Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming

Tho Nguyen Duc, Chanh Minh Tran, Tan Phan Xuan, Eiji Kamioka

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

1 Citation (Scopus)

Abstract

Continuous monitoring of quality of experience (QoE) has increasingly become an important mechanism in quantifying the user's satisfaction over video streaming services. Such mechanism requires approaches with the ability to model the complex temporal dependencies and time-varying characteristics of the QoE. Long-Short Term Memory (LSTM) related approaches carried out by recent research efforts have shown highly potential results since they can leverage past events occurring during a streaming session. However, the unidirectional LSTM structure only consider forward dependencies, leading to high possibility of missing out useful information. In this paper, a novel model for continuous QoE prediction is proposed to consider not only forward dependencies but also backward dependencies. The proposal utilizes a Bidirectional Long Short Term-Memory (BLSTM) model to process inputs obtained from perceptual video quality algorithms, rebuffering, and memory-related temporal data. Comparisons with other state-of-the-art models indicate that the proposed model achieves very promising performance in terms of accuracy.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
PublisherAssociation for Computing Machinery
Pages156-160
Number of pages5
ISBN (Print)9781450361033
DOIs
Publication statusPublished - 2019 Jan 1
Event2nd International Conference on Information Science and System, ICISS 2019 - Tokyo, Japan
Duration: 2019 Mar 162019 Mar 19

Publication series

NameACM International Conference Proceeding Series
VolumePart F148384

Conference

Conference2nd International Conference on Information Science and System, ICISS 2019
CountryJapan
CityTokyo
Period19/3/1619/3/19

Fingerprint

HTTP
Video streaming
Long short-term memory
Data storage equipment
Monitoring

Keywords

  • Bidirectional LSTM
  • HTTP Adaptive Streaming
  • Quality of Experience (QoE)

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Duc, T. N., Tran, C. M., Phan Xuan, T., & Kamioka, E. (2019). Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming. In ACM International Conference Proceeding Series (pp. 156-160). (ACM International Conference Proceeding Series; Vol. Part F148384). Association for Computing Machinery. https://doi.org/10.1145/3322645.3322687

Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming. / Duc, Tho Nguyen; Tran, Chanh Minh; Phan Xuan, Tan; Kamioka, Eiji.

ACM International Conference Proceeding Series. Association for Computing Machinery, 2019. p. 156-160 (ACM International Conference Proceeding Series; Vol. Part F148384).

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

Duc, TN, Tran, CM, Phan Xuan, T & Kamioka, E 2019, Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming. in ACM International Conference Proceeding Series. ACM International Conference Proceeding Series, vol. Part F148384, Association for Computing Machinery, pp. 156-160, 2nd International Conference on Information Science and System, ICISS 2019, Tokyo, Japan, 19/3/16. https://doi.org/10.1145/3322645.3322687
Duc TN, Tran CM, Phan Xuan T, Kamioka E. Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming. In ACM International Conference Proceeding Series. Association for Computing Machinery. 2019. p. 156-160. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3322645.3322687
Duc, Tho Nguyen ; Tran, Chanh Minh ; Phan Xuan, Tan ; Kamioka, Eiji. / Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming. ACM International Conference Proceeding Series. Association for Computing Machinery, 2019. pp. 156-160 (ACM International Conference Proceeding Series).
@inproceedings{cfdcf483cc624252af75045557be84d5,
title = "Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming",
abstract = "Continuous monitoring of quality of experience (QoE) has increasingly become an important mechanism in quantifying the user's satisfaction over video streaming services. Such mechanism requires approaches with the ability to model the complex temporal dependencies and time-varying characteristics of the QoE. Long-Short Term Memory (LSTM) related approaches carried out by recent research efforts have shown highly potential results since they can leverage past events occurring during a streaming session. However, the unidirectional LSTM structure only consider forward dependencies, leading to high possibility of missing out useful information. In this paper, a novel model for continuous QoE prediction is proposed to consider not only forward dependencies but also backward dependencies. The proposal utilizes a Bidirectional Long Short Term-Memory (BLSTM) model to process inputs obtained from perceptual video quality algorithms, rebuffering, and memory-related temporal data. Comparisons with other state-of-the-art models indicate that the proposed model achieves very promising performance in terms of accuracy.",
keywords = "Bidirectional LSTM, HTTP Adaptive Streaming, Quality of Experience (QoE)",
author = "Duc, {Tho Nguyen} and Tran, {Chanh Minh} and {Phan Xuan}, Tan and Eiji Kamioka",
year = "2019",
month = "1",
day = "1",
doi = "10.1145/3322645.3322687",
language = "English",
isbn = "9781450361033",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "156--160",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Bidirectional LSTM for continuously predicting QoE in HTTP adaptive streaming

AU - Duc, Tho Nguyen

AU - Tran, Chanh Minh

AU - Phan Xuan, Tan

AU - Kamioka, Eiji

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Continuous monitoring of quality of experience (QoE) has increasingly become an important mechanism in quantifying the user's satisfaction over video streaming services. Such mechanism requires approaches with the ability to model the complex temporal dependencies and time-varying characteristics of the QoE. Long-Short Term Memory (LSTM) related approaches carried out by recent research efforts have shown highly potential results since they can leverage past events occurring during a streaming session. However, the unidirectional LSTM structure only consider forward dependencies, leading to high possibility of missing out useful information. In this paper, a novel model for continuous QoE prediction is proposed to consider not only forward dependencies but also backward dependencies. The proposal utilizes a Bidirectional Long Short Term-Memory (BLSTM) model to process inputs obtained from perceptual video quality algorithms, rebuffering, and memory-related temporal data. Comparisons with other state-of-the-art models indicate that the proposed model achieves very promising performance in terms of accuracy.

AB - Continuous monitoring of quality of experience (QoE) has increasingly become an important mechanism in quantifying the user's satisfaction over video streaming services. Such mechanism requires approaches with the ability to model the complex temporal dependencies and time-varying characteristics of the QoE. Long-Short Term Memory (LSTM) related approaches carried out by recent research efforts have shown highly potential results since they can leverage past events occurring during a streaming session. However, the unidirectional LSTM structure only consider forward dependencies, leading to high possibility of missing out useful information. In this paper, a novel model for continuous QoE prediction is proposed to consider not only forward dependencies but also backward dependencies. The proposal utilizes a Bidirectional Long Short Term-Memory (BLSTM) model to process inputs obtained from perceptual video quality algorithms, rebuffering, and memory-related temporal data. Comparisons with other state-of-the-art models indicate that the proposed model achieves very promising performance in terms of accuracy.

KW - Bidirectional LSTM

KW - HTTP Adaptive Streaming

KW - Quality of Experience (QoE)

UR - http://www.scopus.com/inward/record.url?scp=85066956905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066956905&partnerID=8YFLogxK

U2 - 10.1145/3322645.3322687

DO - 10.1145/3322645.3322687

M3 - Conference contribution

AN - SCOPUS:85066956905

SN - 9781450361033

T3 - ACM International Conference Proceeding Series

SP - 156

EP - 160

BT - ACM International Conference Proceeding Series

PB - Association for Computing Machinery

ER -