多媒体通信中智能化媒体内同步机制

本文提出了一种智能化视频流量的预测和同步机制（ＩＦＳＭ），它由ＢＰ神经网络流量预测器（ＢＰＮＮ）、输出缓冲区和基于模糊神经网络（ＦＮＮ）的输出速率决策器所组成。ＢＰＮＮ采用一种在线训练的ＢＰ神经网络预测在将来的一定时间间隔（ＦＩ）内的平均分组速率，ＦＮＮ决策器根据预测的流量特性和缓冲区中的分组数动态地调节下一个分组输出的时间。仿真结果表明：与窗口机制相比，ＩＦＳＭ能够使视频流量取得较高的连续性和较低的时延，并且由于ＦＮＮ的学习能力，ＩＦＳＭ可以自适应地调节相应参数以满足不同的服务质量的要求。

Intelligent Intramedia Synchronization for Multimedia Communication

In this paper,an intelligent flow prediction and synchronization mechanism(IFSM)is proposed which is composed of a backpropagation neural network (BPNN)traffic predictor,a playout buffer and a fuzzy neural network(FNN)based playout rate determinator The BPNN traffic predictor no line predicts the mean packet rate of the traffic in the future interval (FI)and the FNN is designed to adaptively determinate the playout time according to the number of packets in the buffer and the traffic character predicted Simulation results show that compared to the window mechanism,IFSM achieves high continuity with accepted delay Furthermore,IFSM can be adaptively modified to meet the QoS of different kinds of services by FNN parameter training