Platform-dependent database and performance estimation for video application in embedded system

Nelson Yen Chung Chang; Kun Bin Lee; Tian-Sheuan Chang

doi:10.1109/APCCAS.2004.1413090

Platform-dependent database and performance estimation for video application in embedded system

Nelson Yen Chung Chang^*, Kun Bin Lee, Tian-Sheuan Chang

^*此作品的通信作者

研究成果 › 同行評審

1 引文斯高帕斯（Scopus）

摘要

The platform-dependent database plays a key role in high-level performance estimation, however issues regard to the database construction are rarely studied. Therefore in this paper, a slope-threshold method is proposed to determine the number of sufficient samples to construct a reliable and accurate platform-dependent database. Besides, to improve estimation accuracy further, we also proposed a node refinement method which decomposes coarsely partitioned subtask into smaller ones. To verify the proposed approaches, MPEG-4 shape coding is taken as an example. The result shows that using the database constructed with the slope-threshold method improves both estimation accuracy and error estimation coverage, especially when subtasks are coarsely partitioned. If node refinement is also incorporated, the estimation error percentage can be improved from 3.20% to 1.85%.

原文	English
頁面	1157-1160
頁數	4
DOIs	https://doi.org/10.1109/APCCAS.2004.1413090
出版狀態	Published - 12月 2004
事件	2004 IEEE Asia-Pacific Conference on Circuits and Systems, APCCAS 2004: SoC Design for Ubiquitous Information Technology - Tainan, 台灣持續時間: 6 12月 2004 → 9 12月 2004

Conference

Conference	2004 IEEE Asia-Pacific Conference on Circuits and Systems, APCCAS 2004: SoC Design for Ubiquitous Information Technology
國家/地區	台灣
城市	Tainan
期間	6/12/04 → 9/12/04

存取文件

10.1109/APCCAS.2004.1413090

其它文件與鏈接

Link to publication in Scopus

引用此

@conference{b093afae4089446abf23ca0ad1cef53d,

title = "Platform-dependent database and performance estimation for video application in embedded system",

abstract = "The platform-dependent database plays a key role in high-level performance estimation, however issues regard to the database construction are rarely studied. Therefore in this paper, a slope-threshold method is proposed to determine the number of sufficient samples to construct a reliable and accurate platform-dependent database. Besides, to improve estimation accuracy further, we also proposed a node refinement method which decomposes coarsely partitioned subtask into smaller ones. To verify the proposed approaches, MPEG-4 shape coding is taken as an example. The result shows that using the database constructed with the slope-threshold method improves both estimation accuracy and error estimation coverage, especially when subtasks are coarsely partitioned. If node refinement is also incorporated, the estimation error percentage can be improved from 3.20% to 1.85%.",

author = "Chang, {Nelson Yen Chung} and Lee, {Kun Bin} and Tian-Sheuan Chang",

year = "2004",

month = dec,

doi = "10.1109/APCCAS.2004.1413090",

language = "English",

pages = "1157--1160",

note = "2004 IEEE Asia-Pacific Conference on Circuits and Systems, APCCAS 2004: SoC Design for Ubiquitous Information Technology ; Conference date: 06-12-2004 Through 09-12-2004",

}

TY - CONF

T1 - Platform-dependent database and performance estimation for video application in embedded system

AU - Chang, Nelson Yen Chung

AU - Lee, Kun Bin

AU - Chang, Tian-Sheuan

PY - 2004/12

Y1 - 2004/12

N2 - The platform-dependent database plays a key role in high-level performance estimation, however issues regard to the database construction are rarely studied. Therefore in this paper, a slope-threshold method is proposed to determine the number of sufficient samples to construct a reliable and accurate platform-dependent database. Besides, to improve estimation accuracy further, we also proposed a node refinement method which decomposes coarsely partitioned subtask into smaller ones. To verify the proposed approaches, MPEG-4 shape coding is taken as an example. The result shows that using the database constructed with the slope-threshold method improves both estimation accuracy and error estimation coverage, especially when subtasks are coarsely partitioned. If node refinement is also incorporated, the estimation error percentage can be improved from 3.20% to 1.85%.

AB - The platform-dependent database plays a key role in high-level performance estimation, however issues regard to the database construction are rarely studied. Therefore in this paper, a slope-threshold method is proposed to determine the number of sufficient samples to construct a reliable and accurate platform-dependent database. Besides, to improve estimation accuracy further, we also proposed a node refinement method which decomposes coarsely partitioned subtask into smaller ones. To verify the proposed approaches, MPEG-4 shape coding is taken as an example. The result shows that using the database constructed with the slope-threshold method improves both estimation accuracy and error estimation coverage, especially when subtasks are coarsely partitioned. If node refinement is also incorporated, the estimation error percentage can be improved from 3.20% to 1.85%.

UR - http://www.scopus.com/inward/record.url?scp=13444261039&partnerID=8YFLogxK

U2 - 10.1109/APCCAS.2004.1413090

DO - 10.1109/APCCAS.2004.1413090

M3 - Paper

AN - SCOPUS:13444261039

SP - 1157

EP - 1160

T2 - 2004 IEEE Asia-Pacific Conference on Circuits and Systems, APCCAS 2004: SoC Design for Ubiquitous Information Technology

Y2 - 6 December 2004 through 9 December 2004

ER -

Platform-dependent database and performance estimation for video application in embedded system

摘要

Conference

存取文件

其它文件與鏈接

指紋

引用此