数据采集与处理2018，Vol.33Issue(1)：75-84,10.DOI:10.16337/j.1004-9037.2018.01.009
非均衡IPTV数据集下的用户报障预测
Prediction for User′s Complaint in Imbalanced IPTV Dataset
摘要
Abstract
In the imbalanced internet protocol television(IPTV)dataset,the traditional algorithm per-forms not well in terms of predicting the user′s complaint.For this problem,this paper combines tradi-tional network parameters that influence the network quality of service(QoS)with MOS score that ob-jectively reflects the quality of experience(QoE)to predict user′s complaint.And then we propose an im-proved algorithm based on the existing ODR-BSMOTE-SVM algorithm for the defects that the over-sam-pling algorithm will produce noise and there is not any optimization for kernel parameters.In the im-proved algorithm,under-sampling algorithm,over-sampling algorithm and data cleaning algorithm are firstly used to process the original imbalanced dataset.Then,through searching for the approximate opti-mal value by adaptive variable kernel parameters,the classification effect is ultimately improved.Experi-mental results show that the improved algorithm performs better than the traditional standard support vector machine(SVM)and the ODR-BSMOTE-SVM algorithm in predicting user′s complaint.关键词
非均衡数据/服务质量/数据清洗/支持向量机Key words
imbalanced data set/quality of service/data cleaning/support vector machine分类
信息技术与安全科学引用本文复制引用
吴志峰,黄若尘,魏昕,黄荣谞,周亮..非均衡IPTV数据集下的用户报障预测[J].数据采集与处理,2018,33(1):75-84,10.基金项目
国家重点基础研究发展计划(2013CB329005)资助项目 （2013CB329005）
国家自然科学基金(61322104,61571240)资助项目 （61322104,61571240）
江苏高校优势学科建设工程资助项目 （）
江苏省自然科学基金(BK20161517)资助项目 （BK20161517）
江苏省青蓝工程资助项目. （）
