计算机应用与软件2016，Vol.33Issue(5)：154-157,211,5.DOI:10.3969/j.issn.1000-386x.2016.05.038
基于 k-mediods 及其改进算法的非法营运车辆识别
RECOGNISING ILLEGAL OPERATION VEHICLES BASED ON K-MEDIODS AND ITS IMPROVED ALGORITHM
摘要
Abstract
In order to recognise the vehicles to be suspected operating illegally from a large number of social vehicles,improve the purposive intention and pertinence of the traffic administration in administrative enforcement,maintain the market order of road transportation and eliminate the hidden traffic safety hazard,we proposed the k-mediods-based illegal operation vehicles recognition algorithm in combination with RFID vehicle information data.In light of the shortcomings of k-mediods algorithm,we made two improvements on it,the distance contribution rate-based and the algorithm contingency-based respectively.To implement the illegal operation vehicles recognition,firstly it needs to extract vehicles’RFID data,and carries out pretreatment on them,and then obtains the behaviour data of vehicles operation;secondly,it acquires the characteristics data of vehicles operation by means of PCA processing;finally,it recognises the illegal operation vehicles by k-mediods-based clustering analysis.Experimental results show that the algorithm has a clear flow,it can recognise the illegal operation vehicles effectively,meanwhile it can improve the stability of the algorithm by improving it,and in turn raises the numbers of correct recognition of the illegal operation vehicles,and decreases the numbers of wrong recognition as well.关键词
k-mediods/距离贡献率/偶然性/RFIDKey words
k-mediods/Distance contribution rate/Contingency/RFID分类
信息技术与安全科学引用本文复制引用
帅丹,蓝章礼,李益才..基于 k-mediods 及其改进算法的非法营运车辆识别[J].计算机应用与软件,2016,33(5):154-157,211,5.基金项目
重庆市教委科学技术研究项目（KJ130421）。 （）
