序列模式挖掘:区分性、意外性与结构化数据探索
1. ConSGapMiner算法基础
ConSGapMiner算法用于挖掘具有区分性的序列模式,其基本流程如下:
Algorithm: ConSGapMiner(pos,neg,g,δ,α)
Assumption: I is the alphabet list, g is the maximum gap constraint,
δ is the minimal support in pos, α is the maximal support in neg,
a global set SMDS is used to contain the patterns generated by SMDS Gen;
Output: g-MDS set MDS;
Method:
1: SMDS ←{};
2: set S to the empty sequence;
3: SMDS Gen(S,g,I,δ,α);
4: let MDS be the result of minimizing SMDS as described above;
5: return MDS;
这个算法的核心目标是找出满足特定条件的最小区分性子序列(MDS)。它通过一系列步骤,从空序列开始,逐步生成并筛选出符合要求的模式。
2. 扩展ConSGapMiner:最小间隔约束
最小间隔约束是最大间隔约束的对偶概念,用正整数 q 来指定。对于序列 S = s1...sn 和子序列
超级会员免费看
订阅专栏 解锁全文

被折叠的 条评论
为什么被折叠?



