摘要
为降低集成特征选择方法的计算复杂性,提出了一种基于粗糙集约简的神经网络集成分类方法。该方法首先通过结合遗传算法求约简和重采样技术的动态约简技术,获得稳定的、泛化能力较强的属性约简集;然后,基于不同约简设计BP网络作为待集成的基分类器,并依据选择性集成思想,通过一定的搜索策略,找到具有最佳泛化性能的集成网络;最后通过多数投票法实现神经网络集成分类。该方法在某地区Landsat 7波段遥感图像的分类实验中得到了验证,由于通过粗糙集约简,过滤掉了大量分类性能欠佳的特征子集,和传统的集成特征选择方法相比,该方法时间开销少,计算复杂性低,具有满意的分类性能。
Neural network ensemble based on rough sets reduction is proposed to decrease the computing complexity of conventional feature ensemble selection algorithms. Firstly, a dynamic reduction technology, which integrates genetic algo- rithm and resample method, is used to get reduct sets that have stable and good generalization ability. Secondly, Multiple BP neural networks based on different reducts are built as base classifiers. According to the idea of selective ensemble, the best generalization ability neural network ensemble can be found by some search strategies. Finally, classification based on neural network ensemble can be completed by combination with vote rule. The method has been verified in the experiment of classifying Landsat 7 bands remote sensing image of chosen area. A number of feature sets of poor performance were discarded by reduction based on rough sets. Compared to conventional feature selection algorithms, the method takes less time, has lower computing complexity, and the performance is satisfying.
出处
《中国图象图形学报》
CSCD
北大核心
2008年第3期480-487,共8页
Journal of Image and Graphics
基金
国家自然科学基金项目(60775047)
湖南省自然科学基金项目(06JJ50112)
关键词
粗糙集
约简
神经网络集成
遥感图像分类
rough sets, reduction, neural network ensemble, remote sensing image classification
