國立虎尾科技大學 |

A Robust Data-Driven Framework for Artificial Intelligent Systems /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A Robust Data-Driven Framework for Artificial Intelligent Systems // Quoc H Nguyen.
作者:	Nguyen, Quoc H.,
面頁冊數:	1 electronic resource (189 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
標題:	Industrial engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31333722
ISBN:	9798383530917

A Robust Data-Driven Framework for Artificial Intelligent Systems /
Nguyen, Quoc H.,

A Robust Data-Driven Framework for Artificial Intelligent Systems /Quoc H Nguyen. - 1 electronic resource (189 pages)

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

Artificial Intelligence (AI) systems have demonstrated remarkable performance across various domains. However, their robustness remains a critical concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI systems by focusing on two key aspects: data robustness and model robustness. Data robustness poses significant challenges, including data shift, concept shifting, limited and imbalanced datasets, and interoperability issues in IoT systems for data collection. Existing methods fall short in handling dynamic business objectives and evolving data landscapes effectively. To bridge these gaps, we propose an IoT framework that ensures interoperability, seamless communication, and scalability for efficient data collection. Furthermore, we employ data-centric approaches and generative AI techniques to enrich data quantity and quality, enabling the AI system to adapt to data shift and concept shifting. Model robustness is hindered by noisy data, which impedes the model's ability to generalize well to unseen examples. Additionally, AI models are susceptible to adversarial attacks designed to deceive the system. Prior research has not adequately explored the potential of data-centric approaches to enhance model robustness and lacks methods that simultaneously address data security and model generalization. To overcome these challenges, we propose a hybrid approach that combines data-centric and model-centric techniques to improve model generalization and resilience to noisy data. Moreover, we leverage federated learning to decentralize model training, enhancing data security and privacy while harnessing diverse data sources. By addressing the identified research gaps and implementing the proposed solutions, this dissertation contributes to the development of robust AI systems that can effectively handle data and model challenges.

English

ISBN: 9798383530917Subjects--Topical Terms:

679492
Industrial engineering.
Subjects--Index Terms:

Data-centric AI

A Robust Data-Driven Framework for Artificial Intelligent Systems /
LDR:03438nam a22004453i 4500 001 1157830
005 20250603111423.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798383530917
035 $a (MiAaPQD)AAI31333722
035 $a AAI31333722
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Nguyen, Quoc H., $e author. $3 1484106
245 1 2 $a A Robust Data-Driven Framework for Artificial Intelligent Systems / $c Quoc H Nguyen.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (189 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: Le, Trung Committee members: Das, Tapas K.; Shah, Ankit; Licato, John; Kong, Jun.
502 $b Ph.D. $c University of South Florida $d 2024.
520 $a Artificial Intelligence (AI) systems have demonstrated remarkable performance across various domains. However, their robustness remains a critical concern, particularly in terms of data and model reliability. This dissertation aims to address the challenges associated with building robust AI systems by focusing on two key aspects: data robustness and model robustness. Data robustness poses significant challenges, including data shift, concept shifting, limited and imbalanced datasets, and interoperability issues in IoT systems for data collection. Existing methods fall short in handling dynamic business objectives and evolving data landscapes effectively. To bridge these gaps, we propose an IoT framework that ensures interoperability, seamless communication, and scalability for efficient data collection. Furthermore, we employ data-centric approaches and generative AI techniques to enrich data quantity and quality, enabling the AI system to adapt to data shift and concept shifting. Model robustness is hindered by noisy data, which impedes the model's ability to generalize well to unseen examples. Additionally, AI models are susceptible to adversarial attacks designed to deceive the system. Prior research has not adequately explored the potential of data-centric approaches to enhance model robustness and lacks methods that simultaneously address data security and model generalization. To overcome these challenges, we propose a hybrid approach that combines data-centric and model-centric techniques to improve model generalization and resilience to noisy data. Moreover, we leverage federated learning to decentralize model training, enhancing data security and privacy while harnessing diverse data sources. By addressing the identified research gaps and implementing the proposed solutions, this dissertation contributes to the development of robust AI systems that can effectively handle data and model challenges.
546 $a English
590 $a School code: 0206
650 4 $a Industrial engineering. $3 679492
650 4 $a Computer science. $3 573171
650 4 $a Engineering. $3 561152
653 $a Data-centric AI
653 $a Federated learning
653 $a Generative AI techniques
653 $a Robust AI systems
653 $a Model generalization
690 $a 0537
690 $a 0984
690 $a 0546
690 $a 0800
710 2 $a University of South Florida. $b Industrial and Management Systems Engineering. $e degree granting institution. $3 1484107
720 1 $a Le, Trung $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 0206
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31333722