首页 | 官方网站   微博 | 高级检索  
     

智能集成VBR MPEG视频流量预测模型
引用本文:刘晓颖,戴琼海,刘晓冬.智能集成VBR MPEG视频流量预测模型[J].电子学报,2006,34(5):833-836.
作者姓名:刘晓颖  戴琼海  刘晓冬
作者单位:1. 清华大学深圳研究生院宽带网多媒体研究中心,广东深圳 518055;2. 清华大学自动化系宽带网数字媒体实验室,北京 100084
基金项目:国家高技术研究发展计划(863计划),国家重点基础研究发展计划(973计划)
摘    要:作为数字媒体网络视频通信的主要方式,VBR MPEG视频流量的预测能力是直接关系缓冲区设计、动态带宽分配及拥塞控制等提高网络服务质量的关键因素.因此针对MPEG视频流的复杂特性,充分利用人工智能方法的优势,提出并建立了基于模糊神经网络的智能集成VBR MPEG 视频流量预测模型.采用模糊预测模型提高预测精度,利用神经网络解决预测的实时性问题.实验结果表明,与标准AR预测模型相比,该模型预测的准确度和可靠性显著提高,且算法简单易于推广到其他方法中使用.

关 键 词:可变比特视频流  视频流量  模糊神经网络  智能集成  预测模型  
文章编号:0372-2112(2006)05-0833-04
收稿时间:2004-11-25
修稿时间:2004-11-252006-03-03

Intelligent Integrated Traffic Prediction Modeling for VBR MPEG Video Transmission
LIU Xiao-ying,DAI Qiong-hai,LIU Xiao-dong.Intelligent Integrated Traffic Prediction Modeling for VBR MPEG Video Transmission[J].Acta Electronica Sinica,2006,34(5):833-836.
Authors:LIU Xiao-ying  DAI Qiong-hai  LIU Xiao-dong
Affiliation:1. Broadband Network & Multimedia Research Center,Graduate School at Shenzhen,Tsinghua University, Shenzhen,Guangdong 518055,China;2. Department of Automation,Tsinghua University,Beijing 100084,China
Abstract:As a main video transmission mode for digital media networks, the capability to predict VBR video traffic can significantly improve the effectiveness of quality of services. Therefore, aiming at the complex characteristics of MPEG videos, a novel intelligent integrated traffic prediction model is proposed based on fuzzy and neural network. The prediction error is reduced by the fuzzy predictor, and the implementation of neural network is used to lower prediction computation for real time. Simulation results show that the proposed method is able to predict the original traffic more accurately than the normal AR method and can be easily applied into other methods.
Keywords:variable bit rate of moving picture experts group(VBR MPEG)  video traffic  fuzzy neural network(FNN)  intelligent integrated  prediction model
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号