期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
ICN Based Vehicle-to-Cloud Delivery for Multimedia Streaming in Urban Vehicular Networks 被引量:1
1
作者 Wei Quan Fei Song +1 位作者 Chengxiao Yu mingchuan zhang 《China Communications》 SCIE CSCD 2016年第9期103-112,共10页
Mobile multimedia streaming is an open topic in vehicular environment. Due to the high intermittent links, it has become a critical challenge to deliver high quality video streaming in vehicular networks. In this pape... Mobile multimedia streaming is an open topic in vehicular environment. Due to the high intermittent links, it has become a critical challenge to deliver high quality video streaming in vehicular networks. In this paper, we reform the Information Centric Networking (ICN) concept for multimedia delivery in urban vehicular networks. By leveraging the 1CN perspective, we highlight that vehicular peers can obtain multimedia chunks via the vehicle-to-cloud (V2C) approach to improve the delivery quality. Based on this, we propose a lightweight multipath selection strategy to guide the network system to adaptively adjust the forwarding means. Extensive simulations show that the proposed solution can optimize the utilization of network paths, lighten network loads as well as avoid wasting resources. 展开更多
关键词 information centric networking vehicle-to-cloud multimedia streaming VANET
下载PDF
Multi-layer collaborative optimization fusion for semi-supervised learning
2
作者 Quanbo GE Muhua LIU +3 位作者 Jianchao zhang Jianqiang SONG Junlong ZHU mingchuan zhang 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2023年第11期342-353,共12页
Recently,the Cooperative Training Algorithm(CTA),a well-known Semi-Supervised Learning(SSL)technique,has garnered significant attention in the field of image classification.However,traditional CTA approaches face chal... Recently,the Cooperative Training Algorithm(CTA),a well-known Semi-Supervised Learning(SSL)technique,has garnered significant attention in the field of image classification.However,traditional CTA approaches face challenges such as high computational complexity and low classification accuracy.To overcome these limitations,we present a novel approach called Weighted fusion based Cooperative Training Algorithm(W-CTA),which leverages the cooperative training technique and unlabeled data to enhance classification performance.Moreover,we introduce the K-means Cooperative Training Algorithm(km-CTA)to prevent the occurrence of local optima during the training phase.Finally,we conduct various experiments to verify the performance of the proposed methods.Experimental results show that W-CTA and km-CTA are effective and efficient on CIFAR-10 dataset. 展开更多
关键词 Collaborative training FUSION Image classification K-means algorithm Semi-supervised learning
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部