Concept evolution detection based on noise reduction soft boundary

Abstract

Concept evolution detection is an important but difficult task in streaming data analysis, and further the noise may seriously limit the detection performance gains. This paper proposed a concept evolution detection method based on noise reduction soft boundary (NRSB). To reduce the negative effect of noise samples near category boundary, the noise reduction soft boundaries are defined based on the introducing of extension distance, intension distance and corresponding noise reduction process. Then the sample space is divided into in-class, mixed-class and out-of-class areas corresponding to each category. For online new coming samples, three strategies of automatic labeling by model, active labeling by expert and multi-class collaborative labeling will be adopted respectively according to different areas they located in. Automatic model labeling does not need to update the model, which may improve the learning efficiency. Expert active labeling will help with difficult samples in mixed-class area. Multi-class collaborative labeling can change the sample label dynamically during online learning. The experimental results show that the proposed method can reflect the character of dynamic evolution of streaming data well and detect the concept evolution effectively.