Non-intrusive method for video quality prediction over LTE using random neural networks (RNN)

Tarik Mohamed Ghalut; Hadi Larijani

doi:10.1109/CSNDSP.2014.6923884

Non-intrusive method for video quality prediction over LTE using random neural networks (RNN)

Tarik Mohamed Ghalut, Hadi Larijani

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

Abstract

Long Term Evolution (LTE) is the preliminary version of a fourth generation (4G) mobile communication system. Its aim is to support different services with high data rates and strict Quality of Experience (QoE) requirements of users. The main aim of this study is to present a prediction model based on Random Neural Networks (RNNs) for objective, non-intrusive prediction of video quality over LTE for video applications. A three layer feed-forward RNN model with gradient descent training algorithm has been developed. This model uses a combination of objective parameters in the application and network layers, such as Content Type (CT), Sender Bit Rate (SBR), resolution size, Frame Rate (FR), codec, and packet loss rate (PLR). The video quality was predicted in terms of the Mean Opinion Score (MOS). The results show an approximate 50% increase in accuracy using this model, compared to previous models. LTE-Sim software has been used to generate different samples for testing and training RNN model.

Original language	English
Title of host publication	Proceedings of the 9th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 14)
Publisher	IEEE
Pages	519-524
Number of pages	6
DOIs	https://doi.org/10.1109/CSNDSP.2014.6923884
Publication status	Published - 2014

Keywords

long term evolution (LTE)
4G mobile communication
random neural networks (RNN)

Documents and Links

10.1109/CSNDSP.2014.6923884

Fingerprint Dive into the research topics of 'Non-intrusive method for video quality prediction over LTE using random neural networks (RNN)'. Together they form a unique fingerprint.

Cite this

@inproceedings{1273c7b78a1f49b8b8e337fb1cabc723,

title = "Non-intrusive method for video quality prediction over LTE using random neural networks (RNN)",

abstract = "Long Term Evolution (LTE) is the preliminary version of a fourth generation (4G) mobile communication system. Its aim is to support different services with high data rates and strict Quality of Experience (QoE) requirements of users. The main aim of this study is to present a prediction model based on Random Neural Networks (RNNs) for objective, non-intrusive prediction of video quality over LTE for video applications. A three layer feed-forward RNN model with gradient descent training algorithm has been developed. This model uses a combination of objective parameters in the application and network layers, such as Content Type (CT), Sender Bit Rate (SBR), resolution size, Frame Rate (FR), codec, and packet loss rate (PLR). The video quality was predicted in terms of the Mean Opinion Score (MOS). The results show an approximate 50% increase in accuracy using this model, compared to previous models. LTE-Sim software has been used to generate different samples for testing and training RNN model.",

keywords = "long term evolution (LTE), 4G mobile communication, random neural networks (RNN)",

author = "Ghalut, {Tarik Mohamed} and Hadi Larijani",

year = "2014",

doi = "10.1109/CSNDSP.2014.6923884",

language = "English",

pages = "519--524",

booktitle = "Proceedings of the 9th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 14)",

publisher = "IEEE",

}

Non-intrusive method for video quality prediction over LTE using random neural networks (RNN). / Ghalut, Tarik Mohamed; Larijani, Hadi.

Proceedings of the 9th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 14). IEEE, 2014. p. 519-524.

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

TY - GEN

T1 - Non-intrusive method for video quality prediction over LTE using random neural networks (RNN)

AU - Ghalut, Tarik Mohamed

AU - Larijani, Hadi

PY - 2014

Y1 - 2014

N2 - Long Term Evolution (LTE) is the preliminary version of a fourth generation (4G) mobile communication system. Its aim is to support different services with high data rates and strict Quality of Experience (QoE) requirements of users. The main aim of this study is to present a prediction model based on Random Neural Networks (RNNs) for objective, non-intrusive prediction of video quality over LTE for video applications. A three layer feed-forward RNN model with gradient descent training algorithm has been developed. This model uses a combination of objective parameters in the application and network layers, such as Content Type (CT), Sender Bit Rate (SBR), resolution size, Frame Rate (FR), codec, and packet loss rate (PLR). The video quality was predicted in terms of the Mean Opinion Score (MOS). The results show an approximate 50% increase in accuracy using this model, compared to previous models. LTE-Sim software has been used to generate different samples for testing and training RNN model.

AB - Long Term Evolution (LTE) is the preliminary version of a fourth generation (4G) mobile communication system. Its aim is to support different services with high data rates and strict Quality of Experience (QoE) requirements of users. The main aim of this study is to present a prediction model based on Random Neural Networks (RNNs) for objective, non-intrusive prediction of video quality over LTE for video applications. A three layer feed-forward RNN model with gradient descent training algorithm has been developed. This model uses a combination of objective parameters in the application and network layers, such as Content Type (CT), Sender Bit Rate (SBR), resolution size, Frame Rate (FR), codec, and packet loss rate (PLR). The video quality was predicted in terms of the Mean Opinion Score (MOS). The results show an approximate 50% increase in accuracy using this model, compared to previous models. LTE-Sim software has been used to generate different samples for testing and training RNN model.

KW - long term evolution (LTE)

KW - 4G mobile communication

KW - random neural networks (RNN)

U2 - 10.1109/CSNDSP.2014.6923884

DO - 10.1109/CSNDSP.2014.6923884

M3 - Conference contribution

SP - 519

EP - 524

BT - Proceedings of the 9th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 14)

PB - IEEE

ER -