电讯技术2016，Vol.56Issue(8)：844-849,6.DOI:10.3969/j.issn.1001-893x.2016.08.003
基于k最近邻回归的频谱占用度预测
Spectrum Occupancy Prediction Based on k-Nearest Neighbor Regression
摘要
Abstract
Cognitive radio technology can conduct spectrum allocation between the authorized users and secondary users. The establishment of predication model can help secondary users infer whether the spec-trum hole is available,which can both improve spectral efficiency and reduce collision rate. By means of theoretical analysis,experiment monitoring,mathematical modeling and data demonstration,spectrum occu-pation modeling theory is researched. For the predictable problems of spectrum,through the analysis of data group,k-Nearest Neighbour( kNN) regression model is used to predict the channel-field value of spec-trum. At the same time,based on the periodicity shown by the observation data,a kNN model is proposed to optimize periodical data and offers predication. Then the predication accuracy is compared in test data of o-riginal kNN regression model and optimized periodical kNN. The result shows the optimized model is of bet-ter predication accuracy than the original kNN model.关键词
认知无线电/频谱分配/频谱占用度/场强预测/k最近邻回归Key words
cognitive radio/spectrum allocation/spectrum occupancy/field strength prediction/kNN regression分类
信息技术与安全科学引用本文复制引用
贾云峰,邱琳,魏鸿浩..基于k最近邻回归的频谱占用度预测[J].电讯技术,2016,56(8):844-849,6.基金项目
国家自然科学基金资助项目(61371007) Foundation Item:The National Natural Science Foundation of China(No.61371007) （61371007）
