ANN based Measurement for No-Reference Video Quality of Experience Metric

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

doi:10.1109/ceec47804.2019.8974336

Cited by 2 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed system performed better value for SRCC 0.83 compared to the result in reference [18]. The correlation value for SRCC was 0.95 in reference [11], but for the proposed system was 0.96. We can summarize that we have applied a suitable model for predicting QoE in real-time with the lowest prediction error rate, good correlation, and with the lowest running time.…”

Section: A Performance Evaluation Of the Proposed Elm Modelmentioning

confidence: 61%

“…Algorithm 1 presents the freezing operation to calculate two frames' resemblance and return a percentage value (0-100). In the testing operation, the results present an inverse relationship between the QoE and freezing, and the freezing feature has a considerable impact on QoE [11].…”

Section: Freezing Featurementioning

confidence: 94%

“…al. [11] purpose an ANN model for predicting video streaming quality of experience. The authors extracted seven features and used them as input for training data.…”

Section: Litruter Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Quality of Experience Measuring for Video Conference in Real-Time

2022

IJCCCE

View full text Add to dashboard Cite

In recent years, especially with COVID-19, video conference applications have become very important. Millions of peoples around the world have become to communicate with each other through using video conference applications. The most critical factor in the performance success of video conference applications is the user's perception of the quality of the experience. In this work, an Extreme Learning Machine (ELM) model was proposed for predicting video quality of experience. The proposed system extracts several features from videos that have a significant impact on the quality of the experience. The model performance was validated with unseen data. Spearman’s Rank Correlation Coefficient (SRCC), Root Mean Square Error (RMSE), Pearson’s Linear Correlation Coefficient (PLCC) metrics have been used to measure the accuracy of the model and correlation. The results demonstrate that the proposed model had better performance than models used by the previous researchers that were used for predicting video QoE in terms of precision, correlation, and running time. Index Terms— Extreme Learning Machine, Quality of Experience, Quality of Service, Video Streaming.

show abstract

Section: A Performance Evaluation Of the Proposed Elm Modelmentioning

confidence: 61%

Section: Freezing Featurementioning

confidence: 94%

See 1 more Smart Citation

Automatic Quality of Experience Measuring for Video Conference in Real-Time

2022

IJCCCE

View full text Add to dashboard Cite

show abstract

“…The best real-time and accuracy performance was provided by the AdaBoost decision tree. Sufiuh et al [11] presented an ANN algorithm to predict the video QoE. They extracted seven features and utilized them as inputs for training data.…”

Section: Literature Reviewmentioning

confidence: 99%

Audio-Visual Quality of Experience Prediction Based on ELM Model

2022

IJIES

View full text Add to dashboard Cite

Measuring end-user satisfaction, or quality of experience (QoE) became necessary to improve video streaming applications. This measure represents the end-user's degree of satisfaction with the quality of their video conference. This study measures both audio and video QoE, using two types of databases; (UnB-AV database and INRS database) have been used in this work. The UnB-AB database has been used as a target dataset. In this work, several features for audio and video files have been extracted. The extreme learning machine algorithm has been used for predicting the audio-visual QoE, and performance of the proposed model was validated with unseen data. Experiments on the two datasets have shown that the ELM model achieving better prediction accuracy when applied on the UnB-AV database than INRS database. The prediction accuracy by depended on UnB-AV dataset was (0.13) but in depended on INRS dataset was (0.16).

show abstract

ANN based Measurement for No-Reference Video Quality of Experience Metric

Cited by 2 publications

References 7 publications

Automatic Quality of Experience Measuring for Video Conference in Real-Time

Automatic Quality of Experience Measuring for Video Conference in Real-Time

Audio-Visual Quality of Experience Prediction Based on ELM Model

Contact Info

Product

Resources

About