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

doi:10.11959/j.issn.1000-0801.2021116

Abstract

Abstract:

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.

CLC Number:

TP391

Xuesen MA, Shuyou CHEN, Xiangdong XU, Zhaokun CHU. Neural network and Markov based combination prediction algorithm of video popularity[J]. Telecommunications Science, 2021, 37(8): 18-26.

Figures/Tables 11

References 15

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	SZABO G , HUBERMAN B A . Predicting the popularity of online content[J]. Communications of the ACM, 2010,53(8): 80-88.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	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.
[13]	SCAPINI V , ZU?IGA E , . A Markov chain approach to model reconstruction[J]. International Journal of Computational Methods and Experimental Measurements, 2020,8(4): 316-325.
[14]	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.
[15]	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.

Metrics

Recommended 0

No Suggested Reading articles found!

时间	起始状态	转移步数	E1	E2	E3	E4
1.25	E3	1	0.200	0	0.600	0.200
1.24	E1	2	0.413	0.25	0.500	0
1.23	E2	3	0.413	0.063	0.425	0.100
1.22	E1	4	0.323	0.075	0.500	0.102
合计			1.348	0.388	2.025	0.402

模型	RMSE	MAE
GM	246.436 7	216.732 5
ES	449.256 5	374.285 7
BP	210.362 5	196.382 4
LSTM	187.346 9	157.714 3
BiLSTM	178.386 0	148.712 4
Mar-BiLSTM	121.491 3	109.857 1

电视剧名称	剧集数/集	均集播放量/次	上线天数/天	均天播放量/次	加权值/次	真实排名	预测排名
斗罗大陆	40	119 000 000	50	95 200 000	214 200 000	1	2
锦心似玉	39	87 435 897	29	117 586 207	205 022 104	2	1
爱的理想生活	43	61 153 846	26	36 976 744	98 130 590	3	3
司藤	30	27 666 667	19	43 684 211	71 350 878	4	4
我的小确幸	28	46 071 429	73	17 671 233	63 742 662	5	6
我就是这般女子	40	33 750 000	68	19 852 941	53 602 941	6	5
玲珑	40	25 250 000	40	17 719 299	42 969 299	7	8
暴风眼	40	17 000 000	32	221 2500 000	38 250 000	8	7
你好，安怡	30	18 333 333	36	15 277 778	33 611 111	9	9
这个世界不看脸	45	11 555 556	75	69 333 33	18 488 889	10	10

Neural network and Markov based combination prediction algorithm of video popularity

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 15

Related Articles 15

Metrics

Recommended 0

[1]	Yudi SUN. A prediction model of massive 5G network users’ revisit behavior based on telecom big data [J]. Telecommunications Science, 2023, 39(2): 157-162.
[2]	Xiaotong YE, Wenfei SUN, Shigen SHEN. Availability evaluation method for extended epidemic model and Markov chain based IoT [J]. Telecommunications Science, 2021, 37(4): 37-45.
[3]	Su DIAO, Cheng JIANG. Trend of mobile communication market pattern under the reform of industry co-competition [J]. Telecommunications Science, 2021, 37(3): 154-161.
[4]	Zhongjie JIA, Ming JIN, Xiaoqun SONG. A multi-band spectrum sensing method based on sticky hidden Markov model [J]. Telecommunications Science, 2021, 37(1): 48-57.
[5]	Wenyu HU,Xiaoyan DOU. Impact of the nationwide implementation of mobile number portabilityon mobile communications market [J]. Telecommunications Science, 2019, 35(9): 124-134.
[6]	Xueting WANG,Qi ZHU,Han HU. A Stackelberg game based content caching algorithm in energy-harvesting small cell networks [J]. Telecommunications Science, 2019, 35(1): 18-29.
[7]	Jian DU,Yuanyi XIA,Junfeng ZHAO,Zheng WANG,He WANG. Transient community awared data forwarding mechanism for intermittent connected wireless network [J]. Telecommunications Science, 2017, 33(11): 179-185.
[8]	Zhiqiang ZHOU,Tong YE,Dong LI. Delay analysis of multi-state Markov channels [J]. Telecommunications Science, 2016, 32(9): 22-28.
[9]	Chaolun BU,Yang XIAO,Tong YE,Peng WU,Xiaojian ZHANG,Junmin WU. Performance analysis of random access network with post-backoff [J]. Telecommunications Science, 2016, 32(2): 34-40.
[10]	Senxin ZHOU,Jianghong HAN,Yaohui ZHANG,Chao LI. Trusted measure model for the communication network system [J]. Telecommunications Science, 2016, 32(1): 66-75.
[11]	Xiong ZHAN,Hao GUO,Peng ZHANG,Shu MAO. A network security situation prediction method based on hidden Markov model [J]. Telecommunications Science, 2015, 31(Z1): 79-84.
[12]	Yan Zhang,Julong Lan,Peng Wang,Yuxiang Hu. A Polymorphic Routing Derivation Mechanism Based on Markov Decision Process [J]. Telecommunications Science, 2015, 31(6): 54-60.
[13]	Senxin Zhou,Jianghong Han,Chao Li,Decheng Wu. Research on Trusted Measurement of Industrial Control Network with Markov Reward Model [J]. Telecommunications Science, 2015, 31(2): 113-117.
[14]	Huangqing Chen,Xiaofeng Zhong,Jian Sun,Jing Wang. Online Popularity Prediction Scheme Based on Converging Property in Content Aware Soft Real Time Media Broadcast System [J]. Telecommunications Science, 2015, 31(11): 1-6.
[15]	Lili Dong,Yong Wang,Yongqiang Dong,Peng Yang. Collaborative Cacbe Management Strategy Based on Ant-Colony Replacement Algoritbm in Named Data Networking [J]. Telecommunications Science, 2014, 30(9): 45-52.