摘要
通过将证据理论引入到流量分类的决策模块中,提出了偏好度和时效度权值,并通过实测数据对多分类器识别模型进行验证,其结果表明该模型较好的克服了单分类器的片面性,通过对多个证据的融合来优化识别的结果。
The concept of multiclassifier fusion was introduced which can improve the classltcatlon accuracy ano over come the disadvantage of single classifier. DS theory was introduced into decision module of traffic classification and preference and timeliness was proposed. After analyzing multiclassifier model by simulation, the results show the new classifier model can overcome one sidedness of single classifier, depending on multiple evidences to optimize the traffic results.
出处
《通信学报》
EI
CSCD
北大核心
2013年第10期143-152,共10页
Journal on Communications
基金
国家重点基础研究发展计划("973"计划)基金资助项目(2009CB320505)
国家科技支撑计划基金资助项目(2008BAH37B04)~~