Using Kohonen networks for WWW document classification

Filip Rudzinski; Adam Gluszek; Michal Kekez

doi:10.1117/12.610756

23 February 2005 Using Kohonen networks for WWW document classification

Filip Rudzinski, Adam Gluszek, Michal Kekez

Proceedings Volume 5775, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments III; (2005) https://doi.org/10.1117/12.610756
Event: Wilga 2004, 2004, Wilga, Poland

Abstract

This paper presents flexible solutions to the clustering and classification of World Wide Web documents. The method proposed in this paper applies the self-organizing Kohonen network known also a self-organizing map (SOM) with two-layer architecture. In this architecture documents become mapped as points on the SOM, in a geometric order that describes the similarity of their contents. This network has been learned by means of unsupervised training technique. After learning process has been completed, the network visualizes semantic relationship between input documents as two-dimensional semantic map. This map is a retrieval interface for an online WWW documents classification system. In this paper, first, the main idea of solution based on SOM has been presented. Next, the operation of this method has been illustrated with the us of synthetic data set. Finally, this technique has been tested by means of real-life WWW documents set.

Citation Download Citation

Filip Rudzinski, Adam Gluszek, and Michal Kekez "Using Kohonen networks for WWW document classification", Proc. SPIE 5775, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments III, (23 February 2005); https://doi.org/10.1117/12.610756

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available