QoS Monitoring

This paper describes the effects of the Packet Wash process on the transmission of layered SVC video streams. We show how the packet size is adapted when using a number of different packing strategies, that map the video data into the BPP packets, and discuss the relationship between the packing strategies on the sender side and the chunk removal in the washing process. We demonstrate how the packing strategy causes different impacts on the number of and the sizes of the washed chunks. As the bandwidth reduces, more of the chunks in a packet get washed away. Although the receiver gets packets that are much smaller than those transmitted by the sender, it is still able to play video with a high QoE as zero packets are dropped. This traffic engineering enables a direct implementation of an in-network video adaption scheme. The experimental evaluation highlights that the effects of Packet Wash become more obvious in environments where there is limited bandwidth.

In this paper, we discuss quality of experience in multimedia networks. We present an architecture and a survey of machine learning methods to predict the quality of experience in an enterprise multimedia network environment. Our approach is based on subjective methods. It consists of the use PRTG (Paessler Router Traffic Grapher) for QoS (quality of service) data collection and Google Forms for the different users of the network MOS (Minimum Score Opinion) parameters collection. We then implement different supervised machine learning schemes using the data collected, and finally analyze their performance. We compare two classes of algorithms namely regression algorithms and classification algorithms. The Random Forest Classifier in the second class algorithm give the best results.

The quality of experience (QoE) is one of the main research lines in ITC industry, which seeks to manage quality as perceived by users. This document analyzes and describes requirements of a QoE driven management system architecture, which has been designed in the Celtic IPNQSIS project. The architecture is grouped into different levels: Data acquisition level, Monitoring level and Control Level. Each level comprises a specific set of capacities, such as Data collector, or Traffic Monitor amongst others. The architecture described in this paper constitutes the guidelines of the IPNQSIS project in terms of a QoE ecosystem that will settle the basis of global customer experience management architecture.

Quality of Experience (QoE) consists of a set of indicators that show the perceived satisfaction of using a multimedia (or other kind of) service by the end user. Being so the QoE presents a subjective metric and the only relevant mechanisms for measuring such indicators are subjective tests. Due to the fact that subjective tests are an expensive, impractical and in cases of live streaming a close to impossible exercise we set out on a twofold task to address this issue. First we set out to build prediction models using traditional Machine Learning (ML) techniques based on subjective test data. Second we explore an approach for reduction of the training dataset that will minimize the need for subjective data whilst keeping the prediction models as accurate as possible. For the first goal we used supervised learning based classification algorithms and we came up with high accuracy (over ninety percent) for the prediction models. To address the issue of high cost training data we developed a novel approach in reducing the training dataset while keeping a high accuracy of the classifiers. The reduction method provides a grading mechanism for unseen data. By having this mechanism in the online learning platform we can optimize the process of asking for user feedback by looking for the most significant cases, and therefore improving the gain on the trade-off between more feedback and more accuracy.

Quality of Experience (QoE) consists of a set of indicators that show the perceived satisfaction of using a multimedia (or other kind of) service by the end user. Being so the QoE presents a subjective metric and the only relevant mechanisms for measuring such indicators are subjective tests. Due to the fact that subjective tests are an expensive, impractical and in cases of live streaming a close to impossible exercise we set out on a twofold task to address this issue. First we set out to build prediction models using traditional Machine Learning (ML) techniques based on subjective test data. Second we explore an approach for reduction of the training dataset that will minimize the need for subjective data whilst keeping the prediction models as accurate as possible. For the first goal we used supervised learning based classification algorithms and we came up with high accuracy (over ninety percent) for the prediction models. To address the issue of high cost training data we developed a novel approach in reducing the training dataset while keeping a high accuracy of the classifiers. The reduction method provides a grading mechanism for unseen data. By having this mechanism in the online learning platform we can optimize the process of asking for user feedback by looking for the most significant cases, and therefore improving the gain on the trade-off between more feedback and more accuracy.

Modern Internet applications rely on rich multimedia contents making the quality of experience (QoE) of end users sensitive to network conditions. Several models were developed in the literature to express QoE as a function of measurements carried out on the traffic of the applications themselves. In this paper, we propose a new methodology based on machine learning able to link expected QoE to network and device level measurements outside the applications' traffic. This direct linking to network and device level measurements is important for the prediction of QoE. We prove the feasibility of the approach in the context of Skype. In particular, we derive and validate a model to predict the Skype QoE as a function of easily measurable network performance metrics. One can see our methodology as a new way of performing measurements in the Internet, where instead of expressing the expected performance in terms of network and device level measurements that only specialists can understand, we express performance in clear terms related to expected quality of experience for different applications.

BBR is a new congestion control algorithm and is seeing increased adoption especially for video traffic. BBR solves the bufferbloat problem in legacy loss-based congestion control algorithms where application performance drops considerably when router buffers are deep. BBR regulates traffic such that router queues don't build up to avoid the bufferbloat problem while still maintaining high throughput. However, our analysis shows that video applications experience significantly poor performance when using BBR under deep buffers. In fact, we find that video traffic sees inflated latencies because of long queues at the router, ultimately degrading video performance. To understand this dichotomy, we study the interaction between BBR and DASH video. Our investigation reveals that BBR under deep buffers and high network burstiness severely overestimates available bandwidth and does not converge to steady state, both of which results in BBR sending substantially more data into the network, causing a queue buildup. This elevated packet sending rate under BBR is ultimately caused by the router's ability to absorb bursts in traffic, which destabilizes BBR's bandwidth estimation and overrides BBR's expected logic for exiting the startup phase. We design a new bandwidth estimation algorithm and apply it to BBR (and a still-unreleased, newer version of BBR called BBR2). Our modified BBR and BBR2 both see significantly improved video QoE even under deep buffers.

BBR is a new congestion control algorithm and is seeing increased adoption especially for video traffic. BBR solves the bufferbloat problem in legacy loss-based congestion control algorithms where application performance drops considerably when router buffers are deep. BBR regulates traffic such that router queues don't build up to avoid the bufferbloat problem while still maintaining high throughput. However, our analysis shows that video applications experience significantly poor performance when using BBR under deep buffers. In fact, we find that video traffic sees inflated latencies because of long queues at the router, ultimately degrading video performance. To understand this dichotomy, we study the interaction between BBR and DASH video. Our investigation reveals that BBR under deep buffers and high network burstiness severely overestimates available bandwidth and does not converge to steady state, both of which results in BBR sending substantially more data into the network, causing a queue buildup. This elevated packet sending rate under BBR is ultimately caused by the router's ability to absorb bursts in traffic, which destabilizes BBR's bandwidth estimation and overrides BBR's expected logic for exiting the startup phase. We design a new bandwidth estimation algorithm and apply it to BBR (and a still-unreleased, newer version of BBR called BBR2). Our modified BBR and BBR2 both see significantly improved video QoE even under deep buffers.

In mobile ad hoc network (MANET) cluster head selection is considered a gigantic challenge. In wireless sensor network LEACH protocol can be used to select cluster head on the bases of energy, but it is still a dispute in mobil ad hoc networks and especially when nodes are itinerant. In this paper we proposed an efficient cluster head selection algorithm (ECHSA), for selection of the cluster head efficiently in Mobile ad hoc networks. We evaluate our proposed algorithm through simulation in OMNet++ as well as on test bed; we experience the result according to our assumption. For further evaluation we also compare our proposed protocol with several other protocols like LEACH-C and consequences show perfection.

In cellular networks, the emergence of machine communications such as connected vehicles increases the high demand of uplink transmissions, thus, degrading the quality of service per user equipment. Enforcing quality-of-service in such cellular network is challenging, as radio phenomena, as well as user (and their devices) mobility and dynamics, are uncontrolled. To solve this issue, estimating what the quality of transmissions will be in a short future for a connected user is essential. For that purpose, we argue that lower layer metrics are a key feature whose evolution can help predict the bandwidth that the considered connections can take advantage of in the following hundreds of milliseconds. The paper then describes how a 4G testbed has been deployed in order to investigate throughput prediction in uplink transmissions at a small time granularity of 100 ms. Based on lower layer metrics (physical and mac layers), the main supervised machine learning algorithms are used, such as Linear Regressor and Random Forest to predict the uplink received bandwidth in different radio phenomena environment. Hence, a deep investigation of the impact of radio issues on bandwidth prediction is conducted. Further, our evaluation shows that the prediction is highly accurate: at the time granularity of 100 ms, the average prediction error is in the range of 6% to 12% for all the scenarios we explored.

In home networks, seamless networking and collaborative streaming-based multimedia content sharing have become challenging issues in providing QoS (Quality of Service) for its users with heterogeneous consumer electronic devices. In order to support the demands for QoS, recently SVC (Scalable Video Coding) scheme has attracted attention. However, existing schemes do not guarantee the quality of multimedia contents as these schemes do not consider the characteristics of the SVC encoding scheme. Moreover, they do not accurately estimate the available network bandwidth. To cope with these problems, this paper presents a simple but effective N-QA (Network-aware Quality Adaptation) scheme that can improve the quality of streaming contents in a device collaboration service. The proposed scheme quickly adjusts the data transmission rate according to the estimated available bandwidth of network. It also controls media quality using SVC characteristics. The experimental result shows that the proposed scheme can significantly improve the media quality 1 .

Multimedia content delivery over the Internet is predominantly using the Hypertext Transfer Protocol (HTTP) as its primary protocol and multiple proprietary solutions exits. The MPEG standard Dynamic Adaptive Streaming over HTTP (DASH) provides an interoperable solution and in recent years various adaptation logics/algorithms have been proposed. However, to the best of our knowledge, there is no comprehensive evaluation of the various logics/algorithms. Therefore, this paper provides a comprehensive evaluation of ten different adaptation logics/algorithms, which have been proposed in the past years. The evaluation is done both objectively and subjectively. The former is using a predefined bandwidth trajectory within a controlled environment and the latter is done in a real-world environment adopting crowdsourcing. The results shall provide insights about which strategy can be adopted in actual deployment scenarios. Additionally, the evaluation methodology described in this paper can...

A lot of attention has been drawn to ensuring a secure communication in an ad hoc network environment. It is important to anonymously send and receive sensitive data from secure sources. Digital signature is one of the powerful ways of ensuring integrity, privacy, confidentiality and nonrepudiation in terms of signing messages. A technique from RSA is employed to propose a new digital signature to be used in wireless networks. This concept also ensures both source and location anonymity. Adversaries will find it difficult to identify the source of a message and exactly where the message is being sent to. With regard to a zone, it will not be possible to identify who sends a message and also who receives it within the group in the zone. It is believed that the signature is light weight and can easily be generated by any of the nodes in the zone. In the context of using the scheme without wireless network, individual uses alternative steps for signing sensitive documents by classifyin...

On the last few years, Media streaming services over TCP have become very popular because TCP's congestion control provides remarkable stability to the Internet. To offer a high quality of Media and also a good user satisfaction, the media streaming service requires the adaptation of the bandwidth availability and other network parameters. Nowadays the streaming video can be projected on different kinds of terminal as tablet, smart phones, laptop....etc. Each user (device) has its own characteristics and parameters which must be taken in consideration on the video streaming adaptation process. The classic Adaptive video streaming services do not take in consideration the user parameters on the adaptation process. In this paper we propose an adaptive video streaming solution to improve the user satisfaction factor by adapting TCP parameters according to the user parameters on mobile networks. The user satisfaction factor is calculated according to the quality of experience (QoE) ...

In this paper we estimate the end-to-end capacity and available bandwidth of a path between a pair of nodes in an IEEE 802.11b ad hoc network using dispersion traces between packet pairs of different lengths. The pairs of packets that suffer the minimum delay are used to estimate the maximum achievable transmission rate as a function of packet length, for any packet length, while the variability of the dispersions is used to estimate the fraction of that capacity that is available for data transmission. To model the dependence of the variability of the dispersion traces on the true fraction of available capacity, we use a neuro-fuzzy estimator trained on data collected from a large set of real and simulated scenarios. The system is shown to provide accurate estimates (within 15% of accuracy 80% of the time on the test data), to be efficient in the use of communication resources (transmits 48 kbps during the test), and to present low computational cost (about 500 floating point opera...

In this paper we estimate the end-to-end capacity and available bandwidth of a path between a pair of nodes in an IEEE 802.11b ad hoc network using dispersion traces between packet pairs of different lengths. The pairs of packets that suffer the minimum delay are used to estimate the maximum achievable transmission rate as a function of packet length, for any packet length, while the variability of the dispersions is used to estimate the fraction of that capacity that is available for data transmission. To model the dependence of the variability of the dispersion traces on the true fraction of available capacity, we use a neuro-fuzzy estimator trained on data collected from a large set of real and simulated scenarios. The system is shown to provide accurate estimates (within 15% of accuracy 80% of the time on the test data), to be efficient in the use of communication resources (transmits 48 kbps during the test), and to present low computational cost (about 500 floating point opera...

This paper presents NANCY, a system that generates adaptive bit rates (ABR) for video and adaptive network coding rates (ANCR) using reinforcement learning (RL) for video distribution over wireless networks. NANCY trains a neural network model with rewards formulated as quality of experience (QoE) metrics. It performs joint optimization in order to select: (i) adaptive bit rates for future video chunks to counter variations in available bandwidth and (ii) adaptive network coding rates to encode the video chunk slices to counter packet losses in wireless networks. We present the design and implementation of NANCY, and evaluate its performance compared to state-of-the-art video rate adaptation algorithms including Pensieve and robustMPC. Our results show that NANCY provides 29.91% and 60.34% higher average QoE than Pensieve and robustMPC, respectively.

Adaptive Bitrate (ABR) is used at large scale in online video streaming to improve viewer perception. The advanced online streaming process utilizes adaptive bitrate adaptation algorithms that works in video-players. To improve viewer’s quality of experience, ABR algorithm has to select high quality video as per the available network throughput and transmit with minimal stops and low-bitrate fluctuation. Although, current ABR algorithms suffers from stops, and low bitrate fluctuations because they don’t consider the influence of the underlying atypical value also known as outlier in statistics during throughput prediction. Here we propose a new ABR Outlier-Removal-based Throughput Improvement Algorithm (OTRIA), that provides a realistic forecast of throughput in changing network circumstances, thus minimizing stops and bitrate fluctuations. We used various statistical methods to detect outliers. We used the method of Inter-Quartile-Range to identify a range of throughput values that...

Video streaming currently accounts for the majority of Internet traffic. One factor that enables video streaming is HTTP Adaptive Streaming (HAS), that allows the users to stream video using a bit rate that closely matches the available bandwidth from the server to the client. MPEG Dynamic Adaptive Streaming over HTTP (DASH) is a widely used standard, that allows the clients to select the resolution to download based on their own estimations. The algorithm for determining the next segment in a DASH stream is not part of the standard, but it is an important factor in the resulting playback quality. Nowadays vehicles are increasingly equipped with mobile communication devices, and in-vehicle multimedia entertainment systems. In this paper, we evaluate the performance of various DASH adaptation algorithms over a vehicular network. We present detailed simulation results highlighting the advantages and disadvantages of various adaptation algorithms in delivering video content to vehicular users, and we show how the different adaptation algorithms perform in terms of throughput, playback interruption time, and number of interruptions.

Quality of Experience (QoE) consists of a set of indicators that show the perceived satisfaction of using a multimedia (or other kind of) service by the end user. Being so the QoE presents a subjective metric and the only relevant mechanisms for measuring such indicators are subjective tests. Due to the fact that subjective tests are an expensive, impractical and in cases of live streaming a close to impossible exercise we set out on a twofold task to address this issue. First we set out to build prediction models using traditional Machine Learning (ML) techniques based on subjective test data. Second we explore an approach for reduction of the training dataset that will minimize the need for subjective data whilst keeping the prediction models as accurate as possible. For the first goal we used supervised learning based classification algorithms and we came up with high accuracy (over ninety percent) for the prediction models. To address the issue of high cost training data we developed a novel approach in reducing the training dataset while keeping a high accuracy of the classifiers. The reduction method provides a grading mechanism for unseen data. By having this mechanism in the online learning platform we can optimize the process of asking for user feedback by looking for the most significant cases, and therefore improving the gain on the trade-off between more feedback and more accuracy.

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 ...

In this survey, we present state-of-the-art bitrate adaptation algorithms for HTTP adaptive streaming (HAS). As a key distinction from other streaming approaches, the bitrate adaptation algorithms in HAS are chiefly executed at each client, i.e., in a distributed manner. The objective of these algorithms is to ensure a high quality of experience (QoE) for viewers in the presence of bandwidth fluctuations due to factors like signal strength, network congestion, network reconvergence events, etc. While such fluctuations are common in public Internet, they can also occur in home networksor even managed networks where there is often admission control and QoS tools. Bitrate adaptation algorithms may take factors like bandwidth estimations, playback buffer fullness, device features, viewer preferences, and content features into account, albeit with different weights. Since the viewer's QoE needs to be determined in real-time during playback, objective metrics are generally used including number of buffer stalls, duration of startup delay, frequency and amount of quality oscillations, and video instability. By design, the standards for HAS do not mandate any particular adaptation algorithm, leaving it to system builders to innovate and implement their own method. This survey provides an overview of the different methods proposed over the last several years.

In this paper, an in depth elaboration and analysis of adaptive streaming is taking place. Current implementation techniques of Dynamic Adaptive Streaming over HTTP from Adobe, Apple and Microsoft are being presented along with all detailed transmission procedures including server, distribution and client components. Specifically, all exploited protocols along with their attributes are being described and then the streaming media preparation and the delivery process are being represented. Following, a simulation of a DASH employment is taking place using JW Player 5 for Flash and HTML5 installed on a server with specific streaming video of 4 quality levels. Finally, measurements are taken through Quality Monitor plugin and reasoned out for a better comprehension of DASH experience.

Most online video streaming services, including major ones such as YouTube and Netflix, use adaptive streaming over HTTP, which dynamically adapts the bitrates of the sessions to maximize the quality of experience (QoE) for different users. Many algorithms have been proposed in the literature, and some deployed in practice, to perform this dynamic adaptation. It is crucial for the research community to occasionally reflect and contrast various adaptation algorithms against each other to discover opportunities for further optimizations. The authors of this paper contribute to this important issue and offer us a deeper understanding of these adaptation algorithms. They compare seven common rate adaptation algorithms, including buffer-based (Bola, BBA0, and Quetra), throughput-based (Shaka), and Model Predictive Controller (Fast MPC), using objective and subjective studies. The objective study utilizes the ITU-T P.1203 QoE model, which calculates a predicted Mean Opinion Score (MOS) of a video based on the bitrate, frame rate, resolution, frame types, and frame sizes. The subjective study was conducted on a cloud platform with more than 800 real users (Amazon Mechanical Turks). Several real videos were each encoded into 11 representations and used in the subjective and objective studies. The authors also used four network profiles to capture some of the real-life scenarios. The paper indeed sheds light on understanding the complex problem of quality adaptation in HTTP video streaming. The results should however be considered as the first step in this direction and should be approached with a critical eye. A workshop paper is a way to share exciting results with the community as early as possible. It is also an invitation to further expand the results. Typical future work that can be built upon this paper includes a more comprehensive evaluation, using more network profiles (maybe from actual datasets) and a more diverse catalog of videos (for example high-motion videos). Another promising extension to this paper is the evaluation of the recent learning-based rate adaptation algorithms.

DASH (Dynamic Adaptive Streaming over HTTP) is now the most popular standard in video streaming. For supporting DASH video transmission over residential networks with small bandwidth variation (such as DSL based network for IPTV), we design an optimal transmission schedule, L2H. Given a transmission rate and an initial delay, the schedule can optimize the QoE (quality of experience) metrics such as rebuffering, lexicographically maximal resolution, number of rate switching events, and smoothness of the rate change. We further present L2HB for considering usage of the system buffer when applying the L2H. L2HB comes up with its benefit when comparing with other research work by objective QoE evaluations. Besides, by introducing the system buffer size constraint, the proposed algorithm can control the transmission schedule to let highest-resolution segments appear as soon as possible for prompting the users to stay tuned.

Quality of Experience (QoE) consists of a set of indicators that show the perceived satisfaction of using a multimedia (or other kind of) service by the end user. Being so the QoE presents a subjective metric and the only relevant mechanisms for measuring such indicators are subjective tests. Due to the fact that subjective tests are an expensive, impractical and in cases of live streaming a close to impossible exercise we set out on a twofold task to address this issue. First we set out to build prediction models using traditional Machine Learning (ML) techniques based on subjective test data. Second we explore an approach for reduction of the training dataset that will minimize the need for subjective data whilst keeping the prediction models as accurate as possible. For the first goal we used supervised learning based classification algorithms and we came up with high accuracy (over ninety percent) for the prediction models. To address the issue of high cost training data we developed a novel approach in reducing the training dataset while keeping a high accuracy of the classifiers. The reduction method provides a grading mechanism for unseen data. By having this mechanism in the online learning platform we can optimize the process of asking for user feedback by looking for the most significant cases, and therefore improving the gain on the trade-off between more feedback and more accuracy.

Measuring and predicting the user's 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 user's feedback. Existing statistical techniques have lead to poor accuracy (order of 70%) and ...

Measuring and predicting the user's 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 user's feedback. Existing statistical techniques have lead to poor accuracy (order of 70%) and ...

Mobile adhoc networks eliminate the need for pre-existing infrastructure by relying on the nodes to carry all network activities. The mobile ad hoc networks are more prone to suffer from malicious behaviors than the traditional wired networks. Therefore, there is a need to pay more attention to the security issues in the mobile ad hoc networks. Clustered Manets is a very promising area of research due to its infrastructure less capability. They have many advantages such as improved bandwidth, power consumption and QoS of the network but one disadvantage is security. This paper has been prepared keeping in mind that it needs to prove itself to be a valuable resource dealing with both the important core and the specialized security issues in this area.

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 ...

Although adaptive video streaming solutions have become very popular over the last years, only a limited number of studies so far have investigated Quality of Experience (QoE) in the context of such services from a real user perspective. In this paper, we present results from a user study (N=32) on adaptive video streaming QoE. Content (i.e., music video clips) was streamed on portable terminal devices (namely iPads), using different bitrate profiles which represent realistic bandwidth conditions. All users conducted the test in two different usage scenarios, representing different social settings. QoE was evaluated in terms of traditional QoE-measures and complemented with a number of alternative, affectivestate related measures. The findings indicate differences between the considered bitrate profiles in terms of QoE (traditional and alternative measures) and indicate that a lower, constant bitrate seems to be preferred over the changing bitrate which is -on averagehigher. This is the case for both separate usage scenarios. Although we found no significant influence of the social setting when considering traditional QoE evaluation measures, some significant differences between both settings were detected when evaluating QoE in terms of delight and annoyance.

Measuring and predicting the user's 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 user's feedback. Existing statistical techniques have lead to poor accuracy (order of 70%) and inability to evolve prediction models with the system's 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.

Managing multimedia network services in a Usercentric 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.

Abstract: The user perceived quality or Quality of Experience (QoE) is of significant importance to multimedia service providers because of its relevance for efficient management of provided services. However, due to its subjective nature, QoE is difficult to estimate. Subjective methods are costly and impractical, while objective methods do not correlate precisely with the subjective perception. In addition to the challenges in estimating QoE, further challenges are presented in determining the means of managing the QoE in ...

Quality of Experience (QoE) consists of a set of indicators that show the perceived satisfaction of using a multimedia (or other kind of) service by the end user. Being so the QoE presents a subjective metric and the only relevant mechanisms for measuring such indicators are subjective tests. Due to the fact that subjective tests are an expensive, impractical and in cases of live streaming a close to impossible exercise we set out on a twofold task to address this issue. First we set out to build prediction models using traditional Machine Learning (ML) techniques based on subjective test data. Second we explore an approach for reduction of the training dataset that will minimize the need for subjective data whilst keeping the prediction models as accurate as possible. For the first goal we used supervised learning based classification algorithms and we came up with high accuracy (over ninety percent) for the prediction models. To address the issue of high cost training data we developed a novel approach in reducing the training dataset while keeping a high accuracy of the classifiers. The reduction method provides a grading mechanism for unseen data. By having this mechanism in the online learning platform we can optimize the process of asking for user feedback by looking for the most significant cases, and therefore improving the gain on the trade-off between more feedback and more accuracy.

Quality of Experience QoE frameworks were proposed and developed to provide quality of service to end users according to their needs and improve user experience. This paper presents survey of recently proposed QoE frameworks based on certain features such as monitoring support, data analysis, reporting to administrator, policy change and parameters for data collection and monitoring. During the survey it has been erudite that mainstream QoE frameworks have limited scope. Few of them do not support client side monitoring, policy change and both subjective, objective QoE combined approaches. QoE data analysis is also concern for negative and positive QoE is not available, which needs to merge to find robust QoE framework.

In the (mobile) communications domain, Quality of Experience (QoE) has become the ultimate metric influencing the success or failure of new applications and services. Since it is increasingly argued in the literature that QoE should be seen as a multi-dimensional concept, this paper focuses on QoE from an interdisciplinary perspective.

Quality of service (QoS) is the mechanism of the network to provide different service level to a different traffic type as business need. The main objective of this work is to improve QoS in network by reducing link load and bandwidth consumption. It uses a routing scheme that satisfies expected demand and minimized link utilization of system. It works on reliability by limited usage of bandwidth. Results are presented to demonstrate the effectiveness of system. The efficient QoS model provides better control and administration of network traffic. Solution of routing problem with help of proposed model allows providing the distribution of traffic between source-and destination-node so that delays along every path are equal.

The transmission of four active users has been illustrated with 5 WDM × 4 TDM × 4 CODE channel at 20 Gbps data rate 3 Dimensional Optical Code Division Multiple Access system based on newly designed Model A having signature sequences in temporal domain, spectral domain and spatial domain with optical orthogonal codes, cubic congruent operator from algebra theory respectively, using Galois field GF (5) with varying receiver attenuation on optsim simulation software. The results, numerically shown in terms of bit error rate and graphically represented in terms of eye diagram and signal strength, indicate that the novel 3D coding technique is designed to support four users with good BER with variable attenuation at the front end of the receiver.

The transmission of four active users has been illustrated with 5 WDM × 4 TDM × 4 CODE channel at 20 Gbps data rate 3 Dimensional Optical Code Division Multiple Access system based on newly designed Model A having signature sequences in temporal domain, spectral domain and spatial domain with optical orthogonal codes, cubic congruent operator from algebra theory respectively, using Galois field GF (5) with varying receiver attenuation on optsim simulation software. The results, numerically shown in terms of bit error rate and graphically represented in terms of eye diagram and signal strength, indicate that the novel 3D coding technique is designed to support four users with good BER with variable attenuation at the front end of the receiver.

The ability to quantify Quality of Experience (QoE, i.e. the users' subjective perception of the 'overall acceptability of an application or service'), will play a major role in the success of future multimedia services such as mobile video watching. Such QoE-evaluations are however still challenging, especially in real life (or so-called 'Living Lab'), user settings. According to our knowledge, this paper is the first to present a methodology for the multi-dimensional quantification of QoE during mobile video watching in real-life settings. A measurement study drawing on the evaluation of objective and subjective QoE aspects by a user panel resulted in a model for quantifying QoE during mobile video watching based on user behavior and technical parameters such as network and video quality.

In the (mobile) communications domain, Quality of Experience (QoE) has become the ultimate metric influencing the success or failure of new applications and services. Since it is increasingly argued in the literature that QoE should be seen as a multi-dimensional concept, this paper focuses on QoE from an interdisciplinary perspective.

Classifier ensembles have emerged in recent years as a promising research area for boosting pattern recognition systems' performance. We present a new base classifier that utilizes Oblique Decision Tree technology based on Support Vector Machines for the construction of oblique (non-axis parallel) tests on the nodes of the decision tree inducted. We describe a number of heuristic techniques for enhancing the tree construction process by better estimation of the gain obtained by an oblique split at any tree node. We then show how embedding the new classifier in an ensemble of classifiers using the classical Hedge(β) algorithm boosts performance of the system. Testing 10-fold cross validation on UCI machine learning repository data sets shows that the new hybrid classifiers outperforms on average by more than 2.1% both the WEKA implementation of C4.5 (J48) and the SMO implementation of SVM in WEKA. The application of the particular ensemble algorithm is an excellent fit for online-learning applications where one seeks to improve performance of self-healing dependable computing systems based on reconfiguration by gradually and adaptively learning what constitutes good system configurations.

In the domain of video streaming, Scalable Video Coding (SVC) comes as a solution that adapts to network bandwidth fluctuation and to terminals heterogeneity. The multi- layer-coding criterion of SVC has increased its correlation with the streaming over multiple paths. However, an important challenge that we still need to face is how to maximize the overall video quality in a

Available bandwidth measurement as simple as running wget Demetres Antoniades1, Manos Athanatos1, Antonis Papadogiannakis1, Evangelos P. Markatos1, Constantine Dovrolis2 1 Institute of Computer Science (ICS) Foundation for Research & Technology Hellas (FORTH) ...

HTTP Adaptive Streaming (HAS) is becoming the de-facto standard for Over-The-Top video streaming. A HAS video consists of multiple segments, encoded at multiple quality levels. Allowing the client to select the quality level for every segment, a smoother playback and a higher Quality of Experience (QoE) can be perceived. Although results are promising, current quality selection heuristics are generally hard coded. Fixed parameter values are used to provide an acceptable QoE under all circumstances, resulting in suboptimal solutions. Furthermore, many commercial HAS implementations focus on a video-ondemand scenario, where a large buffer size is used to avoid playout freezes. When the focus is on a live TV scenario however, a low buffer size is typically preferred, as the video play-out delay should be as low as possible. Hard coded implementations using a fixed buffer size are not capable of dealing with both scenarios. In this paper, the concept of reinforcement learning is introduced at client side, allowing to adaptively change the parameter configuration for existing rate adaptation heuristics. Bandwidth characteristics are taken into account in the decision process, thus allowing to improve the client's bandwidth-awareness. Focus in this paper is on actively reducing the average buffer filling, evaluating results for two heuristics: the Microsoft IIS Smooth Streaming heuristic and the QoE-driven Rate Adaptation Heuristic for Adaptive video Streaming by Petrangeli et al. We show that using the proposed learning-based approach, the average buffer filling can be reduced by 8.3% compared to state of the art, while achieving a comparable level of QoE.

Understanding how quality is perceived by the 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 and therefore is crucial in the process of optimizing the tradeoff between quality and resources. However, accurate estimation of QoE usually entails cumbersome subjective studies that are long and expensive to execute. This paper presents 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 changes in the environment. To maintain the accuracy of the prediction models, we have adopted Online Learning techniques that update the models on data from subjective viewer feedback. Overall this method provides accurate and adaptive QoE prediction models that can become an indispensible component of a QoE-aware management service.

Understanding how quality is perceived by the 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 and therefore is crucial in the process of optimizing the tradeoff between quality and resources. However, accurate estimation of QoE usually entails cumbersome subjective studies that are long and expensive to execute. This paper presents 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 changes in the environment. To maintain the accuracy of the prediction models, we have adopted Online Learning techniques that update the models on data from subjective viewer feedback. Overall this method provides accurate and adaptive QoE prediction models that can become an indispensible component of a QoE-aware management service.