5. Perform the Jarvis-Patrick Clustering (Cluster Analysis: Additional Issues and Algorithms: (2) Density-Based Clustering and Graph-Based...

   

Transcribed Image Text:

5. Perform the Jarvis-Patrick Clustering (Cluster Analysis: Additional Issues and Algorithms: (2) Density-Based Clustering and Graph-Based Clustering, and other issues - Slide 44) on the distance matrix below. (4 points) P1 P2 P3 P4 P5 P6 P1 0 0.20 0.41 0.55 0.35 0.12 P2 0.20 0 0.64 0.47 0.18 0.35 P3 0.41 0.64 0 0.44 0.55 0.54 P4 0.55 0.47 0.44 0 0.76 0.23 P5 0.35 0.18 0.55 0.76 0 0.62 P6 0.12 0.35 0.54 0.23 0.620 a) Construct the K-nearest neighbor graph such that K = 2. b) Construct the shared nearest neighbor graph. c) For a threshold T = 1, construct the clustering using the Jarvis-Patrick Clustering algorithm (Note: If there is only one point in a cluster, the point is considered a noise point and is not included in the clustering). 5. Perform the Jarvis-Patrick Clustering (Cluster Analysis: Additional Issues and Algorithms: (2) Density-Based Clustering and Graph-Based Clustering, and other issues - Slide 44) on the distance matrix below. (4 points) P1 P2 P3 P4 P5 P6 P1 0 0.20 0.41 0.55 0.35 0.12 P2 0.20 0 0.64 0.47 0.18 0.35 P3 0.41 0.64 0 0.44 0.55 0.54 P4 0.55 0.47 0.44 0 0.76 0.23 P5 0.35 0.18 0.55 0.76 0 0.62 P6 0.12 0.35 0.54 0.23 0.620 a) Construct the K-nearest neighbor graph such that K = 2. b) Construct the shared nearest neighbor graph. c) For a threshold T = 1, construct the clustering using the Jarvis-Patrick Clustering algorithm (Note: If there is only one point in a cluster, the point is considered a noise point and is not included in the clustering).