On-Line VBR Video Traffic Prediction Using Neural Network

SU Xiao-xing; CHANG Sheng-jiang; XIONG Tao; GAO Hong-yun; SHEN Jin-yuan; ZHANG Yan-xin

您当前的位置：

首页 >

文章列表页 >

On-Line VBR Video Traffic Prediction Using Neural Network

更新时间：2025-07-16

- On-Line VBR Video Traffic Prediction Using Neural Network
- Acta Electronica Sinica Vol. 33, Issue 7, Pages: 1163-1167(2005)
- 作者机构：
  
  1. 南开大学现代光学研究所教育部光电信息技术重点实验室天津,300071
  2. 中国科学院声学研究所声场声信息国家重点实验室北京,100080
  3. 郑州大学河南省激光与光电信息技术重点实验室河南郑州,450052
  4. 南开大学现代光学研究所,教育部光电信息技术重点实验室,天津,300071
  5. 中国科学院声学研究所,声场声信息国家重点实验室,北京,100080
  6. 郑州大学,河南省激光与光电信息技术重点实验室,河南,郑州,450052
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN919.8
- Published：2005
- 稿件说明：
移动端阅览
SU Xiao-xing, CHANG Sheng-jiang, XIONG Tao, et al. On-Line VBR Video Traffic Prediction Using Neural Network[J]. Acta Electronica Sinica, 2005, 33(7): 1163-1167.
DOI：

SU Xiao-xing, CHANG Sheng-jiang, XIONG Tao, et al. On-Line VBR Video Traffic Prediction Using Neural Network[J]. Acta Electronica Sinica, 2005, 33(7): 1163-1167. DOI：

摘要

VBR(Varible Bit Rate)视频信号具有时变性、非线性和突发性等特点

实现该信号通信量的高精度预测难度较大.针对以上问题

本文提出了一种用于VBR视频通信量预测的自适应神经网络模型

网络训练采用离线与在线相结合的方式

同时通过删除不重要的权重

以优化网络的拓扑结构

提高网络的推广能力

降低网络在线学习的计算复杂度;对VBR视频通信量预测的模拟结果表明该模型具有高的预测精度

并能满足通信系统对预测实时性的要求.

Abstract

An adaptive neural network model for VBR video traffic prediction is proposed in this paper.Firstly

adaptive training and pruning algorithm based on Extended Kalman Filtering(EKF) approach is used to train the Time Delay Neural Network(TDNN).By pruning the unimportant hidden weights

the corresponding redundant hidden neurons can be deleted

as a result a compact TDNN architecture can be obtained.The pruning process results in better generalization ability and lower computational complexity for the online stage.During on-line training stage

the TDNN's weights will be updated using Recursive Least Square(RLS) algorithm according to current prediction error.Since EKF and RLS are second order algorithms

they can estimate the learning step automatically

faster convergence speed and more precise prediction can be obtained.By simulation and comparison

the adaptive neural network model proposed in this paper is shown to be promising and practically feasible in obtaining the best adaptive prediction of real-time VBR video traffic.

关键词

Keywords

references

Views

1281

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Novel Fast Selecting Inter Prediction Mode Algorithm Based H.264

Fast Inter Prediction Method Based H.264

Multi-directional and Variable-Interval Interpolation for Spatial Error Concealment

A Novel Method of Interactive Error-Resilience for Video Communication

Research Advance on Error-Resilience Techniques for Video Communication

Related Author

LI Chun-lin

CHANG Yi-lin

SONG Bin

ZHOU Ning-zhao

CHANG Yi-lin

SONG Bin

ZHOU Yuan-hua

ZHANG Rong-fu

Related Institution

National Key Laboratory on Integrate Services Network,Xidian University

National Key Lab on Integrate Services Network,XiDian University

Institute of Image Communication and Information Processing,Shanghai Jiaotong University

School of Optical and Electronic Information, University of Shanghai for Sience and Technology

Institute of Image Communication and Information ProcessingShanghai Jiaotong UniversityShanghai 200030China

⁰