自适应边界逼近的原型选择算法

Adaptive Boundary Approximation Prototype Selection Algorithm

针对传统原型选择算法易受样本读取序列、异常样本等干扰的缺陷,通过分析原型算法学习规则,借鉴最近特征线法思想,改进传统原型算法,提出一种自适应边界逼近的原型选择算法.该算法在原型学习过程中改进压缩近邻法的同类近邻吸收策略,保留更优于当前最近边界原型的同类样本,同时建立原型更新准则,并运用该准则实现原型集的周期性动态更新.该算法不仅克服读取序列、异常样本对原型选取的影响,而且降低原型集规模.最后通过人工数据和UCI基准数据集验证文中算法.实验表明,文中算法选择的原型集比其他算法产生的原型集更能体现数据集的分布特征,平均压缩率有所提高,且分类精度与运行时间优于其他算法.

The traditional prototype selection algorithms are susceptible to pattern reading sequence, abnormal patterns etc. Aiming at these problems, an improved prototype selection algorithm based on adaptive boundary approximation is proposed by a detailed analysis of the prototype learning rule. The prototype absorption strategy of condensed nearest neighbor algorithm （ CNN ） is improved and the closer homogeneous boundary prototype parallel to its current nearest one is retained. Meanwhile, the prototype updating strategy is built for achieving dynamic periodic updating to the prototype set. The proposed algorithm can overcome the above mentioned issues and effectively reduce the scale of prototype set. Experiments are made on the artificial dataset and UCI benchmark dataset, and the results show that the final prototype set obtained by the proposed algorithm reflects the distribution of the original dataset much better. It improves the average reduction ratio performance, has better classification accuracy and runs faster than other algorithms.