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

Design of embedded systems using dat...

Wong, Jennifer L.

Linked to FindBook

Google Book

Amazon

博客來

Design of embedded systems using data -driven statistical techniques.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Design of embedded systems using data -driven statistical techniques./
Author:	Wong, Jennifer L.
Description:	321 p.
Notes:	Source: Dissertation Abstracts International, Volume: 68-02, Section: B, page: 1095.
Contained By:	Dissertation Abstracts International68-02B.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3251565
ISBN:	9781109897289

Design of embedded systems using data -driven statistical techniques.
Wong, Jennifer L.

Design of embedded systems using data -driven statistical techniques. - 321 p.

Source: Dissertation Abstracts International, Volume: 68-02, Section: B, page: 1095.

Thesis (Ph.D.)--University of California, Los Angeles, 2006.

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

A large variety of applications in areas such as pervasive computing, sensor networks, and microbiological systems is driven by the continuously increasing capabilities of modern embedded systems. The synthesis and analysis of embedded systems is a complex task due to the presence of design and operation variability as well as limited predictability of components and application properties. For example, links in wireless ad-hoc networks are often intermittent and properties such as gate delay and power of modern integrated circuits (IC) are subject to manufacturing variability. Traditionally, embedded systems have been addressed in an ad-hoc manner and are mainly addressed using tools that leverage on combinatorial optimization and formal reasoning techniques from computer science, computer engineering, and electrical engineering (e.g. digital signal processing (DSP) and communication). One of the major points of the thesis is that the next generation of embedded systems and integrated circuits will require the use non-parametric statistical techniques (NSTs) to properly capture and predict the behavior, performance, and properties of complex applications and intricate implementation technologies. More importantly, we demonstrate that NSTs can also be a basis for efficient and effective synthesis of modern embedded systems.

ISBN: 9781109897289Subjects--Topical Terms:

523869
Computer science.

Design of embedded systems using data -driven statistical techniques.
LDR:03705nmm a2200301 4500 001 2059885
005 20150822105422.5
008 170521s2006 ||||||||||||||||| ||eng d
020 $a 9781109897289
035 $a (MiAaPQ)AAI3251565
035 $a AAI3251565
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wong, Jennifer L. $3 3174021
245 1 0 $a Design of embedded systems using data -driven statistical techniques.
300 $a 321 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-02, Section: B, page: 1095.
500 $a Adviser: Miodrag Potkonjak.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2006.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a A large variety of applications in areas such as pervasive computing, sensor networks, and microbiological systems is driven by the continuously increasing capabilities of modern embedded systems. The synthesis and analysis of embedded systems is a complex task due to the presence of design and operation variability as well as limited predictability of components and application properties. For example, links in wireless ad-hoc networks are often intermittent and properties such as gate delay and power of modern integrated circuits (IC) are subject to manufacturing variability. Traditionally, embedded systems have been addressed in an ad-hoc manner and are mainly addressed using tools that leverage on combinatorial optimization and formal reasoning techniques from computer science, computer engineering, and electrical engineering (e.g. digital signal processing (DSP) and communication). One of the major points of the thesis is that the next generation of embedded systems and integrated circuits will require the use non-parametric statistical techniques (NSTs) to properly capture and predict the behavior, performance, and properties of complex applications and intricate implementation technologies. More importantly, we demonstrate that NSTs can also be a basis for efficient and effective synthesis of modern embedded systems.
520 $a The main goal of this thesis is to address three driver applications (manufacturing variability in integrated circuits, lossy links in wireless ad-hoc networks, and energy efficient sensing of a statistically predictable environment) using a systematic systems of NST-based modeling and optimization techniques. The consistent strategy is the use of collected data from traces of deployed or operational systems to drive both the analysis and realization of an embedded system. The analysis leverages on non-parametric statistical techniques and identifies design insights, tractable and accurate optimization objectives, and serves a basis for fast and realistic simulation. We address the use of statistical techniques at two different levels of embedded system design: during the IC design process, and during the application of embedded system components. At the IC design level, a statistical methodology is used for characterization of three variability issues mainly resultant from manufacturing variability: a priori wire-length estimation, wire-length estimation, and statistical timing analysis. At the distributed systems level, variability is addressed through modeling of lossy wireless link communication, in building a localized routing protocol, modeling of sensor phenomena, and for efficient node deployment.
590 $a School code: 0031.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a University of California, Los Angeles. $3 626622
773 0 $t Dissertation Abstracts International $g 68-02B.
790 $a 0031
791 $a Ph.D.
792 $a 2006
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3251565