浏览全部资源
扫码关注微信
1. 合肥工业大学计算机与信息学院,安徽 合肥 230601
2. 中国电信股份有限公司研究院,广东 广州 510630
[ "马学森(1976− ),男,合肥工业大学计算机与信息学院副教授,主要研究方向为移动边缘计算、无线网络" ]
[ "陈树友(1995− ),男,合肥工业大学计算机与信息学院硕士生,主要研究方向为高可靠性分布式系统、移动边缘计算" ]
[ "许向东(1978− ),男,现就职于中国电信股份有限公司研究院,主要研究方向为移动通信、5G智慧应用、物联网应用、大数据及AI系统研发、网络运营技术等" ]
[ "储昭坤(1996− ),男,合肥工业大学计算机与信息学院硕士生,主要研究方向为移动边缘计算、无线网络" ]
网络出版日期:2021-08,
纸质出版日期:2021-08-20
移动端阅览
马学森, 陈树友, 许向东, 等. 基于神经网络与马尔可夫组合模型的视频流行度预测算法[J]. 电信科学, 2021,37(8):18-26.
Xuesen MA, Shuyou CHEN, Xiangdong XU, et al. Neural network and Markov based combination prediction algorithm of video popularity[J]. Telecommunications science, 2021, 37(8): 18-26.
马学森, 陈树友, 许向东, 等. 基于神经网络与马尔可夫组合模型的视频流行度预测算法[J]. 电信科学, 2021,37(8):18-26. DOI: 10.11959/j.issn.1000-0801.2021116.
Xuesen MA, Shuyou CHEN, Xiangdong XU, et al. Neural network and Markov based combination prediction algorithm of video popularity[J]. Telecommunications science, 2021, 37(8): 18-26. DOI: 10.11959/j.issn.1000-0801.2021116.
为了提升用户体验,降低运营商的成本,将播放最多的视频内容提前放入用户侧缓存是业界的通用做法,如何有效预测视频播放热度已经成为业界热点问题。针对传统预测算法非线性映射能力差、预测精度低及自适应性弱等缺点,提出基于神经网络与马尔可夫组合模型的视频流行度预测算法(Mar-BiLSTM),该算法通过构建双向长短期记忆(bi-directional long short-term memory,BiLSTM)网络模型可以保留时间序列两个方向的信息依赖;同时在避免引入外部变量导致模型复杂度增加的情况下,利用马尔可夫性质进一步提高了模型的预测精度。实验结果表明,与传统的时间序列和经典的神经网络算法相比,所提算法提升了视频流行度预测的准确性、时效性,并降低了计算量。
Caching popular video into user-side in advance improves the user experience and reduces operator costs
which is a common practice in the industry.How to effectively predict the popularity of videos has become a hot issue in the industry.On account of the shortcomings of traditional prediction algorithms such as poor nonlinear mapping ability
low prediction accuracy and weak adaptability
a video popularity prediction algorithm based on a neural network and Markov combined model (Mar-BiLSTM) was proposed.Information dependencies were preserved by constructing bidirectional memory network model (bi-directional long short-term memory
BiLSTM)
the prediction accuracy of the model was further improved by using Markov properties while avoiding the increase of the complexity of the model caused by the introduction of external variables.Experimental results show that compared with traditional time series and classic neural network algorithms
the proposed algorithm improves predicting accuracy
effectiveness and reduces the amount of calculation.
YAQOOB A , BI T , MUNTEAN G M . A survey on adaptive 360°video streaming: solutions, challenges and opportunities [J ] . IEEE Communications Surveys & Tutorials , 2020 , 22 ( 4 ): 2801 - 2838 .
孔令义 . 面向 5G 的网络优化和重构 [J ] . 电信科学 , 2020 , 36 ( 2 ): 117 - 125 .
KONG L Y . Network optimization and reconstruction for 5G [J ] . Telecommunications Science , 2020 , 36 ( 2 ): 117 - 125 .
孟令彬 , 李娟 , 薛楠 , 等 . 5G 边缘计算共享研究与展望 [J ] . 电信科学 , 2020 , 36 ( 6 ): 38 - 44 .
MENG L B , LI J , XUE N , et al . Research and prospect of 5G edge computing sharing [J ] . Telecommunications Science , 2020 , 36 ( 6 ): 38 - 44 .
MALIK S U R . Moving toward 5G:significance,differences,and impact on quality of experience [J ] . IEEE Consumer Electronics Magazine , 2020 , 9 ( 6 ): 9 - 14 .
SZABO G , HUBERMAN B A . Predicting the popularity of online content [J ] . Communications of the ACM , 2010 , 53 ( 8 ): 80 - 88 .
TAN Z Y , WANG Y F , ZHANG Y , et al . A novel time series approach for predicting the long-term popularity of online videos [J ] . IEEE Transactions on Broadcasting , 2016 , 62 ( 2 ): 436 - 445 .
陈春燕 , 张钰 , 常标 , 等 . 基于 ARMA 模型的在线电视剧流行度预测 [J ] . 计算机科学与探索 , 2016 , 10 ( 3 ): 425 - 432 .
CHEN C Y , ZHANG Y , CHANG B , et al . Predicting popularity of online teleplays with ARMA models [J ] . Journal of Frontiers of Computer Science and Technology , 2016 , 10 ( 3 ): 425 - 432 .
SU Y T , LI Y , BAI X , et al . Predicting the popularity of micro-videos via a feature-discrimination transductive model [J ] . Multimedia Systems , 2020 , 26 ( 5 ): 519 - 534 .
HASSANPOUR M , HOSEINITABATABAEI S A , BARNAGHI P , et al . Improving the accuracy of the video popularity prediction models through user grouping and video popularity classification [J ] . ACM Transactions on the Web , 2020 , 14 ( 1 ): 1 - 28 .
SMAGULOVA K , JAMES A P . A survey on LSTM memristive neural network architectures and applications [J ] . The European Physical Journal Special Topics , 2019 , 228 ( 10 ): 2313 - 2324 .
权波 , 杨博辰 , 胡可奇 , 等 . 基于 LSTM 的船舶航迹预测模型 [J ] . 计算机科学 , 2018 , 45 ( S2 ): 126 - 131 .
QUAN B , YANG B C , HU K Q , et al . Prediction model of ship trajectory based on LSTM [J ] . Computer Science , 2018 , 45 ( S2 ): 126 - 131 .
王睿怡 , 邓寿提 , 刘琳 , 等 . 基于 LSTM 算法的 LTE 小区级负荷指标预测研究 [J ] . 电信科学 , 2020 , 36 ( Z2 ): 1 - 8 .
WANG R Y , DENG S T , LIU L , et al . Research on LTE cell-level load index prediction based on LSTM algorithm [J ] . Telecommunications Science , 2020 , 36 ( Z2 ): 1 - 8 .
SCAPINI V , ZUÑIGA E , . A Markov chain approach to model reconstruction [J ] . International Journal of Computational Methods and Experimental Measurements , 2020 , 8 ( 4 ): 316 - 325 .
徐晓枫 , 贺樑 , 杨静 . 融合社交与搜索数据的电视剧点播排名预测研究 [J ] . 计算机工程 , 2015 , 41 ( 8 ): 6 - 12 , 17 .
XU X F , HE L , YANG J . Study of TV drama on demand ranking prediction fused with social and search data [J ] . Computer Engineering , 2015 , 41 ( 8 ): 6 - 12 , 17 .
曹婍 , 沈华伟 , 高金华 , 等 . 基于深度学习的流行度预测研究综述 [J ] . 中文信息学报 , 2021 , 35 ( 2 ): 1 - 18 , 32 .
CAO Q , SHEN H W , GAO J H , et al . Survey on deep learning based popularity prediction [J ] . Journal of Chinese Information Processing , 2021 , 35 ( 2 ): 1 - 18 , 32 .
0
浏览量
370
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构