This paper focuses on continuous attributes handling for mining data stream with concept drift. CVFDT is one of the most successful methods for handling concept drift efficiently. In this paper, we revisit this problem and present an algorithm named SL_CVFDT on top of CVFDT. It is fast as hash table when inserting, seeking or deleting attribute value, and it also can sort the attribute value. The average time cost of search, insertion and deletion is O(log2n),and average memory cost of point is O(n).At the same time, it can get best split point just traverse the skip list once.
展开▼
