1. 6. experimental methodologies
1.1. Assesment
1.1.1. Sum of Squared Errors (SSE)
1.1.1.1. compactness of the cluster
1.1.2. purity
1.1.2.1. when labels available
1.1.2.2. related entrophy
1.1.3. Clustering Mapping Measure
1.1.3.1. Missed objects
1.1.3.2. Misplaced objects
1.1.3.3. Noice inclusion
2. Practical issues
3. 5. issues in temporal aspects
3.1. Cluster tracking
3.1.1. internal transitions
3.1.1.1. 1.changes in compactness
3.1.1.2. 2. changes in cluster size
3.1.1.3. 3. changes in location
3.1.2. external transitions
3.1.2.1. 1. cluster survives
3.1.2.2. split in to multiple clusters
3.1.2.3. 3.Absorbed by another cluster
3.1.2.4. cluster disappears
3.1.2.5. 5. new cluster emerges
3.1.3. MONIC algorithm
4. 2. taxonomy/classification of different algorithms
4.1. Object based clustering
4.1.1. 1. data abstraction/online component
4.1.2. 2. clustering step
4.2. Attribute Based Clustering
5. componenets responsible
5.1. 3. Online processing
5.1.1. Data Structures
5.1.1.1. 3.1 data structures
5.1.1.1.1. feature vectors
5.1.1.1.2. prototype arrays
5.1.1.1.3. coreset trees
5.1.1.1.4. data grids
5.1.2. Window models
5.1.2.1. 3.2 summarizing/ distinct window models
5.1.2.1.1. sliding window model
5.1.2.1.2. landmark model
5.1.2.1.3. damped model
5.1.3. Outlier detection mechanisms