[vc_empty_space][vc_empty_space]
An efficient technique for cluster number prediction in graph clustering using nullity of laplacian matrix
Atastina I.a, Sitohang B.a, Saptawati G.a, Moertini V.S.b
a Institut Teknologi Bandung, Bandung, 40132, Indonesia
b Chatolic Parahyangan University, Bandung, 41311, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2005 – ongoing JATIT & LLS.Clustering graph dataset representing users’ interactions can be used to detect groups or communities. Many existing graph clustering algorithms require an initial cluster number. The closer the initial cluster numbers to the real or final ones, the faster the algorithm will converge. Hence, finding the right initial cluster number is important for increasing the efficiency of the algorithms. This research proposes a novel technique for computing the initial cluster number using the nullity of the Laplacian Matrix of Adjacency Matrix. The fact that nullity relates to the properties of the eigenvalues in the Laplacian matrix of a connected component is used to predict the best cluster numbers. By using this technique, trial and error experiments for finding the right clusters is no longer needed. The experiment results using artificial and real dataset and modularity values (for measuring the clusters quality) showed that our proposed technique is efficient in finding initial cluster numbers, which is also the real best cluster numbers.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Adjacency Matrix,Estimating the Number of Clusters,Graph Clustering,Laplacian Matrix,Nullity[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]