Vlado Menkovski

Predicting quality of experience in multimedia streaming

Measuring and predicting the users Quality of Experience (QoE) of a multimedia stream is the first step towards improving and optimizing the provision of mobile streaming services. This enables us to better understand how Quality of Service (QoS) parameters affect service quality, as it is actually perceived by the end user. Over the last years this goal has been pursued by means of subjective tests and through the analysis of the users feedback. Existing statistical techniques have lead to poor accuracy (order of 70%) and inability to evolve prediction models with the systems dynamics. In this paper, we propose a novel approach for building accurate and adaptive QoE prediction models using Machine Learning classification algorithms, trained on subjective test data. These models can be used for real-time prediction of QoE and can be efficiently integrated into online learning systems that can adapt the models according to changes in the environment. Providing high accuracy of above 90%, the classification algorithms become an indispensible component of a mobile multimedia QoE management system.

Intelligent control for adaptive video streaming

We present an autonomous learning agent for adaptive video streaming in best effort networks. The agent learns an optimal control strategy in regards to the delivered quality of experience without the need for implementation of a complex heuristics.

Quality of Experience Models for Multimedia Streaming

Understanding how quality is perceived by viewers of multimedia streaming services is essential for efficient management of those services. Quality of Experience QoE is a subjective metric that quantifies the perceived quality, which is crucial in the process of optimizing tradeoff between quality and resources. However, accurate estimation of QoE often entails cumbersome studies that are long and expensive to execute. In this regard, the authors present a QoE estimation methodology for developing Machine Learning prediction models based on initial restricted-size subjective tests. Experimental results on subjective data from streaming multimedia tests show that the Machine Learning models outperform other statistical methods achieving accuracy greater than 90%. These models are suitable for real-time use due to their small computational complexity. Even though they have high accuracy, these models are static and cannot adapt to environmental change. To maintain the accuracy of the prediction models, the authors have adopted Online Learning techniques that update the models on data from subjective viewer feedback. This method provides accurate and adaptive QoE prediction models that are an indispensible component of a QoE-aware management service.

Adaptive psychometric scaling for video quality assessment

Video quality estimation is crucial for the efficient management of video delivery services. Particularly with the advances in screen technology and content delivery networks, getting an accurate estimation of the video quality as it is actually perceived by the user, is a key factor in delivering high quality-of-experience. Psychometric scaling provides the tools to measure the impact that different types of impairments have on the delivered quality. In contrast to the more conventional subjective rating procedures, psychometric scaling does not suffer from biases and has significantly lower variability. However, the existing psychometric methods such as Maximum Likelihood Difference Scaling (MLDS) entail a large number subjective tests. Herein we present an adaptive approach that leads to improvement in the learning rate and, in turn, to resource-efficient video delivery systems.

Instantaneous Video Quality Assessment for lightweight devices

Monitoring and controlling the users Quality of Experience (QoE) in modern video services is a challenging proposition, mainly due to the limitations of current video quality assessment algorithms. While subjective QoE methods would better reflect the nature of human perception, these are not suitable in real-time automation cases. On the other hand, the existing objective algorithms are either too complex or too inaccurate, particularly in the context of lightweight devices such as camera sensors or smart phones. This paper introduces a novel objective QoE algorithm, Instantaneous Video Quality Assessment (IVQA), that is comparably as accurate as the most heavyweight algorithm available in the literature but can also be run in real-time. This approach is tested against a selection of ten objective metrics and benchmarked with a subjective user dataset.

Machine Learning Approach for Quality of Experience Aware Networks

Efficient management of multimedia services necessitates the understanding of how the quality of these services is perceived by the users. Estimation of the perceived quality or Quality of Experience (QoE) of the service is a challenging process due to the subjective nature of QoE. This process usually incorporates complex subjective studies that need to recreate the viewing conditions of the service in a controlled environment. In this paper we present Machine Learning techniques for modeling the dependencies of different network and application layer quality of service parameters to the QoE of network services using subjective quality feedback. These accurate QoE prediction models allow us to further develop a geometrical method for calculating the possible remedies per network stream for reaching the desired level of QoE. Finally we present a set of possible network techniques that can deliver the desired improvement to the multimedia streams.

Estimations and Remedies for Quality of Experience in Multimedia Streaming

Managing multimedia network services in a User-centric manner provides for more delivered quality to the users, whilst maintaining a limited footprint on the network resources. For efficient User-centric management it is imperative to have a precise metric for perceived quality. Quality of Experience (QoE) is such a metric, which captures many different aspects that compose the perception of quality. The drawback of using QoE is that due to its subjectiveness, accurate measurement necessitates execution of cumbersome subjective studies. In this work we propose a method that uses Machine Learning techniques to build QoE prediction models based on limited subjective data. Using those models we have developed an algorithm that generates the remedies for improving the QoE of observed multimedia stream. Selecting the optimal remedy is done by comparing the costs in resources associated to each of them. Coupling the QoE estimation and calculation of remedies produces a tool for effective implementation of a User-centric management loop for multimedia streaming services.

SKYPE RESILIENCE TO HIGH MOTION VIDEOS

Skype is one of the most popular video call services in the current Internet world. One of its strengths is the use of an adaptive mechanism to match the constraints of the underlying network. This work is focused on how this mechanism can maximize the video quality as perceived by the viewers using objective assessment methods. We built a testbed to stream certain video sequences through Skype between two clients over impaired communication channels. Original and recorded videos were compared to assess the achieved quality. Extensive experimentation has shown that Skype has problems when transmitting high motion videos and especially complex videos with frequent interchange between frames of low and high temporal information. The results suggest that random packet loss intensifies quality degradation for those videos more than packet loss bursts or jitter.

QoE for Mobile Streaming

After its debut in personal computers and home entertainment devices, streaming video has found its place in the mobile environment as well. However, the characteristics of the mobile devices present a different set of challenges for delivering satisfactory video services. They are typically smaller in size designed to be handheld or carried on person in some manner. They have reduced screen size and somewhat limited computational power due to restrictions in size and power consumption. These technical challenges necessitate the adaptation of the content to the particular device so that successful reproduction is possible and desired quality is met. When the mobile device is exposed to unadjusted content in spatial resolution and frame-rate, unnecessary penalties in computational load are incurred mostly due to processing of the downscaling. This in turn leads to higher power consumption and can lower the quality if the device fails to execute the task on time. In general the issue of over and underprovisioning is present in any video streaming service. However, in mobile streaming it is particularly evident due to specific limitations of the mobile devices and the larger variety in the design of the user interface and the mode of interaction.

Network analysis on skype end-to-end video quality

Purpose – This paper aims to argue on the efficiency of Quality of Service (QoS)-based adaptive streaming with regards to perceived quality Quality of Experience (QoE). Although QoS parameters are extensively used even by high-end adaptive streaming algorithms, achieved QoE fails to justify their use in real-time streaming videos with high motion. While subjective measurements of video quality are difficult to be applied at runtime, objective QoE assessment can be easier to automate. For end-to-end QoS optimization of live streaming of high-motion video, objective QoE is a more applicable approach. This paper contributes to the understanding of how specific QoS parameters affect objective QoE measurements on real-time high-motion video streaming. Design/methodology/approach – The paper approached the question through real-life and extensive experimentation using the Skype adaptive mechanisms. Two Skype terminals were connected through a QoS impairment box. A reference video was used as input to one Skype ...