Y. B. Youssef, Mériem Afif, Riadh Ksantini, S. Tabbane
{"title":"A Novel Online QoE Prediction Model Based on Multiclass Incremental Support Vector Machine","authors":"Y. B. Youssef, Mériem Afif, Riadh Ksantini, S. Tabbane","doi":"10.1109/AINA.2018.00058","DOIUrl":null,"url":null,"abstract":"Satisfying the user it's a primary goal to reach by telecom operators. Therefore, Quality of Experience (QoE), which is the measure of the user-perceived quality of a received service, has become a pivotal topic in the academic research. Generally, an efficient QoE model should be able to handle dynamic environments with large scale data, in order to continuously acquire feedback from the user, and then provide a real-time and accurate description of his perception. This paper proposes a novel online QoE estimation model, which is able to classify user perception toward video streaming service, using incremental multiclass SVM (multiclass-iSVM). The proposed online QoE model investigates the effectiveness of incremental learning, in order to handle large scale dynamic data and to improve prediction accuracy of QoE. In fact, it uses the mathematical properties of SVM and updates its unknown weights, as well as, the classification results incrementally, as new observations are considered. Comparative evaluation of the proposed multiclass iSVM-based QoE model is performed to show its superiority over relevant batch learning based models, in terms of QoE prediction accuracy and computational complexity. In particular, this model has achieved the highest classification rate of 89%, starting with only 10% of the dataset at the beginning of the incremental process.","PeriodicalId":239730,"journal":{"name":"2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AINA.2018.00058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
Satisfying the user it's a primary goal to reach by telecom operators. Therefore, Quality of Experience (QoE), which is the measure of the user-perceived quality of a received service, has become a pivotal topic in the academic research. Generally, an efficient QoE model should be able to handle dynamic environments with large scale data, in order to continuously acquire feedback from the user, and then provide a real-time and accurate description of his perception. This paper proposes a novel online QoE estimation model, which is able to classify user perception toward video streaming service, using incremental multiclass SVM (multiclass-iSVM). The proposed online QoE model investigates the effectiveness of incremental learning, in order to handle large scale dynamic data and to improve prediction accuracy of QoE. In fact, it uses the mathematical properties of SVM and updates its unknown weights, as well as, the classification results incrementally, as new observations are considered. Comparative evaluation of the proposed multiclass iSVM-based QoE model is performed to show its superiority over relevant batch learning based models, in terms of QoE prediction accuracy and computational complexity. In particular, this model has achieved the highest classification rate of 89%, starting with only 10% of the dataset at the beginning of the incremental process.
让用户满意是电信运营商的首要目标。因此,衡量用户感知到的所接受服务质量的体验质量(Quality of Experience, QoE)已成为学术界研究的关键课题。通常,一个高效的QoE模型应该能够处理具有大规模数据的动态环境,以便持续获取用户的反馈,然后实时准确地描述用户的感知。本文提出了一种新的在线QoE估计模型,该模型利用增量多类支持向量机(multiclass- isvm)对用户对视频流服务的感知进行分类。提出的在线QoE模型考察了增量学习的有效性,以处理大规模动态数据,提高QoE的预测精度。实际上,它利用了支持向量机的数学特性,并随着新的观测值的考虑,增量地更新其未知权重以及分类结果。对所提出的基于isvm的多类QoE模型进行了比较评价,以显示其在QoE预测精度和计算复杂度方面优于相关的基于批处理学习的模型。特别是,该模型在增量过程开始时仅从10%的数据集开始,实现了89%的最高分类率。