Cube Kohonen Self-Organizing Map (CKSOM) Model With New Equations in Organizing Unstructured Data Presenter : Yu-Ting LU Authors : Seng Poh Lim and Habibollah Haron 2013. TNNLS
Outlines Motivation Objectives Methodology Experiments Conclusions Comments
Motivation For unstructured data, there is no connectivity information between data points. As a result, incorrect shapes will be obtained during the imaging process. 2-D Kohonen maps are limited because they are unable to cover the whole surface of closed 3-D surface data.
closed surface open surfaces
Objectives The aim of this paper is to use KSOM to organize unstructured data for closed surfaces. Enhancements to the KSOM for organizing unstructured data for closed 3-D surfaces and solving the problems of 2-D and 3-D KSOM. 本研究的目的在使用KSOM來組織封閉表面的非結構化資料 本文提出增強KSOM組織封閉3-D表面的非結構化資料的方法,和解決2-D和3-D的問題
Methodology
Methodology – Acquiring data Talus bone data 5,235 points.
Methodology – Acquiring data
Methodology – Initializing parameters
Methodology – Merging neurons
Methodology – Merging neurons
Methodology – Merging neurons
Methodology – Merging neurons
Methodology – Detecting neighbors
Methodology – Generating weights, learning process and producing output
Experiments - Analysis and validation of images
Experiments - Analysis and validation of images
Experiments - Analysis and validation of metric evaluation
Experiments - Analysis and validation of equations
Experiments - Analysis and validation of equations
Quantization errors =0.0001 Quantization errors =0.00007
Conclusions The model solved 2-D KSOM problems by covering the whole surface of a closed surface and handled connectivity problems of 3-D KSOM. The model also contained fewer quantization errors compared to 2-D and 3-D KSOM.
Comments Advantages Fewer quantization errors Applications Self-Organization Map Organization medical image data