Multi-resolution online classification algorithm for data streams
一种多分辨率数据流在线分类算法

An incremental classification algorithm based on nearest neighbor technology, which adapts to the sudden concept shift over data streams, was proposed. The algorithms uses grid technique to quantize the feature space of data set and uses a multi-resolution data representation based on Haar wavelets to find adaptive class label of a test point. Experiments performed on both synthetic and real-life data indicate that the proposed classifier outperforms existing algorithms for data streams in terms of accuracy. The algorithm's low update and computational cost makes it highly suitable for data stream applications.