A three-stage computational approach to network matching

Network matching is frequently needed for integrating data that come from different sources. Traditional ways of finding correspondences between networks are time-consuming and require considerable manual manipulation. This paper describes a three-stage matching algorithm (node matching, segment matching, and edge matching) that combines bottom-up and top-down procedures to carry out the matching computation. As it uses sensitive matching measures, the proposed algorithm promises good improvement to existing algorithms. An experiment of matching two waterway networks is reported in the paper. The results of this experiment demonstrate that a reasonable matching rate and good computational efficiency can be achieved with this algorithm. The paper also briefly discusses necessary improvements in areas of linear alignment, aspatial matching and higher-level matching.