This paper presents ddstream , a data driven video streaming network module based on p2p , and builds a three - tiered application layer multicast architecture composed of video server , super peers and common peers . in the ddstream , every peer periodically exchanges data availability with others , retrieves unavailable data or supplies available data to others . ddstream makes a good tradeoff among bandwidth efficiency , delay and reliability 根据对各种视频流媒体网络中典型模型的分析总结,本课题设计并实现了一个基于p2p技术的视频流媒体网络模型ddstream ? ?以数据驱动的方式进行视频流媒体数据分发的模型,并构建了一种以视频流媒体服务器、超级节点sp和普通节点三层体系结构的高效但又简单易行的视频流媒体网络。
When taking part in the bci competition iii , t - weighted approach for feature extraction and reinforcement learning of classifier design are proposed . compared to other methods , t - weight approach has the advantages of requiring less a prior knowledge , exploring more information and computing faster . reinforcement learning is an optimization method both model driven and data driven aiming at mining the discriminative information as more as possible , and improving both the fitting and generalization ability of an existing classifier 相比其它特征提取方法, t加权方法具有对先验知识要求少、信息利用充分、计算快速等优点;而分类器设计的强化学习方法是模型驱动与数据驱动相结合的一种分类器优化方法,其思想在于充分挖掘样本判别信息,在已有分类器基础上进一步提高对数据的拟合能力及泛化能力。