发布求助
文献互助 智能选刊 最新文献

2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology最新文献

筛选
英文 中文
XenLR: Xen-based Logging for Deterministic Replay 基于XenLR的确定性重放日志
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.31
Haikun Liu, Hai Jin, Xiaofei Liao, Zhengqi Pan
{"title":"XenLR: Xen-based Logging for Deterministic Replay","authors":"Haikun Liu, Hai Jin, Xiaofei Liao, Zhengqi Pan","doi":"10.1109/FCST.2008.31","DOIUrl":"https://doi.org/10.1109/FCST.2008.31","url":null,"abstract":"Virtual machine (VM) based logging-and-replay technology has attracted much attention for system security, fault tolerance, and debugging. However, so far there is not a replay system designed on virtual machine monitor Xen. In this paper, XenLR presents the design and implementation of a logging tool for full system replay on Xen. To reduce the design complexity, XenLR is achieved on a lightweight VM mini OS. Our preliminary work dedicates to identify architectural non-deterministic events and record them compactly. XenLR does not modify the guest OS and only need to record the external inputs (keyboard input and time update on mini OS). The log data are saved in the privileged domain¿s file system through transmission channels. The experiments indicate that XenLR results in low time and space overhead. Overhead due to logging is imperceptible for interactive use. The log files grow at 1.4 MByte/day, so it causes litter space consumption for today¿s large capacity disk storage.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125325116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Optimizing Two-Dimensional Continuous Dynamic Programming for Cell Broadband Engine Processors 蜂窝宽带引擎处理器的二维连续动态规划优化
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.35
T. Machino, Shintaro Iwazaki, Y. Okuyama, J. Kitamichi, Kenichi Kuroda, R. Oka
{"title":"Optimizing Two-Dimensional Continuous Dynamic Programming for Cell Broadband Engine Processors","authors":"T. Machino, Shintaro Iwazaki, Y. Okuyama, J. Kitamichi, Kenichi Kuroda, R. Oka","doi":"10.1109/FCST.2008.35","DOIUrl":"https://doi.org/10.1109/FCST.2008.35","url":null,"abstract":"Two-dimensional continuous dynamic programming (2DCDP), a specialized DP matching method for image recognition, can be applied to many applications such as object tracking, pattern matching, etc. However, the execution time is large, and the current general purpose processor does not achieve performance in real-time. In this paper, we present our approach to real-time image recognition using a cell broadband engine processor (Cell processor). We optimize 2DCDP for the cell processor by vectorizing with SIMD instructions, parallelizing with multiple SPEs, dynamic branch prediction in assembly level, and so on. Finally, the performance on the Cell processor is achieved over 15 times faster than the performance on an Intel Xeon 5160 processor.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116651663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
TSPSCDP: A Time-Stamp Continuous Data Protection Approach Based on Pipeline Strategy 基于管道策略的时间戳连续数据保护方法
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.27
Jingning Liu, Tianming Yang, Zuoheng Li, Ke Zhou
{"title":"TSPSCDP: A Time-Stamp Continuous Data Protection Approach Based on Pipeline Strategy","authors":"Jingning Liu, Tianming Yang, Zuoheng Li, Ke Zhou","doi":"10.1109/FCST.2008.27","DOIUrl":"https://doi.org/10.1109/FCST.2008.27","url":null,"abstract":"Traditional cold backup technology can not fight against data loss between two consecutive backups which usually has a time span of 24 hours. Hot backup technology, such as snapshot decreases the amount of potential data loss, but still cannot completely prevent data loss. More recently, a new technology called continuous data protection (CDP) is emerging to provide more powerful data protection. CDP captures every change to the data volume hence can provide any point-in-time data views and enable timely recovery to any point-in-time of user data. However, existing implementations of CDP usually suffer from poor write performance and cannot meet the data protection demand of some high performance application environments. How to improve the CDP performance in terms of write throughput and response time is one of the most important considerations in implementing CDP. This paper presents a time-stamp pipeline strategy continuous data protection approach called TSPSCDP which uses pipeline strategy in write operation of CDP to improve data processing capability. Our experiments demonstrated that TSPSCDP can not only recover data to any point-in-time upon a failure but also improve the CDP performance in terms of write throughput and respond time upon the ordinary CDP by a factor of 2 and about 25% respectively.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123036867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Hand Tracking by Particle Filtering with Elite Particles Mean Shift 基于精英粒子Mean Shift的粒子滤波手部跟踪
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.9
S. Zhong, Fei Hao
{"title":"Hand Tracking by Particle Filtering with Elite Particles Mean Shift","authors":"S. Zhong, Fei Hao","doi":"10.1109/FCST.2008.9","DOIUrl":"https://doi.org/10.1109/FCST.2008.9","url":null,"abstract":"This paper presents an improved particle filtering for hand tracking in a video sequence in real time. In this method, we incorporate mean shift process of elite particles into conventional particle filtering for hand tacking which aims to improve the tracking efficiency. The elite particles are chosen from the particles with higher weights based on observation model. The proposed method can significantly improve the tracking performance, as well as reducing the computational cost compared to conventional particle filtering. Experiments result of the hand tracking show the effectiveness of proposed method.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133673994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 18
Towards Better Content Visibility in Video Recommender Systems 视频推荐系统中更好的内容可见性
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.36
Nalin Chakoo, Rahul Gupta, Jayaprada Hiremath
{"title":"Towards Better Content Visibility in Video Recommender Systems","authors":"Nalin Chakoo, Rahul Gupta, Jayaprada Hiremath","doi":"10.1109/FCST.2008.36","DOIUrl":"https://doi.org/10.1109/FCST.2008.36","url":null,"abstract":"Current recommender systems based on filtering techniques implement a rather limited model for video content visibility. Most of these systems fall short to provide visual precursor to the user and concentrate only on making more accurate predictions; however, a few of them that focus their attention to the aspect of multimedia (video) item visibility do so in a limited scope. In this paper, we address this problem and propose to augment the existing recommender systems with a dynamic user-based scheme to provide users with superior, high-quality recommendation formulation and customized visibility of the recommended item. The domain of content visibility is dynamically crafted using the existing recommender system algorithm.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122530068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
Head Pose Recognition with NNC-Trees 基于nnc树的头部姿态识别
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.28
Jie Ji, Kei Sato, Naoki Tominaga, Qiangfu Zhao
{"title":"Head Pose Recognition with NNC-Trees","authors":"Jie Ji, Kei Sato, Naoki Tominaga, Qiangfu Zhao","doi":"10.1109/FCST.2008.28","DOIUrl":"https://doi.org/10.1109/FCST.2008.28","url":null,"abstract":"Pose recognition is important in many practical applications. For example, a driver assistance system can detect if the driver is tired, sleepy, or careless from the poses. A pet robot can detect certain behavior patterns of the human user. The main purpose of this study is to develop a driver assistance system that can protect the drivers from careless accidents. As the first step, we propose a system for recognizing different poses of a human from the face images by using NNC-Tree. An NNC-Tree is a decision tree (DT) with each internal node containing a nearest neighbor classifier (NNC). We also developed a GUI for visualizing the prototypes in each NNC, as well as the whole tree. This interface makes it possible to understand, analyze, and reuse the learning results. This paper is a summary of what we have done so far.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130987759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Spatial Data Compression Techniques for GML 面向GML的空间数据压缩技术
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.8
Yuzhen Li, T. Imaizumi, S. Sakata, H. Sekiya, J. Guan
{"title":"Spatial Data Compression Techniques for GML","authors":"Yuzhen Li, T. Imaizumi, S. Sakata, H. Sekiya, J. Guan","doi":"10.1109/FCST.2008.8","DOIUrl":"https://doi.org/10.1109/FCST.2008.8","url":null,"abstract":"The Geography Markup Language (GML) has been introduced to standardize the representation of geographical data in Extensible Markup Language (XML), which makes the exchanging and sharing of geographical information easier. As GML becomes the geospatial language of the Web, the compression of GML files becomes a new challenge to the compression research field. That is because, GML documents tend to be much larger in size than other documents containing the same information, which raising concerns about processing and transportation. In this paper, we first introduce the architecture of the explored GML compressor. Then, analyze the main redundancy characteristic of GML. After that, we explain the precision decrease, delta compression and extrapolation techniques for GML spatial data compression. Experimental results show the efficiency of our proposed methods.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124934521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
An Energy Efficient, Low Cost, Hybrid Storage System Based on Utility 基于效用的节能、低成本混合存储系统
2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology Pub Date : 2008-12-27 DOI: 10.1109/FCST.2008.13
Lingfang Zeng, D. Feng, B. Veeravalli, Q. Wei
{"title":"An Energy Efficient, Low Cost, Hybrid Storage System Based on Utility","authors":"Lingfang Zeng, D. Feng, B. Veeravalli, Q. Wei","doi":"10.1109/FCST.2008.13","DOIUrl":"https://doi.org/10.1109/FCST.2008.13","url":null,"abstract":"To get large disk-like characteristics and offset the significant power demands of hard disk drives, we propose a fully functional hybrid archive system (called Pseudodisk) composed of an array of disks and a tape library. To get an energy conservation, low cost archive system, Pseudodisk uses data value model and utility function to guild data management. Two novel algorithms are proposed for data placement and data migration, which are referred to as utility-based data placement (UDP) and and system utility percentage (SUP) algorithms respectively. To validate the efficiency of the proposed archive system, we conduct the performance evaluation and the power-saving simulation.","PeriodicalId":206207,"journal":{"name":"2008 Japan-China Joint Workshop on Frontier of Computer Science and Technology","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130519393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信