $a Hybrid Intelligence
653 $a Intelligent Decision Support Systems
653 $a Physical Stroke Rehabilitation Therapy
653 $a Socially Assistive Robotics
690 $a 0984
690 $a 0771
690 $a 0382
690 $a 0800
710 2 $a Carnegie Mellon University. $b Electrical and Computer Engineering. $3 2094139
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0041
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28648408