线要素化简及参数自动设置的案例推理方法

Automatic Line Simplification Algorithm Selecting and Parameter Setting Based on Case-Based Reasoning

目前,线要素化简的人机协同机制研究得较少,化简算法的选择以及参数设置依赖于人工反复修正,影响了算法的易用性。针对该问题,提出了通过案例进行类比推理得到线要素化简算法及参数的寻优方法。该方法采用案例推理(case-based reasoning,CBR)思想,计算机参考专家化简案例,通过相似性评价指标和参数寻优策略对参数候选集进行类比推理,自动筛选出与案例同一类区域和比例尺下的线要素化简算法及参数的最佳设置,从而省去制图员不断试错的繁琐过程。实验结果表明,该方法能够自动得到算法和参数的最优组合,化简结果与已有成果数据吻合度较高,能够有效地提高参数设置的效率和准确性,降低化简算法工具的使用难度。

Currently,there are few researches on human-machine collaboration mechanism in the process of using line simplification algorithm tools.The simplification algorithm selecting and parameter setting depend on manual repeated correction,which reduces the usability of the algorithm.To solve this problem,we propose a case-based reasoning method for automatic line simplification algorithm selecting and parameter setting.Under the reference of the case,the computer performs case-based analogical reasoning on the candidate parameter sets through the similarity evaluation index and parameter optimization strategy,and automatically selects the best combination of line simplification algorithm and parameter in the same region and scale,without the cartographys continuous trial and error procedure.In the experiment,this method is used to distinguish the results of three linear simplification algorithms D-P(Douglas-Peucker)algorithm,Li-Openshaw algorithm and Bend Group algorithm,and automatically select the optimal algorithm and threshold.The experiment shows that the algorithm and parameters can be optimized automatically by this method,and the results of simplification are in good match with the existing data.It can effectively improve the efficiency and accuracy of the parameter setting and reduce the difficulty of using the simplification algorithm tool.