基于张量模型的多因素影响程度分析方法-计算机工程与应用.PDF

94 2017 ，53（17） Computer Engineering and Applications 计算机工程与应用 基于张量模型的多因素影响程度分析方法 用 1，2 1，2 1，2 王卿云 ，李红燕 ，洪申达 应 WANG Qingyun1，2 , LI Hongyan1，2 , HONG Shenda1，2 与 1.北京大学 机器感知与智能教育部重点实验室，北京 100871 程 2.北京大学 信息科学技术学院，北京 100871 g r 1.Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing 100871, China 工 o 2.School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China . 机 j a WANG Qingyun, LI Hongyan, HONG Shenda. Multi factors influencing degree analysis method based on tensor 算 e model. Computer Engineering and Applications, 2017, 53 （17）：94-100. c 计 . Abstract: The influencing degree analysis can be divided into independent influencing degree analysis and the combined w influencing degree analysis. The traditional influencing degree analysis method is difficult to take the two into account, w and is trapped in the number of influencing factors and multicollinearity between factors. Some methods even cannot be w applied to large scale data sets, which undoubtedly hinder the improvement of the accuracy of the analysis and the wide application of the methods. So it proposes the Multi factors influencing degree Analysis method based on Tensor decom- position and reconstruction （MAT ）, which eliminates the multicollinearity between factors, and realizes the analysis of independent and combined influencing degree at the same time. The experiments on the real large scale mobile co