• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.188-198
• /
• 2018

With recent development of high-speed wide-area wireless networks and wide spread of highperformance wireless devices, the demand on seamless video streaming services in Long Term Evolution (LTE) network environments is ever increasing. To meet the demand and provide enhanced Quality of Experience (QoE) with mobile users, the Dynamic Adaptive Streaming over HTTP (DASH) has been actively studied to achieve QoE enhanced video streaming service in dynamic network environments. However, the existing DASH algorithm to select the quality of requesting video segments is based on a procedural algorithm so that it reveals a limitation to adapt its performance to dynamic network situations. To overcome this limitation this paper proposes a novel quality selection mechanism based on a Deep Q-Network (DQN) model, the DQN-based DASH ABR($DQN_{ABR}$) mechanism. The $DQN_{ABR}$ mechanism replaces the existing DASH ABR algorithm with an intelligent deep learning model which optimizes service quality to mobile users through reinforcement learning. Compared to the existing approaches, the experimental analysis shows that the proposed solution outperforms in terms of adapting to dynamic wireless network situations and improving QoE experience of end users.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.12
• /
• pp.1811-1818
• /
• 2013

As the broadband network are being deployed recently, the IPTV (Internet Protocol TV) has appeared and become a most representative service that incorporates audio, video, etc. In spite of the long-period efforts, however, no standardized method exists to measure and evaluate the quality of video that is experienced through TV in the customer's premises. Therefore, before developing a method to measure and evaluate the quality of experience (QoE) for video that is the ultimate goal, this paper reviews the outcomes from the past standardization activities and drive a few important implications that would be reflected to the method to measure and evaluate QoE for video.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.308-324
• /
• 2018

HTTP adaptive streaming (HAS) is a promising technology for delivering video content over the Internet. HAS-based video streaming solutions rely on bandwidth estimation to select the appropriate video bitrate. Video streaming solutions that consider network conditions provide users with seamless video playback. However, when multiple clients compete for a common bottleneck link, conventional bandwidth estimation schemes that consider only one client overestimate the network bandwidth due to the ON-OFF traffic pattern. The bandwidth overestimation can cause Quality of Experience (QoE) degradation, such as unnecessary changes in video quality, and unfairness of video quality. In this paper, we propose a client-side bandwidth estimation scheme to obtain a better QoE of HAS in the multiple-client environment. The proposed scheme differentiates the client buffer status according to the buffer occupancy, and then estimates the available network bandwidth based on the buffer status and segment throughput. We evaluate the performance of HAS implemented in the ns-3 network simulator. Simulation results show that compared with the conventional schemes, the proposed scheme can enhance the QoE.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.320-325
• /
• 2009

네트워크 서비스에 있어서 품질을 정확히 측정하고 품질지수를 도출하는 것은 매우 중요하다. 종래의 네트워크 서비스에 대한 품질지수는 QoS(Quality of Service)로서 많은 연구가 있어왔다. 하지만 QosS를 통한 사용자 품질지수는 실제 사용자의 서비스 만족도를 효과적으로 표현해 주지 못하였다. 그래서 본 연구에서는 QoE(Quality of Experience)라는 개념을 도입하여, 사용자가 실제로 느낀 서비스의 만족도를 도출하고자 하였다. 사용자의 서비스 만족도를 잘 표현해주는 QoE를 도출하기 위하여 본 연구에서는 QoE Framework를 제안한다. QoE Framework는 framework를 위해 동작하는 agent들로 구성된다. QoE Framework의 agent는 크게 서비스 제공자측과 서비스 사용자 측으로 나눌 수 있는데, 서비스 사용자 측의 agent는 서비스를 이용하다가 사용자가 서비스 불만족을 감지하였을 때, 서비스 제공자측 agent는 사용자측 agent로부터 받은 서비스 불만족에 대한 feedback으로부터 QoE도출 알고리즘을 사용하여 최적의 QoE를 도출하는 기능을 한다. 서비스 제공자측 agent의 QoE도출 알고리즘으로 GA(Genetic Algorithm)을 사용하여 최적의 값을 구하게 된다. QoE framework의 알고리즘에서는 불만족 feedbaek을 이루는 QoS 파라미터들간의 중요도와 관계를 도출하여, 주어진 서비스 개선 비용으로 최적의 QoE를 도출함으로써, 네트워크 서비스에 대한 사용자의 만족도를 최대로 높이는 결과를 도출하게 된다.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.229-234
• /
• 2021

The explosive growth of video-based services is considered as the dominant contributor to Internet traffic. Hence it is very important for video service providers to meet the quality expectations of end-users. In the past, the Quality of Service (QoS) was the key performance of networks but it considers only the network performances (e.g., bandwidth, delay, packet loss rate) which fail to give an indication of the satisfaction of users. Therefore, Quality of Experience (QoE) may allow content servers to be smarter and more efficient. This work is motivated by the inherent relationship between the QoE and the QoS. We present a no-reference (NR) prediction model based on Deep Neural Network (DNN) to predict video QoE. The DNN-based model shows a high correlation between the objective QoE measurement and QoE prediction. The performance of the proposed model was also evaluated and compared with other types of neural network architectures, and three known machine learning methodologies, the performance comparison shows that the proposed model appears as a promising way to solve the problems.

• ETRI Journal
• /
• v.32 no.6
• /
• pp.843-853
• /
• 2010

A successful deployment of multimedia applications over wireless environments entails improving the quality of service (QoS), not only from a technical point of view, but also considering the quality of experience (QoE) from the final user's perception. Although objective QoE measure models avoid the difficulties of subjective surveys, subjective QoE assessments are essential to understand the way users evaluate the QoS. In this work, we study the effect of a wide range of parameters on the QoE of VVoIP applications in a real wireless scenario. Through a complete statistical analysis of users' ratings, we identify the following facts. Although the use of VVoIP in wireless networks does not yet represent an advantage for users, there are great expectations for all applications under study, and with greater popularity comes higher expectations. It is easier for respondents to identify good behavior than poor behavior. Whereas the respondents' frequency of Internet use does not impact on the scores, respondents' gender does. Finally, the most determining parameters of quality from a user's perspective were instability, video quality, voice distortion, usefulness, and graphical interface.

• Journal of KIISE
• /
• v.42 no.8
• /
• pp.1039-1048
• /
• 2015

Recently, the web-based adaptive streaming service, DASH (Dynamic Adaptive Streaming over HTTP), is receiving more attention. However, existing network-based and buffer-based video quality control schemes in DASH environments make oscillation of segment throughput, causing degradation of the quality of experience (QoE) with frequent quality changes and playback interruptions because these schemes do not consider the content characteristics. In this paper, we propose a C-DASH (Content Characteristics based Dynamic Adaptive Streaming over HTTP) scheme in order to improve the QoE in DASH environments. The C-DASH scheme performs seamless and smooth quality control based on the segment throughput, buffer status, and segment size of the content. Based on simulation results, it is confirmed that the C-DASH scheme can improve the QoE, when compared with the existing quality control schemes.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.9
• /
• pp.73-80
• /
• 2011

Conventional content-delivering services over the Internet were mainly based on the "best effort" scheme, which have been failed to provide a concrete profit model to the content providers. Mean while, a quality assuring network service is expected to provide reasonable profit model. However the relation between the cost and profit of the quality service is under studies. Recently, the Quality of Experience (QoE) was introduced to measure the real satisfaction level of users and used to develope profit models of quality services. The QoE can be used as a key tool for efficient service providing and also criteria for accurate satisfaction measurement. Especially, the QoE based feedback on the intention to pay for the service will be an important information to the content providers. This paper will introduce a model for the costs of quality services, and a profit model based on the QoE. The result of the paper can be used to develope business models for contents services over the growing networks.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.346-348
• /
• 2010

In this paper, we propose the IPTV QoE evaluation method reflecting service user's preference. This method can evaluate the IPTV service QoE using the fuzzy integral because it usefully employs a subjective decision for QoE(Quality of Experience) evaluation. IPTV subscribers can prepare a criterion to select an IPTV provider who provides high qualityQoE.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.7
• /
• pp.17-22
• /
• 2016

In this paper we propose a novel QoE control scheme based on Service Level Agreement (SLA) which enables to guarantee the user perceived service quality of various high-quality mobile multimedia services such as mobile video streaming and real-time network games to a certain level. For this purpose, a SLA control structure is adopted to provision QoE, and a novel resource management scheme gets coupled with this control structure. Simulation results show that our proposed scheme can decrease the average delay and increase the total throughput by adjusting SLA.