Real-time big data analytics for multimedia transmission and storage

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

With increase demand on wireless services, equipment supporting multimedia applications has been becoming more and more popular in recent years. With billions of devices involved in mobile Internet, data volume is undergoing an extremely rapid growth. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive study has been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this paper, a hybrid-stream big data analytics model is proposed to perform big data video analysis. This model contains four procedures, i.e., data preprocessing, data classification, data recognition and data load reduction. Specifically, an innovative multi-dimensional Convolution Neural Network (CNN) is proposed to obtain the importance of each video frame. Thus, those unimportant frames can be dropped by a reliable decision-making algorithm. Then, a reliable key frame extraction mechanism will recognize the importance of each frame or clip and then decide whether to abandon it automatically by a series of correlation operations. Simulation results illustrate that the size of the processed video has been effectively reduced. The simulation also shows that proposed model performs steadily and is robust enough to keep up with the big data crush in multimedia era.

Original languageEnglish
Title of host publication2016 IEEE/CIC International Conference on Communications in China, ICCC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509021437
DOIs
Publication statusPublished - 2016 Oct 21
Event2016 IEEE/CIC International Conference on Communications in China, ICCC 2016 - Chengdu, China
Duration: 2016 Jul 272016 Jul 29

Publication series

Name2016 IEEE/CIC International Conference on Communications in China, ICCC 2016

Other

Other2016 IEEE/CIC International Conference on Communications in China, ICCC 2016
CountryChina
CityChengdu
Period16-07-2716-07-29

Fingerprint

Convolution
Image analysis
Decision making
Internet
Neural networks
Big data
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing

Cite this

Wang, K., Mi, J., Xu, C., Shu, L., & Deng, D-J. (2016). Real-time big data analytics for multimedia transmission and storage. In 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016 [7636815] (2016 IEEE/CIC International Conference on Communications in China, ICCC 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCChina.2016.7636815
Wang, Kun ; Mi, Jun ; Xu, Chenhan ; Shu, Lei ; Deng, Der-Jiunn. / Real-time big data analytics for multimedia transmission and storage. 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE/CIC International Conference on Communications in China, ICCC 2016).
@inproceedings{b45a313586cc4bf0bdbb48ec49f14cf6,
title = "Real-time big data analytics for multimedia transmission and storage",
abstract = "With increase demand on wireless services, equipment supporting multimedia applications has been becoming more and more popular in recent years. With billions of devices involved in mobile Internet, data volume is undergoing an extremely rapid growth. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive study has been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this paper, a hybrid-stream big data analytics model is proposed to perform big data video analysis. This model contains four procedures, i.e., data preprocessing, data classification, data recognition and data load reduction. Specifically, an innovative multi-dimensional Convolution Neural Network (CNN) is proposed to obtain the importance of each video frame. Thus, those unimportant frames can be dropped by a reliable decision-making algorithm. Then, a reliable key frame extraction mechanism will recognize the importance of each frame or clip and then decide whether to abandon it automatically by a series of correlation operations. Simulation results illustrate that the size of the processed video has been effectively reduced. The simulation also shows that proposed model performs steadily and is robust enough to keep up with the big data crush in multimedia era.",
author = "Kun Wang and Jun Mi and Chenhan Xu and Lei Shu and Der-Jiunn Deng",
year = "2016",
month = "10",
day = "21",
doi = "10.1109/ICCChina.2016.7636815",
language = "English",
series = "2016 IEEE/CIC International Conference on Communications in China, ICCC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2016 IEEE/CIC International Conference on Communications in China, ICCC 2016",
address = "United States",

}

Wang, K, Mi, J, Xu, C, Shu, L & Deng, D-J 2016, Real-time big data analytics for multimedia transmission and storage. in 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016., 7636815, 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016, Chengdu, China, 16-07-27. https://doi.org/10.1109/ICCChina.2016.7636815

Real-time big data analytics for multimedia transmission and storage. / Wang, Kun; Mi, Jun; Xu, Chenhan; Shu, Lei; Deng, Der-Jiunn.

2016 IEEE/CIC International Conference on Communications in China, ICCC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7636815 (2016 IEEE/CIC International Conference on Communications in China, ICCC 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Real-time big data analytics for multimedia transmission and storage

AU - Wang, Kun

AU - Mi, Jun

AU - Xu, Chenhan

AU - Shu, Lei

AU - Deng, Der-Jiunn

PY - 2016/10/21

Y1 - 2016/10/21

N2 - With increase demand on wireless services, equipment supporting multimedia applications has been becoming more and more popular in recent years. With billions of devices involved in mobile Internet, data volume is undergoing an extremely rapid growth. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive study has been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this paper, a hybrid-stream big data analytics model is proposed to perform big data video analysis. This model contains four procedures, i.e., data preprocessing, data classification, data recognition and data load reduction. Specifically, an innovative multi-dimensional Convolution Neural Network (CNN) is proposed to obtain the importance of each video frame. Thus, those unimportant frames can be dropped by a reliable decision-making algorithm. Then, a reliable key frame extraction mechanism will recognize the importance of each frame or clip and then decide whether to abandon it automatically by a series of correlation operations. Simulation results illustrate that the size of the processed video has been effectively reduced. The simulation also shows that proposed model performs steadily and is robust enough to keep up with the big data crush in multimedia era.

AB - With increase demand on wireless services, equipment supporting multimedia applications has been becoming more and more popular in recent years. With billions of devices involved in mobile Internet, data volume is undergoing an extremely rapid growth. Therefore, data processing and network overload have become two urgent problems. To address these problems, extensive study has been published on image analysis using deep learning, but only a few works have exploited this approach for video analysis. In this paper, a hybrid-stream big data analytics model is proposed to perform big data video analysis. This model contains four procedures, i.e., data preprocessing, data classification, data recognition and data load reduction. Specifically, an innovative multi-dimensional Convolution Neural Network (CNN) is proposed to obtain the importance of each video frame. Thus, those unimportant frames can be dropped by a reliable decision-making algorithm. Then, a reliable key frame extraction mechanism will recognize the importance of each frame or clip and then decide whether to abandon it automatically by a series of correlation operations. Simulation results illustrate that the size of the processed video has been effectively reduced. The simulation also shows that proposed model performs steadily and is robust enough to keep up with the big data crush in multimedia era.

UR - http://www.scopus.com/inward/record.url?scp=84997815804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997815804&partnerID=8YFLogxK

U2 - 10.1109/ICCChina.2016.7636815

DO - 10.1109/ICCChina.2016.7636815

M3 - Conference contribution

AN - SCOPUS:84997815804

T3 - 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016

BT - 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wang K, Mi J, Xu C, Shu L, Deng D-J. Real-time big data analytics for multimedia transmission and storage. In 2016 IEEE/CIC International Conference on Communications in China, ICCC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7636815. (2016 IEEE/CIC International Conference on Communications in China, ICCC 2016). https://doi.org/10.1109/ICCChina.2016.7636815