ANN based measurement for no-reference video quality of experience metric

Amal Sufiuh Ajrash; Rana Fareed Ghani; Laith Al-Jobouri

doi:10.1109/CEEC47804.2019.8974336

ANN based measurement for no-reference video quality of experience metric

Amal Sufiuh Ajrash, Rana Fareed Ghani, Laith Al-Jobouri

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In recent years, there has been a tremendous development in information technology, which has led to the possibility of fast access to different data types over the Internet, one of the data type is video and the ability for the user to watch video directly online. This paper provides a video streaming QoE evaluation metric that does not require any information on the reference video. The proposed system extract numbers of features from videos that are used to train the neural network and finally evaluate the QoE value. Verify training models prediction using 10-fold cross-validation. The proposed system had the best correlation result 0.95 in SRCC metric.

Original language	English
Title of host publication	2019 11th Computer Science and Electronic Engineering Conference (CEEC)
Subtitle of host publication	conference proceedings
Place of Publication	Piscataway
Publisher	IEEE
Pages	128-133
Number of pages	6
ISBN (Electronic)	9781728129525, 9781728129518
ISBN (Print)	9781728129532
DOIs	https://doi.org/10.1109/CEEC47804.2019.8974336
Publication status	Published - 30 Jan 2020
Externally published	Yes
Event	11th Computer Science and Electronic Engineering Conference - University of Essex, Colchester, United Kingdom Duration: 18 Sept 2019 → 20 Sept 2019 Conference number: 11th

Conference

Conference	11th Computer Science and Electronic Engineering Conference
Abbreviated title	CEEC 2019
Country/Territory	United Kingdom
City	Colchester
Period	18/09/19 → 20/09/19

Keywords

Quality of experience (QoE)
Quality of service (QoS)
Neural network
Freezing feature
Cross validation

Access to Document

10.1109/CEEC47804.2019.8974336

Cite this

@inproceedings{5c34c604b2e841aa9860b8e9de10298d,

title = "ANN based measurement for no-reference video quality of experience metric",

abstract = "In recent years, there has been a tremendous development in information technology, which has led to the possibility of fast access to different data types over the Internet, one of the data type is video and the ability for the user to watch video directly online. This paper provides a video streaming QoE evaluation metric that does not require any information on the reference video. The proposed system extract numbers of features from videos that are used to train the neural network and finally evaluate the QoE value. Verify training models prediction using 10-fold cross-validation. The proposed system had the best correlation result 0.95 in SRCC metric.",

author = "Ajrash, \{Amal Sufiuh\} and Ghani, \{Rana Fareed\} and Laith Al-Jobouri",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 11th Computer Science and Electronic Engineering Conference, CEEC 2019 ; Conference date: 18-09-2019 Through 20-09-2019",

year = "2020",

month = jan,

day = "30",

doi = "10.1109/CEEC47804.2019.8974336",

language = "English",

isbn = "9781728129532",

pages = "128--133",

booktitle = "2019 11th Computer Science and Electronic Engineering Conference (CEEC)",

publisher = "IEEE ",

}

Ajrash, AS, Ghani, RF & Al-Jobouri, L 2020, ANN based measurement for no-reference video quality of experience metric. in 2019 11th Computer Science and Electronic Engineering Conference (CEEC): conference proceedings. IEEE , Piscataway, pp. 128-133, 11th Computer Science and Electronic Engineering Conference, Colchester, United Kingdom, 18/09/19. https://doi.org/10.1109/CEEC47804.2019.8974336

TY - GEN

T1 - ANN based measurement for no-reference video quality of experience metric

AU - Ajrash, Amal Sufiuh

AU - Ghani, Rana Fareed

AU - Al-Jobouri, Laith

N1 - Conference code: 11th

PY - 2020/1/30

Y1 - 2020/1/30

N2 - In recent years, there has been a tremendous development in information technology, which has led to the possibility of fast access to different data types over the Internet, one of the data type is video and the ability for the user to watch video directly online. This paper provides a video streaming QoE evaluation metric that does not require any information on the reference video. The proposed system extract numbers of features from videos that are used to train the neural network and finally evaluate the QoE value. Verify training models prediction using 10-fold cross-validation. The proposed system had the best correlation result 0.95 in SRCC metric.

AB - In recent years, there has been a tremendous development in information technology, which has led to the possibility of fast access to different data types over the Internet, one of the data type is video and the ability for the user to watch video directly online. This paper provides a video streaming QoE evaluation metric that does not require any information on the reference video. The proposed system extract numbers of features from videos that are used to train the neural network and finally evaluate the QoE value. Verify training models prediction using 10-fold cross-validation. The proposed system had the best correlation result 0.95 in SRCC metric.

U2 - 10.1109/CEEC47804.2019.8974336

DO - 10.1109/CEEC47804.2019.8974336

M3 - Conference contribution

AN - SCOPUS:85079349068

SN - 9781728129532

SP - 128

EP - 133

BT - 2019 11th Computer Science and Electronic Engineering Conference (CEEC)

PB - IEEE

CY - Piscataway

T2 - 11th Computer Science and Electronic Engineering Conference

Y2 - 18 September 2019 through 20 September 2019

ER -

ANN based measurement for no-reference video quality of experience metric

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this