STrenD: Subspace Trend Discovery

Revision as of 21:50, 28 September 2011 (view source) Yan Xu (Talk | contribs) (Created page with "My first page")		Revision as of 22:15, 28 September 2011 (view source) Yan Xu (Talk | contribs) Newer edit →
Line 1:		Line 1:
−	My first page	+
		+	== Clustering ==
		+	Clustering is for data dimension deduction to speed up the analysis.
		+
		+	== Minimum Spanning Tree ==
		+	Build MST for each clustering module so as to tell how cells are related to each other in every module.
		+
		+	== Similarity Matrix ==
		+	Based on the MSTs, implement the Earth Mover's Distance(EMD) method for every two modules to see how each module is similar to the other.
		+
		+	== Progression Tree ==
		+	By checking the visualized similarity matrix, choose the ideal modules for the progression tree generation.

---

Revision as of 22:15, 28 September 2011

Contents 1 Clustering 2 Minimum Spanning Tree 3 Similarity Matrix 4 Progression Tree

Clustering

Clustering is for data dimension deduction to speed up the analysis.

Minimum Spanning Tree

Build MST for each clustering module so as to tell how cells are related to each other in every module.

Similarity Matrix

Based on the MSTs, implement the Earth Mover's Distance(EMD) method for every two modules to see how each module is similar to the other.

Progression Tree

By checking the visualized similarity matrix, choose the ideal modules for the progression tree generation.