Quality of experience（QoE） has been one of the most important factors for service providers and operators to develop and deploy services. Previous works have shown that Weber-Fechner law（WFL） can be used to promot...Quality of experience（QoE） has been one of the most important factors for service providers and operators to develop and deploy services. Previous works have shown that Weber-Fechner law（WFL） can be used to promote the accuracy of best-effort（BE） services＇ QoE assessment. In this paper, based on WFL, we take a deep insight into the visual information of BE services and its role in WFL, especially in web browsing services, and propose an enhanced QoE assessment model for BE services by taking the visual information into account. Both images and texts visual information are extracted and combined to get the visual information for web pages. Finally, a subjective experiment is performed to validate performance of proposed QoE assessment model, which shows that it performs better than traditional WFL based model.展开更多
This paper examines dependencies of voice and video contents on human perception of group (or inter-destination) synchronization error in remote learning by Quality of Experience (QoE) assessment. In our assessment, w...This paper examines dependencies of voice and video contents on human perception of group (or inter-destination) synchronization error in remote learning by Quality of Experience (QoE) assessment. In our assessment, we use two videos and three voices (two voices for one video and one voice for the other video). We also investigate influences of silence periods in the voices and temporal relations between the voices and videos (called the tightly-coupled and loosely-coupled contents here). The voices are spoken by a teacher according to the videos. Each subject as a student assesses the group synchronization quality by watching each lecture video and the corresponding explanation voice, and then the subject answers whether he/she perceives the group synchronization error or not. As a result, assessment results illustrate that silence periods mitigate the perception rate of the error, and we can also find that we can more easily perceive the error for tightly-coupled contents than loosely-coupled ones.展开更多
基金supported by the Beijing Municipal Science and Technology Commission Research Fund Project (D151100000115002 )the Ministry of Education. CMCC Research fund (MCM20130132)
文摘Quality of experience（QoE） has been one of the most important factors for service providers and operators to develop and deploy services. Previous works have shown that Weber-Fechner law（WFL） can be used to promote the accuracy of best-effort（BE） services＇ QoE assessment. In this paper, based on WFL, we take a deep insight into the visual information of BE services and its role in WFL, especially in web browsing services, and propose an enhanced QoE assessment model for BE services by taking the visual information into account. Both images and texts visual information are extracted and combined to get the visual information for web pages. Finally, a subjective experiment is performed to validate performance of proposed QoE assessment model, which shows that it performs better than traditional WFL based model.
文摘This paper examines dependencies of voice and video contents on human perception of group (or inter-destination) synchronization error in remote learning by Quality of Experience (QoE) assessment. In our assessment, we use two videos and three voices (two voices for one video and one voice for the other video). We also investigate influences of silence periods in the voices and temporal relations between the voices and videos (called the tightly-coupled and loosely-coupled contents here). The voices are spoken by a teacher according to the videos. Each subject as a student assesses the group synchronization quality by watching each lecture video and the corresponding explanation voice, and then the subject answers whether he/she perceives the group synchronization error or not. As a result, assessment results illustrate that silence periods mitigate the perception rate of the error, and we can also find that we can more easily perceive the error for tightly-coupled contents than loosely-coupled ones.
