交通检测器获得的数据存在无效、冗余、错误、时间点漂移及丢失等质量问题.为此,在分析影响数据质量问题原因的基础上,给出交通流数据清洗的概念,研究“脏数据”的清洗规则与清洗步骤,并对环形线圈检测器检测到的数据进行验证.结果表明,该清洗规则对错误、丢失、冗余等“脏数据”的识别率均在90％以上.%Aiming at that many quality problems are existed inevitably in detected data, including inefficacy, redundancy, error, missing, time dot excursion etc, the definition of data cleaning is proposed on the basis of sufficient study and analysis for the influence reasons of data quality, the cleaning rules and cleaning steps of "dirty data" are studied at the same time. And the proposed cleaning rules are calibrated with the detected data of loop vehicle detector. Results show that the recognition rates of "dirty data" is up to 90%.
展开▼
