Tree-structured Data Clustering

Date

2018-11-04

Author

Dinler, Derya
Tural, Mustafa Kemal
Özdemirel, Nur Evin

Metadata

Show full item record

Item Usage Stats

128
views

0
downloads

Tree-structured Data ClusteringWe consider a clustering problem in which data objects are rooted trees withunweighted or weighted edges and propose a k-means based algorithm whichrepeats assignment and update steps until convergence. The assignment steputilizes Vertex Edge Overlap to assign each data object to the most similarcentroid. In the update step, each centroid is updated by considering the dataobjects assigned to it. For the unweighted edges case, we propose a NonlinearInteger Programming (NIP) formulation to find the centroid of a given cluster andsolve the formulation to optimality with a heuristic. When edges are weighted,we also provide an NIP formulation for which we have a heuristic notguaranteeing optimality.

URI

https://hdl.handle.net/11511/86531

Collections

Unverified, Conference / Seminar

Suggestions

OpenMETU
Core

Tree-structured Data Clustering Dinler, Derya; Tural, Mustafa Kemal; Özdemirel, Nur Evin (2019-11-04) Tree-structured Data ClusteringWe consider a clustering problem in which data objects are rooted trees withunweighted or weighted edges and propose a k-means based algorithm whichrepeats assignment and update steps until convergence. The assignment steputilizes Vertex Edge Overlap to assign each data object to the most similarcentroid. In the update step, each centroid is updated by considering the dataobjects assigned to it. For the unweighted edges case, we propose a NonlinearInteger Programming (NIP) for...
UNCERTAINTY AND A NEW MEASURE FOR CLASSIFICATION UNCERTAINTY Damgacioglu, Haluk; İyigün, Cem (2012-08-29) Ben-Israel and Iyigun ([1] and [2]) presents a new clustering method which is probabilistic distance clustering (P-D Clustering). In this method, the probability of assignment to cluster for each point is inversely proportional to distances between data point and centers of clusters according to given number of clusters and their centers. In this paper, we study on new uncertainty measure for classification using the assignment probabilities of P-D Clustering. Moreover, the relationship of the new measure w...
Comparison of feature-based and image registration-based retrieval of image data using multidimensional data access methods Arslan, Serdar; Yazıcı, Adnan; Sacan, Ahmet; Toroslu, İsmail Hakkı; Acar, Esra (Elsevier BV, 2013-07-01) In information retrieval, efficient similarity search in multimedia collections is a critical task In this paper, we present a rigorous comparison of three different approaches to the image retrieval problem, including cluster-based indexing, distance-based indexing, and multidimensional scaling methods. The time and accuracy trade-offs for each of these methods are demonstrated on three different image data sets. Similarity of images is obtained either by a feature-based similarity measure using four MPEG-...
Implicit monolithic parallel solution algorithm for seismic analysis of dam-reservoir systems Özmen, Semih; Kurç, Özgür; Department of Civil Engineering (2016) This research mainly focuses on developing a computationally scalable and efficient solution algorithm that can handle linear dynamic analysis of dam-reservoir interaction problem. Lagrangian fluid finite elements are utilized and compressibility and viscosity of the fluid are taken into consideration during the reservoir modeling. In order to provide computational scalability and efficiency, domain decomposition methods implemented with parallel computing approaches such as Finite Element Tearing and Inter...
Implementation Studies of Robot Swarm Navigation Using Potential Functions and Panel Methods Merheb, Abdel-Razzak; GAZİ, VEYSEL; Sezer Uzol, Nilay (2016-10-01) This paper presents a practical swarm navigation algorithm based on potential functions and properties of inviscid incompressible flows. Panel methods are used to solve the flow equations around complex shaped obstacles and to generate the flowlines, which provide collision-free paths to the goal position. Safe swarm navigation is achieved by following the generated streamlines. Potential functions are used to achieve and maintain group cohesion or a geometric formation during navigation. The algorithm is i...

Citation Formats

D. Dinler, M. K. Tural, and N. E. Özdemirel, “Tree-structured Data Clustering,” 2018, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/86531.