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

Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks./
Author:	Chen, Yu.
Description:	1 online resource (127 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30548567click for full text (PQDT)
ISBN:	9798379566623

Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks.
Chen, Yu.

Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks. - 1 online resource (127 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--University of Michigan, 2023.

Includes bibliographical references

Localization systems solve the problem of identifying the location of the agent or surrounding objects with the information gathered from various sensors. It enables a wide range of practical applications, such as autonomous navigation, self-driving cars, virtual reality, augmented reality, and enhanced surveillance. In recent years, deep neural networks have achieved great success in various computer vision and machine learning tasks, including more accurate localization systems with extensive computation complexity and power consumption. However, deploying such systems on energy-constrained mobile Internet-of-Things (IoT) platforms remains a big challenge due to the contradiction between system performance and power consumption. This thesis presents several practical approaches to develop energy-efficient localization systems for real-world applications. First, a real-time visual based simultaneous localization and mapping system is investigated and optimized for hardware implementation, which is ported on a low-power, application specific integrated circuit accelerator. The second work focuses on reducing the complexity of deep learning based visual-inertial odometry systems by finding the most efficient network architecture through neural architecture search and adaptively disabling visual sensor modality on the fly. The third work proposes an accurate learning based end-to-end audio source separation and localization framework with only low-power microphone sensor array, taking advantage of self-supervised learning and adversarial learning techniques. Finally, a new hardware-efficient heterogeneous transform-domain neural network is introduced to reduce computation complexity by replacing convolution operations with element-wise multiplications, learning sparse-orthogonal weights in heterogeneous transform domains, and non-uniform quantization with canonical-signed-digit representation. These works explore four different yet effective ways to balance the system performance and power consumption for mobile IoT platforms, namely reducing deep neural network complexity, adaptively selecting and fusing sensor modalities, employing lower power sensors, and developing hardware-efficient systems for specialized accelerators.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379566623Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Localization systemIndex Terms--Genre/Form:

542853
Electronic books.

Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks.
LDR:03676nmm a2200397K 4500 001 2362778
005 20231102122823.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379566623
035 $a (MiAaPQ)AAI30548567
035 $a (MiAaPQ)umichrackham004916
035 $a AAI30548567
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Chen, Yu. $3 1260328
245 1 0 $a Low-Power Localization Systems with Hardware-Efficient Deep Neural Networks.
264 0 $c 2023
300 $a 1 online resource (127 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: 84-12, Section: B.
500 $a Advisor: Kim, Hun-Seok.
502 $a Thesis (Ph.D.)--University of Michigan, 2023.
504 $a Includes bibliographical references
520 $a Localization systems solve the problem of identifying the location of the agent or surrounding objects with the information gathered from various sensors. It enables a wide range of practical applications, such as autonomous navigation, self-driving cars, virtual reality, augmented reality, and enhanced surveillance. In recent years, deep neural networks have achieved great success in various computer vision and machine learning tasks, including more accurate localization systems with extensive computation complexity and power consumption. However, deploying such systems on energy-constrained mobile Internet-of-Things (IoT) platforms remains a big challenge due to the contradiction between system performance and power consumption. This thesis presents several practical approaches to develop energy-efficient localization systems for real-world applications. First, a real-time visual based simultaneous localization and mapping system is investigated and optimized for hardware implementation, which is ported on a low-power, application specific integrated circuit accelerator. The second work focuses on reducing the complexity of deep learning based visual-inertial odometry systems by finding the most efficient network architecture through neural architecture search and adaptively disabling visual sensor modality on the fly. The third work proposes an accurate learning based end-to-end audio source separation and localization framework with only low-power microphone sensor array, taking advantage of self-supervised learning and adversarial learning techniques. Finally, a new hardware-efficient heterogeneous transform-domain neural network is introduced to reduce computation complexity by replacing convolution operations with element-wise multiplications, learning sparse-orthogonal weights in heterogeneous transform domains, and non-uniform quantization with canonical-signed-digit representation. These works explore four different yet effective ways to balance the system performance and power consumption for mobile IoT platforms, namely reducing deep neural network complexity, adaptively selecting and fusing sensor modalities, employing lower power sensors, and developing hardware-efficient systems for specialized accelerators.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer engineering. $3 621879
653 $a Localization system
653 $a Deep neural network
653 $a Hardware-efficient system
653 $a Internet-of-Things
653 $a System performance
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0544
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Michigan. $b Electrical and Computer Engineering. $3 3284714
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30548567 $z click for full text (PQDT)