Wireless Propagation Multipath Clustering: On Simultaneously Solving the Membership and the Number of Clusters

Multipaths from COST 2100 channel model (C2CM) semi-urban scenario obtained from IEEE DataPort are clustered using simultaneous clustering and model selection (SCAMS). SCAMS jointly solves the problem on model selection and clustering by determining simultaneously the number of clusters and their membership unlike well-known clustering approaches that give only the number of clusters. The number and membership of clusters depend on ߣ and ߛ, the parameters that weigh the penalty terms so that the trivial solution of the affinity matrix is avoided. The clustered multipaths from SCAMS are compared with the reference multipath clustering datasets available at IEEE DataPort using Jaccard index which examines the accuracy of the clustering approach.