Self-similarity for data mining and predictive modeling: a case study for network data

Jafar Adibi; Wei-Min Shen; Eaman Noorbakhsh

doi:10.1117/12.460227

12 March 2002 Self-similarity for data mining and predictive modeling: a case study for network data

Jafar Adibi, Wei-Min Shen, Eaman Noorbakhsh

Proceedings Volume 4730, Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV; (2002) https://doi.org/10.1117/12.460227
Event: AeroSense 2002, 2002, Orlando, FL, United States

Abstract

Recently there are a handful study and research on observing self-similarity and fractals in natural structures and scientific database such as traffic data from networks. However, there are few works on employing such information for predictive modeling, data mining and knowledge discovery. In this paper we study, analyze our experiments and observation of self-similar structure embedded in Network data for prediction through Self Similar Layered Hidden Markov Model (SSLHMM). SSLHMM is a novel alternative of Hidden Markov Models (HMM) which proven to be useful in a variety of real world applications. SSLHMM leverage HMM power and extend such capability to self-similar structures and exploit this property to reduce the complexity of predictive modeling process. We show that SSLHMM approach can captures self-similar information and provides more accurate and interpretable model comparing to conventional techniques and one-step, flat method for model constructions such as HMM.

Citation Download Citation

Jafar Adibi, Wei-Min Shen, and Eaman Noorbakhsh "Self-similarity for data mining and predictive modeling: a case study for network data", Proc. SPIE 4730, Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV, (12 March 2002); https://doi.org/10.1117/12.460227

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