Real-Time load reduction in multimedia big data for mobile internet

Kun Wang, Jun Mi, Chenhan Xu, Qingquan Zhu, Lei Shu, Der-Jiunn Deng

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

In the age of multimedia big data, the popularity of mobile devices has been in an unprecedented growth, the speed of data increasing is faster than ever before, and Internet traffic is rapidly increasing, not only in volume but also in heterogeneity. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive papers have been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this article, a hybrid-stream model is proposed to solve these problems for video analysis. Functionality of this model covers Data Preprocessing, Data Classification, and Data-Load-Reduction Processing. Specifically, an improved Convolutional Neural Networks (CNN) classification algorithm is designed to evaluate the importance of each video frame and video clip to enhance classification precision. Then, a reliable keyframe extraction mechanism will recognize the importance of each frame or clip, and decide whether to abandon it automatically by a series of correlation operations. The model will reduce data load to a dynamic threshold changed by σ, control the input size of the video in mobile Internet, and thus reduce network overload. Through experimental simulations, we find that the size of processed video has been effectively reduced and the quality of experience (QoE) has not been lowered due to a suitably selected parameter η. The simulation also shows that the model has a steady performance and is powerful enough for continuously growing multimedia big data.

Original languageEnglish
Article number2990473
JournalACM Transactions on Multimedia Computing, Communications and Applications
Volume12
Issue number5s
DOIs
Publication statusPublished - 2016 Oct 1

Fingerprint

Internet
Mobile devices
Image analysis
Neural networks
Big data
Processing
Deep learning

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{b227424270b64e9c8c18b1e465be1708,
title = "Real-Time load reduction in multimedia big data for mobile internet",
abstract = "In the age of multimedia big data, the popularity of mobile devices has been in an unprecedented growth, the speed of data increasing is faster than ever before, and Internet traffic is rapidly increasing, not only in volume but also in heterogeneity. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive papers have been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this article, a hybrid-stream model is proposed to solve these problems for video analysis. Functionality of this model covers Data Preprocessing, Data Classification, and Data-Load-Reduction Processing. Specifically, an improved Convolutional Neural Networks (CNN) classification algorithm is designed to evaluate the importance of each video frame and video clip to enhance classification precision. Then, a reliable keyframe extraction mechanism will recognize the importance of each frame or clip, and decide whether to abandon it automatically by a series of correlation operations. The model will reduce data load to a dynamic threshold changed by σ, control the input size of the video in mobile Internet, and thus reduce network overload. Through experimental simulations, we find that the size of processed video has been effectively reduced and the quality of experience (QoE) has not been lowered due to a suitably selected parameter η. The simulation also shows that the model has a steady performance and is powerful enough for continuously growing multimedia big data.",
author = "Kun Wang and Jun Mi and Chenhan Xu and Qingquan Zhu and Lei Shu and Der-Jiunn Deng",
year = "2016",
month = "10",
day = "1",
doi = "10.1145/2990473",
language = "English",
volume = "12",
journal = "ACM Transactions on Multimedia Computing, Communications and Applications",
issn = "1551-6857",
publisher = "Association for Computing Machinery (ACM)",
number = "5s",

}

Real-Time load reduction in multimedia big data for mobile internet. / Wang, Kun; Mi, Jun; Xu, Chenhan; Zhu, Qingquan; Shu, Lei; Deng, Der-Jiunn.

In: ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 12, No. 5s, 2990473, 01.10.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-Time load reduction in multimedia big data for mobile internet

AU - Wang, Kun

AU - Mi, Jun

AU - Xu, Chenhan

AU - Zhu, Qingquan

AU - Shu, Lei

AU - Deng, Der-Jiunn

PY - 2016/10/1

Y1 - 2016/10/1

N2 - In the age of multimedia big data, the popularity of mobile devices has been in an unprecedented growth, the speed of data increasing is faster than ever before, and Internet traffic is rapidly increasing, not only in volume but also in heterogeneity. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive papers have been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this article, a hybrid-stream model is proposed to solve these problems for video analysis. Functionality of this model covers Data Preprocessing, Data Classification, and Data-Load-Reduction Processing. Specifically, an improved Convolutional Neural Networks (CNN) classification algorithm is designed to evaluate the importance of each video frame and video clip to enhance classification precision. Then, a reliable keyframe extraction mechanism will recognize the importance of each frame or clip, and decide whether to abandon it automatically by a series of correlation operations. The model will reduce data load to a dynamic threshold changed by σ, control the input size of the video in mobile Internet, and thus reduce network overload. Through experimental simulations, we find that the size of processed video has been effectively reduced and the quality of experience (QoE) has not been lowered due to a suitably selected parameter η. The simulation also shows that the model has a steady performance and is powerful enough for continuously growing multimedia big data.

AB - In the age of multimedia big data, the popularity of mobile devices has been in an unprecedented growth, the speed of data increasing is faster than ever before, and Internet traffic is rapidly increasing, not only in volume but also in heterogeneity. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive papers have been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this article, a hybrid-stream model is proposed to solve these problems for video analysis. Functionality of this model covers Data Preprocessing, Data Classification, and Data-Load-Reduction Processing. Specifically, an improved Convolutional Neural Networks (CNN) classification algorithm is designed to evaluate the importance of each video frame and video clip to enhance classification precision. Then, a reliable keyframe extraction mechanism will recognize the importance of each frame or clip, and decide whether to abandon it automatically by a series of correlation operations. The model will reduce data load to a dynamic threshold changed by σ, control the input size of the video in mobile Internet, and thus reduce network overload. Through experimental simulations, we find that the size of processed video has been effectively reduced and the quality of experience (QoE) has not been lowered due to a suitably selected parameter η. The simulation also shows that the model has a steady performance and is powerful enough for continuously growing multimedia big data.

UR - http://www.scopus.com/inward/record.url?scp=84994531567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994531567&partnerID=8YFLogxK

U2 - 10.1145/2990473

DO - 10.1145/2990473

M3 - Article

AN - SCOPUS:84994531567

VL - 12

JO - ACM Transactions on Multimedia Computing, Communications and Applications

JF - ACM Transactions on Multimedia Computing, Communications and Applications

SN - 1551-6857

IS - 5s

M1 - 2990473

ER -