國立虎尾科技大學 |

Real-Time Machine Learning in Embedded Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Real-Time Machine Learning in Embedded Systems./
作者:	Chai, Fangming.
面頁冊數:	1 online resource (102 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-07, Section: A.
Contained By:	Dissertations Abstracts International85-07A.
標題:	Information science. -
電子資源:	click for full text (PQDT)
ISBN:	9798381430790

Real-Time Machine Learning in Embedded Systems.
Chai, Fangming.

Real-Time Machine Learning in Embedded Systems. - 1 online resource (102 pages)

Source: Dissertations Abstracts International, Volume: 85-07, Section: A.

Thesis (Ph.D.)--State University of New York at Binghamton, 2023.

Includes bibliographical references

Over the past decade, the field of machine learning has garnered significant attention within the realm of embedded systems, aiming to address new challenges and enhance solutions for existing issues. Machine learning techniques, such as data analysis and prediction, have played a transformative role in altering algorithms and applications deployed in embedded systems. Nevertheless, the utilization of machine learning in such systems is confronted with formidable constraints, most notably limited computational resources including CPU and memory. These constraints impose significant challenges in meeting critical requirements encompassing latency, power consumption, memory utilization, and computational capabilities.This scholarly work endeavors to present a diverse set of techniques applicable to networking, security, and real-time deep learning in the context of embedded systems. First, we introduce a novel approach to enhance transmission efficiency through the utilization of Bayes models in networking. This improvement is achieved through a meticulous analysis of link correlation patterns in Internet of Things (IoT) networks. Second, our research delves into the design of a new attack strategy, which centers on the analysis of Dynamic Voltage and Frequency Scaling (DVFS) enabled systems for the purpose of power analysis attacks. Additionally, we offer countermeasures to mitigate the vulnerabilities associated with such attacks. Finally, to meet the stringent real-time deadline requirements imposed on Convolutional Neural Networks (CNNs) in embedded systems, we propose a tailored design approach that involves the selection of appropriate models.To assess the efficacy of the solutions in this dissertation, we conduct a series of comprehensive simulations, providing empirical evidence of their effectiveness and performance characteristics.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381430790Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Embedded systemsIndex Terms--Genre/Form:

554714
Electronic books.

Real-Time Machine Learning in Embedded Systems.
LDR:03230ntm a22003977 4500 001 1147341
005 20240909100801.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381430790
035 $a (MiAaPQ)AAI30815427
035 $a AAI30815427
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Chai, Fangming. $3 1473045
245 1 0 $a Real-Time Machine Learning in Embedded Systems.
264 0 $c 2023
300 $a 1 online resource (102 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: 85-07, Section: A.
500 $a Advisor: Kang, Kyoung-Don.
502 $a Thesis (Ph.D.)--State University of New York at Binghamton, 2023.
504 $a Includes bibliographical references
520 $a Over the past decade, the field of machine learning has garnered significant attention within the realm of embedded systems, aiming to address new challenges and enhance solutions for existing issues. Machine learning techniques, such as data analysis and prediction, have played a transformative role in altering algorithms and applications deployed in embedded systems. Nevertheless, the utilization of machine learning in such systems is confronted with formidable constraints, most notably limited computational resources including CPU and memory. These constraints impose significant challenges in meeting critical requirements encompassing latency, power consumption, memory utilization, and computational capabilities.This scholarly work endeavors to present a diverse set of techniques applicable to networking, security, and real-time deep learning in the context of embedded systems. First, we introduce a novel approach to enhance transmission efficiency through the utilization of Bayes models in networking. This improvement is achieved through a meticulous analysis of link correlation patterns in Internet of Things (IoT) networks. Second, our research delves into the design of a new attack strategy, which centers on the analysis of Dynamic Voltage and Frequency Scaling (DVFS) enabled systems for the purpose of power analysis attacks. Additionally, we offer countermeasures to mitigate the vulnerabilities associated with such attacks. Finally, to meet the stringent real-time deadline requirements imposed on Convolutional Neural Networks (CNNs) in embedded systems, we propose a tailored design approach that involves the selection of appropriate models.To assess the efficacy of the solutions in this dissertation, we conduct a series of comprehensive simulations, providing empirical evidence of their effectiveness and performance characteristics.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Communication. $3 556422
650 4 $a Computer science. $3 573171
653 $a Embedded systems
653 $a Real-time
653 $a Machine learning
653 $a Deep learning
653 $a Internet of Things
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0723
690 $a 0459
710 2 $a State University of New York at Binghamton. $b Computer Science. $3 845523
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-07A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30815427 $z click for full text (PQDT)