A Comprehensive Evaluation Model for Traffic Data Quality Based on GRA and TOPSIS

Abstract

With the increasing of motor vehicles, Intelligent Transportation Systems (ITS) has become a major trend, and the traffic data quality is becoming a critical issue which has great influence on the system. In order to evaluate the quality of traffic data, a comprehensive evaluation model based on Grey Relational Analysis(GRA) and Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS) is proposed in this paper. On the basis of comprehensive analysis of traffic data, integrity, effectiveness, relative error of an occupancy speed model and relative error of an occupancy flow model are defined as four evaluation indices. Correlation coefficient is used to determine the reasonable weights. Then, the comprehensive evaluation value is computed by combining TOPSIS method and GRA method, which makes the improved grey correlation method not only has the positive reference sequence, but also has the negative reference sequence. Therefore, the results of the comprehensive evaluation show the difference and correlation between traffic data more obviously, which is more conducive to distinguish the quality of data. Finally, compared to GRA and TOPSIS, the experimental results show that the novel model is more scientific, objective and effective.