Vector quantization based approximate spectral clustering of large datasets

Automatic assessment of land parcel identification systems for agricultural management

“…Formally, CONN(i, j) = |RFij| + |RFji|; RFij is part of RFi (receptive field of wi) where wj is the second BMU, and |.| is the cardinality of the set. Contrary to the distance-based similarity requiring user-set parameters, CONN similarity is advantageous for spectral clustering, since it is constructed using intrinsic data details without any user-set parameters, it is sparse by definition, and it is supported by empirical studies [4]. Let D be the diagonal matrix denoting the degree of N nodes where di = j s(i, j); and define normalized Laplacian matrix,…”

“…In the first step, the proposed method discriminates different land cover types (clusters) by self-organizing maps (SOM) based spectral clustering [4], a recent method utilizing both the SOM properties and the advantages of spectral clustering. The SOM, an unsupervised neural network commonly used for cluster extraction from remotely sensed images [5,6,7], is trained to obtain data representatives by a faithful vector quantization in a topology preserving manner.…”

Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs

“…However, spectral clustering is known to suffer from a high computational cost associated with the n × n matrix W , especially when n is large. Consequently, there has been considerable effort to develop fast, approximate algorithms that can handle large data sets (Fowlkes et al, 2004;Yan et al, 2009;Sakai and Imiya, 2009;Wang et al, 2009;Chen and Cai, 2011;Wang et al, 2011;Tasdemir, 2012;Choromanska et al, 2013;Cai and Chen, 2015;Moazzen and Tasdemir, 2016;Chen, 2018). Interestingly, a considerable fraction of them use a landmark set to help reduce the computational complexity of spectral clustering.…”

A Novel Spectral Clustering Based on Nonlinear Low Dimensional Embedding Feature Selection

“…Among them, spectral clustering algorithms have currently become one of the hotspot in machine learning. Spectral clustering has been utilized in dimension reduction, irregular data clustering, image segmentation, video analysis and so on which has attract much attention [1][2]. Spectral clustering reveals the intrinsic cluster structure of data, and can be used to detect the non convex and non linear structure with eigenvectors of the Laplace matrix.…”