Re:DM: Pointers in K-NN for temporal data

[C. K. Krishnadas]

To:     datamine-l@nautilus-sys.com
cc:      
Subject:        DM: Pointers in K-NN for temporal data



        Dear dataminers!
        Has anyone ideas or pointers about the use of nearest-neighbor
algorithm with temporal data? Are there specific nearest-neighbor
algorithms when data present a temporal organization & structure?
        Can anyone help us?
        Thanks in advance. Best regards for the new year.

********************************************************************
Inaki Inza
Computer Sciences and Artificial Intelligence Department
University of the Basque Country
P.O. Box 649
E-20080 Donostia - San Sebastian
Basque Country
Spain

Telephone number: (+34) 943448000 (extension 5106)
FAX number: (+34) 943219306
e-mail: ccbincai@si.ehu.es
******************************************************************
Here is a summary opf responses to a similar query I asked recently in
 another mailing list (timeseries).  
 Would be glad to see a similar summary to update my own list.

  -- Krishnadas

--------------------------------------------------------------------

Jens Timmer  
http://phym1.physik.uni-freiburg.de/~jeti/ 

there is a book by H. Kantz and T Schreiber "Nonlinear
time series analysis", 
Cambridge University Press, 1997, where these topics are discussed
 and many references are given. 
---------------------------------------------------------------------

Jan G. De Gooijer 
http://www.fee.uva.nl/vak_groep/ake/jandeg.htm 

Perhaps you should take a look at  a paper published in the 
Journal of Int.Money and Finance (1998), 
513-534 entitled Forecasting Exchange Rates Using TSMARS. 

-------------------------------------------------------------

Ron Addie 
Ron.Addie@vtt.fi, 
addie@usq.edu.au, http://www.sci.usq.edu.au/staff/addie 

@article{Yakowitz87, 
 title="Nearest-Neighbour Methods for Time Series Analysis", 
 author="S. Yakowitz", 
 journal="Journal of Time Series Analysis", 
 volume=8, 
 number=2, 
 year=1987} 
------------------------------------------------------------

Dr. Jose-Manuel Zaldivar Comenges 
jose.zaldivar-comenges@jrc.it 

I will recomend to you the following book: 

Henry D. I. Abarbanel 
Analysis of Observed Chaotic Data, 1996, Springer-Verlag, New York 
ISBN 0-387-94523-7 

There you will find a complete explanation about phase-space
reconstruction and all the references about the FNN method
(it was developed originally by Abarbanel) and how to use all
these techniches for forecasting. 
------------------------------------------------------------------

Eric Kostelich, Professor and Associate Chair, Dept. of Mathematics, 
Box 871804, Arizona State University, Tempe, AZ 85287-1804. 
Telephone:  (602) 965-5006.   Fax:  (602) 965-8119.

See for example E.J. Kostelich and T. Schreiber, Phys. Rev. E 47 
(1993), 305-310 and references therein.  It is a survey article 
that discusses embedding methods and noise reduction in chaotic 
data, which is one application of short-term forecasting. 
-------------------------------------------------------------------

Professor David Lowe 
Neural Computing Research Group
        www:   http://www.ncrg.aston.ac.uk/ 

@InCollection{neep98_2, 
author = "{Neep Hazarika and David Lowe}", 
editor= "Tony Constantinides and  S._Y. Kung and Mahesan Niranjan and 
                  Elizabeth Wilson", 
title = "{A Neural-Network Extension of the Method of Analogues 
for Iterated Time Series Prediction}", 
BOOKTITLE = "{Proceedings, Neural Networks for Signal Processing VIII} 
pages = "458--466", 
year = 1998, 
} 

---------------------------------------------------------------- 

Prof. Upmanu Lall 
Web: http://grumpy.usu.edu/~FALALL/ulall.html 
http://publish.uwrl.usu.edu/faculty/lall.html 

download software from ftp kernel.uwrl.usu.edu 
username guest 
password waterlab 

-----------------------------------------------------------------

Giannis Dimoticalis, PhD Techn. Univ. Crete, Chania, Greece: 

You can find the some links at: 
http://www.geocities.com/Athens/Delphi/6606/ 

see for example 
Santa Fe institute 
and Dr Tarasvirta 
pages in Denmark (i havent now the link...) 

Windows application (Local Forecasting) is developed in VB 3.00 but 
unfortunately is in greek (the menus, commans, buttons, help, etc) 
because is part of my PhD thesis in 1995...

Abarbanel H.D.I., Brown R. and Kadtke J.B., Prediction in chaotic nonlinear systems: Methods for time series with broadband Fourier Spectra, Physical Review A, Vol 41, No 4, 1990.

Abarbanel H.D.I., Brown R., Sidorowich J.J. and Tsimring L.S., The analysis of observed chaotic data in physical systems, Reviews of Modern Physics, Vol 65, No 4, 1331-1392, 1993.

Brock W.A. and Malliaris A.G., Advanced Textbooks in Economics 77: Differential equations, Stability and chaos in dynamic economics, North-Holland, 1990.

Brock W.A., Hsieh D.A. and Lebaron B., Nonlinear Dynamics, Chaos, and Instability, MIT Press, 1992.

Brock W.A., Hsieh D.A. and LeBaron B., Nonlinear Dynamics, Chaos, and Instability: Statistical Theory and Economic Evidence, MIT Press, Second Printing, 1992.

Broomhead D.S. and King G.P., Extracting Qualitative dynamics from experimental data, Physica D 20, 217-236, 1986.

Casdagli M., Nonlinear prediction of chaotic time series, Physica D 35, 335-356, 1989.

Casdagli M, A Dynamical Systems Approach to Modeling Input-Output Systems, in Nonlinear Modeling and Forecasting, SFI Studies in the Sciences of Complexity, Proc. Vol. XII, Casdagli M. and Eubank S. (Eds), Addison-Wesley, 265-281, 1992.

Casdagli M., Des Jardins D., Eubank S., Farmer J.D., Gibson J., Theiler J. and Hunter N., Nonlinear modeling of chaotic time series: theory and applications, in Applied Chaos, Jong Hyun Kim and John Stringer (Eds), John Wiley & Sons, 1992.

Elms D., Forecasting in financial markets, in Chaos and Non-Linear Models in Economics: Theory and Applications, Creedy J. and Martin V.L. (eds), Edward Elgar, 1994.

Eubank S. and Farmer D., An introduction to chaos and randomness, in 1989 Lecture in Complex Systems, SFI Studies in the Sciences of Complexity, Lect. Vol. II, Erica Jen (Ed), Addison-Wesley, 1990.

Feichtinger G. and Kopel M., Chaos in nonlinear dynamical systems exemplified by R & D model, European Journal of Operational Research 68, 145-159, 1993.

Giona M., Lentini F. and Cimagalli V., Functional reconstruction and local prediction of chaotic time series, Physical Review A, Vol 44, No 6, 3496-3502, 1991.

Gordon T.J. and Greenspan D., Chaos and Fractals: New Tools for Technological and Social Forecasting, Technological Forecasting and Social Change 34, 1-25, 1988.

Gordon T.J., Notes on forecasting a chaotic series using regression, Technological Forec. & Soc. Change 39, 337-348, 1991.

Granger C.W.J. and Tarasvirta T., Experiments in Modeling Nonlinear Relationships between Time Series, in Nonlinear Modeling and Forecasting, SFI Studies in the Sciences of Complexity, Proc. Vol. XIII, Casdagli M. and Eubank S. (Eds), Addison-Wesley, 189-197, 1992.

LeBaron Blake, Nonlinear Forecasting for S&P Stock Index, in Nonlinear Modeling and Forecasting, SFI Studies in the Sciences of Complexity, Proc. Vol. XIII, Casdagli M. and Eubank S. (Eds), Addison-Wesley, 381-393, 1992.

Mulhern F.J. and Caprara R.J., A nearest neighbor model for forecasting market response, Int. J. of Forecasting 10, 181-189, 1994.

Peters E., Chaos and Order in the Capital Markets: a new view of cycles, prices, and market volatility, New York, John Wiley, 1991.

Rossler O.E., The Future of Chaos, in Applied Chaos, Jong Hyun Kim and John Stringer, John Wiley & Sons, 1992.

Ruelle D., The Claude Bernard Lecture 1989: Deterministic chaos: the science and the fiction , Proc. R. Soc. Lond. A, 427, 241-248, 1990.

Sugihara G. and May R.M., Nonlinear forecasting as a way of distinguishing chaos from measurement error in times series, Nature 344, 734-741, 1990.

Tong H., Non-Linear time Series: A dynamical system approach, Clarendon Press Oxford, New York, 1990.

Tsonis A.A., CHAOS: from theory to applications, Plenum Press, 1992

-----------------------------------------------------------------

The following  reference reproduced  from "nonlin-sys digest" of 
last week was also very informative: 

  -- Krishnadas 

\\ 
Paper: chao-dyn/9810005 
From: Thomas Schreiber  
Date: Wed, 30 Sep 1998 11:15:07 GMT   (366kb) 

Title: Practical implementation of nonlinear time series methods: The TISEAN 
  package 
Authors: Rainer Hegger, Holger Kantz, Thomas Schreiber 
Comments: 27 pages, 21 figures, downloadable software at 
  http://www.mpipks-dresden.mpg.de/~tisean 
Report-no: WUB 98-33 
\\ 

  Nonlinear time series analysis is becoming a more and more reliable tool for 
the study of complicated dynamics from measurements. The concept of 
low-dimensional chaos has proven to be fruitful in the understanding of many 
complex phenomena despite the fact that very few natural systems have actually 
been found to be low dimensional deterministic in the sense of the theory. In 
order to evaluate the long term usefulness of the nonlinear time series 
approach as inspired by chaos theory, it will be important that the 
corresponding methods become more widely accessible. This paper, while not a 
proper review on nonlinear time series analysis, tries to make a contribution 
to this process by describing the actual implementation of the algorithms, and 
their proper usage. Most of the methods require the choice of certain 
parameters for each specific time series application. We will try to give 
guidance in this respect. The scope and selection of topics in this article, as 
well as the implementational choices that have been made, correspond to the 
contents of the software package TISEAN which is publicly available from 
http://www.mpipks-dresden.mpg.de/~tisean . In fact, this paper can be seen as 
an extended manual for the TISEAN programs. It fills the gap between the 
technical documentation and the existing literature, providing the necessary 
entry points for a more thorough study of the theoretical background.

\\ ( http://xxx.lanl.gov/abs/chao-dyn/9810005 ,  366kb) 
--------------------------------------------------------------
\\