國立虎尾科技大學 |

Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems // Mostaan Lotfalian Saremi.
作者:	Lotfalian Saremi, Mostaan,
面頁冊數:	1 electronic resource (140 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144078
ISBN:	9798383181683

Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems /
Lotfalian Saremi, Mostaan,

Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems /Mostaan Lotfalian Saremi. - 1 electronic resource (140 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

In today's rapidly evolving world, intelligent systems are taking on a crucial role in assisting humans across various fields, spanning healthcare to transportation. Within this context, the level of user reliance becomes a crucial factor determining how effectively intelligent systems can support human decision-makers in numerous domains. How much a user should rely on an intelligent system to maximize the benefits is an open question. In this dissertation we study the dynamics of human - AI interaction, aiming to investigate the optimal level of trust and reliance that leads to effective collaboration.In this research, we utilize a multidimensional approach that combines computational modelling and human subject experimentation. Through the lens of computational simulation, we study the optimal reliance level that is needed to achieve the maximum performance in human-decision support system partnering. By analyzing various characteristics, our research unearths how user should appropriately rely on intelligent systems to maximize collaboration performance. This novel perspective helps system designers to build an appropriate level of reliance on AI systems effectively. Transitioning to empirical study, we develop an engaging computer game to investigate human trust and reliance on embedded AI in solving classification problems. The experimental findings shed light on the effect of transparency, robustness and fairness in shaping human-AI partnering. Notably, transparency, robustness and fairness enhancements correlate with improved collaboration performance, albeit at the cost of added mental workload. Furthermore, our results show no significant differences in gender performance and reliance on AI, highlighting the systems' universal impact.Finally, we verify our research using continuous design problems, bridging different problem classes. This cross-domain investigation offers a comprehensive understanding of how reliance and system design intricately intertwine to facilitate effective human-AI collaboration. By unveiling the underpinnings of these interactions, this research provides invaluable insights into designing AI systems that are not only technically capable but also seamlessly integrated with human decision-making processes. Ultimately, these findings pave the way for optimizing the synergy between humans and intelligent systems, driving us towards a future of enhanced collaboration and improved decision- making across various domain.

English

ISBN: 9798383181683Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Human computer interaction

Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems /
LDR:03973nam a22004333i 4500 001 1157758
005 20250603111409.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798383181683
035 $a (MiAaPQD)AAI31144078
035 $a AAI31144078
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Lotfalian Saremi, Mostaan, $e author. $3 1484024
245 1 0 $a Impact of Human Reliance on Collaboration With Intelligent Decision Support Systems / $c Mostaan Lotfalian Saremi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (140 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: Dissertations Abstracts International, Volume: 86-01, Section: B.
500 $a Advisors: Asan, Onur Committee members: Bayrak, Alparslan Emrah; Liao, Ting; Dominick, Peter.
502 $b Ph.D. $c Stevens Institute of Technology $d 2024.
520 $a In today's rapidly evolving world, intelligent systems are taking on a crucial role in assisting humans across various fields, spanning healthcare to transportation. Within this context, the level of user reliance becomes a crucial factor determining how effectively intelligent systems can support human decision-makers in numerous domains. How much a user should rely on an intelligent system to maximize the benefits is an open question. In this dissertation we study the dynamics of human - AI interaction, aiming to investigate the optimal level of trust and reliance that leads to effective collaboration.In this research, we utilize a multidimensional approach that combines computational modelling and human subject experimentation. Through the lens of computational simulation, we study the optimal reliance level that is needed to achieve the maximum performance in human-decision support system partnering. By analyzing various characteristics, our research unearths how user should appropriately rely on intelligent systems to maximize collaboration performance. This novel perspective helps system designers to build an appropriate level of reliance on AI systems effectively. Transitioning to empirical study, we develop an engaging computer game to investigate human trust and reliance on embedded AI in solving classification problems. The experimental findings shed light on the effect of transparency, robustness and fairness in shaping human-AI partnering. Notably, transparency, robustness and fairness enhancements correlate with improved collaboration performance, albeit at the cost of added mental workload. Furthermore, our results show no significant differences in gender performance and reliance on AI, highlighting the systems' universal impact.Finally, we verify our research using continuous design problems, bridging different problem classes. This cross-domain investigation offers a comprehensive understanding of how reliance and system design intricately intertwine to facilitate effective human-AI collaboration. By unveiling the underpinnings of these interactions, this research provides invaluable insights into designing AI systems that are not only technically capable but also seamlessly integrated with human decision-making processes. Ultimately, these findings pave the way for optimizing the synergy between humans and intelligent systems, driving us towards a future of enhanced collaboration and improved decision- making across various domain.
546 $a English
590 $a School code: 0733
650 4 $a Computer science. $3 573171
650 4 $a Systems science. $3 1148479
653 $a Human computer interaction
653 $a Reliance
653 $a Robustness
653 $a Transparency
653 $a Trust
690 $a 0790
690 $a 0984
690 $a 0800
710 2 $a Stevens Institute of Technology. $b School of Systems and Enterprises. $3 1185313
720 1 $a Asan, Onur $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 0733
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144078