Pub Date : 2016-06-06DOI: 10.1109/QoMEX.2016.7498962
Maria Plakia, Michalis Katsarakis, Paulos Charonyktakis, M. Papadopouli, Ioannis Markopoulos
Assessing the impact of different network conditions on user experience is important for improving the telecommunication services. We have developed a modular framework that includes monitoring and data collection tools and algorithms for user-centric analysis and prediction of the QoE in video streaming. The MLQoE employs several machine learning (ML) algorithms and tunes their hyper-parameters. It dynamically selects the ML algorithm that exhibits the best performance and its parameters automatically based on the input (e.g., network and systems metrics). We applied the MLQoE for predicting the QoE of the video streaming service in the context of two field studies, one performed in the production environment of a large telecom operator and the other at our Institute. The analysis indicated the parameters with the dominant impact on the perceived QoE and revealed that the QoE vary across users. This motivates the use of customized adaptation mechanisms in video streaming under network performance degradation. The MLQoE results in fairly accurate predictions e.g., a median error in predicting the QoE of 0.0991 and 0.5517 in the first (second) field study, respectively, on the MOS scale.
{"title":"On user-centric analysis and prediction of QoE for video streaming using empirical measurements","authors":"Maria Plakia, Michalis Katsarakis, Paulos Charonyktakis, M. Papadopouli, Ioannis Markopoulos","doi":"10.1109/QoMEX.2016.7498962","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498962","url":null,"abstract":"Assessing the impact of different network conditions on user experience is important for improving the telecommunication services. We have developed a modular framework that includes monitoring and data collection tools and algorithms for user-centric analysis and prediction of the QoE in video streaming. The MLQoE employs several machine learning (ML) algorithms and tunes their hyper-parameters. It dynamically selects the ML algorithm that exhibits the best performance and its parameters automatically based on the input (e.g., network and systems metrics). We applied the MLQoE for predicting the QoE of the video streaming service in the context of two field studies, one performed in the production environment of a large telecom operator and the other at our Institute. The analysis indicated the parameters with the dominant impact on the perceived QoE and revealed that the QoE vary across users. This motivates the use of customized adaptation mechanisms in video streaming under network performance degradation. The MLQoE results in fairly accurate predictions e.g., a median error in predicting the QoE of 0.0991 and 0.5517 in the first (second) field study, respectively, on the MOS scale.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"112 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87630017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-06DOI: 10.1109/QoMEX.2016.7498972
Arslan Ahmad, Alessandro Floris, L. Atzori
The objective of this work is the investigation of a possible collaboration between Over-The-Top (OTTs) service providers and Internet Service Providers (ISPs), which is centered around the Quality of Experience (QoE). Initially, we define a reference architecture with the required modules and interfaces for the interaction between the two providers. Then, we focus on the modeling of the revenue, whose maximization drives the collaboration. It is considered as depending on the user churn, which in turn is affected by the QoE and is modeled using the Sigmoid function. We illustrate simulation results based on our proposed collaboration approach which highlights how the proposed strategy increases the revenue generation and QoE for both players hence providing a ground for ISP to join the loop of revenue generation between OTT and users.
{"title":"QoE-aware service delivery: A joint-venture approach for content and network providers","authors":"Arslan Ahmad, Alessandro Floris, L. Atzori","doi":"10.1109/QoMEX.2016.7498972","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498972","url":null,"abstract":"The objective of this work is the investigation of a possible collaboration between Over-The-Top (OTTs) service providers and Internet Service Providers (ISPs), which is centered around the Quality of Experience (QoE). Initially, we define a reference architecture with the required modules and interfaces for the interaction between the two providers. Then, we focus on the modeling of the revenue, whose maximization drives the collaboration. It is considered as depending on the user churn, which in turn is affected by the QoE and is modeled using the Sigmoid function. We illustrate simulation results based on our proposed collaboration approach which highlights how the proposed strategy increases the revenue generation and QoE for both players hence providing a ground for ISP to join the loop of revenue generation between OTT and users.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"3 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82052658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-06DOI: 10.1109/QoMEX.2016.7498937
A. Wilson, B. Fazenda
In many subjective listening tests, audio is evaluated on either “quality” or “preference”. These terms are often conflated. Little evidence has been gathered which explains the subtle differences between these terms in audio perception - we may not necessarily prefer high-quality audio samples. In the case of music, hedonic preference is strongly related to familiarity with the audio samples, which is informed by one's musical tastes, itself based on autobiographical memory. However, for unfamiliar music, the two concepts can overlap considerably. This paper will explore the relationship between these two concepts in three experiments - with familiar music, unfamiliar music and alternate mixes of an unfamiliar song. It was shown that quality ratings and like ratings become more correlated when familiarity is removed and also when inter-song variation is removed. For the case of music mixes, both concepts are strongly correlated (R2=0.82), although there are subtle differences in the ways these ratings were described by participants.
{"title":"Relationship between hedonic preference and audio quality in tests of music production quality","authors":"A. Wilson, B. Fazenda","doi":"10.1109/QoMEX.2016.7498937","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498937","url":null,"abstract":"In many subjective listening tests, audio is evaluated on either “quality” or “preference”. These terms are often conflated. Little evidence has been gathered which explains the subtle differences between these terms in audio perception - we may not necessarily prefer high-quality audio samples. In the case of music, hedonic preference is strongly related to familiarity with the audio samples, which is informed by one's musical tastes, itself based on autobiographical memory. However, for unfamiliar music, the two concepts can overlap considerably. This paper will explore the relationship between these two concepts in three experiments - with familiar music, unfamiliar music and alternate mixes of an unfamiliar song. It was shown that quality ratings and like ratings become more correlated when familiarity is removed and also when inter-song variation is removed. For the case of music mixes, both concepts are strongly correlated (R2=0.82), although there are subtle differences in the ways these ratings were described by participants.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"144 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79921407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-06DOI: 10.1109/QoMEX.2016.7498968
M. Sužnjević, Iva Slivar, Lea Skorin-Kapov
Cloud gaming represents a highly interactive service whereby game logic is rendered in the cloud and streamed as a video to end devices. While benefits include the ability to stream high-quality graphics games to practically any end user device, drawbacks include high bandwidth requirements and very low latency. Consequently, a challenge faced by cloud gaming service providers is the design of algorithms for adapting video streaming parameters to meet the end user system and network resource constraints. In this paper, we conduct an analysis of the commercial NVIDIA GeForce NOW game streaming platform adaptation mechanisms in light of variable network conditions. We further conduct an empirical user study involving the GeForce NOW platform to assess player Quality of Experience when such adaptation mechanisms are employed. The results provide insight into limitations of the currently deployed mechanisms, as well as aim to provide input for the proposal of designing future video encoding adaptation strategies.
{"title":"Analysis and QoE evaluation of cloud gaming service adaptation under different network conditions: The case of NVIDIA GeForce NOW","authors":"M. Sužnjević, Iva Slivar, Lea Skorin-Kapov","doi":"10.1109/QoMEX.2016.7498968","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498968","url":null,"abstract":"Cloud gaming represents a highly interactive service whereby game logic is rendered in the cloud and streamed as a video to end devices. While benefits include the ability to stream high-quality graphics games to practically any end user device, drawbacks include high bandwidth requirements and very low latency. Consequently, a challenge faced by cloud gaming service providers is the design of algorithms for adapting video streaming parameters to meet the end user system and network resource constraints. In this paper, we conduct an analysis of the commercial NVIDIA GeForce NOW game streaming platform adaptation mechanisms in light of variable network conditions. We further conduct an empirical user study involving the GeForce NOW platform to assess player Quality of Experience when such adaptation mechanisms are employed. The results provide insight into limitations of the currently deployed mechanisms, as well as aim to provide input for the proposal of designing future video encoding adaptation strategies.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"31 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90810699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-01DOI: 10.1109/QoMEX.2016.7498961
Marwin Schmitt, J. Redi, Pablo César, D. Bulterman
Most video platforms deliver HD video in high bitrate encoding. Modern video-conferencing systems are capable of handling HD streams, but using multiparty conferencing, average internet connections in the home are on their bandwidth limit. For properly managing the encoding bitrate in videoconferencing, we must know what is the minimum bitrate requirement to provide users an acceptable experience, and what is the bitrate level after which QoE saturates?. Most available subjective studies in this area used rather dated technologies. We report on a multiparty study on video quality with HD resolution. We tested different encoding bitrates (256kbs, 1024kbs and 4096kbs) and packet loss rates (0, 0.5%) in groups of 4 participants with a scenario based on the ITU building blocks task. We discuss the influence of group interaction and individual idiosyncrasies based on different mixed models, and look at covariates engagement and enjoyment as further explanatory factors. We found that 256kbs is still sufficient to provide a fair overall experience, but video quality is noticed to be poor. On the higher bitrate end, most people will not perceive the difference between 1024kbs and 4096kbs, considering in both cases the quality to be close to excellent. Independent on bitrate, packet loss has a small but significant impact, quantifiable in, on average, less than half a point difference on a 5-point ITU scale.
{"title":"1Mbps is enough: Video quality and individual idiosyncrasies in multiparty HD video-conferencing","authors":"Marwin Schmitt, J. Redi, Pablo César, D. Bulterman","doi":"10.1109/QoMEX.2016.7498961","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498961","url":null,"abstract":"Most video platforms deliver HD video in high bitrate encoding. Modern video-conferencing systems are capable of handling HD streams, but using multiparty conferencing, average internet connections in the home are on their bandwidth limit. For properly managing the encoding bitrate in videoconferencing, we must know what is the minimum bitrate requirement to provide users an acceptable experience, and what is the bitrate level after which QoE saturates?. Most available subjective studies in this area used rather dated technologies. We report on a multiparty study on video quality with HD resolution. We tested different encoding bitrates (256kbs, 1024kbs and 4096kbs) and packet loss rates (0, 0.5%) in groups of 4 participants with a scenario based on the ITU building blocks task. We discuss the influence of group interaction and individual idiosyncrasies based on different mixed models, and look at covariates engagement and enjoyment as further explanatory factors. We found that 256kbs is still sufficient to provide a fair overall experience, but video quality is noticed to be poor. On the higher bitrate end, most people will not perceive the difference between 1024kbs and 4096kbs, considering in both cases the quality to be close to excellent. Independent on bitrate, packet loss has a small but significant impact, quantifiable in, on average, less than half a point difference on a 5-point ITU scale.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"6 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88236273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-04-14DOI: 10.1109/QoMEX.2016.7498955
Samuel F. Dodge, Lina Karam
Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks. In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, contrast, JPEG, and JPEG2000 compression. We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise. These results enable future work in developing deep neural networks that are more invariant to quality distortions.
{"title":"Understanding how image quality affects deep neural networks","authors":"Samuel F. Dodge, Lina Karam","doi":"10.1109/QoMEX.2016.7498955","DOIUrl":"https://doi.org/10.1109/QoMEX.2016.7498955","url":null,"abstract":"Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks. In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, contrast, JPEG, and JPEG2000 compression. We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise. These results enable future work in developing deep neural networks that are more invariant to quality distortions.","PeriodicalId":6645,"journal":{"name":"2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX)","volume":"12 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2016-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77743943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：