A Survey of Machine Learning Techniques for Video Quality Prediction from Quality of Delivery Metrics

Abstract

A growing number of video streaming networks are incorporating machine learning (ML) applications. The growth of video streaming services places enormous pressure on network and video content providers who need to proactively maintain high levels of video quality. ML has been applied to predict the quality of video streams. Quality of delivery (QoD) measurements, which capture the end-to-end performances of network services, have been leveraged in video quality prediction. The drive for end-to-end encryption, for privacy and digital rights management, has brought about a lack of visibility for operators who desire insights from video quality metrics. In response, numerous solutions have been proposed to tackle the challenge of video quality prediction from QoD-derived metrics. This survey provides a review of studies that focus on ML techniques for predicting the QoD metrics in video streaming services. In the context of video quality measurements, we focus on QoD metrics, which are not tied to a particular type of video streaming service. Unlike previous reviews in the area, this contribution considers papers published between 2016 and 2021. Approaches for predicting QoD for video are grouped under the following headings: (1) video quality prediction under QoD impairments, (2) prediction of video quality from encrypted video streaming traffic, (3) predicting the video quality in HAS applications, (4) predicting the video quality in SDN applications, (5) predicting the video quality in wireless settings, and (6) predicting the video quality in WebRTC applications. Throughout the survey, some research challenges and directions in this area are discussed, including (1) machine learning over deep learning; (2) adaptive deep learning for improved video delivery; (3) computational cost and interpretability; (4) self-healing networks and failure recovery. The survey findings reveal that traditional ML algorithms are the most widely adopted models for solving video quality prediction problems. This family of algorithms has a lot of potential because they are well understood, easy to deploy, and have lower computational requirements than deep learning techniques.

PVPBC: Privacy and Verifiability Preserving E-Voting Based on Permissioned Blockchain

“…Secondly, due consideration is not given to information propagation delay, which is an on-going concern in public networks that maintain DLs [25,26]. Potential solutions exist in the form of modern machine-learning approaches that aim to minimize variation in propagation times [27,28] and deep-learning-based traffic-classification schemes [29] which seek to utilize network resources better. The net result of these issues is that votes might be absent from the DL at the end of an election.…”

Integrating Visual and Network Data with Deep Learning for Streaming Video Quality Assessment

“…The disadvantages of subjective and objective methods have led to using machine learning-based methods for QoE prediction [40]. Deep learning is a subcategory of machine learning [41], with convolutional neural networks (CNNs) being one of the most popular and remarkable deep learning networks [42].…”

A Taxonomy for Generative Adversarial Networks in Dynamic Adaptive Streaming Over HTTP

“…Chunk-Based Adaptation [7)]: GAN models utilized to determine the optimal chunk size and quality level for video streaming, dynamically adjusting the streaming parameters. Chunk-based adaptation is a technique used in video streaming to dynamically adjust the size and quality level of video chunks based on network conditions and user preferences.…”