基于机器学习分析VoLTE视频通话质量的研究及应用

钟其柱

doi:10.11959/j.issn.1000-0801.2020021

您当前的位置：

首页 >

文章列表页 >

基于机器学习分析VoLTE视频通话质量的研究及应用

运营技术广角 | 更新时间：2024-06-05

- 基于机器学习分析VoLTE视频通话质量的研究及应用
- Research and application of VoLTE video call quality based on machine learning
- 电信科学 2020年36卷第3期页码：156-165
- 作者机构：
- 作者简介：
  
  [ "钟其柱（1985– ），男，中国移动通信集团广东有限公司中山分公司网络管理中心高级工程师，主要研究方向为移动通信网络的分析优化" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2020021
  中图分类号： TN919.8
- 网络出版日期：2020-03，
  
  纸质出版日期：2020-03-20
- 稿件说明：
移动端阅览
钟其柱. 基于机器学习分析VoLTE视频通话质量的研究及应用[J]. 电信科学, 2020,36(3):156-165.

Qizhu ZHONG. Research and application of VoLTE video call quality based on machine learning[J]. Telecommunications science, 2020, 36(3): 156-165.
钟其柱. 基于机器学习分析VoLTE视频通话质量的研究及应用[J]. 电信科学, 2020,36(3):156-165. DOI： 10.11959/j.issn.1000-0801.2020021.

Qizhu ZHONG. Research and application of VoLTE video call quality based on machine learning[J]. Telecommunications science, 2020, 36(3): 156-165. DOI： 10.11959/j.issn.1000-0801.2020021.

摘要

针对目前评估VoLTE视频通话质量的方法的缺点，提出了一种基于机器学习和网络指标参数的VoLTE视频通话质量评估方法。首先，采集解码核心网的网络参数指标数据，并进行预处理；然后，选取用于VoLTE视频通话质量评估的关键特征，并通过对比选取合适的机器学习算法，构建VoLTE视频质量评估的评估模型，从而实现不依赖于测试环境和原始视频的VoLTE视频通话质量实时评估。通过对从XDR（用户话单）数据中提取的特征指标数据进行预处理研究，解决了特征指标的标准化问题，便于指标特征输入评估模型；通过特征工程选出评估VoLTE视频通话的关键特征，减少特征维数，从而降低了算法的复杂度；同时采用先进的机器学习技术保证和提升算法的评估准确性。

Abstract

To overcome the shortcomings of current methods for evaluating VoLTE video call quality

a method for evaluating VoLTE video call quality without reference based on machine learning and network index parameters was proposed.Firstly

the network parameters of the decoding core network were collected and preprocessed; then

the key features for VoLTE video call quality assessment were selected

and a reference-free evaluation model for VoLTE video quality assessment was constructed by comparing and selecting appropriate machine learning algorithms

so as to achieve real-time VoLTE video call quality assessment independent of the test environment and the original video.By researching the preprocessing of feature index data extracted from XDR data

the standardization of feature index was solved

and the evaluation model of feature input was convenient; the key features of VoLTE video call were selected and evaluated by feature engineering

which reduced the feature dimension and the complexity of the algorithm; at the same time

advanced machine learning technology was adopted to ensure and enhance the algorithm assessment accuracy.

关键词

Keywords

references

冯赟中 . VoLTE 技术演进与改进对策研究 [J ] . 通讯世界:下半月 , 2016 ( 7 ): 90 - 91 .

FENG Y Z . Research on VoLTE technology evolution and improvement countermeasures [J ] . Communication World:Second Half of the Month , 2016 ( 7 ): 90 - 91 .

温婧芙 . 4G+高清语音 VoLTE [J ] . 科技与创新 , 2017 ( 9 ): 15 - 16 .

WEN J F . 4G+ VoLTE [J ] . Technology and Innovation , 2017 ( 9 ): 15 - 16 .

北京理工大学 . 一种 VoLTE 视频通话用户体验质量评估方法:201710127004.X 2017-06-20.

Beijing Institute of Technology . VoLTE video call user experience quality evaluation method:201710127004.X [P ] .2017-06-20

北京理工大学 . 基于神经网络的 VoIP 无参考视频通信质量客观评价方法:201710268980.7 2017-08-08.

Beijing Institute of Technology . Objective evaluation method of VoIP unreferenced video communication quality based on neural network:201710268980.7 [P ] .2017-08-08

TOM M . Machine learning [M ] . New York : McGraw-HillPress , 1997 .

VALIANT L G . A theory of learnable [J ] . Communications of the ACM , 1984 , 27 ( 11 ): 1134 - 1142 .

陈凯 , 朱钰 . 机器学习及其相关算法综述 [J ] . 统计与信息论坛 , 2007 , 22 ( 5 ): 105 - 112 .

CHEN K , ZHU Y . Overview of machine learning and related algorithms [J ] . Statistics and Information Forum , 2007 , 22 ( 5 ): 105 - 112 .

浏览量

641

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于可解释机器学习模型的电信行业客户流失预测研究

基于流量特征重构与映射的物联网DDoS攻击单流检测方法

基于5G语音质差自适应算法研究及应用

基于区块链与深度学习的空间分集协作频谱感知系统

基于柔性太阳能电池和超薄水凝胶薄膜的手势识别